Training in progress, epoch 7, checkpoint
Browse files- .gitattributes +1 -0
- checkpoint-441/README.md +202 -0
- checkpoint-441/adapter_config.json +29 -0
- checkpoint-441/adapter_model.safetensors +3 -0
- checkpoint-441/optimizer.pt +3 -0
- checkpoint-441/rng_state.pth +3 -0
- checkpoint-441/scheduler.pt +3 -0
- checkpoint-441/special_tokens_map.json +23 -0
- checkpoint-441/tokenizer.json +3 -0
- checkpoint-441/tokenizer_config.json +2063 -0
- checkpoint-441/trainer_state.json +3184 -0
- checkpoint-441/training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -40,3 +40,4 @@ checkpoint-189/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
| 40 |
checkpoint-252/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 41 |
checkpoint-315/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 42 |
checkpoint-378/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 40 |
checkpoint-252/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 41 |
checkpoint-315/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 42 |
checkpoint-378/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
checkpoint-441/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
checkpoint-441/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.2
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.13.2
|
checkpoint-441/adapter_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.2",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 64,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"v_proj"
|
| 25 |
+
],
|
| 26 |
+
"task_type": "CAUSAL_LM",
|
| 27 |
+
"use_dora": false,
|
| 28 |
+
"use_rslora": false
|
| 29 |
+
}
|
checkpoint-441/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2a9b0a25b170b3d2790cfeb9d708a320eb7c3b4bdfe0672045142c808e8e043
|
| 3 |
+
size 109069176
|
checkpoint-441/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd1e6225aa634921464260154b7b8ea524a88d77f826974891b381fd7f91fd7d
|
| 3 |
+
size 218211962
|
checkpoint-441/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58c3fde5e8f8e2370570446bb7a53708cca6f8f35a901ae96b26fa6c070c2608
|
| 3 |
+
size 14244
|
checkpoint-441/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45974299f553122f63dcd9c4fe691cb501a999e4e61d9859455d50380b032112
|
| 3 |
+
size 1064
|
checkpoint-441/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin_of_text|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|eot_id|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|finetune_right_pad_id|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
checkpoint-441/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:268aef6511a866fd03104209ff6592ded093172c0cdaf8885ff9c97d62e32869
|
| 3 |
+
size 17209958
|
checkpoint-441/tokenizer_config.json
ADDED
|
@@ -0,0 +1,2063 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"128000": {
|
| 4 |
+
"content": "<|begin_of_text|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"128001": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"128002": {
|
| 20 |
+
"content": "<|reserved_special_token_0|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"128003": {
|
| 28 |
+
"content": "<|reserved_special_token_1|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128004": {
|
| 36 |
+
"content": "<|finetune_right_pad_id|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128005": {
|
| 44 |
+
"content": "<|reserved_special_token_3|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"128006": {
|
| 52 |
+
"content": "<|start_header_id|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"128007": {
|
| 60 |
+
"content": "<|end_header_id|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"128008": {
|
| 68 |
+
"content": "<|reserved_special_token_4|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"128009": {
|
| 76 |
+
"content": "<|eot_id|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"128010": {
|
| 84 |
+
"content": "<|reserved_special_token_5|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"128011": {
|
| 92 |
+
"content": "<|reserved_special_token_6|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"128012": {
|
| 100 |
+
"content": "<|reserved_special_token_7|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"128013": {
|
| 108 |
+
"content": "<|reserved_special_token_8|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"128014": {
|
| 116 |
+
"content": "<|reserved_special_token_9|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"128015": {
|
| 124 |
+
"content": "<|reserved_special_token_10|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"128016": {
|
| 132 |
+
"content": "<|reserved_special_token_11|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"128017": {
|
| 140 |
+
"content": "<|reserved_special_token_12|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"128018": {
|
| 148 |
+
"content": "<|reserved_special_token_13|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "<|reserved_special_token_14|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"128020": {
|
| 164 |
+
"content": "<|reserved_special_token_15|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"128021": {
|
| 172 |
+
"content": "<|reserved_special_token_16|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"128022": {
|
| 180 |
+
"content": "<|reserved_special_token_17|>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"128023": {
|
| 188 |
+
"content": "<|reserved_special_token_18|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"128024": {
|
| 196 |
+
"content": "<|reserved_special_token_19|>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"128025": {
|
| 204 |
+
"content": "<|reserved_special_token_20|>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"128026": {
|
| 212 |
+
"content": "<|reserved_special_token_21|>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"128027": {
|
| 220 |
+
"content": "<|reserved_special_token_22|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"128028": {
|
| 228 |
+
"content": "<|reserved_special_token_23|>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"128029": {
|
| 236 |
+
"content": "<|reserved_special_token_24|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"128030": {
|
| 244 |
+
"content": "<|reserved_special_token_25|>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"128031": {
|
| 252 |
+
"content": "<|reserved_special_token_26|>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"128032": {
|
| 260 |
+
"content": "<|reserved_special_token_27|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"128033": {
|
| 268 |
+
"content": "<|reserved_special_token_28|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"128034": {
|
| 276 |
+
"content": "<|reserved_special_token_29|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"128035": {
|
| 284 |
+
"content": "<|reserved_special_token_30|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"128036": {
|
| 292 |
+
"content": "<|reserved_special_token_31|>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"128037": {
|
| 300 |
+
"content": "<|reserved_special_token_32|>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"128038": {
|
| 308 |
+
"content": "<|reserved_special_token_33|>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"128039": {
|
| 316 |
+
"content": "<|reserved_special_token_34|>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"128040": {
|
| 324 |
+
"content": "<|reserved_special_token_35|>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"128041": {
|
| 332 |
+
"content": "<|reserved_special_token_36|>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"128042": {
|
| 340 |
+
"content": "<|reserved_special_token_37|>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"128043": {
|
| 348 |
+
"content": "<|reserved_special_token_38|>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"128044": {
|
| 356 |
+
"content": "<|reserved_special_token_39|>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"128045": {
|
| 364 |
+
"content": "<|reserved_special_token_40|>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"128046": {
|
| 372 |
+
"content": "<|reserved_special_token_41|>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"128047": {
|
| 380 |
+
"content": "<|reserved_special_token_42|>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"128048": {
|
| 388 |
+
"content": "<|reserved_special_token_43|>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"128049": {
|
| 396 |
+
"content": "<|reserved_special_token_44|>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"128050": {
|
| 404 |
+
"content": "<|reserved_special_token_45|>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"128051": {
|
| 412 |
+
"content": "<|reserved_special_token_46|>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"128052": {
|
| 420 |
+
"content": "<|reserved_special_token_47|>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"128053": {
|
| 428 |
+
"content": "<|reserved_special_token_48|>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"128054": {
|
| 436 |
+
"content": "<|reserved_special_token_49|>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"128055": {
|
| 444 |
+
"content": "<|reserved_special_token_50|>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"128056": {
|
| 452 |
+
"content": "<|reserved_special_token_51|>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"128057": {
|
| 460 |
+
"content": "<|reserved_special_token_52|>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"128058": {
|
| 468 |
+
"content": "<|reserved_special_token_53|>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"128059": {
|
| 476 |
+
"content": "<|reserved_special_token_54|>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"128060": {
|
| 484 |
+
"content": "<|reserved_special_token_55|>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"128061": {
|
| 492 |
+
"content": "<|reserved_special_token_56|>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"128062": {
|
| 500 |
+
"content": "<|reserved_special_token_57|>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"128063": {
|
| 508 |
+
"content": "<|reserved_special_token_58|>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"128064": {
|
| 516 |
+
"content": "<|reserved_special_token_59|>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"128065": {
|
| 524 |
+
"content": "<|reserved_special_token_60|>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"128066": {
|
| 532 |
+
"content": "<|reserved_special_token_61|>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"128067": {
|
| 540 |
+
"content": "<|reserved_special_token_62|>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"128068": {
|
| 548 |
+
"content": "<|reserved_special_token_63|>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"128069": {
|
| 556 |
+
"content": "<|reserved_special_token_64|>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"128070": {
|
| 564 |
+
"content": "<|reserved_special_token_65|>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"128071": {
|
| 572 |
+
"content": "<|reserved_special_token_66|>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"128072": {
|
| 580 |
+
"content": "<|reserved_special_token_67|>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"128073": {
|
| 588 |
+
"content": "<|reserved_special_token_68|>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"128074": {
|
| 596 |
+
"content": "<|reserved_special_token_69|>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"128075": {
|
| 604 |
+
"content": "<|reserved_special_token_70|>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"128076": {
|
| 612 |
+
"content": "<|reserved_special_token_71|>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"128077": {
|
| 620 |
+
"content": "<|reserved_special_token_72|>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"128078": {
|
| 628 |
+
"content": "<|reserved_special_token_73|>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"128079": {
|
| 636 |
+
"content": "<|reserved_special_token_74|>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"128080": {
|
| 644 |
+
"content": "<|reserved_special_token_75|>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"128081": {
|
| 652 |
+
"content": "<|reserved_special_token_76|>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"128082": {
|
| 660 |
+
"content": "<|reserved_special_token_77|>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"128083": {
|
| 668 |
+
"content": "<|reserved_special_token_78|>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"128084": {
|
| 676 |
+
"content": "<|reserved_special_token_79|>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"128085": {
|
| 684 |
+
"content": "<|reserved_special_token_80|>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"128086": {
|
| 692 |
+
"content": "<|reserved_special_token_81|>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"128087": {
|
| 700 |
+
"content": "<|reserved_special_token_82|>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"128088": {
|
| 708 |
+
"content": "<|reserved_special_token_83|>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"128089": {
|
| 716 |
+
"content": "<|reserved_special_token_84|>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"128090": {
|
| 724 |
+
"content": "<|reserved_special_token_85|>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"128091": {
|
| 732 |
+
"content": "<|reserved_special_token_86|>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"128092": {
|
| 740 |
+
"content": "<|reserved_special_token_87|>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"128093": {
|
| 748 |
+
"content": "<|reserved_special_token_88|>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"128094": {
|
| 756 |
+
"content": "<|reserved_special_token_89|>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"128095": {
|
| 764 |
+
"content": "<|reserved_special_token_90|>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"128096": {
|
| 772 |
+
"content": "<|reserved_special_token_91|>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"128097": {
|
| 780 |
+
"content": "<|reserved_special_token_92|>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"128098": {
|
| 788 |
+
"content": "<|reserved_special_token_93|>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"128099": {
|
| 796 |
+
"content": "<|reserved_special_token_94|>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"128100": {
|
| 804 |
+
"content": "<|reserved_special_token_95|>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"128101": {
|
| 812 |
+
"content": "<|reserved_special_token_96|>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"128102": {
|
| 820 |
+
"content": "<|reserved_special_token_97|>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"128103": {
|
| 828 |
+
"content": "<|reserved_special_token_98|>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"128104": {
|
| 836 |
+
"content": "<|reserved_special_token_99|>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"128105": {
|
| 844 |
+
"content": "<|reserved_special_token_100|>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"128106": {
|
| 852 |
+
"content": "<|reserved_special_token_101|>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"128107": {
|
| 860 |
+
"content": "<|reserved_special_token_102|>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"128108": {
|
| 868 |
+
"content": "<|reserved_special_token_103|>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"128109": {
|
| 876 |
+
"content": "<|reserved_special_token_104|>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"128110": {
|
| 884 |
+
"content": "<|reserved_special_token_105|>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"128111": {
|
| 892 |
+
"content": "<|reserved_special_token_106|>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"128112": {
|
| 900 |
+
"content": "<|reserved_special_token_107|>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"128113": {
|
| 908 |
+
"content": "<|reserved_special_token_108|>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"128114": {
|
| 916 |
+
"content": "<|reserved_special_token_109|>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"128115": {
|
| 924 |
+
"content": "<|reserved_special_token_110|>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"128116": {
|
| 932 |
+
"content": "<|reserved_special_token_111|>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"128117": {
|
| 940 |
+
"content": "<|reserved_special_token_112|>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"128118": {
|
| 948 |
+
"content": "<|reserved_special_token_113|>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"128119": {
|
| 956 |
+
"content": "<|reserved_special_token_114|>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"128120": {
|
| 964 |
+
"content": "<|reserved_special_token_115|>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"128121": {
|
| 972 |
+
"content": "<|reserved_special_token_116|>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"128122": {
|
| 980 |
+
"content": "<|reserved_special_token_117|>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"128123": {
|
| 988 |
+
"content": "<|reserved_special_token_118|>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"128124": {
|
| 996 |
+
"content": "<|reserved_special_token_119|>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"128125": {
|
| 1004 |
+
"content": "<|reserved_special_token_120|>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"128126": {
|
| 1012 |
+
"content": "<|reserved_special_token_121|>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"128127": {
|
| 1020 |
+
"content": "<|reserved_special_token_122|>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"128128": {
|
| 1028 |
+
"content": "<|reserved_special_token_123|>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"128129": {
|
| 1036 |
+
"content": "<|reserved_special_token_124|>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"128130": {
|
| 1044 |
+
"content": "<|reserved_special_token_125|>",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"128131": {
|
| 1052 |
+
"content": "<|reserved_special_token_126|>",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"128132": {
|
| 1060 |
+
"content": "<|reserved_special_token_127|>",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"128133": {
|
| 1068 |
+
"content": "<|reserved_special_token_128|>",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"128134": {
|
| 1076 |
+
"content": "<|reserved_special_token_129|>",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"128135": {
|
| 1084 |
+
"content": "<|reserved_special_token_130|>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"128136": {
|
| 1092 |
+
"content": "<|reserved_special_token_131|>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"128137": {
|
| 1100 |
+
"content": "<|reserved_special_token_132|>",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"128138": {
|
| 1108 |
+
"content": "<|reserved_special_token_133|>",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"128139": {
|
| 1116 |
+
"content": "<|reserved_special_token_134|>",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"128140": {
|
| 1124 |
+
"content": "<|reserved_special_token_135|>",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"128141": {
|
| 1132 |
+
"content": "<|reserved_special_token_136|>",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"128142": {
|
| 1140 |
+
"content": "<|reserved_special_token_137|>",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"128143": {
|
| 1148 |
+
"content": "<|reserved_special_token_138|>",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"128144": {
|
| 1156 |
+
"content": "<|reserved_special_token_139|>",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"128145": {
|
| 1164 |
+
"content": "<|reserved_special_token_140|>",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"128146": {
|
| 1172 |
+
"content": "<|reserved_special_token_141|>",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"128147": {
|
| 1180 |
+
"content": "<|reserved_special_token_142|>",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"128148": {
|
| 1188 |
+
"content": "<|reserved_special_token_143|>",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"128149": {
|
| 1196 |
+
"content": "<|reserved_special_token_144|>",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"128150": {
|
| 1204 |
+
"content": "<|reserved_special_token_145|>",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"128151": {
|
| 1212 |
+
"content": "<|reserved_special_token_146|>",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"128152": {
|
| 1220 |
+
"content": "<|reserved_special_token_147|>",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"128153": {
|
| 1228 |
+
"content": "<|reserved_special_token_148|>",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"128154": {
|
| 1236 |
+
"content": "<|reserved_special_token_149|>",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"128155": {
|
| 1244 |
+
"content": "<|reserved_special_token_150|>",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"128156": {
|
| 1252 |
+
"content": "<|reserved_special_token_151|>",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"128157": {
|
| 1260 |
+
"content": "<|reserved_special_token_152|>",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"128158": {
|
| 1268 |
+
"content": "<|reserved_special_token_153|>",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"128159": {
|
| 1276 |
+
"content": "<|reserved_special_token_154|>",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"128160": {
|
| 1284 |
+
"content": "<|reserved_special_token_155|>",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"128161": {
|
| 1292 |
+
"content": "<|reserved_special_token_156|>",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"128162": {
|
| 1300 |
+
"content": "<|reserved_special_token_157|>",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"128163": {
|
| 1308 |
+
"content": "<|reserved_special_token_158|>",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"128164": {
|
| 1316 |
+
"content": "<|reserved_special_token_159|>",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"128165": {
|
| 1324 |
+
"content": "<|reserved_special_token_160|>",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"128166": {
|
| 1332 |
+
"content": "<|reserved_special_token_161|>",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"128167": {
|
| 1340 |
+
"content": "<|reserved_special_token_162|>",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"128168": {
|
| 1348 |
+
"content": "<|reserved_special_token_163|>",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"128169": {
|
| 1356 |
+
"content": "<|reserved_special_token_164|>",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"128170": {
|
| 1364 |
+
"content": "<|reserved_special_token_165|>",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"128171": {
|
| 1372 |
+
"content": "<|reserved_special_token_166|>",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"128172": {
|
| 1380 |
+
"content": "<|reserved_special_token_167|>",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"128173": {
|
| 1388 |
+
"content": "<|reserved_special_token_168|>",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"128174": {
|
| 1396 |
+
"content": "<|reserved_special_token_169|>",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"128175": {
|
| 1404 |
+
"content": "<|reserved_special_token_170|>",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"128176": {
|
| 1412 |
+
"content": "<|reserved_special_token_171|>",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"128177": {
|
| 1420 |
+
"content": "<|reserved_special_token_172|>",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"128178": {
|
| 1428 |
+
"content": "<|reserved_special_token_173|>",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"128179": {
|
| 1436 |
+
"content": "<|reserved_special_token_174|>",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"128180": {
|
| 1444 |
+
"content": "<|reserved_special_token_175|>",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"128181": {
|
| 1452 |
+
"content": "<|reserved_special_token_176|>",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"128182": {
|
| 1460 |
+
"content": "<|reserved_special_token_177|>",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"128183": {
|
| 1468 |
+
"content": "<|reserved_special_token_178|>",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"128184": {
|
| 1476 |
+
"content": "<|reserved_special_token_179|>",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"128185": {
|
| 1484 |
+
"content": "<|reserved_special_token_180|>",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"128186": {
|
| 1492 |
+
"content": "<|reserved_special_token_181|>",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"128187": {
|
| 1500 |
+
"content": "<|reserved_special_token_182|>",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"128188": {
|
| 1508 |
+
"content": "<|reserved_special_token_183|>",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"128189": {
|
| 1516 |
+
"content": "<|reserved_special_token_184|>",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"128190": {
|
| 1524 |
+
"content": "<|reserved_special_token_185|>",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"128191": {
|
| 1532 |
+
"content": "<|reserved_special_token_186|>",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"128192": {
|
| 1540 |
+
"content": "<|reserved_special_token_187|>",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"128193": {
|
| 1548 |
+
"content": "<|reserved_special_token_188|>",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"128194": {
|
| 1556 |
+
"content": "<|reserved_special_token_189|>",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"128195": {
|
| 1564 |
+
"content": "<|reserved_special_token_190|>",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"128196": {
|
| 1572 |
+
"content": "<|reserved_special_token_191|>",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"128197": {
|
| 1580 |
+
"content": "<|reserved_special_token_192|>",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"128198": {
|
| 1588 |
+
"content": "<|reserved_special_token_193|>",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"128199": {
|
| 1596 |
+
"content": "<|reserved_special_token_194|>",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"128200": {
|
| 1604 |
+
"content": "<|reserved_special_token_195|>",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"128201": {
|
| 1612 |
+
"content": "<|reserved_special_token_196|>",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"128202": {
|
| 1620 |
+
"content": "<|reserved_special_token_197|>",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"128203": {
|
| 1628 |
+
"content": "<|reserved_special_token_198|>",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"128204": {
|
| 1636 |
+
"content": "<|reserved_special_token_199|>",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"128205": {
|
| 1644 |
+
"content": "<|reserved_special_token_200|>",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"128206": {
|
| 1652 |
+
"content": "<|reserved_special_token_201|>",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"128207": {
|
| 1660 |
+
"content": "<|reserved_special_token_202|>",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"128208": {
|
| 1668 |
+
"content": "<|reserved_special_token_203|>",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"128209": {
|
| 1676 |
+
"content": "<|reserved_special_token_204|>",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"128210": {
|
| 1684 |
+
"content": "<|reserved_special_token_205|>",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
},
|
| 1691 |
+
"128211": {
|
| 1692 |
+
"content": "<|reserved_special_token_206|>",
|
| 1693 |
+
"lstrip": false,
|
| 1694 |
+
"normalized": false,
|
| 1695 |
+
"rstrip": false,
|
| 1696 |
+
"single_word": false,
|
| 1697 |
+
"special": true
|
| 1698 |
+
},
|
| 1699 |
+
"128212": {
|
| 1700 |
+
"content": "<|reserved_special_token_207|>",
|
| 1701 |
+
"lstrip": false,
|
| 1702 |
+
"normalized": false,
|
| 1703 |
+
"rstrip": false,
|
| 1704 |
+
"single_word": false,
|
| 1705 |
+
"special": true
|
| 1706 |
+
},
|
| 1707 |
+
"128213": {
|
| 1708 |
+
"content": "<|reserved_special_token_208|>",
|
| 1709 |
+
"lstrip": false,
|
| 1710 |
+
"normalized": false,
|
| 1711 |
+
"rstrip": false,
|
| 1712 |
+
"single_word": false,
|
| 1713 |
+
"special": true
|
| 1714 |
+
},
|
| 1715 |
+
"128214": {
|
| 1716 |
+
"content": "<|reserved_special_token_209|>",
|
| 1717 |
+
"lstrip": false,
|
| 1718 |
+
"normalized": false,
|
| 1719 |
+
"rstrip": false,
|
| 1720 |
+
"single_word": false,
|
| 1721 |
+
"special": true
|
| 1722 |
+
},
|
| 1723 |
+
"128215": {
|
| 1724 |
+
"content": "<|reserved_special_token_210|>",
|
| 1725 |
+
"lstrip": false,
|
| 1726 |
+
"normalized": false,
|
| 1727 |
+
"rstrip": false,
|
| 1728 |
+
"single_word": false,
|
| 1729 |
+
"special": true
|
| 1730 |
+
},
|
| 1731 |
+
"128216": {
|
| 1732 |
+
"content": "<|reserved_special_token_211|>",
|
| 1733 |
+
"lstrip": false,
|
| 1734 |
+
"normalized": false,
|
| 1735 |
+
"rstrip": false,
|
| 1736 |
+
"single_word": false,
|
| 1737 |
+
"special": true
|
| 1738 |
+
},
|
| 1739 |
+
"128217": {
|
| 1740 |
+
"content": "<|reserved_special_token_212|>",
|
| 1741 |
+
"lstrip": false,
|
| 1742 |
+
"normalized": false,
|
| 1743 |
+
"rstrip": false,
|
| 1744 |
+
"single_word": false,
|
| 1745 |
+
"special": true
|
| 1746 |
+
},
|
| 1747 |
+
"128218": {
|
| 1748 |
+
"content": "<|reserved_special_token_213|>",
|
| 1749 |
+
"lstrip": false,
|
| 1750 |
+
"normalized": false,
|
| 1751 |
+
"rstrip": false,
|
| 1752 |
+
"single_word": false,
|
| 1753 |
+
"special": true
|
| 1754 |
+
},
|
| 1755 |
+
"128219": {
|
| 1756 |
+
"content": "<|reserved_special_token_214|>",
|
| 1757 |
+
"lstrip": false,
|
| 1758 |
+
"normalized": false,
|
| 1759 |
+
"rstrip": false,
|
| 1760 |
+
"single_word": false,
|
| 1761 |
+
"special": true
|
| 1762 |
+
},
|
| 1763 |
+
"128220": {
|
| 1764 |
+
"content": "<|reserved_special_token_215|>",
|
| 1765 |
+
"lstrip": false,
|
| 1766 |
+
"normalized": false,
|
| 1767 |
+
"rstrip": false,
|
| 1768 |
+
"single_word": false,
|
| 1769 |
+
"special": true
|
| 1770 |
+
},
|
| 1771 |
+
"128221": {
|
| 1772 |
+
"content": "<|reserved_special_token_216|>",
|
| 1773 |
+
"lstrip": false,
|
| 1774 |
+
"normalized": false,
|
| 1775 |
+
"rstrip": false,
|
| 1776 |
+
"single_word": false,
|
| 1777 |
+
"special": true
|
| 1778 |
+
},
|
| 1779 |
+
"128222": {
|
| 1780 |
+
"content": "<|reserved_special_token_217|>",
|
| 1781 |
+
"lstrip": false,
|
| 1782 |
+
"normalized": false,
|
| 1783 |
+
"rstrip": false,
|
| 1784 |
+
"single_word": false,
|
| 1785 |
+
"special": true
|
| 1786 |
+
},
|
| 1787 |
+
"128223": {
|
| 1788 |
+
"content": "<|reserved_special_token_218|>",
|
| 1789 |
+
"lstrip": false,
|
| 1790 |
+
"normalized": false,
|
| 1791 |
+
"rstrip": false,
|
| 1792 |
+
"single_word": false,
|
| 1793 |
+
"special": true
|
| 1794 |
+
},
|
| 1795 |
+
"128224": {
|
| 1796 |
+
"content": "<|reserved_special_token_219|>",
|
| 1797 |
+
"lstrip": false,
|
| 1798 |
+
"normalized": false,
|
| 1799 |
+
"rstrip": false,
|
| 1800 |
+
"single_word": false,
|
| 1801 |
+
"special": true
|
| 1802 |
+
},
|
| 1803 |
+
"128225": {
|
| 1804 |
+
"content": "<|reserved_special_token_220|>",
|
| 1805 |
+
"lstrip": false,
|
| 1806 |
+
"normalized": false,
|
| 1807 |
+
"rstrip": false,
|
| 1808 |
+
"single_word": false,
|
| 1809 |
+
"special": true
|
| 1810 |
+
},
|
| 1811 |
+
"128226": {
|
| 1812 |
+
"content": "<|reserved_special_token_221|>",
|
| 1813 |
+
"lstrip": false,
|
| 1814 |
+
"normalized": false,
|
| 1815 |
+
"rstrip": false,
|
| 1816 |
+
"single_word": false,
|
| 1817 |
+
"special": true
|
| 1818 |
+
},
|
| 1819 |
+
"128227": {
|
| 1820 |
+
"content": "<|reserved_special_token_222|>",
|
| 1821 |
+
"lstrip": false,
|
| 1822 |
+
"normalized": false,
|
| 1823 |
+
"rstrip": false,
|
| 1824 |
+
"single_word": false,
|
| 1825 |
+
"special": true
|
| 1826 |
+
},
|
| 1827 |
+
"128228": {
|
| 1828 |
+
"content": "<|reserved_special_token_223|>",
|
| 1829 |
+
"lstrip": false,
|
| 1830 |
+
"normalized": false,
|
| 1831 |
+
"rstrip": false,
|
| 1832 |
+
"single_word": false,
|
| 1833 |
+
"special": true
|
| 1834 |
+
},
|
| 1835 |
+
"128229": {
|
| 1836 |
+
"content": "<|reserved_special_token_224|>",
|
| 1837 |
+
"lstrip": false,
|
| 1838 |
+
"normalized": false,
|
| 1839 |
+
"rstrip": false,
|
| 1840 |
+
"single_word": false,
|
| 1841 |
+
"special": true
|
| 1842 |
+
},
|
| 1843 |
+
"128230": {
|
| 1844 |
+
"content": "<|reserved_special_token_225|>",
|
| 1845 |
+
"lstrip": false,
|
| 1846 |
+
"normalized": false,
|
| 1847 |
+
"rstrip": false,
|
| 1848 |
+
"single_word": false,
|
| 1849 |
+
"special": true
|
| 1850 |
+
},
|
| 1851 |
+
"128231": {
|
| 1852 |
+
"content": "<|reserved_special_token_226|>",
|
| 1853 |
+
"lstrip": false,
|
| 1854 |
+
"normalized": false,
|
| 1855 |
+
"rstrip": false,
|
| 1856 |
+
"single_word": false,
|
| 1857 |
+
"special": true
|
| 1858 |
+
},
|
| 1859 |
+
"128232": {
|
| 1860 |
+
"content": "<|reserved_special_token_227|>",
|
| 1861 |
+
"lstrip": false,
|
| 1862 |
+
"normalized": false,
|
| 1863 |
+
"rstrip": false,
|
| 1864 |
+
"single_word": false,
|
| 1865 |
+
"special": true
|
| 1866 |
+
},
|
| 1867 |
+
"128233": {
|
| 1868 |
+
"content": "<|reserved_special_token_228|>",
|
| 1869 |
+
"lstrip": false,
|
| 1870 |
+
"normalized": false,
|
| 1871 |
+
"rstrip": false,
|
| 1872 |
+
"single_word": false,
|
| 1873 |
+
"special": true
|
| 1874 |
+
},
|
| 1875 |
+
"128234": {
|
| 1876 |
+
"content": "<|reserved_special_token_229|>",
|
| 1877 |
+
"lstrip": false,
|
| 1878 |
+
"normalized": false,
|
| 1879 |
+
"rstrip": false,
|
| 1880 |
+
"single_word": false,
|
| 1881 |
+
"special": true
|
| 1882 |
+
},
|
| 1883 |
+
"128235": {
|
| 1884 |
+
"content": "<|reserved_special_token_230|>",
|
| 1885 |
+
"lstrip": false,
|
| 1886 |
+
"normalized": false,
|
| 1887 |
+
"rstrip": false,
|
| 1888 |
+
"single_word": false,
|
| 1889 |
+
"special": true
|
| 1890 |
+
},
|
| 1891 |
+
"128236": {
|
| 1892 |
+
"content": "<|reserved_special_token_231|>",
|
| 1893 |
+
"lstrip": false,
|
| 1894 |
+
"normalized": false,
|
| 1895 |
+
"rstrip": false,
|
| 1896 |
+
"single_word": false,
|
| 1897 |
+
"special": true
|
| 1898 |
+
},
|
| 1899 |
+
"128237": {
|
| 1900 |
+
"content": "<|reserved_special_token_232|>",
|
| 1901 |
+
"lstrip": false,
|
| 1902 |
+
"normalized": false,
|
| 1903 |
+
"rstrip": false,
|
| 1904 |
+
"single_word": false,
|
| 1905 |
+
"special": true
|
| 1906 |
+
},
|
| 1907 |
+
"128238": {
|
| 1908 |
+
"content": "<|reserved_special_token_233|>",
|
| 1909 |
+
"lstrip": false,
|
| 1910 |
+
"normalized": false,
|
| 1911 |
+
"rstrip": false,
|
| 1912 |
+
"single_word": false,
|
| 1913 |
+
"special": true
|
| 1914 |
+
},
|
| 1915 |
+
"128239": {
|
| 1916 |
+
"content": "<|reserved_special_token_234|>",
|
| 1917 |
+
"lstrip": false,
|
| 1918 |
+
"normalized": false,
|
| 1919 |
+
"rstrip": false,
|
| 1920 |
+
"single_word": false,
|
| 1921 |
+
"special": true
|
| 1922 |
+
},
|
| 1923 |
+
"128240": {
|
| 1924 |
+
"content": "<|reserved_special_token_235|>",
|
| 1925 |
+
"lstrip": false,
|
| 1926 |
+
"normalized": false,
|
| 1927 |
+
"rstrip": false,
|
| 1928 |
+
"single_word": false,
|
| 1929 |
+
"special": true
|
| 1930 |
+
},
|
| 1931 |
+
"128241": {
|
| 1932 |
+
"content": "<|reserved_special_token_236|>",
|
| 1933 |
+
"lstrip": false,
|
| 1934 |
+
"normalized": false,
|
| 1935 |
+
"rstrip": false,
|
| 1936 |
+
"single_word": false,
|
| 1937 |
+
"special": true
|
| 1938 |
+
},
|
| 1939 |
+
"128242": {
|
| 1940 |
+
"content": "<|reserved_special_token_237|>",
|
| 1941 |
+
"lstrip": false,
|
| 1942 |
+
"normalized": false,
|
| 1943 |
+
"rstrip": false,
|
| 1944 |
+
"single_word": false,
|
| 1945 |
+
"special": true
|
| 1946 |
+
},
|
| 1947 |
+
"128243": {
|
| 1948 |
+
"content": "<|reserved_special_token_238|>",
|
| 1949 |
+
"lstrip": false,
|
| 1950 |
+
"normalized": false,
|
| 1951 |
+
"rstrip": false,
|
| 1952 |
+
"single_word": false,
|
| 1953 |
+
"special": true
|
| 1954 |
+
},
|
| 1955 |
+
"128244": {
|
| 1956 |
+
"content": "<|reserved_special_token_239|>",
|
| 1957 |
+
"lstrip": false,
|
| 1958 |
+
"normalized": false,
|
| 1959 |
+
"rstrip": false,
|
| 1960 |
+
"single_word": false,
|
| 1961 |
+
"special": true
|
| 1962 |
+
},
|
| 1963 |
+
"128245": {
|
| 1964 |
+
"content": "<|reserved_special_token_240|>",
|
| 1965 |
+
"lstrip": false,
|
| 1966 |
+
"normalized": false,
|
| 1967 |
+
"rstrip": false,
|
| 1968 |
+
"single_word": false,
|
| 1969 |
+
"special": true
|
| 1970 |
+
},
|
| 1971 |
+
"128246": {
|
| 1972 |
+
"content": "<|reserved_special_token_241|>",
|
| 1973 |
+
"lstrip": false,
|
| 1974 |
+
"normalized": false,
|
| 1975 |
+
"rstrip": false,
|
| 1976 |
+
"single_word": false,
|
| 1977 |
+
"special": true
|
| 1978 |
+
},
|
| 1979 |
+
"128247": {
|
| 1980 |
+
"content": "<|reserved_special_token_242|>",
|
| 1981 |
+
"lstrip": false,
|
| 1982 |
+
"normalized": false,
|
| 1983 |
+
"rstrip": false,
|
| 1984 |
+
"single_word": false,
|
| 1985 |
+
"special": true
|
| 1986 |
+
},
|
| 1987 |
+
"128248": {
|
| 1988 |
+
"content": "<|reserved_special_token_243|>",
|
| 1989 |
+
"lstrip": false,
|
| 1990 |
+
"normalized": false,
|
| 1991 |
+
"rstrip": false,
|
| 1992 |
+
"single_word": false,
|
| 1993 |
+
"special": true
|
| 1994 |
+
},
|
| 1995 |
+
"128249": {
|
| 1996 |
+
"content": "<|reserved_special_token_244|>",
|
| 1997 |
+
"lstrip": false,
|
| 1998 |
+
"normalized": false,
|
| 1999 |
+
"rstrip": false,
|
| 2000 |
+
"single_word": false,
|
| 2001 |
+
"special": true
|
| 2002 |
+
},
|
| 2003 |
+
"128250": {
|
| 2004 |
+
"content": "<|reserved_special_token_245|>",
|
| 2005 |
+
"lstrip": false,
|
| 2006 |
+
"normalized": false,
|
| 2007 |
+
"rstrip": false,
|
| 2008 |
+
"single_word": false,
|
| 2009 |
+
"special": true
|
| 2010 |
+
},
|
| 2011 |
+
"128251": {
|
| 2012 |
+
"content": "<|reserved_special_token_246|>",
|
| 2013 |
+
"lstrip": false,
|
| 2014 |
+
"normalized": false,
|
| 2015 |
+
"rstrip": false,
|
| 2016 |
+
"single_word": false,
|
| 2017 |
+
"special": true
|
| 2018 |
+
},
|
| 2019 |
+
"128252": {
|
| 2020 |
+
"content": "<|reserved_special_token_247|>",
|
| 2021 |
+
"lstrip": false,
|
| 2022 |
+
"normalized": false,
|
| 2023 |
+
"rstrip": false,
|
| 2024 |
+
"single_word": false,
|
| 2025 |
+
"special": true
|
| 2026 |
+
},
|
| 2027 |
+
"128253": {
|
| 2028 |
+
"content": "<|reserved_special_token_248|>",
|
| 2029 |
+
"lstrip": false,
|
| 2030 |
+
"normalized": false,
|
| 2031 |
+
"rstrip": false,
|
| 2032 |
+
"single_word": false,
|
| 2033 |
+
"special": true
|
| 2034 |
+
},
|
| 2035 |
+
"128254": {
|
| 2036 |
+
"content": "<|reserved_special_token_249|>",
|
| 2037 |
+
"lstrip": false,
|
| 2038 |
+
"normalized": false,
|
| 2039 |
+
"rstrip": false,
|
| 2040 |
+
"single_word": false,
|
| 2041 |
+
"special": true
|
| 2042 |
+
},
|
| 2043 |
+
"128255": {
|
| 2044 |
+
"content": "<|reserved_special_token_250|>",
|
| 2045 |
+
"lstrip": false,
|
| 2046 |
+
"normalized": false,
|
| 2047 |
+
"rstrip": false,
|
| 2048 |
+
"single_word": false,
|
| 2049 |
+
"special": true
|
| 2050 |
+
}
|
| 2051 |
+
},
|
| 2052 |
+
"bos_token": "<|begin_of_text|>",
|
| 2053 |
+
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
| 2054 |
+
"clean_up_tokenization_spaces": true,
|
| 2055 |
+
"eos_token": "<|eot_id|>",
|
| 2056 |
+
"model_input_names": [
|
| 2057 |
+
"input_ids",
|
| 2058 |
+
"attention_mask"
|
| 2059 |
+
],
|
| 2060 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 2061 |
+
"pad_token": "<|finetune_right_pad_id|>",
|
| 2062 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2063 |
+
}
|
checkpoint-441/trainer_state.json
ADDED
|
@@ -0,0 +1,3184 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 7.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 441,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0,
|
| 13 |
+
"eval_loss": 3.201144218444824,
|
| 14 |
+
"eval_runtime": 137.3071,
|
| 15 |
+
"eval_samples_per_second": 141.697,
|
| 16 |
+
"eval_steps_per_second": 1.107,
|
| 17 |
+
"step": 0
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.015873015873015872,
|
| 21 |
+
"grad_norm": 0.1918456107378006,
|
| 22 |
+
"learning_rate": 0.0001,
|
| 23 |
+
"loss": 3.2274,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.031746031746031744,
|
| 28 |
+
"grad_norm": 0.21201364696025848,
|
| 29 |
+
"learning_rate": 0.0001,
|
| 30 |
+
"loss": 2.9728,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.047619047619047616,
|
| 35 |
+
"grad_norm": 0.1865563839673996,
|
| 36 |
+
"learning_rate": 0.0001,
|
| 37 |
+
"loss": 3.1107,
|
| 38 |
+
"step": 3
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.06349206349206349,
|
| 42 |
+
"grad_norm": 0.256558358669281,
|
| 43 |
+
"learning_rate": 0.0001,
|
| 44 |
+
"loss": 3.1054,
|
| 45 |
+
"step": 4
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.07936507936507936,
|
| 49 |
+
"grad_norm": 0.30679622292518616,
|
| 50 |
+
"learning_rate": 0.0001,
|
| 51 |
+
"loss": 3.1735,
|
| 52 |
+
"step": 5
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.09523809523809523,
|
| 56 |
+
"grad_norm": 0.27670395374298096,
|
| 57 |
+
"learning_rate": 0.0001,
|
| 58 |
+
"loss": 3.175,
|
| 59 |
+
"step": 6
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.1111111111111111,
|
| 63 |
+
"grad_norm": 0.29917973279953003,
|
| 64 |
+
"learning_rate": 0.0001,
|
| 65 |
+
"loss": 3.0947,
|
| 66 |
+
"step": 7
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.12698412698412698,
|
| 70 |
+
"grad_norm": 0.28829720616340637,
|
| 71 |
+
"learning_rate": 0.0001,
|
| 72 |
+
"loss": 2.9762,
|
| 73 |
+
"step": 8
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.14285714285714285,
|
| 77 |
+
"grad_norm": 0.363932728767395,
|
| 78 |
+
"learning_rate": 0.0001,
|
| 79 |
+
"loss": 3.0589,
|
| 80 |
+
"step": 9
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.15873015873015872,
|
| 84 |
+
"grad_norm": 0.3397577702999115,
|
| 85 |
+
"learning_rate": 0.0001,
|
| 86 |
+
"loss": 3.0165,
|
| 87 |
+
"step": 10
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.1746031746031746,
|
| 91 |
+
"grad_norm": 0.3906390368938446,
|
| 92 |
+
"learning_rate": 0.0001,
|
| 93 |
+
"loss": 2.9656,
|
| 94 |
+
"step": 11
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.19047619047619047,
|
| 98 |
+
"grad_norm": 0.39602699875831604,
|
| 99 |
+
"learning_rate": 0.0001,
|
| 100 |
+
"loss": 2.9934,
|
| 101 |
+
"step": 12
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.20634920634920634,
|
| 105 |
+
"grad_norm": 0.5025639533996582,
|
| 106 |
+
"learning_rate": 0.0001,
|
| 107 |
+
"loss": 2.9371,
|
| 108 |
+
"step": 13
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.2222222222222222,
|
| 112 |
+
"grad_norm": 0.41868922114372253,
|
| 113 |
+
"learning_rate": 0.0001,
|
| 114 |
+
"loss": 2.8788,
|
| 115 |
+
"step": 14
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.23809523809523808,
|
| 119 |
+
"grad_norm": 0.4148877263069153,
|
| 120 |
+
"learning_rate": 0.0001,
|
| 121 |
+
"loss": 2.8633,
|
| 122 |
+
"step": 15
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.25396825396825395,
|
| 126 |
+
"grad_norm": 0.36584576964378357,
|
| 127 |
+
"learning_rate": 0.0001,
|
| 128 |
+
"loss": 2.7781,
|
| 129 |
+
"step": 16
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.2698412698412698,
|
| 133 |
+
"grad_norm": 0.5037583112716675,
|
| 134 |
+
"learning_rate": 0.0001,
|
| 135 |
+
"loss": 2.7633,
|
| 136 |
+
"step": 17
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.2857142857142857,
|
| 140 |
+
"grad_norm": 0.37624871730804443,
|
| 141 |
+
"learning_rate": 0.0001,
|
| 142 |
+
"loss": 2.7114,
|
| 143 |
+
"step": 18
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.30158730158730157,
|
| 147 |
+
"grad_norm": 0.3943127989768982,
|
| 148 |
+
"learning_rate": 0.0001,
|
| 149 |
+
"loss": 2.7029,
|
| 150 |
+
"step": 19
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.31746031746031744,
|
| 154 |
+
"grad_norm": 0.300891250371933,
|
| 155 |
+
"learning_rate": 0.0001,
|
| 156 |
+
"loss": 2.5994,
|
| 157 |
+
"step": 20
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.3333333333333333,
|
| 161 |
+
"grad_norm": 0.2970874309539795,
|
| 162 |
+
"learning_rate": 0.0001,
|
| 163 |
+
"loss": 2.6166,
|
| 164 |
+
"step": 21
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.3492063492063492,
|
| 168 |
+
"grad_norm": 0.29132720828056335,
|
| 169 |
+
"learning_rate": 0.0001,
|
| 170 |
+
"loss": 2.627,
|
| 171 |
+
"step": 22
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.36507936507936506,
|
| 175 |
+
"grad_norm": 0.259672075510025,
|
| 176 |
+
"learning_rate": 0.0001,
|
| 177 |
+
"loss": 2.6551,
|
| 178 |
+
"step": 23
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.38095238095238093,
|
| 182 |
+
"grad_norm": 0.3438767194747925,
|
| 183 |
+
"learning_rate": 0.0001,
|
| 184 |
+
"loss": 2.62,
|
| 185 |
+
"step": 24
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.3968253968253968,
|
| 189 |
+
"grad_norm": 0.36698848009109497,
|
| 190 |
+
"learning_rate": 0.0001,
|
| 191 |
+
"loss": 2.5411,
|
| 192 |
+
"step": 25
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.4126984126984127,
|
| 196 |
+
"grad_norm": 0.500142514705658,
|
| 197 |
+
"learning_rate": 0.0001,
|
| 198 |
+
"loss": 2.5366,
|
| 199 |
+
"step": 26
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.42857142857142855,
|
| 203 |
+
"grad_norm": 0.3668989837169647,
|
| 204 |
+
"learning_rate": 0.0001,
|
| 205 |
+
"loss": 2.5864,
|
| 206 |
+
"step": 27
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.4444444444444444,
|
| 210 |
+
"grad_norm": 0.5424588322639465,
|
| 211 |
+
"learning_rate": 0.0001,
|
| 212 |
+
"loss": 2.5303,
|
| 213 |
+
"step": 28
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.4603174603174603,
|
| 217 |
+
"grad_norm": 0.4026002585887909,
|
| 218 |
+
"learning_rate": 0.0001,
|
| 219 |
+
"loss": 2.4917,
|
| 220 |
+
"step": 29
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.47619047619047616,
|
| 224 |
+
"grad_norm": 0.5646772384643555,
|
| 225 |
+
"learning_rate": 0.0001,
|
| 226 |
+
"loss": 2.4438,
|
| 227 |
+
"step": 30
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.49206349206349204,
|
| 231 |
+
"grad_norm": 0.43536150455474854,
|
| 232 |
+
"learning_rate": 0.0001,
|
| 233 |
+
"loss": 2.4743,
|
| 234 |
+
"step": 31
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.5079365079365079,
|
| 238 |
+
"grad_norm": 0.34031543135643005,
|
| 239 |
+
"learning_rate": 0.0001,
|
| 240 |
+
"loss": 2.4207,
|
| 241 |
+
"step": 32
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.5238095238095238,
|
| 245 |
+
"grad_norm": 0.30232375860214233,
|
| 246 |
+
"learning_rate": 0.0001,
|
| 247 |
+
"loss": 2.4499,
|
| 248 |
+
"step": 33
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.5396825396825397,
|
| 252 |
+
"grad_norm": 0.31755775213241577,
|
| 253 |
+
"learning_rate": 0.0001,
|
| 254 |
+
"loss": 2.2954,
|
| 255 |
+
"step": 34
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.5555555555555556,
|
| 259 |
+
"grad_norm": 0.2854190170764923,
|
| 260 |
+
"learning_rate": 0.0001,
|
| 261 |
+
"loss": 2.4148,
|
| 262 |
+
"step": 35
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.5714285714285714,
|
| 266 |
+
"grad_norm": 0.2745571434497833,
|
| 267 |
+
"learning_rate": 0.0001,
|
| 268 |
+
"loss": 2.2658,
|
| 269 |
+
"step": 36
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.5873015873015873,
|
| 273 |
+
"grad_norm": 0.26832568645477295,
|
| 274 |
+
"learning_rate": 0.0001,
|
| 275 |
+
"loss": 2.4336,
|
| 276 |
+
"step": 37
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.6031746031746031,
|
| 280 |
+
"grad_norm": 0.2571115493774414,
|
| 281 |
+
"learning_rate": 0.0001,
|
| 282 |
+
"loss": 2.3325,
|
| 283 |
+
"step": 38
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.6190476190476191,
|
| 287 |
+
"grad_norm": 0.27978894114494324,
|
| 288 |
+
"learning_rate": 0.0001,
|
| 289 |
+
"loss": 2.3623,
|
| 290 |
+
"step": 39
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.6349206349206349,
|
| 294 |
+
"grad_norm": 0.27634117007255554,
|
| 295 |
+
"learning_rate": 0.0001,
|
| 296 |
+
"loss": 2.3947,
|
| 297 |
+
"step": 40
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.6507936507936508,
|
| 301 |
+
"grad_norm": 0.2856747806072235,
|
| 302 |
+
"learning_rate": 0.0001,
|
| 303 |
+
"loss": 2.3065,
|
| 304 |
+
"step": 41
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.6666666666666666,
|
| 308 |
+
"grad_norm": 0.273630827665329,
|
| 309 |
+
"learning_rate": 0.0001,
|
| 310 |
+
"loss": 2.2969,
|
| 311 |
+
"step": 42
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.6825396825396826,
|
| 315 |
+
"grad_norm": 0.294461190700531,
|
| 316 |
+
"learning_rate": 0.0001,
|
| 317 |
+
"loss": 2.3315,
|
| 318 |
+
"step": 43
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.6984126984126984,
|
| 322 |
+
"grad_norm": 0.27730676531791687,
|
| 323 |
+
"learning_rate": 0.0001,
|
| 324 |
+
"loss": 2.2656,
|
| 325 |
+
"step": 44
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.7142857142857143,
|
| 329 |
+
"grad_norm": 0.28087306022644043,
|
| 330 |
+
"learning_rate": 0.0001,
|
| 331 |
+
"loss": 2.1831,
|
| 332 |
+
"step": 45
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.7301587301587301,
|
| 336 |
+
"grad_norm": 0.2754216194152832,
|
| 337 |
+
"learning_rate": 0.0001,
|
| 338 |
+
"loss": 2.2577,
|
| 339 |
+
"step": 46
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.746031746031746,
|
| 343 |
+
"grad_norm": 0.29807186126708984,
|
| 344 |
+
"learning_rate": 0.0001,
|
| 345 |
+
"loss": 2.3723,
|
| 346 |
+
"step": 47
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.7619047619047619,
|
| 350 |
+
"grad_norm": 0.3020806908607483,
|
| 351 |
+
"learning_rate": 0.0001,
|
| 352 |
+
"loss": 2.309,
|
| 353 |
+
"step": 48
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.7777777777777778,
|
| 357 |
+
"grad_norm": 0.2983008027076721,
|
| 358 |
+
"learning_rate": 0.0001,
|
| 359 |
+
"loss": 2.1748,
|
| 360 |
+
"step": 49
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.7936507936507936,
|
| 364 |
+
"grad_norm": 0.30773478746414185,
|
| 365 |
+
"learning_rate": 0.0001,
|
| 366 |
+
"loss": 2.2758,
|
| 367 |
+
"step": 50
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.8095238095238095,
|
| 371 |
+
"grad_norm": 0.30065926909446716,
|
| 372 |
+
"learning_rate": 0.0001,
|
| 373 |
+
"loss": 2.2587,
|
| 374 |
+
"step": 51
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.8253968253968254,
|
| 378 |
+
"grad_norm": 0.3026188313961029,
|
| 379 |
+
"learning_rate": 0.0001,
|
| 380 |
+
"loss": 2.1818,
|
| 381 |
+
"step": 52
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.8412698412698413,
|
| 385 |
+
"grad_norm": 0.30180782079696655,
|
| 386 |
+
"learning_rate": 0.0001,
|
| 387 |
+
"loss": 2.1304,
|
| 388 |
+
"step": 53
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.8571428571428571,
|
| 392 |
+
"grad_norm": 0.29865095019340515,
|
| 393 |
+
"learning_rate": 0.0001,
|
| 394 |
+
"loss": 2.2356,
|
| 395 |
+
"step": 54
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.873015873015873,
|
| 399 |
+
"grad_norm": 0.30642348527908325,
|
| 400 |
+
"learning_rate": 0.0001,
|
| 401 |
+
"loss": 2.2411,
|
| 402 |
+
"step": 55
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.8888888888888888,
|
| 406 |
+
"grad_norm": 0.30322977900505066,
|
| 407 |
+
"learning_rate": 0.0001,
|
| 408 |
+
"loss": 2.2252,
|
| 409 |
+
"step": 56
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.9047619047619048,
|
| 413 |
+
"grad_norm": 0.2848075032234192,
|
| 414 |
+
"learning_rate": 0.0001,
|
| 415 |
+
"loss": 2.1687,
|
| 416 |
+
"step": 57
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.9206349206349206,
|
| 420 |
+
"grad_norm": 0.2916617691516876,
|
| 421 |
+
"learning_rate": 0.0001,
|
| 422 |
+
"loss": 2.1998,
|
| 423 |
+
"step": 58
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.9365079365079365,
|
| 427 |
+
"grad_norm": 0.2930757999420166,
|
| 428 |
+
"learning_rate": 0.0001,
|
| 429 |
+
"loss": 2.2222,
|
| 430 |
+
"step": 59
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.9523809523809523,
|
| 434 |
+
"grad_norm": 0.28044334053993225,
|
| 435 |
+
"learning_rate": 0.0001,
|
| 436 |
+
"loss": 2.1614,
|
| 437 |
+
"step": 60
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.9682539682539683,
|
| 441 |
+
"grad_norm": 0.29108643531799316,
|
| 442 |
+
"learning_rate": 0.0001,
|
| 443 |
+
"loss": 2.2684,
|
| 444 |
+
"step": 61
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.9841269841269841,
|
| 448 |
+
"grad_norm": 0.2764103412628174,
|
| 449 |
+
"learning_rate": 0.0001,
|
| 450 |
+
"loss": 2.152,
|
| 451 |
+
"step": 62
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.0,
|
| 455 |
+
"grad_norm": 0.290540486574173,
|
| 456 |
+
"learning_rate": 0.0001,
|
| 457 |
+
"loss": 2.2189,
|
| 458 |
+
"step": 63
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.0,
|
| 462 |
+
"eval_loss": 2.1553854942321777,
|
| 463 |
+
"eval_runtime": 134.4627,
|
| 464 |
+
"eval_samples_per_second": 144.694,
|
| 465 |
+
"eval_steps_per_second": 1.13,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.0158730158730158,
|
| 470 |
+
"grad_norm": 0.28722119331359863,
|
| 471 |
+
"learning_rate": 0.0001,
|
| 472 |
+
"loss": 2.119,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.0317460317460316,
|
| 477 |
+
"grad_norm": 0.2941075265407562,
|
| 478 |
+
"learning_rate": 0.0001,
|
| 479 |
+
"loss": 2.1355,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 1.0476190476190477,
|
| 484 |
+
"grad_norm": 0.27956002950668335,
|
| 485 |
+
"learning_rate": 0.0001,
|
| 486 |
+
"loss": 2.0956,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 1.0634920634920635,
|
| 491 |
+
"grad_norm": 0.2902751863002777,
|
| 492 |
+
"learning_rate": 0.0001,
|
| 493 |
+
"loss": 2.1677,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.0793650793650793,
|
| 498 |
+
"grad_norm": 0.28545236587524414,
|
| 499 |
+
"learning_rate": 0.0001,
|
| 500 |
+
"loss": 2.1038,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.0952380952380953,
|
| 505 |
+
"grad_norm": 0.28611037135124207,
|
| 506 |
+
"learning_rate": 0.0001,
|
| 507 |
+
"loss": 2.0701,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 1.1111111111111112,
|
| 512 |
+
"grad_norm": 0.2909831404685974,
|
| 513 |
+
"learning_rate": 0.0001,
|
| 514 |
+
"loss": 2.1483,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.126984126984127,
|
| 519 |
+
"grad_norm": 0.29801449179649353,
|
| 520 |
+
"learning_rate": 0.0001,
|
| 521 |
+
"loss": 2.0127,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 1.1428571428571428,
|
| 526 |
+
"grad_norm": 0.3016774356365204,
|
| 527 |
+
"learning_rate": 0.0001,
|
| 528 |
+
"loss": 2.072,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 1.1587301587301586,
|
| 533 |
+
"grad_norm": 0.302207887172699,
|
| 534 |
+
"learning_rate": 0.0001,
|
| 535 |
+
"loss": 2.0818,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 1.1746031746031746,
|
| 540 |
+
"grad_norm": 0.3024630844593048,
|
| 541 |
+
"learning_rate": 0.0001,
|
| 542 |
+
"loss": 2.0775,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 1.1904761904761905,
|
| 547 |
+
"grad_norm": 0.3113912045955658,
|
| 548 |
+
"learning_rate": 0.0001,
|
| 549 |
+
"loss": 2.0484,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 1.2063492063492063,
|
| 554 |
+
"grad_norm": 0.3100714385509491,
|
| 555 |
+
"learning_rate": 0.0001,
|
| 556 |
+
"loss": 2.0322,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 1.2222222222222223,
|
| 561 |
+
"grad_norm": 0.31157463788986206,
|
| 562 |
+
"learning_rate": 0.0001,
|
| 563 |
+
"loss": 2.0123,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 1.2380952380952381,
|
| 568 |
+
"grad_norm": 0.30897048115730286,
|
| 569 |
+
"learning_rate": 0.0001,
|
| 570 |
+
"loss": 2.0196,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 1.253968253968254,
|
| 575 |
+
"grad_norm": 0.32494208216667175,
|
| 576 |
+
"learning_rate": 0.0001,
|
| 577 |
+
"loss": 2.1164,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 1.2698412698412698,
|
| 582 |
+
"grad_norm": 0.3228481113910675,
|
| 583 |
+
"learning_rate": 0.0001,
|
| 584 |
+
"loss": 2.0119,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 1.2857142857142856,
|
| 589 |
+
"grad_norm": 0.31433093547821045,
|
| 590 |
+
"learning_rate": 0.0001,
|
| 591 |
+
"loss": 1.9773,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 1.3015873015873016,
|
| 596 |
+
"grad_norm": 0.33841848373413086,
|
| 597 |
+
"learning_rate": 0.0001,
|
| 598 |
+
"loss": 2.0676,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 1.3174603174603174,
|
| 603 |
+
"grad_norm": 0.33233773708343506,
|
| 604 |
+
"learning_rate": 0.0001,
|
| 605 |
+
"loss": 2.0717,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 1.3333333333333333,
|
| 610 |
+
"grad_norm": 0.34447962045669556,
|
| 611 |
+
"learning_rate": 0.0001,
|
| 612 |
+
"loss": 2.1348,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 1.3492063492063493,
|
| 617 |
+
"grad_norm": 0.33957433700561523,
|
| 618 |
+
"learning_rate": 0.0001,
|
| 619 |
+
"loss": 2.0339,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 1.3650793650793651,
|
| 624 |
+
"grad_norm": 0.3519391715526581,
|
| 625 |
+
"learning_rate": 0.0001,
|
| 626 |
+
"loss": 2.0317,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 1.380952380952381,
|
| 631 |
+
"grad_norm": 0.3266676068305969,
|
| 632 |
+
"learning_rate": 0.0001,
|
| 633 |
+
"loss": 1.9932,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 1.3968253968253967,
|
| 638 |
+
"grad_norm": 0.3306258022785187,
|
| 639 |
+
"learning_rate": 0.0001,
|
| 640 |
+
"loss": 1.9695,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 1.4126984126984126,
|
| 645 |
+
"grad_norm": 0.3315640389919281,
|
| 646 |
+
"learning_rate": 0.0001,
|
| 647 |
+
"loss": 1.9975,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 1.4285714285714286,
|
| 652 |
+
"grad_norm": 0.33888551592826843,
|
| 653 |
+
"learning_rate": 0.0001,
|
| 654 |
+
"loss": 2.0804,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 1.4444444444444444,
|
| 659 |
+
"grad_norm": 0.3356088399887085,
|
| 660 |
+
"learning_rate": 0.0001,
|
| 661 |
+
"loss": 2.0882,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 1.4603174603174602,
|
| 666 |
+
"grad_norm": 0.3448535203933716,
|
| 667 |
+
"learning_rate": 0.0001,
|
| 668 |
+
"loss": 2.0641,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.4761904761904763,
|
| 673 |
+
"grad_norm": 0.33544135093688965,
|
| 674 |
+
"learning_rate": 0.0001,
|
| 675 |
+
"loss": 2.0657,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 1.492063492063492,
|
| 680 |
+
"grad_norm": 0.32962003350257874,
|
| 681 |
+
"learning_rate": 0.0001,
|
| 682 |
+
"loss": 1.9702,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 1.507936507936508,
|
| 687 |
+
"grad_norm": 0.3348037898540497,
|
| 688 |
+
"learning_rate": 0.0001,
|
| 689 |
+
"loss": 2.0495,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 1.5238095238095237,
|
| 694 |
+
"grad_norm": 0.35935646295547485,
|
| 695 |
+
"learning_rate": 0.0001,
|
| 696 |
+
"loss": 2.0343,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 1.5396825396825395,
|
| 701 |
+
"grad_norm": 0.35089877247810364,
|
| 702 |
+
"learning_rate": 0.0001,
|
| 703 |
+
"loss": 1.9913,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 1.5555555555555556,
|
| 708 |
+
"grad_norm": 0.35951006412506104,
|
| 709 |
+
"learning_rate": 0.0001,
|
| 710 |
+
"loss": 2.036,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.5714285714285714,
|
| 715 |
+
"grad_norm": 0.3543176054954529,
|
| 716 |
+
"learning_rate": 0.0001,
|
| 717 |
+
"loss": 2.0005,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 1.5873015873015874,
|
| 722 |
+
"grad_norm": 0.34387317299842834,
|
| 723 |
+
"learning_rate": 0.0001,
|
| 724 |
+
"loss": 2.0283,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 1.6031746031746033,
|
| 729 |
+
"grad_norm": 0.3506092429161072,
|
| 730 |
+
"learning_rate": 0.0001,
|
| 731 |
+
"loss": 2.0301,
|
| 732 |
+
"step": 101
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 1.619047619047619,
|
| 736 |
+
"grad_norm": 0.3446710705757141,
|
| 737 |
+
"learning_rate": 0.0001,
|
| 738 |
+
"loss": 1.9749,
|
| 739 |
+
"step": 102
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 1.6349206349206349,
|
| 743 |
+
"grad_norm": 0.3415977656841278,
|
| 744 |
+
"learning_rate": 0.0001,
|
| 745 |
+
"loss": 1.9853,
|
| 746 |
+
"step": 103
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 1.6507936507936507,
|
| 750 |
+
"grad_norm": 0.3609831631183624,
|
| 751 |
+
"learning_rate": 0.0001,
|
| 752 |
+
"loss": 2.0477,
|
| 753 |
+
"step": 104
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 1.6666666666666665,
|
| 757 |
+
"grad_norm": 0.35015106201171875,
|
| 758 |
+
"learning_rate": 0.0001,
|
| 759 |
+
"loss": 2.0356,
|
| 760 |
+
"step": 105
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 1.6825396825396826,
|
| 764 |
+
"grad_norm": 0.3593216836452484,
|
| 765 |
+
"learning_rate": 0.0001,
|
| 766 |
+
"loss": 1.8311,
|
| 767 |
+
"step": 106
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 1.6984126984126984,
|
| 771 |
+
"grad_norm": 0.35230639576911926,
|
| 772 |
+
"learning_rate": 0.0001,
|
| 773 |
+
"loss": 1.9562,
|
| 774 |
+
"step": 107
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 1.7142857142857144,
|
| 778 |
+
"grad_norm": 0.3519164025783539,
|
| 779 |
+
"learning_rate": 0.0001,
|
| 780 |
+
"loss": 2.0257,
|
| 781 |
+
"step": 108
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 1.7301587301587302,
|
| 785 |
+
"grad_norm": 0.3627997934818268,
|
| 786 |
+
"learning_rate": 0.0001,
|
| 787 |
+
"loss": 2.0012,
|
| 788 |
+
"step": 109
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 1.746031746031746,
|
| 792 |
+
"grad_norm": 0.37876084446907043,
|
| 793 |
+
"learning_rate": 0.0001,
|
| 794 |
+
"loss": 1.9746,
|
| 795 |
+
"step": 110
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 1.7619047619047619,
|
| 799 |
+
"grad_norm": 0.37692707777023315,
|
| 800 |
+
"learning_rate": 0.0001,
|
| 801 |
+
"loss": 2.0422,
|
| 802 |
+
"step": 111
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 1.7777777777777777,
|
| 806 |
+
"grad_norm": 0.3628651201725006,
|
| 807 |
+
"learning_rate": 0.0001,
|
| 808 |
+
"loss": 1.9981,
|
| 809 |
+
"step": 112
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 1.7936507936507935,
|
| 813 |
+
"grad_norm": 0.35194242000579834,
|
| 814 |
+
"learning_rate": 0.0001,
|
| 815 |
+
"loss": 1.9343,
|
| 816 |
+
"step": 113
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 1.8095238095238095,
|
| 820 |
+
"grad_norm": 0.36310839653015137,
|
| 821 |
+
"learning_rate": 0.0001,
|
| 822 |
+
"loss": 2.0421,
|
| 823 |
+
"step": 114
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 1.8253968253968254,
|
| 827 |
+
"grad_norm": 0.3339640200138092,
|
| 828 |
+
"learning_rate": 0.0001,
|
| 829 |
+
"loss": 1.9606,
|
| 830 |
+
"step": 115
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 1.8412698412698414,
|
| 834 |
+
"grad_norm": 0.3632456958293915,
|
| 835 |
+
"learning_rate": 0.0001,
|
| 836 |
+
"loss": 1.8558,
|
| 837 |
+
"step": 116
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 1.8571428571428572,
|
| 841 |
+
"grad_norm": 0.36308878660202026,
|
| 842 |
+
"learning_rate": 0.0001,
|
| 843 |
+
"loss": 2.0127,
|
| 844 |
+
"step": 117
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 1.873015873015873,
|
| 848 |
+
"grad_norm": 0.3537601828575134,
|
| 849 |
+
"learning_rate": 0.0001,
|
| 850 |
+
"loss": 1.9704,
|
| 851 |
+
"step": 118
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 1.8888888888888888,
|
| 855 |
+
"grad_norm": 0.3581252098083496,
|
| 856 |
+
"learning_rate": 0.0001,
|
| 857 |
+
"loss": 1.9086,
|
| 858 |
+
"step": 119
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 1.9047619047619047,
|
| 862 |
+
"grad_norm": 0.37275415658950806,
|
| 863 |
+
"learning_rate": 0.0001,
|
| 864 |
+
"loss": 2.0914,
|
| 865 |
+
"step": 120
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 1.9206349206349205,
|
| 869 |
+
"grad_norm": 0.36517035961151123,
|
| 870 |
+
"learning_rate": 0.0001,
|
| 871 |
+
"loss": 1.9529,
|
| 872 |
+
"step": 121
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 1.9365079365079365,
|
| 876 |
+
"grad_norm": 0.3566952049732208,
|
| 877 |
+
"learning_rate": 0.0001,
|
| 878 |
+
"loss": 1.8498,
|
| 879 |
+
"step": 122
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 1.9523809523809523,
|
| 883 |
+
"grad_norm": 0.36236587166786194,
|
| 884 |
+
"learning_rate": 0.0001,
|
| 885 |
+
"loss": 1.9652,
|
| 886 |
+
"step": 123
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 1.9682539682539684,
|
| 890 |
+
"grad_norm": 0.3652929663658142,
|
| 891 |
+
"learning_rate": 0.0001,
|
| 892 |
+
"loss": 2.0085,
|
| 893 |
+
"step": 124
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 1.9841269841269842,
|
| 897 |
+
"grad_norm": 0.3546443581581116,
|
| 898 |
+
"learning_rate": 0.0001,
|
| 899 |
+
"loss": 1.9192,
|
| 900 |
+
"step": 125
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 2.0,
|
| 904 |
+
"grad_norm": 0.3752649128437042,
|
| 905 |
+
"learning_rate": 0.0001,
|
| 906 |
+
"loss": 1.9932,
|
| 907 |
+
"step": 126
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 2.0,
|
| 911 |
+
"eval_loss": 1.9884382486343384,
|
| 912 |
+
"eval_runtime": 134.41,
|
| 913 |
+
"eval_samples_per_second": 144.751,
|
| 914 |
+
"eval_steps_per_second": 1.131,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 2.015873015873016,
|
| 919 |
+
"grad_norm": 0.35680314898490906,
|
| 920 |
+
"learning_rate": 0.0001,
|
| 921 |
+
"loss": 2.0274,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 2.0317460317460316,
|
| 926 |
+
"grad_norm": 0.34379494190216064,
|
| 927 |
+
"learning_rate": 0.0001,
|
| 928 |
+
"loss": 1.944,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 2.0476190476190474,
|
| 933 |
+
"grad_norm": 0.351840615272522,
|
| 934 |
+
"learning_rate": 0.0001,
|
| 935 |
+
"loss": 1.9053,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 2.0634920634920633,
|
| 940 |
+
"grad_norm": 0.38462555408477783,
|
| 941 |
+
"learning_rate": 0.0001,
|
| 942 |
+
"loss": 1.9082,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 2.0793650793650795,
|
| 947 |
+
"grad_norm": 0.37032756209373474,
|
| 948 |
+
"learning_rate": 0.0001,
|
| 949 |
+
"loss": 1.9048,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 2.0952380952380953,
|
| 954 |
+
"grad_norm": 0.36423760652542114,
|
| 955 |
+
"learning_rate": 0.0001,
|
| 956 |
+
"loss": 1.9041,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 2.111111111111111,
|
| 961 |
+
"grad_norm": 0.36103999614715576,
|
| 962 |
+
"learning_rate": 0.0001,
|
| 963 |
+
"loss": 1.7832,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 2.126984126984127,
|
| 968 |
+
"grad_norm": 0.36970341205596924,
|
| 969 |
+
"learning_rate": 0.0001,
|
| 970 |
+
"loss": 1.8562,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 2.142857142857143,
|
| 975 |
+
"grad_norm": 0.38281646370887756,
|
| 976 |
+
"learning_rate": 0.0001,
|
| 977 |
+
"loss": 1.8671,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 2.1587301587301586,
|
| 982 |
+
"grad_norm": 0.4053700864315033,
|
| 983 |
+
"learning_rate": 0.0001,
|
| 984 |
+
"loss": 2.0125,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 2.1746031746031744,
|
| 989 |
+
"grad_norm": 0.40937232971191406,
|
| 990 |
+
"learning_rate": 0.0001,
|
| 991 |
+
"loss": 1.9053,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 2.1904761904761907,
|
| 996 |
+
"grad_norm": 0.39173007011413574,
|
| 997 |
+
"learning_rate": 0.0001,
|
| 998 |
+
"loss": 1.9645,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 2.2063492063492065,
|
| 1003 |
+
"grad_norm": 0.39559757709503174,
|
| 1004 |
+
"learning_rate": 0.0001,
|
| 1005 |
+
"loss": 1.9285,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 2.2222222222222223,
|
| 1010 |
+
"grad_norm": 0.4081740975379944,
|
| 1011 |
+
"learning_rate": 0.0001,
|
| 1012 |
+
"loss": 1.8501,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 2.238095238095238,
|
| 1017 |
+
"grad_norm": 0.4095621705055237,
|
| 1018 |
+
"learning_rate": 0.0001,
|
| 1019 |
+
"loss": 1.9005,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 2.253968253968254,
|
| 1024 |
+
"grad_norm": 0.4242890179157257,
|
| 1025 |
+
"learning_rate": 0.0001,
|
| 1026 |
+
"loss": 1.8266,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 2.2698412698412698,
|
| 1031 |
+
"grad_norm": 0.4077770709991455,
|
| 1032 |
+
"learning_rate": 0.0001,
|
| 1033 |
+
"loss": 1.8656,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 2.2857142857142856,
|
| 1038 |
+
"grad_norm": 0.4218343496322632,
|
| 1039 |
+
"learning_rate": 0.0001,
|
| 1040 |
+
"loss": 1.9931,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 2.3015873015873014,
|
| 1045 |
+
"grad_norm": 0.3991089463233948,
|
| 1046 |
+
"learning_rate": 0.0001,
|
| 1047 |
+
"loss": 1.8629,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 2.317460317460317,
|
| 1052 |
+
"grad_norm": 0.42081835865974426,
|
| 1053 |
+
"learning_rate": 0.0001,
|
| 1054 |
+
"loss": 1.8855,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 2.3333333333333335,
|
| 1059 |
+
"grad_norm": 0.4178907573223114,
|
| 1060 |
+
"learning_rate": 0.0001,
|
| 1061 |
+
"loss": 1.8834,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 2.3492063492063493,
|
| 1066 |
+
"grad_norm": 0.4098721146583557,
|
| 1067 |
+
"learning_rate": 0.0001,
|
| 1068 |
+
"loss": 1.7691,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 2.365079365079365,
|
| 1073 |
+
"grad_norm": 0.4463600814342499,
|
| 1074 |
+
"learning_rate": 0.0001,
|
| 1075 |
+
"loss": 2.0333,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 2.380952380952381,
|
| 1080 |
+
"grad_norm": 0.4598867893218994,
|
| 1081 |
+
"learning_rate": 0.0001,
|
| 1082 |
+
"loss": 1.8711,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 2.3968253968253967,
|
| 1087 |
+
"grad_norm": 0.42520642280578613,
|
| 1088 |
+
"learning_rate": 0.0001,
|
| 1089 |
+
"loss": 1.8435,
|
| 1090 |
+
"step": 151
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 2.4126984126984126,
|
| 1094 |
+
"grad_norm": 0.43913593888282776,
|
| 1095 |
+
"learning_rate": 0.0001,
|
| 1096 |
+
"loss": 1.9094,
|
| 1097 |
+
"step": 152
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 2.4285714285714284,
|
| 1101 |
+
"grad_norm": 0.4239555299282074,
|
| 1102 |
+
"learning_rate": 0.0001,
|
| 1103 |
+
"loss": 1.795,
|
| 1104 |
+
"step": 153
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 2.4444444444444446,
|
| 1108 |
+
"grad_norm": 0.43195414543151855,
|
| 1109 |
+
"learning_rate": 0.0001,
|
| 1110 |
+
"loss": 1.9467,
|
| 1111 |
+
"step": 154
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 2.4603174603174605,
|
| 1115 |
+
"grad_norm": 0.42905962467193604,
|
| 1116 |
+
"learning_rate": 0.0001,
|
| 1117 |
+
"loss": 1.8613,
|
| 1118 |
+
"step": 155
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 2.4761904761904763,
|
| 1122 |
+
"grad_norm": 0.44274038076400757,
|
| 1123 |
+
"learning_rate": 0.0001,
|
| 1124 |
+
"loss": 1.9131,
|
| 1125 |
+
"step": 156
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 2.492063492063492,
|
| 1129 |
+
"grad_norm": 0.42327380180358887,
|
| 1130 |
+
"learning_rate": 0.0001,
|
| 1131 |
+
"loss": 1.8945,
|
| 1132 |
+
"step": 157
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 2.507936507936508,
|
| 1136 |
+
"grad_norm": 0.43506136536598206,
|
| 1137 |
+
"learning_rate": 0.0001,
|
| 1138 |
+
"loss": 1.8626,
|
| 1139 |
+
"step": 158
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 2.5238095238095237,
|
| 1143 |
+
"grad_norm": 0.4368724524974823,
|
| 1144 |
+
"learning_rate": 0.0001,
|
| 1145 |
+
"loss": 1.8973,
|
| 1146 |
+
"step": 159
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 2.5396825396825395,
|
| 1150 |
+
"grad_norm": 0.43993279337882996,
|
| 1151 |
+
"learning_rate": 0.0001,
|
| 1152 |
+
"loss": 1.8404,
|
| 1153 |
+
"step": 160
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 2.5555555555555554,
|
| 1157 |
+
"grad_norm": 0.43752744793891907,
|
| 1158 |
+
"learning_rate": 0.0001,
|
| 1159 |
+
"loss": 1.9374,
|
| 1160 |
+
"step": 161
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 2.571428571428571,
|
| 1164 |
+
"grad_norm": 0.4344784915447235,
|
| 1165 |
+
"learning_rate": 0.0001,
|
| 1166 |
+
"loss": 1.8943,
|
| 1167 |
+
"step": 162
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 2.5873015873015874,
|
| 1171 |
+
"grad_norm": 0.41896679997444153,
|
| 1172 |
+
"learning_rate": 0.0001,
|
| 1173 |
+
"loss": 1.8438,
|
| 1174 |
+
"step": 163
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 2.6031746031746033,
|
| 1178 |
+
"grad_norm": 0.43420085310935974,
|
| 1179 |
+
"learning_rate": 0.0001,
|
| 1180 |
+
"loss": 1.9431,
|
| 1181 |
+
"step": 164
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 2.619047619047619,
|
| 1185 |
+
"grad_norm": 0.444305419921875,
|
| 1186 |
+
"learning_rate": 0.0001,
|
| 1187 |
+
"loss": 1.8149,
|
| 1188 |
+
"step": 165
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 2.634920634920635,
|
| 1192 |
+
"grad_norm": 0.44758594036102295,
|
| 1193 |
+
"learning_rate": 0.0001,
|
| 1194 |
+
"loss": 1.8166,
|
| 1195 |
+
"step": 166
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 2.6507936507936507,
|
| 1199 |
+
"grad_norm": 0.44555145502090454,
|
| 1200 |
+
"learning_rate": 0.0001,
|
| 1201 |
+
"loss": 1.9017,
|
| 1202 |
+
"step": 167
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 2.6666666666666665,
|
| 1206 |
+
"grad_norm": 0.4599977135658264,
|
| 1207 |
+
"learning_rate": 0.0001,
|
| 1208 |
+
"loss": 1.8222,
|
| 1209 |
+
"step": 168
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 2.682539682539683,
|
| 1213 |
+
"grad_norm": 0.4442943036556244,
|
| 1214 |
+
"learning_rate": 0.0001,
|
| 1215 |
+
"loss": 1.8178,
|
| 1216 |
+
"step": 169
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 2.6984126984126986,
|
| 1220 |
+
"grad_norm": 0.4303114116191864,
|
| 1221 |
+
"learning_rate": 0.0001,
|
| 1222 |
+
"loss": 1.8585,
|
| 1223 |
+
"step": 170
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 2.7142857142857144,
|
| 1227 |
+
"grad_norm": 0.45859652757644653,
|
| 1228 |
+
"learning_rate": 0.0001,
|
| 1229 |
+
"loss": 1.8548,
|
| 1230 |
+
"step": 171
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 2.7301587301587302,
|
| 1234 |
+
"grad_norm": 0.449211448431015,
|
| 1235 |
+
"learning_rate": 0.0001,
|
| 1236 |
+
"loss": 1.7996,
|
| 1237 |
+
"step": 172
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 2.746031746031746,
|
| 1241 |
+
"grad_norm": 0.458112508058548,
|
| 1242 |
+
"learning_rate": 0.0001,
|
| 1243 |
+
"loss": 1.8924,
|
| 1244 |
+
"step": 173
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 2.761904761904762,
|
| 1248 |
+
"grad_norm": 0.4440052807331085,
|
| 1249 |
+
"learning_rate": 0.0001,
|
| 1250 |
+
"loss": 1.8414,
|
| 1251 |
+
"step": 174
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 2.7777777777777777,
|
| 1255 |
+
"grad_norm": 0.4355706572532654,
|
| 1256 |
+
"learning_rate": 0.0001,
|
| 1257 |
+
"loss": 1.8404,
|
| 1258 |
+
"step": 175
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 2.7936507936507935,
|
| 1262 |
+
"grad_norm": 0.4662310779094696,
|
| 1263 |
+
"learning_rate": 0.0001,
|
| 1264 |
+
"loss": 1.9346,
|
| 1265 |
+
"step": 176
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 2.8095238095238093,
|
| 1269 |
+
"grad_norm": 0.44040319323539734,
|
| 1270 |
+
"learning_rate": 0.0001,
|
| 1271 |
+
"loss": 1.8736,
|
| 1272 |
+
"step": 177
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 2.825396825396825,
|
| 1276 |
+
"grad_norm": 0.4506472945213318,
|
| 1277 |
+
"learning_rate": 0.0001,
|
| 1278 |
+
"loss": 1.9329,
|
| 1279 |
+
"step": 178
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 2.8412698412698414,
|
| 1283 |
+
"grad_norm": 0.44710540771484375,
|
| 1284 |
+
"learning_rate": 0.0001,
|
| 1285 |
+
"loss": 1.8787,
|
| 1286 |
+
"step": 179
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 2.857142857142857,
|
| 1290 |
+
"grad_norm": 0.43612954020500183,
|
| 1291 |
+
"learning_rate": 0.0001,
|
| 1292 |
+
"loss": 1.8405,
|
| 1293 |
+
"step": 180
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 2.873015873015873,
|
| 1297 |
+
"grad_norm": 0.4578387439250946,
|
| 1298 |
+
"learning_rate": 0.0001,
|
| 1299 |
+
"loss": 1.746,
|
| 1300 |
+
"step": 181
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 2.888888888888889,
|
| 1304 |
+
"grad_norm": 0.4509958326816559,
|
| 1305 |
+
"learning_rate": 0.0001,
|
| 1306 |
+
"loss": 1.8539,
|
| 1307 |
+
"step": 182
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 2.9047619047619047,
|
| 1311 |
+
"grad_norm": 0.44833552837371826,
|
| 1312 |
+
"learning_rate": 0.0001,
|
| 1313 |
+
"loss": 1.8407,
|
| 1314 |
+
"step": 183
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 2.9206349206349205,
|
| 1318 |
+
"grad_norm": 0.4552953541278839,
|
| 1319 |
+
"learning_rate": 0.0001,
|
| 1320 |
+
"loss": 1.8312,
|
| 1321 |
+
"step": 184
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 2.9365079365079367,
|
| 1325 |
+
"grad_norm": 0.4556235671043396,
|
| 1326 |
+
"learning_rate": 0.0001,
|
| 1327 |
+
"loss": 1.8324,
|
| 1328 |
+
"step": 185
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 2.9523809523809526,
|
| 1332 |
+
"grad_norm": 0.44649648666381836,
|
| 1333 |
+
"learning_rate": 0.0001,
|
| 1334 |
+
"loss": 1.9377,
|
| 1335 |
+
"step": 186
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 2.9682539682539684,
|
| 1339 |
+
"grad_norm": 0.47388994693756104,
|
| 1340 |
+
"learning_rate": 0.0001,
|
| 1341 |
+
"loss": 1.9287,
|
| 1342 |
+
"step": 187
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 2.984126984126984,
|
| 1346 |
+
"grad_norm": 0.43568143248558044,
|
| 1347 |
+
"learning_rate": 0.0001,
|
| 1348 |
+
"loss": 1.854,
|
| 1349 |
+
"step": 188
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 3.0,
|
| 1353 |
+
"grad_norm": 0.44688650965690613,
|
| 1354 |
+
"learning_rate": 0.0001,
|
| 1355 |
+
"loss": 1.8136,
|
| 1356 |
+
"step": 189
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 3.0,
|
| 1360 |
+
"eval_loss": 1.9275089502334595,
|
| 1361 |
+
"eval_runtime": 134.3105,
|
| 1362 |
+
"eval_samples_per_second": 144.858,
|
| 1363 |
+
"eval_steps_per_second": 1.132,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 3.015873015873016,
|
| 1368 |
+
"grad_norm": 0.4342663586139679,
|
| 1369 |
+
"learning_rate": 0.0001,
|
| 1370 |
+
"loss": 1.797,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 3.0317460317460316,
|
| 1375 |
+
"grad_norm": 0.4304012060165405,
|
| 1376 |
+
"learning_rate": 0.0001,
|
| 1377 |
+
"loss": 1.7864,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 3.0476190476190474,
|
| 1382 |
+
"grad_norm": 0.437054842710495,
|
| 1383 |
+
"learning_rate": 0.0001,
|
| 1384 |
+
"loss": 1.7892,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 3.0634920634920633,
|
| 1389 |
+
"grad_norm": 0.4523293077945709,
|
| 1390 |
+
"learning_rate": 0.0001,
|
| 1391 |
+
"loss": 1.8249,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 3.0793650793650795,
|
| 1396 |
+
"grad_norm": 0.43690723180770874,
|
| 1397 |
+
"learning_rate": 0.0001,
|
| 1398 |
+
"loss": 1.7554,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 3.0952380952380953,
|
| 1403 |
+
"grad_norm": 0.46181079745292664,
|
| 1404 |
+
"learning_rate": 0.0001,
|
| 1405 |
+
"loss": 1.8204,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 3.111111111111111,
|
| 1410 |
+
"grad_norm": 0.44550421833992004,
|
| 1411 |
+
"learning_rate": 0.0001,
|
| 1412 |
+
"loss": 1.7289,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 3.126984126984127,
|
| 1417 |
+
"grad_norm": 0.47702673077583313,
|
| 1418 |
+
"learning_rate": 0.0001,
|
| 1419 |
+
"loss": 1.6293,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 3.142857142857143,
|
| 1424 |
+
"grad_norm": 0.4934547543525696,
|
| 1425 |
+
"learning_rate": 0.0001,
|
| 1426 |
+
"loss": 1.7969,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 3.1587301587301586,
|
| 1431 |
+
"grad_norm": 0.4907466173171997,
|
| 1432 |
+
"learning_rate": 0.0001,
|
| 1433 |
+
"loss": 1.7924,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 3.1746031746031744,
|
| 1438 |
+
"grad_norm": 0.47944095730781555,
|
| 1439 |
+
"learning_rate": 0.0001,
|
| 1440 |
+
"loss": 1.8156,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 3.1904761904761907,
|
| 1445 |
+
"grad_norm": 0.49679121375083923,
|
| 1446 |
+
"learning_rate": 0.0001,
|
| 1447 |
+
"loss": 1.727,
|
| 1448 |
+
"step": 201
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 3.2063492063492065,
|
| 1452 |
+
"grad_norm": 0.4857705235481262,
|
| 1453 |
+
"learning_rate": 0.0001,
|
| 1454 |
+
"loss": 1.7839,
|
| 1455 |
+
"step": 202
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 3.2222222222222223,
|
| 1459 |
+
"grad_norm": 0.4953521490097046,
|
| 1460 |
+
"learning_rate": 0.0001,
|
| 1461 |
+
"loss": 1.8301,
|
| 1462 |
+
"step": 203
|
| 1463 |
+
},
|
| 1464 |
+
{
|
| 1465 |
+
"epoch": 3.238095238095238,
|
| 1466 |
+
"grad_norm": 0.5127764344215393,
|
| 1467 |
+
"learning_rate": 0.0001,
|
| 1468 |
+
"loss": 1.7512,
|
| 1469 |
+
"step": 204
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 3.253968253968254,
|
| 1473 |
+
"grad_norm": 0.49370840191841125,
|
| 1474 |
+
"learning_rate": 0.0001,
|
| 1475 |
+
"loss": 1.7538,
|
| 1476 |
+
"step": 205
|
| 1477 |
+
},
|
| 1478 |
+
{
|
| 1479 |
+
"epoch": 3.2698412698412698,
|
| 1480 |
+
"grad_norm": 0.512405276298523,
|
| 1481 |
+
"learning_rate": 0.0001,
|
| 1482 |
+
"loss": 1.7816,
|
| 1483 |
+
"step": 206
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"epoch": 3.2857142857142856,
|
| 1487 |
+
"grad_norm": 0.5077876448631287,
|
| 1488 |
+
"learning_rate": 0.0001,
|
| 1489 |
+
"loss": 1.8121,
|
| 1490 |
+
"step": 207
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 3.3015873015873014,
|
| 1494 |
+
"grad_norm": 0.521603524684906,
|
| 1495 |
+
"learning_rate": 0.0001,
|
| 1496 |
+
"loss": 1.8113,
|
| 1497 |
+
"step": 208
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 3.317460317460317,
|
| 1501 |
+
"grad_norm": 0.5323950052261353,
|
| 1502 |
+
"learning_rate": 0.0001,
|
| 1503 |
+
"loss": 1.7352,
|
| 1504 |
+
"step": 209
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"epoch": 3.3333333333333335,
|
| 1508 |
+
"grad_norm": 0.4839828908443451,
|
| 1509 |
+
"learning_rate": 0.0001,
|
| 1510 |
+
"loss": 1.7951,
|
| 1511 |
+
"step": 210
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 3.3492063492063493,
|
| 1515 |
+
"grad_norm": 0.4893435537815094,
|
| 1516 |
+
"learning_rate": 0.0001,
|
| 1517 |
+
"loss": 1.7454,
|
| 1518 |
+
"step": 211
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 3.365079365079365,
|
| 1522 |
+
"grad_norm": 0.5195879936218262,
|
| 1523 |
+
"learning_rate": 0.0001,
|
| 1524 |
+
"loss": 1.7687,
|
| 1525 |
+
"step": 212
|
| 1526 |
+
},
|
| 1527 |
+
{
|
| 1528 |
+
"epoch": 3.380952380952381,
|
| 1529 |
+
"grad_norm": 0.5112190246582031,
|
| 1530 |
+
"learning_rate": 0.0001,
|
| 1531 |
+
"loss": 1.8483,
|
| 1532 |
+
"step": 213
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 3.3968253968253967,
|
| 1536 |
+
"grad_norm": 0.5115760564804077,
|
| 1537 |
+
"learning_rate": 0.0001,
|
| 1538 |
+
"loss": 1.7195,
|
| 1539 |
+
"step": 214
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 3.4126984126984126,
|
| 1543 |
+
"grad_norm": 0.5073997378349304,
|
| 1544 |
+
"learning_rate": 0.0001,
|
| 1545 |
+
"loss": 1.6674,
|
| 1546 |
+
"step": 215
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 3.4285714285714284,
|
| 1550 |
+
"grad_norm": 0.5142124891281128,
|
| 1551 |
+
"learning_rate": 0.0001,
|
| 1552 |
+
"loss": 1.7467,
|
| 1553 |
+
"step": 216
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 3.4444444444444446,
|
| 1557 |
+
"grad_norm": 0.5431984066963196,
|
| 1558 |
+
"learning_rate": 0.0001,
|
| 1559 |
+
"loss": 1.81,
|
| 1560 |
+
"step": 217
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"epoch": 3.4603174603174605,
|
| 1564 |
+
"grad_norm": 0.5300880670547485,
|
| 1565 |
+
"learning_rate": 0.0001,
|
| 1566 |
+
"loss": 1.8346,
|
| 1567 |
+
"step": 218
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 3.4761904761904763,
|
| 1571 |
+
"grad_norm": 0.5360419750213623,
|
| 1572 |
+
"learning_rate": 0.0001,
|
| 1573 |
+
"loss": 1.8337,
|
| 1574 |
+
"step": 219
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 3.492063492063492,
|
| 1578 |
+
"grad_norm": 0.5350140929222107,
|
| 1579 |
+
"learning_rate": 0.0001,
|
| 1580 |
+
"loss": 1.7478,
|
| 1581 |
+
"step": 220
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 3.507936507936508,
|
| 1585 |
+
"grad_norm": 0.5557613372802734,
|
| 1586 |
+
"learning_rate": 0.0001,
|
| 1587 |
+
"loss": 1.7755,
|
| 1588 |
+
"step": 221
|
| 1589 |
+
},
|
| 1590 |
+
{
|
| 1591 |
+
"epoch": 3.5238095238095237,
|
| 1592 |
+
"grad_norm": 0.5221186280250549,
|
| 1593 |
+
"learning_rate": 0.0001,
|
| 1594 |
+
"loss": 1.784,
|
| 1595 |
+
"step": 222
|
| 1596 |
+
},
|
| 1597 |
+
{
|
| 1598 |
+
"epoch": 3.5396825396825395,
|
| 1599 |
+
"grad_norm": 0.5102700591087341,
|
| 1600 |
+
"learning_rate": 0.0001,
|
| 1601 |
+
"loss": 1.8084,
|
| 1602 |
+
"step": 223
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 3.5555555555555554,
|
| 1606 |
+
"grad_norm": 0.5124233961105347,
|
| 1607 |
+
"learning_rate": 0.0001,
|
| 1608 |
+
"loss": 1.7171,
|
| 1609 |
+
"step": 224
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 3.571428571428571,
|
| 1613 |
+
"grad_norm": 0.5118602514266968,
|
| 1614 |
+
"learning_rate": 0.0001,
|
| 1615 |
+
"loss": 1.715,
|
| 1616 |
+
"step": 225
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 3.5873015873015874,
|
| 1620 |
+
"grad_norm": 0.5495670437812805,
|
| 1621 |
+
"learning_rate": 0.0001,
|
| 1622 |
+
"loss": 1.7706,
|
| 1623 |
+
"step": 226
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 3.6031746031746033,
|
| 1627 |
+
"grad_norm": 0.5196232795715332,
|
| 1628 |
+
"learning_rate": 0.0001,
|
| 1629 |
+
"loss": 1.8667,
|
| 1630 |
+
"step": 227
|
| 1631 |
+
},
|
| 1632 |
+
{
|
| 1633 |
+
"epoch": 3.619047619047619,
|
| 1634 |
+
"grad_norm": 0.5266917943954468,
|
| 1635 |
+
"learning_rate": 0.0001,
|
| 1636 |
+
"loss": 1.8147,
|
| 1637 |
+
"step": 228
|
| 1638 |
+
},
|
| 1639 |
+
{
|
| 1640 |
+
"epoch": 3.634920634920635,
|
| 1641 |
+
"grad_norm": 0.5159206986427307,
|
| 1642 |
+
"learning_rate": 0.0001,
|
| 1643 |
+
"loss": 1.825,
|
| 1644 |
+
"step": 229
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 3.6507936507936507,
|
| 1648 |
+
"grad_norm": 0.540160596370697,
|
| 1649 |
+
"learning_rate": 0.0001,
|
| 1650 |
+
"loss": 1.8403,
|
| 1651 |
+
"step": 230
|
| 1652 |
+
},
|
| 1653 |
+
{
|
| 1654 |
+
"epoch": 3.6666666666666665,
|
| 1655 |
+
"grad_norm": 0.5076445937156677,
|
| 1656 |
+
"learning_rate": 0.0001,
|
| 1657 |
+
"loss": 1.7875,
|
| 1658 |
+
"step": 231
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 3.682539682539683,
|
| 1662 |
+
"grad_norm": 0.5336344242095947,
|
| 1663 |
+
"learning_rate": 0.0001,
|
| 1664 |
+
"loss": 1.8266,
|
| 1665 |
+
"step": 232
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 3.6984126984126986,
|
| 1669 |
+
"grad_norm": 0.5361369848251343,
|
| 1670 |
+
"learning_rate": 0.0001,
|
| 1671 |
+
"loss": 1.8214,
|
| 1672 |
+
"step": 233
|
| 1673 |
+
},
|
| 1674 |
+
{
|
| 1675 |
+
"epoch": 3.7142857142857144,
|
| 1676 |
+
"grad_norm": 0.5275120735168457,
|
| 1677 |
+
"learning_rate": 0.0001,
|
| 1678 |
+
"loss": 1.8582,
|
| 1679 |
+
"step": 234
|
| 1680 |
+
},
|
| 1681 |
+
{
|
| 1682 |
+
"epoch": 3.7301587301587302,
|
| 1683 |
+
"grad_norm": 0.5130988359451294,
|
| 1684 |
+
"learning_rate": 0.0001,
|
| 1685 |
+
"loss": 1.7332,
|
| 1686 |
+
"step": 235
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 3.746031746031746,
|
| 1690 |
+
"grad_norm": 0.5083476305007935,
|
| 1691 |
+
"learning_rate": 0.0001,
|
| 1692 |
+
"loss": 1.7494,
|
| 1693 |
+
"step": 236
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 3.761904761904762,
|
| 1697 |
+
"grad_norm": 0.5329089760780334,
|
| 1698 |
+
"learning_rate": 0.0001,
|
| 1699 |
+
"loss": 1.7756,
|
| 1700 |
+
"step": 237
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 3.7777777777777777,
|
| 1704 |
+
"grad_norm": 0.5432071089744568,
|
| 1705 |
+
"learning_rate": 0.0001,
|
| 1706 |
+
"loss": 1.8236,
|
| 1707 |
+
"step": 238
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 3.7936507936507935,
|
| 1711 |
+
"grad_norm": 0.5371318459510803,
|
| 1712 |
+
"learning_rate": 0.0001,
|
| 1713 |
+
"loss": 1.7974,
|
| 1714 |
+
"step": 239
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 3.8095238095238093,
|
| 1718 |
+
"grad_norm": 0.5571925044059753,
|
| 1719 |
+
"learning_rate": 0.0001,
|
| 1720 |
+
"loss": 1.7686,
|
| 1721 |
+
"step": 240
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 3.825396825396825,
|
| 1725 |
+
"grad_norm": 0.5296266674995422,
|
| 1726 |
+
"learning_rate": 0.0001,
|
| 1727 |
+
"loss": 1.8263,
|
| 1728 |
+
"step": 241
|
| 1729 |
+
},
|
| 1730 |
+
{
|
| 1731 |
+
"epoch": 3.8412698412698414,
|
| 1732 |
+
"grad_norm": 0.5619531273841858,
|
| 1733 |
+
"learning_rate": 0.0001,
|
| 1734 |
+
"loss": 1.7917,
|
| 1735 |
+
"step": 242
|
| 1736 |
+
},
|
| 1737 |
+
{
|
| 1738 |
+
"epoch": 3.857142857142857,
|
| 1739 |
+
"grad_norm": 0.558754563331604,
|
| 1740 |
+
"learning_rate": 0.0001,
|
| 1741 |
+
"loss": 1.7522,
|
| 1742 |
+
"step": 243
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 3.873015873015873,
|
| 1746 |
+
"grad_norm": 0.5290083289146423,
|
| 1747 |
+
"learning_rate": 0.0001,
|
| 1748 |
+
"loss": 1.8235,
|
| 1749 |
+
"step": 244
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 3.888888888888889,
|
| 1753 |
+
"grad_norm": 0.5214211940765381,
|
| 1754 |
+
"learning_rate": 0.0001,
|
| 1755 |
+
"loss": 1.7943,
|
| 1756 |
+
"step": 245
|
| 1757 |
+
},
|
| 1758 |
+
{
|
| 1759 |
+
"epoch": 3.9047619047619047,
|
| 1760 |
+
"grad_norm": 0.5196910500526428,
|
| 1761 |
+
"learning_rate": 0.0001,
|
| 1762 |
+
"loss": 1.7309,
|
| 1763 |
+
"step": 246
|
| 1764 |
+
},
|
| 1765 |
+
{
|
| 1766 |
+
"epoch": 3.9206349206349205,
|
| 1767 |
+
"grad_norm": 0.5027257800102234,
|
| 1768 |
+
"learning_rate": 0.0001,
|
| 1769 |
+
"loss": 1.7205,
|
| 1770 |
+
"step": 247
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"epoch": 3.9365079365079367,
|
| 1774 |
+
"grad_norm": 0.529344916343689,
|
| 1775 |
+
"learning_rate": 0.0001,
|
| 1776 |
+
"loss": 1.7981,
|
| 1777 |
+
"step": 248
|
| 1778 |
+
},
|
| 1779 |
+
{
|
| 1780 |
+
"epoch": 3.9523809523809526,
|
| 1781 |
+
"grad_norm": 0.5742695331573486,
|
| 1782 |
+
"learning_rate": 0.0001,
|
| 1783 |
+
"loss": 1.7418,
|
| 1784 |
+
"step": 249
|
| 1785 |
+
},
|
| 1786 |
+
{
|
| 1787 |
+
"epoch": 3.9682539682539684,
|
| 1788 |
+
"grad_norm": 0.5311470627784729,
|
| 1789 |
+
"learning_rate": 0.0001,
|
| 1790 |
+
"loss": 1.8385,
|
| 1791 |
+
"step": 250
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"epoch": 3.984126984126984,
|
| 1795 |
+
"grad_norm": 0.5246540904045105,
|
| 1796 |
+
"learning_rate": 0.0001,
|
| 1797 |
+
"loss": 1.7643,
|
| 1798 |
+
"step": 251
|
| 1799 |
+
},
|
| 1800 |
+
{
|
| 1801 |
+
"epoch": 4.0,
|
| 1802 |
+
"grad_norm": 0.5105009078979492,
|
| 1803 |
+
"learning_rate": 0.0001,
|
| 1804 |
+
"loss": 1.8055,
|
| 1805 |
+
"step": 252
|
| 1806 |
+
},
|
| 1807 |
+
{
|
| 1808 |
+
"epoch": 4.0,
|
| 1809 |
+
"eval_loss": 1.8985581398010254,
|
| 1810 |
+
"eval_runtime": 134.1721,
|
| 1811 |
+
"eval_samples_per_second": 145.008,
|
| 1812 |
+
"eval_steps_per_second": 1.133,
|
| 1813 |
+
"step": 252
|
| 1814 |
+
},
|
| 1815 |
+
{
|
| 1816 |
+
"epoch": 4.015873015873016,
|
| 1817 |
+
"grad_norm": 0.504828691482544,
|
| 1818 |
+
"learning_rate": 0.0001,
|
| 1819 |
+
"loss": 1.6673,
|
| 1820 |
+
"step": 253
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"epoch": 4.031746031746032,
|
| 1824 |
+
"grad_norm": 0.5102445483207703,
|
| 1825 |
+
"learning_rate": 0.0001,
|
| 1826 |
+
"loss": 1.6781,
|
| 1827 |
+
"step": 254
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"epoch": 4.0476190476190474,
|
| 1831 |
+
"grad_norm": 0.5210107564926147,
|
| 1832 |
+
"learning_rate": 0.0001,
|
| 1833 |
+
"loss": 1.746,
|
| 1834 |
+
"step": 255
|
| 1835 |
+
},
|
| 1836 |
+
{
|
| 1837 |
+
"epoch": 4.063492063492063,
|
| 1838 |
+
"grad_norm": 0.5053814649581909,
|
| 1839 |
+
"learning_rate": 0.0001,
|
| 1840 |
+
"loss": 1.6573,
|
| 1841 |
+
"step": 256
|
| 1842 |
+
},
|
| 1843 |
+
{
|
| 1844 |
+
"epoch": 4.079365079365079,
|
| 1845 |
+
"grad_norm": 0.5346547365188599,
|
| 1846 |
+
"learning_rate": 0.0001,
|
| 1847 |
+
"loss": 1.7657,
|
| 1848 |
+
"step": 257
|
| 1849 |
+
},
|
| 1850 |
+
{
|
| 1851 |
+
"epoch": 4.095238095238095,
|
| 1852 |
+
"grad_norm": 0.5420466661453247,
|
| 1853 |
+
"learning_rate": 0.0001,
|
| 1854 |
+
"loss": 1.6815,
|
| 1855 |
+
"step": 258
|
| 1856 |
+
},
|
| 1857 |
+
{
|
| 1858 |
+
"epoch": 4.111111111111111,
|
| 1859 |
+
"grad_norm": 0.5454694032669067,
|
| 1860 |
+
"learning_rate": 0.0001,
|
| 1861 |
+
"loss": 1.6885,
|
| 1862 |
+
"step": 259
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"epoch": 4.1269841269841265,
|
| 1866 |
+
"grad_norm": 0.5450710654258728,
|
| 1867 |
+
"learning_rate": 0.0001,
|
| 1868 |
+
"loss": 1.7451,
|
| 1869 |
+
"step": 260
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 4.142857142857143,
|
| 1873 |
+
"grad_norm": 0.5478411316871643,
|
| 1874 |
+
"learning_rate": 0.0001,
|
| 1875 |
+
"loss": 1.6725,
|
| 1876 |
+
"step": 261
|
| 1877 |
+
},
|
| 1878 |
+
{
|
| 1879 |
+
"epoch": 4.158730158730159,
|
| 1880 |
+
"grad_norm": 0.5402894020080566,
|
| 1881 |
+
"learning_rate": 0.0001,
|
| 1882 |
+
"loss": 1.7032,
|
| 1883 |
+
"step": 262
|
| 1884 |
+
},
|
| 1885 |
+
{
|
| 1886 |
+
"epoch": 4.174603174603175,
|
| 1887 |
+
"grad_norm": 0.5409881472587585,
|
| 1888 |
+
"learning_rate": 0.0001,
|
| 1889 |
+
"loss": 1.6136,
|
| 1890 |
+
"step": 263
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"epoch": 4.190476190476191,
|
| 1894 |
+
"grad_norm": 0.5661287307739258,
|
| 1895 |
+
"learning_rate": 0.0001,
|
| 1896 |
+
"loss": 1.7142,
|
| 1897 |
+
"step": 264
|
| 1898 |
+
},
|
| 1899 |
+
{
|
| 1900 |
+
"epoch": 4.2063492063492065,
|
| 1901 |
+
"grad_norm": 0.5954362750053406,
|
| 1902 |
+
"learning_rate": 0.0001,
|
| 1903 |
+
"loss": 1.7897,
|
| 1904 |
+
"step": 265
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 4.222222222222222,
|
| 1908 |
+
"grad_norm": 0.5734924077987671,
|
| 1909 |
+
"learning_rate": 0.0001,
|
| 1910 |
+
"loss": 1.7376,
|
| 1911 |
+
"step": 266
|
| 1912 |
+
},
|
| 1913 |
+
{
|
| 1914 |
+
"epoch": 4.238095238095238,
|
| 1915 |
+
"grad_norm": 0.5600322484970093,
|
| 1916 |
+
"learning_rate": 0.0001,
|
| 1917 |
+
"loss": 1.7021,
|
| 1918 |
+
"step": 267
|
| 1919 |
+
},
|
| 1920 |
+
{
|
| 1921 |
+
"epoch": 4.253968253968254,
|
| 1922 |
+
"grad_norm": 0.5609176158905029,
|
| 1923 |
+
"learning_rate": 0.0001,
|
| 1924 |
+
"loss": 1.7,
|
| 1925 |
+
"step": 268
|
| 1926 |
+
},
|
| 1927 |
+
{
|
| 1928 |
+
"epoch": 4.26984126984127,
|
| 1929 |
+
"grad_norm": 0.5671024322509766,
|
| 1930 |
+
"learning_rate": 0.0001,
|
| 1931 |
+
"loss": 1.7088,
|
| 1932 |
+
"step": 269
|
| 1933 |
+
},
|
| 1934 |
+
{
|
| 1935 |
+
"epoch": 4.285714285714286,
|
| 1936 |
+
"grad_norm": 0.5769540071487427,
|
| 1937 |
+
"learning_rate": 0.0001,
|
| 1938 |
+
"loss": 1.6991,
|
| 1939 |
+
"step": 270
|
| 1940 |
+
},
|
| 1941 |
+
{
|
| 1942 |
+
"epoch": 4.301587301587301,
|
| 1943 |
+
"grad_norm": 0.5442491769790649,
|
| 1944 |
+
"learning_rate": 0.0001,
|
| 1945 |
+
"loss": 1.6078,
|
| 1946 |
+
"step": 271
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 4.317460317460317,
|
| 1950 |
+
"grad_norm": 0.568550705909729,
|
| 1951 |
+
"learning_rate": 0.0001,
|
| 1952 |
+
"loss": 1.7105,
|
| 1953 |
+
"step": 272
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 4.333333333333333,
|
| 1957 |
+
"grad_norm": 0.5768945217132568,
|
| 1958 |
+
"learning_rate": 0.0001,
|
| 1959 |
+
"loss": 1.6811,
|
| 1960 |
+
"step": 273
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"epoch": 4.349206349206349,
|
| 1964 |
+
"grad_norm": 0.5782952308654785,
|
| 1965 |
+
"learning_rate": 0.0001,
|
| 1966 |
+
"loss": 1.6546,
|
| 1967 |
+
"step": 274
|
| 1968 |
+
},
|
| 1969 |
+
{
|
| 1970 |
+
"epoch": 4.365079365079365,
|
| 1971 |
+
"grad_norm": 0.5882396697998047,
|
| 1972 |
+
"learning_rate": 0.0001,
|
| 1973 |
+
"loss": 1.6932,
|
| 1974 |
+
"step": 275
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 4.380952380952381,
|
| 1978 |
+
"grad_norm": 0.6056164503097534,
|
| 1979 |
+
"learning_rate": 0.0001,
|
| 1980 |
+
"loss": 1.6682,
|
| 1981 |
+
"step": 276
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 4.396825396825397,
|
| 1985 |
+
"grad_norm": 0.5785002112388611,
|
| 1986 |
+
"learning_rate": 0.0001,
|
| 1987 |
+
"loss": 1.7191,
|
| 1988 |
+
"step": 277
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 4.412698412698413,
|
| 1992 |
+
"grad_norm": 0.5849601030349731,
|
| 1993 |
+
"learning_rate": 0.0001,
|
| 1994 |
+
"loss": 1.6608,
|
| 1995 |
+
"step": 278
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"epoch": 4.428571428571429,
|
| 1999 |
+
"grad_norm": 0.5964322686195374,
|
| 2000 |
+
"learning_rate": 0.0001,
|
| 2001 |
+
"loss": 1.6604,
|
| 2002 |
+
"step": 279
|
| 2003 |
+
},
|
| 2004 |
+
{
|
| 2005 |
+
"epoch": 4.444444444444445,
|
| 2006 |
+
"grad_norm": 0.5840972065925598,
|
| 2007 |
+
"learning_rate": 0.0001,
|
| 2008 |
+
"loss": 1.7149,
|
| 2009 |
+
"step": 280
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"epoch": 4.4603174603174605,
|
| 2013 |
+
"grad_norm": 0.5837913751602173,
|
| 2014 |
+
"learning_rate": 0.0001,
|
| 2015 |
+
"loss": 1.6206,
|
| 2016 |
+
"step": 281
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"epoch": 4.476190476190476,
|
| 2020 |
+
"grad_norm": 0.5978841185569763,
|
| 2021 |
+
"learning_rate": 0.0001,
|
| 2022 |
+
"loss": 1.6779,
|
| 2023 |
+
"step": 282
|
| 2024 |
+
},
|
| 2025 |
+
{
|
| 2026 |
+
"epoch": 4.492063492063492,
|
| 2027 |
+
"grad_norm": 0.5810064077377319,
|
| 2028 |
+
"learning_rate": 0.0001,
|
| 2029 |
+
"loss": 1.6058,
|
| 2030 |
+
"step": 283
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 4.507936507936508,
|
| 2034 |
+
"grad_norm": 0.5861958861351013,
|
| 2035 |
+
"learning_rate": 0.0001,
|
| 2036 |
+
"loss": 1.6532,
|
| 2037 |
+
"step": 284
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 4.523809523809524,
|
| 2041 |
+
"grad_norm": 0.6071611642837524,
|
| 2042 |
+
"learning_rate": 0.0001,
|
| 2043 |
+
"loss": 1.7506,
|
| 2044 |
+
"step": 285
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 4.5396825396825395,
|
| 2048 |
+
"grad_norm": 0.6125015616416931,
|
| 2049 |
+
"learning_rate": 0.0001,
|
| 2050 |
+
"loss": 1.6361,
|
| 2051 |
+
"step": 286
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 4.555555555555555,
|
| 2055 |
+
"grad_norm": 0.6398947238922119,
|
| 2056 |
+
"learning_rate": 0.0001,
|
| 2057 |
+
"loss": 1.794,
|
| 2058 |
+
"step": 287
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 4.571428571428571,
|
| 2062 |
+
"grad_norm": 0.575025737285614,
|
| 2063 |
+
"learning_rate": 0.0001,
|
| 2064 |
+
"loss": 1.6847,
|
| 2065 |
+
"step": 288
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 4.587301587301587,
|
| 2069 |
+
"grad_norm": 0.5949602127075195,
|
| 2070 |
+
"learning_rate": 0.0001,
|
| 2071 |
+
"loss": 1.6739,
|
| 2072 |
+
"step": 289
|
| 2073 |
+
},
|
| 2074 |
+
{
|
| 2075 |
+
"epoch": 4.603174603174603,
|
| 2076 |
+
"grad_norm": 0.5899695158004761,
|
| 2077 |
+
"learning_rate": 0.0001,
|
| 2078 |
+
"loss": 1.7115,
|
| 2079 |
+
"step": 290
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 4.619047619047619,
|
| 2083 |
+
"grad_norm": 0.570034384727478,
|
| 2084 |
+
"learning_rate": 0.0001,
|
| 2085 |
+
"loss": 1.6493,
|
| 2086 |
+
"step": 291
|
| 2087 |
+
},
|
| 2088 |
+
{
|
| 2089 |
+
"epoch": 4.634920634920634,
|
| 2090 |
+
"grad_norm": 0.6042748689651489,
|
| 2091 |
+
"learning_rate": 0.0001,
|
| 2092 |
+
"loss": 1.6458,
|
| 2093 |
+
"step": 292
|
| 2094 |
+
},
|
| 2095 |
+
{
|
| 2096 |
+
"epoch": 4.650793650793651,
|
| 2097 |
+
"grad_norm": 0.6089054942131042,
|
| 2098 |
+
"learning_rate": 0.0001,
|
| 2099 |
+
"loss": 1.6585,
|
| 2100 |
+
"step": 293
|
| 2101 |
+
},
|
| 2102 |
+
{
|
| 2103 |
+
"epoch": 4.666666666666667,
|
| 2104 |
+
"grad_norm": 0.5755547881126404,
|
| 2105 |
+
"learning_rate": 0.0001,
|
| 2106 |
+
"loss": 1.6305,
|
| 2107 |
+
"step": 294
|
| 2108 |
+
},
|
| 2109 |
+
{
|
| 2110 |
+
"epoch": 4.682539682539683,
|
| 2111 |
+
"grad_norm": 0.6182751059532166,
|
| 2112 |
+
"learning_rate": 0.0001,
|
| 2113 |
+
"loss": 1.6819,
|
| 2114 |
+
"step": 295
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 4.698412698412699,
|
| 2118 |
+
"grad_norm": 0.5718191266059875,
|
| 2119 |
+
"learning_rate": 0.0001,
|
| 2120 |
+
"loss": 1.7166,
|
| 2121 |
+
"step": 296
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"epoch": 4.714285714285714,
|
| 2125 |
+
"grad_norm": 0.5688255429267883,
|
| 2126 |
+
"learning_rate": 0.0001,
|
| 2127 |
+
"loss": 1.6764,
|
| 2128 |
+
"step": 297
|
| 2129 |
+
},
|
| 2130 |
+
{
|
| 2131 |
+
"epoch": 4.73015873015873,
|
| 2132 |
+
"grad_norm": 0.6010944843292236,
|
| 2133 |
+
"learning_rate": 0.0001,
|
| 2134 |
+
"loss": 1.713,
|
| 2135 |
+
"step": 298
|
| 2136 |
+
},
|
| 2137 |
+
{
|
| 2138 |
+
"epoch": 4.746031746031746,
|
| 2139 |
+
"grad_norm": 0.5783191919326782,
|
| 2140 |
+
"learning_rate": 0.0001,
|
| 2141 |
+
"loss": 1.6451,
|
| 2142 |
+
"step": 299
|
| 2143 |
+
},
|
| 2144 |
+
{
|
| 2145 |
+
"epoch": 4.761904761904762,
|
| 2146 |
+
"grad_norm": 0.5913519859313965,
|
| 2147 |
+
"learning_rate": 0.0001,
|
| 2148 |
+
"loss": 1.6593,
|
| 2149 |
+
"step": 300
|
| 2150 |
+
},
|
| 2151 |
+
{
|
| 2152 |
+
"epoch": 4.777777777777778,
|
| 2153 |
+
"grad_norm": 0.5958235263824463,
|
| 2154 |
+
"learning_rate": 0.0001,
|
| 2155 |
+
"loss": 1.7118,
|
| 2156 |
+
"step": 301
|
| 2157 |
+
},
|
| 2158 |
+
{
|
| 2159 |
+
"epoch": 4.7936507936507935,
|
| 2160 |
+
"grad_norm": 0.6042026281356812,
|
| 2161 |
+
"learning_rate": 0.0001,
|
| 2162 |
+
"loss": 1.7029,
|
| 2163 |
+
"step": 302
|
| 2164 |
+
},
|
| 2165 |
+
{
|
| 2166 |
+
"epoch": 4.809523809523809,
|
| 2167 |
+
"grad_norm": 0.6563578248023987,
|
| 2168 |
+
"learning_rate": 0.0001,
|
| 2169 |
+
"loss": 1.7293,
|
| 2170 |
+
"step": 303
|
| 2171 |
+
},
|
| 2172 |
+
{
|
| 2173 |
+
"epoch": 4.825396825396825,
|
| 2174 |
+
"grad_norm": 0.6379770636558533,
|
| 2175 |
+
"learning_rate": 0.0001,
|
| 2176 |
+
"loss": 1.7129,
|
| 2177 |
+
"step": 304
|
| 2178 |
+
},
|
| 2179 |
+
{
|
| 2180 |
+
"epoch": 4.841269841269841,
|
| 2181 |
+
"grad_norm": 0.609699547290802,
|
| 2182 |
+
"learning_rate": 0.0001,
|
| 2183 |
+
"loss": 1.7837,
|
| 2184 |
+
"step": 305
|
| 2185 |
+
},
|
| 2186 |
+
{
|
| 2187 |
+
"epoch": 4.857142857142857,
|
| 2188 |
+
"grad_norm": 0.6002169251441956,
|
| 2189 |
+
"learning_rate": 0.0001,
|
| 2190 |
+
"loss": 1.7679,
|
| 2191 |
+
"step": 306
|
| 2192 |
+
},
|
| 2193 |
+
{
|
| 2194 |
+
"epoch": 4.8730158730158735,
|
| 2195 |
+
"grad_norm": 0.6270914673805237,
|
| 2196 |
+
"learning_rate": 0.0001,
|
| 2197 |
+
"loss": 1.8535,
|
| 2198 |
+
"step": 307
|
| 2199 |
+
},
|
| 2200 |
+
{
|
| 2201 |
+
"epoch": 4.888888888888889,
|
| 2202 |
+
"grad_norm": 0.5831117630004883,
|
| 2203 |
+
"learning_rate": 0.0001,
|
| 2204 |
+
"loss": 1.6862,
|
| 2205 |
+
"step": 308
|
| 2206 |
+
},
|
| 2207 |
+
{
|
| 2208 |
+
"epoch": 4.904761904761905,
|
| 2209 |
+
"grad_norm": 0.5913400650024414,
|
| 2210 |
+
"learning_rate": 0.0001,
|
| 2211 |
+
"loss": 1.7302,
|
| 2212 |
+
"step": 309
|
| 2213 |
+
},
|
| 2214 |
+
{
|
| 2215 |
+
"epoch": 4.920634920634921,
|
| 2216 |
+
"grad_norm": 0.5977728366851807,
|
| 2217 |
+
"learning_rate": 0.0001,
|
| 2218 |
+
"loss": 1.7369,
|
| 2219 |
+
"step": 310
|
| 2220 |
+
},
|
| 2221 |
+
{
|
| 2222 |
+
"epoch": 4.936507936507937,
|
| 2223 |
+
"grad_norm": 0.6250127553939819,
|
| 2224 |
+
"learning_rate": 0.0001,
|
| 2225 |
+
"loss": 1.7179,
|
| 2226 |
+
"step": 311
|
| 2227 |
+
},
|
| 2228 |
+
{
|
| 2229 |
+
"epoch": 4.9523809523809526,
|
| 2230 |
+
"grad_norm": 0.6085378527641296,
|
| 2231 |
+
"learning_rate": 0.0001,
|
| 2232 |
+
"loss": 1.7917,
|
| 2233 |
+
"step": 312
|
| 2234 |
+
},
|
| 2235 |
+
{
|
| 2236 |
+
"epoch": 4.968253968253968,
|
| 2237 |
+
"grad_norm": 0.5821117162704468,
|
| 2238 |
+
"learning_rate": 0.0001,
|
| 2239 |
+
"loss": 1.7269,
|
| 2240 |
+
"step": 313
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"epoch": 4.984126984126984,
|
| 2244 |
+
"grad_norm": 0.5807305574417114,
|
| 2245 |
+
"learning_rate": 0.0001,
|
| 2246 |
+
"loss": 1.6895,
|
| 2247 |
+
"step": 314
|
| 2248 |
+
},
|
| 2249 |
+
{
|
| 2250 |
+
"epoch": 5.0,
|
| 2251 |
+
"grad_norm": 0.5902681946754456,
|
| 2252 |
+
"learning_rate": 0.0001,
|
| 2253 |
+
"loss": 1.6631,
|
| 2254 |
+
"step": 315
|
| 2255 |
+
},
|
| 2256 |
+
{
|
| 2257 |
+
"epoch": 5.0,
|
| 2258 |
+
"eval_loss": 1.890466332435608,
|
| 2259 |
+
"eval_runtime": 134.223,
|
| 2260 |
+
"eval_samples_per_second": 144.953,
|
| 2261 |
+
"eval_steps_per_second": 1.132,
|
| 2262 |
+
"step": 315
|
| 2263 |
+
},
|
| 2264 |
+
{
|
| 2265 |
+
"epoch": 5.015873015873016,
|
| 2266 |
+
"grad_norm": 0.5895299315452576,
|
| 2267 |
+
"learning_rate": 0.0001,
|
| 2268 |
+
"loss": 1.6979,
|
| 2269 |
+
"step": 316
|
| 2270 |
+
},
|
| 2271 |
+
{
|
| 2272 |
+
"epoch": 5.031746031746032,
|
| 2273 |
+
"grad_norm": 0.5639784336090088,
|
| 2274 |
+
"learning_rate": 0.0001,
|
| 2275 |
+
"loss": 1.6163,
|
| 2276 |
+
"step": 317
|
| 2277 |
+
},
|
| 2278 |
+
{
|
| 2279 |
+
"epoch": 5.0476190476190474,
|
| 2280 |
+
"grad_norm": 0.5612320899963379,
|
| 2281 |
+
"learning_rate": 0.0001,
|
| 2282 |
+
"loss": 1.6123,
|
| 2283 |
+
"step": 318
|
| 2284 |
+
},
|
| 2285 |
+
{
|
| 2286 |
+
"epoch": 5.063492063492063,
|
| 2287 |
+
"grad_norm": 0.5958861708641052,
|
| 2288 |
+
"learning_rate": 0.0001,
|
| 2289 |
+
"loss": 1.6315,
|
| 2290 |
+
"step": 319
|
| 2291 |
+
},
|
| 2292 |
+
{
|
| 2293 |
+
"epoch": 5.079365079365079,
|
| 2294 |
+
"grad_norm": 0.6226083636283875,
|
| 2295 |
+
"learning_rate": 0.0001,
|
| 2296 |
+
"loss": 1.5719,
|
| 2297 |
+
"step": 320
|
| 2298 |
+
},
|
| 2299 |
+
{
|
| 2300 |
+
"epoch": 5.095238095238095,
|
| 2301 |
+
"grad_norm": 0.6249291896820068,
|
| 2302 |
+
"learning_rate": 0.0001,
|
| 2303 |
+
"loss": 1.6299,
|
| 2304 |
+
"step": 321
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"epoch": 5.111111111111111,
|
| 2308 |
+
"grad_norm": 0.6529788374900818,
|
| 2309 |
+
"learning_rate": 0.0001,
|
| 2310 |
+
"loss": 1.6471,
|
| 2311 |
+
"step": 322
|
| 2312 |
+
},
|
| 2313 |
+
{
|
| 2314 |
+
"epoch": 5.1269841269841265,
|
| 2315 |
+
"grad_norm": 0.6908319592475891,
|
| 2316 |
+
"learning_rate": 0.0001,
|
| 2317 |
+
"loss": 1.5909,
|
| 2318 |
+
"step": 323
|
| 2319 |
+
},
|
| 2320 |
+
{
|
| 2321 |
+
"epoch": 5.142857142857143,
|
| 2322 |
+
"grad_norm": 0.6459047198295593,
|
| 2323 |
+
"learning_rate": 0.0001,
|
| 2324 |
+
"loss": 1.603,
|
| 2325 |
+
"step": 324
|
| 2326 |
+
},
|
| 2327 |
+
{
|
| 2328 |
+
"epoch": 5.158730158730159,
|
| 2329 |
+
"grad_norm": 0.6827127933502197,
|
| 2330 |
+
"learning_rate": 0.0001,
|
| 2331 |
+
"loss": 1.6419,
|
| 2332 |
+
"step": 325
|
| 2333 |
+
},
|
| 2334 |
+
{
|
| 2335 |
+
"epoch": 5.174603174603175,
|
| 2336 |
+
"grad_norm": 0.6518094539642334,
|
| 2337 |
+
"learning_rate": 0.0001,
|
| 2338 |
+
"loss": 1.5266,
|
| 2339 |
+
"step": 326
|
| 2340 |
+
},
|
| 2341 |
+
{
|
| 2342 |
+
"epoch": 5.190476190476191,
|
| 2343 |
+
"grad_norm": 0.6539126038551331,
|
| 2344 |
+
"learning_rate": 0.0001,
|
| 2345 |
+
"loss": 1.588,
|
| 2346 |
+
"step": 327
|
| 2347 |
+
},
|
| 2348 |
+
{
|
| 2349 |
+
"epoch": 5.2063492063492065,
|
| 2350 |
+
"grad_norm": 0.6845505237579346,
|
| 2351 |
+
"learning_rate": 0.0001,
|
| 2352 |
+
"loss": 1.6856,
|
| 2353 |
+
"step": 328
|
| 2354 |
+
},
|
| 2355 |
+
{
|
| 2356 |
+
"epoch": 5.222222222222222,
|
| 2357 |
+
"grad_norm": 0.6854626536369324,
|
| 2358 |
+
"learning_rate": 0.0001,
|
| 2359 |
+
"loss": 1.5232,
|
| 2360 |
+
"step": 329
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"epoch": 5.238095238095238,
|
| 2364 |
+
"grad_norm": 0.6708223223686218,
|
| 2365 |
+
"learning_rate": 0.0001,
|
| 2366 |
+
"loss": 1.6428,
|
| 2367 |
+
"step": 330
|
| 2368 |
+
},
|
| 2369 |
+
{
|
| 2370 |
+
"epoch": 5.253968253968254,
|
| 2371 |
+
"grad_norm": 0.6958265900611877,
|
| 2372 |
+
"learning_rate": 0.0001,
|
| 2373 |
+
"loss": 1.6378,
|
| 2374 |
+
"step": 331
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 5.26984126984127,
|
| 2378 |
+
"grad_norm": 0.6913191676139832,
|
| 2379 |
+
"learning_rate": 0.0001,
|
| 2380 |
+
"loss": 1.6985,
|
| 2381 |
+
"step": 332
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"epoch": 5.285714285714286,
|
| 2385 |
+
"grad_norm": 0.6984105110168457,
|
| 2386 |
+
"learning_rate": 0.0001,
|
| 2387 |
+
"loss": 1.62,
|
| 2388 |
+
"step": 333
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 5.301587301587301,
|
| 2392 |
+
"grad_norm": 0.66806960105896,
|
| 2393 |
+
"learning_rate": 0.0001,
|
| 2394 |
+
"loss": 1.6127,
|
| 2395 |
+
"step": 334
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 5.317460317460317,
|
| 2399 |
+
"grad_norm": 0.7090312838554382,
|
| 2400 |
+
"learning_rate": 0.0001,
|
| 2401 |
+
"loss": 1.6946,
|
| 2402 |
+
"step": 335
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 5.333333333333333,
|
| 2406 |
+
"grad_norm": 0.6773918867111206,
|
| 2407 |
+
"learning_rate": 0.0001,
|
| 2408 |
+
"loss": 1.6279,
|
| 2409 |
+
"step": 336
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 5.349206349206349,
|
| 2413 |
+
"grad_norm": 0.6838431358337402,
|
| 2414 |
+
"learning_rate": 0.0001,
|
| 2415 |
+
"loss": 1.6754,
|
| 2416 |
+
"step": 337
|
| 2417 |
+
},
|
| 2418 |
+
{
|
| 2419 |
+
"epoch": 5.365079365079365,
|
| 2420 |
+
"grad_norm": 0.6330438852310181,
|
| 2421 |
+
"learning_rate": 0.0001,
|
| 2422 |
+
"loss": 1.6442,
|
| 2423 |
+
"step": 338
|
| 2424 |
+
},
|
| 2425 |
+
{
|
| 2426 |
+
"epoch": 5.380952380952381,
|
| 2427 |
+
"grad_norm": 0.6538076996803284,
|
| 2428 |
+
"learning_rate": 0.0001,
|
| 2429 |
+
"loss": 1.5448,
|
| 2430 |
+
"step": 339
|
| 2431 |
+
},
|
| 2432 |
+
{
|
| 2433 |
+
"epoch": 5.396825396825397,
|
| 2434 |
+
"grad_norm": 0.6480404138565063,
|
| 2435 |
+
"learning_rate": 0.0001,
|
| 2436 |
+
"loss": 1.5462,
|
| 2437 |
+
"step": 340
|
| 2438 |
+
},
|
| 2439 |
+
{
|
| 2440 |
+
"epoch": 5.412698412698413,
|
| 2441 |
+
"grad_norm": 0.6559010148048401,
|
| 2442 |
+
"learning_rate": 0.0001,
|
| 2443 |
+
"loss": 1.5379,
|
| 2444 |
+
"step": 341
|
| 2445 |
+
},
|
| 2446 |
+
{
|
| 2447 |
+
"epoch": 5.428571428571429,
|
| 2448 |
+
"grad_norm": 0.6348094344139099,
|
| 2449 |
+
"learning_rate": 0.0001,
|
| 2450 |
+
"loss": 1.6161,
|
| 2451 |
+
"step": 342
|
| 2452 |
+
},
|
| 2453 |
+
{
|
| 2454 |
+
"epoch": 5.444444444444445,
|
| 2455 |
+
"grad_norm": 0.6932337880134583,
|
| 2456 |
+
"learning_rate": 0.0001,
|
| 2457 |
+
"loss": 1.6454,
|
| 2458 |
+
"step": 343
|
| 2459 |
+
},
|
| 2460 |
+
{
|
| 2461 |
+
"epoch": 5.4603174603174605,
|
| 2462 |
+
"grad_norm": 0.64915531873703,
|
| 2463 |
+
"learning_rate": 0.0001,
|
| 2464 |
+
"loss": 1.538,
|
| 2465 |
+
"step": 344
|
| 2466 |
+
},
|
| 2467 |
+
{
|
| 2468 |
+
"epoch": 5.476190476190476,
|
| 2469 |
+
"grad_norm": 0.6293311715126038,
|
| 2470 |
+
"learning_rate": 0.0001,
|
| 2471 |
+
"loss": 1.5464,
|
| 2472 |
+
"step": 345
|
| 2473 |
+
},
|
| 2474 |
+
{
|
| 2475 |
+
"epoch": 5.492063492063492,
|
| 2476 |
+
"grad_norm": 0.6604505777359009,
|
| 2477 |
+
"learning_rate": 0.0001,
|
| 2478 |
+
"loss": 1.5553,
|
| 2479 |
+
"step": 346
|
| 2480 |
+
},
|
| 2481 |
+
{
|
| 2482 |
+
"epoch": 5.507936507936508,
|
| 2483 |
+
"grad_norm": 0.6476812958717346,
|
| 2484 |
+
"learning_rate": 0.0001,
|
| 2485 |
+
"loss": 1.5847,
|
| 2486 |
+
"step": 347
|
| 2487 |
+
},
|
| 2488 |
+
{
|
| 2489 |
+
"epoch": 5.523809523809524,
|
| 2490 |
+
"grad_norm": 0.6579138040542603,
|
| 2491 |
+
"learning_rate": 0.0001,
|
| 2492 |
+
"loss": 1.6174,
|
| 2493 |
+
"step": 348
|
| 2494 |
+
},
|
| 2495 |
+
{
|
| 2496 |
+
"epoch": 5.5396825396825395,
|
| 2497 |
+
"grad_norm": 0.6614880561828613,
|
| 2498 |
+
"learning_rate": 0.0001,
|
| 2499 |
+
"loss": 1.6354,
|
| 2500 |
+
"step": 349
|
| 2501 |
+
},
|
| 2502 |
+
{
|
| 2503 |
+
"epoch": 5.555555555555555,
|
| 2504 |
+
"grad_norm": 0.6744685769081116,
|
| 2505 |
+
"learning_rate": 0.0001,
|
| 2506 |
+
"loss": 1.6388,
|
| 2507 |
+
"step": 350
|
| 2508 |
+
},
|
| 2509 |
+
{
|
| 2510 |
+
"epoch": 5.571428571428571,
|
| 2511 |
+
"grad_norm": 0.6690863370895386,
|
| 2512 |
+
"learning_rate": 0.0001,
|
| 2513 |
+
"loss": 1.6034,
|
| 2514 |
+
"step": 351
|
| 2515 |
+
},
|
| 2516 |
+
{
|
| 2517 |
+
"epoch": 5.587301587301587,
|
| 2518 |
+
"grad_norm": 0.6661965847015381,
|
| 2519 |
+
"learning_rate": 0.0001,
|
| 2520 |
+
"loss": 1.6286,
|
| 2521 |
+
"step": 352
|
| 2522 |
+
},
|
| 2523 |
+
{
|
| 2524 |
+
"epoch": 5.603174603174603,
|
| 2525 |
+
"grad_norm": 0.6643967032432556,
|
| 2526 |
+
"learning_rate": 0.0001,
|
| 2527 |
+
"loss": 1.5426,
|
| 2528 |
+
"step": 353
|
| 2529 |
+
},
|
| 2530 |
+
{
|
| 2531 |
+
"epoch": 5.619047619047619,
|
| 2532 |
+
"grad_norm": 0.6881186962127686,
|
| 2533 |
+
"learning_rate": 0.0001,
|
| 2534 |
+
"loss": 1.6907,
|
| 2535 |
+
"step": 354
|
| 2536 |
+
},
|
| 2537 |
+
{
|
| 2538 |
+
"epoch": 5.634920634920634,
|
| 2539 |
+
"grad_norm": 0.7087846994400024,
|
| 2540 |
+
"learning_rate": 0.0001,
|
| 2541 |
+
"loss": 1.6521,
|
| 2542 |
+
"step": 355
|
| 2543 |
+
},
|
| 2544 |
+
{
|
| 2545 |
+
"epoch": 5.650793650793651,
|
| 2546 |
+
"grad_norm": 0.650434672832489,
|
| 2547 |
+
"learning_rate": 0.0001,
|
| 2548 |
+
"loss": 1.523,
|
| 2549 |
+
"step": 356
|
| 2550 |
+
},
|
| 2551 |
+
{
|
| 2552 |
+
"epoch": 5.666666666666667,
|
| 2553 |
+
"grad_norm": 0.7101690173149109,
|
| 2554 |
+
"learning_rate": 0.0001,
|
| 2555 |
+
"loss": 1.6927,
|
| 2556 |
+
"step": 357
|
| 2557 |
+
},
|
| 2558 |
+
{
|
| 2559 |
+
"epoch": 5.682539682539683,
|
| 2560 |
+
"grad_norm": 0.6721552610397339,
|
| 2561 |
+
"learning_rate": 0.0001,
|
| 2562 |
+
"loss": 1.5502,
|
| 2563 |
+
"step": 358
|
| 2564 |
+
},
|
| 2565 |
+
{
|
| 2566 |
+
"epoch": 5.698412698412699,
|
| 2567 |
+
"grad_norm": 0.6540137529373169,
|
| 2568 |
+
"learning_rate": 0.0001,
|
| 2569 |
+
"loss": 1.6293,
|
| 2570 |
+
"step": 359
|
| 2571 |
+
},
|
| 2572 |
+
{
|
| 2573 |
+
"epoch": 5.714285714285714,
|
| 2574 |
+
"grad_norm": 0.6534785628318787,
|
| 2575 |
+
"learning_rate": 0.0001,
|
| 2576 |
+
"loss": 1.5925,
|
| 2577 |
+
"step": 360
|
| 2578 |
+
},
|
| 2579 |
+
{
|
| 2580 |
+
"epoch": 5.73015873015873,
|
| 2581 |
+
"grad_norm": 0.6745355725288391,
|
| 2582 |
+
"learning_rate": 0.0001,
|
| 2583 |
+
"loss": 1.5922,
|
| 2584 |
+
"step": 361
|
| 2585 |
+
},
|
| 2586 |
+
{
|
| 2587 |
+
"epoch": 5.746031746031746,
|
| 2588 |
+
"grad_norm": 0.6722214818000793,
|
| 2589 |
+
"learning_rate": 0.0001,
|
| 2590 |
+
"loss": 1.6273,
|
| 2591 |
+
"step": 362
|
| 2592 |
+
},
|
| 2593 |
+
{
|
| 2594 |
+
"epoch": 5.761904761904762,
|
| 2595 |
+
"grad_norm": 0.6378102898597717,
|
| 2596 |
+
"learning_rate": 0.0001,
|
| 2597 |
+
"loss": 1.5504,
|
| 2598 |
+
"step": 363
|
| 2599 |
+
},
|
| 2600 |
+
{
|
| 2601 |
+
"epoch": 5.777777777777778,
|
| 2602 |
+
"grad_norm": 0.6449686884880066,
|
| 2603 |
+
"learning_rate": 0.0001,
|
| 2604 |
+
"loss": 1.6315,
|
| 2605 |
+
"step": 364
|
| 2606 |
+
},
|
| 2607 |
+
{
|
| 2608 |
+
"epoch": 5.7936507936507935,
|
| 2609 |
+
"grad_norm": 0.6779683232307434,
|
| 2610 |
+
"learning_rate": 0.0001,
|
| 2611 |
+
"loss": 1.5937,
|
| 2612 |
+
"step": 365
|
| 2613 |
+
},
|
| 2614 |
+
{
|
| 2615 |
+
"epoch": 5.809523809523809,
|
| 2616 |
+
"grad_norm": 0.6729435324668884,
|
| 2617 |
+
"learning_rate": 0.0001,
|
| 2618 |
+
"loss": 1.6205,
|
| 2619 |
+
"step": 366
|
| 2620 |
+
},
|
| 2621 |
+
{
|
| 2622 |
+
"epoch": 5.825396825396825,
|
| 2623 |
+
"grad_norm": 0.6568869352340698,
|
| 2624 |
+
"learning_rate": 0.0001,
|
| 2625 |
+
"loss": 1.6838,
|
| 2626 |
+
"step": 367
|
| 2627 |
+
},
|
| 2628 |
+
{
|
| 2629 |
+
"epoch": 5.841269841269841,
|
| 2630 |
+
"grad_norm": 0.657180905342102,
|
| 2631 |
+
"learning_rate": 0.0001,
|
| 2632 |
+
"loss": 1.6873,
|
| 2633 |
+
"step": 368
|
| 2634 |
+
},
|
| 2635 |
+
{
|
| 2636 |
+
"epoch": 5.857142857142857,
|
| 2637 |
+
"grad_norm": 0.6792422533035278,
|
| 2638 |
+
"learning_rate": 0.0001,
|
| 2639 |
+
"loss": 1.6572,
|
| 2640 |
+
"step": 369
|
| 2641 |
+
},
|
| 2642 |
+
{
|
| 2643 |
+
"epoch": 5.8730158730158735,
|
| 2644 |
+
"grad_norm": 0.674778938293457,
|
| 2645 |
+
"learning_rate": 0.0001,
|
| 2646 |
+
"loss": 1.5743,
|
| 2647 |
+
"step": 370
|
| 2648 |
+
},
|
| 2649 |
+
{
|
| 2650 |
+
"epoch": 5.888888888888889,
|
| 2651 |
+
"grad_norm": 0.6656611561775208,
|
| 2652 |
+
"learning_rate": 0.0001,
|
| 2653 |
+
"loss": 1.6039,
|
| 2654 |
+
"step": 371
|
| 2655 |
+
},
|
| 2656 |
+
{
|
| 2657 |
+
"epoch": 5.904761904761905,
|
| 2658 |
+
"grad_norm": 0.6537423729896545,
|
| 2659 |
+
"learning_rate": 0.0001,
|
| 2660 |
+
"loss": 1.5889,
|
| 2661 |
+
"step": 372
|
| 2662 |
+
},
|
| 2663 |
+
{
|
| 2664 |
+
"epoch": 5.920634920634921,
|
| 2665 |
+
"grad_norm": 0.6616511344909668,
|
| 2666 |
+
"learning_rate": 0.0001,
|
| 2667 |
+
"loss": 1.6258,
|
| 2668 |
+
"step": 373
|
| 2669 |
+
},
|
| 2670 |
+
{
|
| 2671 |
+
"epoch": 5.936507936507937,
|
| 2672 |
+
"grad_norm": 0.6798099279403687,
|
| 2673 |
+
"learning_rate": 0.0001,
|
| 2674 |
+
"loss": 1.6653,
|
| 2675 |
+
"step": 374
|
| 2676 |
+
},
|
| 2677 |
+
{
|
| 2678 |
+
"epoch": 5.9523809523809526,
|
| 2679 |
+
"grad_norm": 0.6805852651596069,
|
| 2680 |
+
"learning_rate": 0.0001,
|
| 2681 |
+
"loss": 1.5925,
|
| 2682 |
+
"step": 375
|
| 2683 |
+
},
|
| 2684 |
+
{
|
| 2685 |
+
"epoch": 5.968253968253968,
|
| 2686 |
+
"grad_norm": 0.6990432739257812,
|
| 2687 |
+
"learning_rate": 0.0001,
|
| 2688 |
+
"loss": 1.6191,
|
| 2689 |
+
"step": 376
|
| 2690 |
+
},
|
| 2691 |
+
{
|
| 2692 |
+
"epoch": 5.984126984126984,
|
| 2693 |
+
"grad_norm": 0.6628381609916687,
|
| 2694 |
+
"learning_rate": 0.0001,
|
| 2695 |
+
"loss": 1.6047,
|
| 2696 |
+
"step": 377
|
| 2697 |
+
},
|
| 2698 |
+
{
|
| 2699 |
+
"epoch": 6.0,
|
| 2700 |
+
"grad_norm": 0.6924659013748169,
|
| 2701 |
+
"learning_rate": 0.0001,
|
| 2702 |
+
"loss": 1.648,
|
| 2703 |
+
"step": 378
|
| 2704 |
+
},
|
| 2705 |
+
{
|
| 2706 |
+
"epoch": 6.0,
|
| 2707 |
+
"eval_loss": 1.893735408782959,
|
| 2708 |
+
"eval_runtime": 134.3253,
|
| 2709 |
+
"eval_samples_per_second": 144.842,
|
| 2710 |
+
"eval_steps_per_second": 1.132,
|
| 2711 |
+
"step": 378
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 6.015873015873016,
|
| 2715 |
+
"grad_norm": 0.6388320922851562,
|
| 2716 |
+
"learning_rate": 0.0001,
|
| 2717 |
+
"loss": 1.4293,
|
| 2718 |
+
"step": 379
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 6.031746031746032,
|
| 2722 |
+
"grad_norm": 0.6490210294723511,
|
| 2723 |
+
"learning_rate": 0.0001,
|
| 2724 |
+
"loss": 1.4351,
|
| 2725 |
+
"step": 380
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 6.0476190476190474,
|
| 2729 |
+
"grad_norm": 0.6522358059883118,
|
| 2730 |
+
"learning_rate": 0.0001,
|
| 2731 |
+
"loss": 1.5777,
|
| 2732 |
+
"step": 381
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 6.063492063492063,
|
| 2736 |
+
"grad_norm": 0.6604855060577393,
|
| 2737 |
+
"learning_rate": 0.0001,
|
| 2738 |
+
"loss": 1.4703,
|
| 2739 |
+
"step": 382
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 6.079365079365079,
|
| 2743 |
+
"grad_norm": 0.7197854518890381,
|
| 2744 |
+
"learning_rate": 0.0001,
|
| 2745 |
+
"loss": 1.5503,
|
| 2746 |
+
"step": 383
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 6.095238095238095,
|
| 2750 |
+
"grad_norm": 0.6556975245475769,
|
| 2751 |
+
"learning_rate": 0.0001,
|
| 2752 |
+
"loss": 1.4253,
|
| 2753 |
+
"step": 384
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 6.111111111111111,
|
| 2757 |
+
"grad_norm": 0.7312705516815186,
|
| 2758 |
+
"learning_rate": 0.0001,
|
| 2759 |
+
"loss": 1.5137,
|
| 2760 |
+
"step": 385
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 6.1269841269841265,
|
| 2764 |
+
"grad_norm": 0.7358348369598389,
|
| 2765 |
+
"learning_rate": 0.0001,
|
| 2766 |
+
"loss": 1.4937,
|
| 2767 |
+
"step": 386
|
| 2768 |
+
},
|
| 2769 |
+
{
|
| 2770 |
+
"epoch": 6.142857142857143,
|
| 2771 |
+
"grad_norm": 0.7860615849494934,
|
| 2772 |
+
"learning_rate": 0.0001,
|
| 2773 |
+
"loss": 1.4851,
|
| 2774 |
+
"step": 387
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 6.158730158730159,
|
| 2778 |
+
"grad_norm": 0.7622462511062622,
|
| 2779 |
+
"learning_rate": 0.0001,
|
| 2780 |
+
"loss": 1.5141,
|
| 2781 |
+
"step": 388
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 6.174603174603175,
|
| 2785 |
+
"grad_norm": 0.7551783919334412,
|
| 2786 |
+
"learning_rate": 0.0001,
|
| 2787 |
+
"loss": 1.5183,
|
| 2788 |
+
"step": 389
|
| 2789 |
+
},
|
| 2790 |
+
{
|
| 2791 |
+
"epoch": 6.190476190476191,
|
| 2792 |
+
"grad_norm": 0.7600305080413818,
|
| 2793 |
+
"learning_rate": 0.0001,
|
| 2794 |
+
"loss": 1.5138,
|
| 2795 |
+
"step": 390
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 6.2063492063492065,
|
| 2799 |
+
"grad_norm": 0.7626650929450989,
|
| 2800 |
+
"learning_rate": 0.0001,
|
| 2801 |
+
"loss": 1.5289,
|
| 2802 |
+
"step": 391
|
| 2803 |
+
},
|
| 2804 |
+
{
|
| 2805 |
+
"epoch": 6.222222222222222,
|
| 2806 |
+
"grad_norm": 0.7509219646453857,
|
| 2807 |
+
"learning_rate": 0.0001,
|
| 2808 |
+
"loss": 1.5369,
|
| 2809 |
+
"step": 392
|
| 2810 |
+
},
|
| 2811 |
+
{
|
| 2812 |
+
"epoch": 6.238095238095238,
|
| 2813 |
+
"grad_norm": 0.7860161066055298,
|
| 2814 |
+
"learning_rate": 0.0001,
|
| 2815 |
+
"loss": 1.6698,
|
| 2816 |
+
"step": 393
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 6.253968253968254,
|
| 2820 |
+
"grad_norm": 0.7737497091293335,
|
| 2821 |
+
"learning_rate": 0.0001,
|
| 2822 |
+
"loss": 1.5183,
|
| 2823 |
+
"step": 394
|
| 2824 |
+
},
|
| 2825 |
+
{
|
| 2826 |
+
"epoch": 6.26984126984127,
|
| 2827 |
+
"grad_norm": 0.7612232565879822,
|
| 2828 |
+
"learning_rate": 0.0001,
|
| 2829 |
+
"loss": 1.5428,
|
| 2830 |
+
"step": 395
|
| 2831 |
+
},
|
| 2832 |
+
{
|
| 2833 |
+
"epoch": 6.285714285714286,
|
| 2834 |
+
"grad_norm": 0.7460598945617676,
|
| 2835 |
+
"learning_rate": 0.0001,
|
| 2836 |
+
"loss": 1.4845,
|
| 2837 |
+
"step": 396
|
| 2838 |
+
},
|
| 2839 |
+
{
|
| 2840 |
+
"epoch": 6.301587301587301,
|
| 2841 |
+
"grad_norm": 0.7065163254737854,
|
| 2842 |
+
"learning_rate": 0.0001,
|
| 2843 |
+
"loss": 1.5558,
|
| 2844 |
+
"step": 397
|
| 2845 |
+
},
|
| 2846 |
+
{
|
| 2847 |
+
"epoch": 6.317460317460317,
|
| 2848 |
+
"grad_norm": 0.7342137098312378,
|
| 2849 |
+
"learning_rate": 0.0001,
|
| 2850 |
+
"loss": 1.587,
|
| 2851 |
+
"step": 398
|
| 2852 |
+
},
|
| 2853 |
+
{
|
| 2854 |
+
"epoch": 6.333333333333333,
|
| 2855 |
+
"grad_norm": 0.7295916080474854,
|
| 2856 |
+
"learning_rate": 0.0001,
|
| 2857 |
+
"loss": 1.547,
|
| 2858 |
+
"step": 399
|
| 2859 |
+
},
|
| 2860 |
+
{
|
| 2861 |
+
"epoch": 6.349206349206349,
|
| 2862 |
+
"grad_norm": 0.7360773682594299,
|
| 2863 |
+
"learning_rate": 0.0001,
|
| 2864 |
+
"loss": 1.5068,
|
| 2865 |
+
"step": 400
|
| 2866 |
+
},
|
| 2867 |
+
{
|
| 2868 |
+
"epoch": 6.365079365079365,
|
| 2869 |
+
"grad_norm": 0.70721435546875,
|
| 2870 |
+
"learning_rate": 0.0001,
|
| 2871 |
+
"loss": 1.4583,
|
| 2872 |
+
"step": 401
|
| 2873 |
+
},
|
| 2874 |
+
{
|
| 2875 |
+
"epoch": 6.380952380952381,
|
| 2876 |
+
"grad_norm": 0.7247203588485718,
|
| 2877 |
+
"learning_rate": 0.0001,
|
| 2878 |
+
"loss": 1.4748,
|
| 2879 |
+
"step": 402
|
| 2880 |
+
},
|
| 2881 |
+
{
|
| 2882 |
+
"epoch": 6.396825396825397,
|
| 2883 |
+
"grad_norm": 0.7227998375892639,
|
| 2884 |
+
"learning_rate": 0.0001,
|
| 2885 |
+
"loss": 1.4848,
|
| 2886 |
+
"step": 403
|
| 2887 |
+
},
|
| 2888 |
+
{
|
| 2889 |
+
"epoch": 6.412698412698413,
|
| 2890 |
+
"grad_norm": 0.7279331684112549,
|
| 2891 |
+
"learning_rate": 0.0001,
|
| 2892 |
+
"loss": 1.5815,
|
| 2893 |
+
"step": 404
|
| 2894 |
+
},
|
| 2895 |
+
{
|
| 2896 |
+
"epoch": 6.428571428571429,
|
| 2897 |
+
"grad_norm": 0.7601774334907532,
|
| 2898 |
+
"learning_rate": 0.0001,
|
| 2899 |
+
"loss": 1.5399,
|
| 2900 |
+
"step": 405
|
| 2901 |
+
},
|
| 2902 |
+
{
|
| 2903 |
+
"epoch": 6.444444444444445,
|
| 2904 |
+
"grad_norm": 0.757248044013977,
|
| 2905 |
+
"learning_rate": 0.0001,
|
| 2906 |
+
"loss": 1.5974,
|
| 2907 |
+
"step": 406
|
| 2908 |
+
},
|
| 2909 |
+
{
|
| 2910 |
+
"epoch": 6.4603174603174605,
|
| 2911 |
+
"grad_norm": 0.7181381583213806,
|
| 2912 |
+
"learning_rate": 0.0001,
|
| 2913 |
+
"loss": 1.4998,
|
| 2914 |
+
"step": 407
|
| 2915 |
+
},
|
| 2916 |
+
{
|
| 2917 |
+
"epoch": 6.476190476190476,
|
| 2918 |
+
"grad_norm": 0.720007598400116,
|
| 2919 |
+
"learning_rate": 0.0001,
|
| 2920 |
+
"loss": 1.4671,
|
| 2921 |
+
"step": 408
|
| 2922 |
+
},
|
| 2923 |
+
{
|
| 2924 |
+
"epoch": 6.492063492063492,
|
| 2925 |
+
"grad_norm": 0.7401720285415649,
|
| 2926 |
+
"learning_rate": 0.0001,
|
| 2927 |
+
"loss": 1.5884,
|
| 2928 |
+
"step": 409
|
| 2929 |
+
},
|
| 2930 |
+
{
|
| 2931 |
+
"epoch": 6.507936507936508,
|
| 2932 |
+
"grad_norm": 0.7520825266838074,
|
| 2933 |
+
"learning_rate": 0.0001,
|
| 2934 |
+
"loss": 1.5311,
|
| 2935 |
+
"step": 410
|
| 2936 |
+
},
|
| 2937 |
+
{
|
| 2938 |
+
"epoch": 6.523809523809524,
|
| 2939 |
+
"grad_norm": 0.8031005859375,
|
| 2940 |
+
"learning_rate": 0.0001,
|
| 2941 |
+
"loss": 1.4992,
|
| 2942 |
+
"step": 411
|
| 2943 |
+
},
|
| 2944 |
+
{
|
| 2945 |
+
"epoch": 6.5396825396825395,
|
| 2946 |
+
"grad_norm": 0.7898001074790955,
|
| 2947 |
+
"learning_rate": 0.0001,
|
| 2948 |
+
"loss": 1.5633,
|
| 2949 |
+
"step": 412
|
| 2950 |
+
},
|
| 2951 |
+
{
|
| 2952 |
+
"epoch": 6.555555555555555,
|
| 2953 |
+
"grad_norm": 0.7533549070358276,
|
| 2954 |
+
"learning_rate": 0.0001,
|
| 2955 |
+
"loss": 1.5405,
|
| 2956 |
+
"step": 413
|
| 2957 |
+
},
|
| 2958 |
+
{
|
| 2959 |
+
"epoch": 6.571428571428571,
|
| 2960 |
+
"grad_norm": 0.754895806312561,
|
| 2961 |
+
"learning_rate": 0.0001,
|
| 2962 |
+
"loss": 1.5365,
|
| 2963 |
+
"step": 414
|
| 2964 |
+
},
|
| 2965 |
+
{
|
| 2966 |
+
"epoch": 6.587301587301587,
|
| 2967 |
+
"grad_norm": 0.7513403296470642,
|
| 2968 |
+
"learning_rate": 0.0001,
|
| 2969 |
+
"loss": 1.5621,
|
| 2970 |
+
"step": 415
|
| 2971 |
+
},
|
| 2972 |
+
{
|
| 2973 |
+
"epoch": 6.603174603174603,
|
| 2974 |
+
"grad_norm": 0.7395815253257751,
|
| 2975 |
+
"learning_rate": 0.0001,
|
| 2976 |
+
"loss": 1.5415,
|
| 2977 |
+
"step": 416
|
| 2978 |
+
},
|
| 2979 |
+
{
|
| 2980 |
+
"epoch": 6.619047619047619,
|
| 2981 |
+
"grad_norm": 0.7354024052619934,
|
| 2982 |
+
"learning_rate": 0.0001,
|
| 2983 |
+
"loss": 1.5583,
|
| 2984 |
+
"step": 417
|
| 2985 |
+
},
|
| 2986 |
+
{
|
| 2987 |
+
"epoch": 6.634920634920634,
|
| 2988 |
+
"grad_norm": 0.7478825449943542,
|
| 2989 |
+
"learning_rate": 0.0001,
|
| 2990 |
+
"loss": 1.5716,
|
| 2991 |
+
"step": 418
|
| 2992 |
+
},
|
| 2993 |
+
{
|
| 2994 |
+
"epoch": 6.650793650793651,
|
| 2995 |
+
"grad_norm": 0.754396915435791,
|
| 2996 |
+
"learning_rate": 0.0001,
|
| 2997 |
+
"loss": 1.5412,
|
| 2998 |
+
"step": 419
|
| 2999 |
+
},
|
| 3000 |
+
{
|
| 3001 |
+
"epoch": 6.666666666666667,
|
| 3002 |
+
"grad_norm": 0.7304781079292297,
|
| 3003 |
+
"learning_rate": 0.0001,
|
| 3004 |
+
"loss": 1.5346,
|
| 3005 |
+
"step": 420
|
| 3006 |
+
},
|
| 3007 |
+
{
|
| 3008 |
+
"epoch": 6.682539682539683,
|
| 3009 |
+
"grad_norm": 0.7279454469680786,
|
| 3010 |
+
"learning_rate": 0.0001,
|
| 3011 |
+
"loss": 1.5421,
|
| 3012 |
+
"step": 421
|
| 3013 |
+
},
|
| 3014 |
+
{
|
| 3015 |
+
"epoch": 6.698412698412699,
|
| 3016 |
+
"grad_norm": 0.7421950697898865,
|
| 3017 |
+
"learning_rate": 0.0001,
|
| 3018 |
+
"loss": 1.5446,
|
| 3019 |
+
"step": 422
|
| 3020 |
+
},
|
| 3021 |
+
{
|
| 3022 |
+
"epoch": 6.714285714285714,
|
| 3023 |
+
"grad_norm": 0.7641916871070862,
|
| 3024 |
+
"learning_rate": 0.0001,
|
| 3025 |
+
"loss": 1.5919,
|
| 3026 |
+
"step": 423
|
| 3027 |
+
},
|
| 3028 |
+
{
|
| 3029 |
+
"epoch": 6.73015873015873,
|
| 3030 |
+
"grad_norm": 0.7338146567344666,
|
| 3031 |
+
"learning_rate": 0.0001,
|
| 3032 |
+
"loss": 1.5636,
|
| 3033 |
+
"step": 424
|
| 3034 |
+
},
|
| 3035 |
+
{
|
| 3036 |
+
"epoch": 6.746031746031746,
|
| 3037 |
+
"grad_norm": 0.7525890469551086,
|
| 3038 |
+
"learning_rate": 0.0001,
|
| 3039 |
+
"loss": 1.4048,
|
| 3040 |
+
"step": 425
|
| 3041 |
+
},
|
| 3042 |
+
{
|
| 3043 |
+
"epoch": 6.761904761904762,
|
| 3044 |
+
"grad_norm": 0.7142500877380371,
|
| 3045 |
+
"learning_rate": 0.0001,
|
| 3046 |
+
"loss": 1.5079,
|
| 3047 |
+
"step": 426
|
| 3048 |
+
},
|
| 3049 |
+
{
|
| 3050 |
+
"epoch": 6.777777777777778,
|
| 3051 |
+
"grad_norm": 0.7610086798667908,
|
| 3052 |
+
"learning_rate": 0.0001,
|
| 3053 |
+
"loss": 1.5715,
|
| 3054 |
+
"step": 427
|
| 3055 |
+
},
|
| 3056 |
+
{
|
| 3057 |
+
"epoch": 6.7936507936507935,
|
| 3058 |
+
"grad_norm": 0.7412837147712708,
|
| 3059 |
+
"learning_rate": 0.0001,
|
| 3060 |
+
"loss": 1.574,
|
| 3061 |
+
"step": 428
|
| 3062 |
+
},
|
| 3063 |
+
{
|
| 3064 |
+
"epoch": 6.809523809523809,
|
| 3065 |
+
"grad_norm": 0.7154977917671204,
|
| 3066 |
+
"learning_rate": 0.0001,
|
| 3067 |
+
"loss": 1.571,
|
| 3068 |
+
"step": 429
|
| 3069 |
+
},
|
| 3070 |
+
{
|
| 3071 |
+
"epoch": 6.825396825396825,
|
| 3072 |
+
"grad_norm": 0.7311663031578064,
|
| 3073 |
+
"learning_rate": 0.0001,
|
| 3074 |
+
"loss": 1.5427,
|
| 3075 |
+
"step": 430
|
| 3076 |
+
},
|
| 3077 |
+
{
|
| 3078 |
+
"epoch": 6.841269841269841,
|
| 3079 |
+
"grad_norm": 0.7270447015762329,
|
| 3080 |
+
"learning_rate": 0.0001,
|
| 3081 |
+
"loss": 1.4732,
|
| 3082 |
+
"step": 431
|
| 3083 |
+
},
|
| 3084 |
+
{
|
| 3085 |
+
"epoch": 6.857142857142857,
|
| 3086 |
+
"grad_norm": 0.7176763415336609,
|
| 3087 |
+
"learning_rate": 0.0001,
|
| 3088 |
+
"loss": 1.5265,
|
| 3089 |
+
"step": 432
|
| 3090 |
+
},
|
| 3091 |
+
{
|
| 3092 |
+
"epoch": 6.8730158730158735,
|
| 3093 |
+
"grad_norm": 0.7348573803901672,
|
| 3094 |
+
"learning_rate": 0.0001,
|
| 3095 |
+
"loss": 1.5003,
|
| 3096 |
+
"step": 433
|
| 3097 |
+
},
|
| 3098 |
+
{
|
| 3099 |
+
"epoch": 6.888888888888889,
|
| 3100 |
+
"grad_norm": 0.7507191300392151,
|
| 3101 |
+
"learning_rate": 0.0001,
|
| 3102 |
+
"loss": 1.5573,
|
| 3103 |
+
"step": 434
|
| 3104 |
+
},
|
| 3105 |
+
{
|
| 3106 |
+
"epoch": 6.904761904761905,
|
| 3107 |
+
"grad_norm": 0.7464054226875305,
|
| 3108 |
+
"learning_rate": 0.0001,
|
| 3109 |
+
"loss": 1.4821,
|
| 3110 |
+
"step": 435
|
| 3111 |
+
},
|
| 3112 |
+
{
|
| 3113 |
+
"epoch": 6.920634920634921,
|
| 3114 |
+
"grad_norm": 0.7474199533462524,
|
| 3115 |
+
"learning_rate": 0.0001,
|
| 3116 |
+
"loss": 1.5352,
|
| 3117 |
+
"step": 436
|
| 3118 |
+
},
|
| 3119 |
+
{
|
| 3120 |
+
"epoch": 6.936507936507937,
|
| 3121 |
+
"grad_norm": 0.7470847964286804,
|
| 3122 |
+
"learning_rate": 0.0001,
|
| 3123 |
+
"loss": 1.4832,
|
| 3124 |
+
"step": 437
|
| 3125 |
+
},
|
| 3126 |
+
{
|
| 3127 |
+
"epoch": 6.9523809523809526,
|
| 3128 |
+
"grad_norm": 0.7664744853973389,
|
| 3129 |
+
"learning_rate": 0.0001,
|
| 3130 |
+
"loss": 1.6228,
|
| 3131 |
+
"step": 438
|
| 3132 |
+
},
|
| 3133 |
+
{
|
| 3134 |
+
"epoch": 6.968253968253968,
|
| 3135 |
+
"grad_norm": 0.7515738010406494,
|
| 3136 |
+
"learning_rate": 0.0001,
|
| 3137 |
+
"loss": 1.5293,
|
| 3138 |
+
"step": 439
|
| 3139 |
+
},
|
| 3140 |
+
{
|
| 3141 |
+
"epoch": 6.984126984126984,
|
| 3142 |
+
"grad_norm": 0.7518280148506165,
|
| 3143 |
+
"learning_rate": 0.0001,
|
| 3144 |
+
"loss": 1.532,
|
| 3145 |
+
"step": 440
|
| 3146 |
+
},
|
| 3147 |
+
{
|
| 3148 |
+
"epoch": 7.0,
|
| 3149 |
+
"grad_norm": 0.7737464904785156,
|
| 3150 |
+
"learning_rate": 0.0001,
|
| 3151 |
+
"loss": 1.5843,
|
| 3152 |
+
"step": 441
|
| 3153 |
+
},
|
| 3154 |
+
{
|
| 3155 |
+
"epoch": 7.0,
|
| 3156 |
+
"eval_loss": 1.914687156677246,
|
| 3157 |
+
"eval_runtime": 134.2233,
|
| 3158 |
+
"eval_samples_per_second": 144.953,
|
| 3159 |
+
"eval_steps_per_second": 1.132,
|
| 3160 |
+
"step": 441
|
| 3161 |
+
}
|
| 3162 |
+
],
|
| 3163 |
+
"logging_steps": 1,
|
| 3164 |
+
"max_steps": 504,
|
| 3165 |
+
"num_input_tokens_seen": 0,
|
| 3166 |
+
"num_train_epochs": 8,
|
| 3167 |
+
"save_steps": 500,
|
| 3168 |
+
"stateful_callbacks": {
|
| 3169 |
+
"TrainerControl": {
|
| 3170 |
+
"args": {
|
| 3171 |
+
"should_epoch_stop": false,
|
| 3172 |
+
"should_evaluate": false,
|
| 3173 |
+
"should_log": false,
|
| 3174 |
+
"should_save": true,
|
| 3175 |
+
"should_training_stop": false
|
| 3176 |
+
},
|
| 3177 |
+
"attributes": {}
|
| 3178 |
+
}
|
| 3179 |
+
},
|
| 3180 |
+
"total_flos": 2.521883441872503e+18,
|
| 3181 |
+
"train_batch_size": 128,
|
| 3182 |
+
"trial_name": null,
|
| 3183 |
+
"trial_params": null
|
| 3184 |
+
}
|
checkpoint-441/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e9be0ddf49abe710fcf99a1b2b043dcf393ad929536b792a3f42789e14f0bca
|
| 3 |
+
size 5496
|