Hugging Face's logo

balajipitchumani
/
axol-openllmama-1k-qlora

PEFT
TensorBoard
Safetensors
llama
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files
xet
Metrics Community
balajipitchumani commited on
Commit
c024946
·
verified ·
1 Parent(s): a840e42

Upload folder using huggingface_hub

Browse files
Files changed (25) hide show
  1. README.md +139 -0
  2. adapter_config.json +33 -0
  3. adapter_model.bin +3 -0
  4. checkpoint-426/README.md +202 -0
  5. checkpoint-426/adapter_config.json +33 -0
  6. checkpoint-426/adapter_model.safetensors +3 -0
  7. checkpoint-426/optimizer.pt +3 -0
  8. checkpoint-426/rng_state.pth +3 -0
  9. checkpoint-426/scheduler.pt +3 -0
  10. checkpoint-426/trainer_state.json +3035 -0
  11. checkpoint-426/training_args.bin +3 -0
  12. checkpoint-852/README.md +202 -0
  13. checkpoint-852/adapter_config.json +33 -0
  14. checkpoint-852/adapter_model.safetensors +3 -0
  15. checkpoint-852/optimizer.pt +3 -0
  16. checkpoint-852/rng_state.pth +3 -0
  17. checkpoint-852/scheduler.pt +3 -0
  18. checkpoint-852/trainer_state.json +0 -0
  19. checkpoint-852/training_args.bin +3 -0
  20. config.json +43 -0
  21. runs/Mar10_09-02-34_451e0eacc3ea/events.out.tfevents.1710061354.451e0eacc3ea.39.0 +3 -0
  22. runs/Mar10_09-15-58_451e0eacc3ea/events.out.tfevents.1710062158.451e0eacc3ea.175.0 +3 -0
  23. special_tokens_map.json +24 -0
  24. tokenizer.model +3 -0
  25. tokenizer_config.json +43 -0
README.md ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: openlm-research/open_llama_3b_v2
7
+ model-index:
8
+ - name: qlora-out
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
16
+ <details><summary>See axolotl config</summary>
17
+
18
+ axolotl version: `0.4.0`
19
+ ```yaml
20
+ base_model: openlm-research/open_llama_3b_v2
21
+ model_type: LlamaForCausalLM
22
+ tokenizer_type: LlamaTokenizer
23
+ load_in_8bit: false
24
+ load_in_4bit: true
25
+ strict: false
26
+ push_dataset_to_hub:
27
+ datasets:
28
+ - path: mhenrichsen/alpaca_2k_test
29
+ type: alpaca
30
+ dataset_prepared_path:
31
+ val_set_size: 0.05
32
+ adapter: qlora
33
+ lora_model_dir:
34
+ sequence_len: 1024
35
+ sample_packing: true
36
+ lora_r: 8
37
+ lora_alpha: 32
38
+ lora_dropout: 0.05
39
+ lora_target_modules:
40
+ lora_target_linear: true
41
+ lora_fan_in_fan_out:
42
+ wandb_project:
43
+ wandb_entity:
44
+ wandb_watch:
45
+ wandb_name:
46
+ wandb_log_model:
47
+ output_dir: ./qlora-out
48
+ gradient_accumulation_steps: 1
49
+ micro_batch_size: 1
50
+ num_epochs: 2
51
+ optimizer: paged_adamw_32bit
52
+ torchdistx_path:
53
+ lr_scheduler: cosine
54
+ learning_rate: 0.0002
55
+ train_on_inputs: false
56
+ group_by_length: false
57
+ bf16: false
58
+ fp16: true
59
+ tf32: false
60
+ gradient_checkpointing: true
61
+ early_stopping_patience:
62
+ resume_from_checkpoint:
63
+ local_rank:
64
+ logging_steps: 1
65
+ xformers_attention:
66
+ flash_attention: true
67
+ gptq_groupsize:
68
+ gptq_model_v1:
69
+ warmup_steps: 20
70
+ evals_per_epoch: 4
71
+ saves_per_epoch: 1
72
+ debug:
73
+ deepspeed:
74
+ weight_decay: 0.1
75
+ fsdp:
76
+ fsdp_config:
77
+ special_tokens:
78
+ bos_token: "<s>"
79
+ eos_token: "</s>"
80
+ unk_token: "<unk>"
81
+
82
+ ```
83
+
84
+ </details><br>
85
+
86
+ # qlora-out
87
+
88
+ This model is a fine-tuned version of [openlm-research/open_llama_3b_v2](https://huggingface.co/openlm-research/open_llama_3b_v2) on the None dataset.
89
+ It achieves the following results on the evaluation set:
90
+ - Loss: 1.1425
91
+
92
+ ## Model description
93
+
94
+ More information needed
95
+
96
+ ## Intended uses & limitations
97
+
98
+ More information needed
99
+
100
+ ## Training and evaluation data
101
+
102
+ More information needed
103
+
104
+ ## Training procedure
105
+
106
+ ### Training hyperparameters
107
+
108
+ The following hyperparameters were used during training:
109
+ - learning_rate: 0.0002
110
+ - train_batch_size: 1
111
+ - eval_batch_size: 1
112
+ - seed: 42
113
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
114
+ - lr_scheduler_type: cosine
115
+ - lr_scheduler_warmup_steps: 20
116
+ - num_epochs: 2
117
+ - mixed_precision_training: Native AMP
118
+
119
+ ### Training results
120
+
121
+ | Training Loss | Epoch | Step | Validation Loss |
122
+ |:-------------:|:-----:|:----:|:---------------:|
123
+ | 1.2567 | 0.0 | 1 | 1.3470 |
124
+ | 1.0032 | 0.25 | 107 | 1.1363 |
125
+ | 1.0994 | 0.5 | 214 | 1.1272 |
126
+ | 1.3518 | 0.75 | 321 | 1.1147 |
127
+ | 1.1638 | 1.0 | 428 | 1.1096 |
128
+ | 1.1003 | 1.23 | 535 | 1.1364 |
129
+ | 0.7622 | 1.48 | 642 | 1.1427 |
130
+ | 1.8904 | 1.73 | 749 | 1.1425 |
131
+
132
+
133
+ ### Framework versions
134
+
135
+ - PEFT 0.9.0
136
+ - Transformers 4.38.2
137
+ - Pytorch 2.1.2+cu118
138
+ - Datasets 2.18.0
139
+ - Tokenizers 0.15.0
adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "openlm-research/open_llama_3b_v2",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 32,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 8,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "gate_proj",
23
+ "down_proj",
24
+ "v_proj",
25
+ "q_proj",
26
+ "k_proj",
27
+ "o_proj",
28
+ "up_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_dora": false,
32
+ "use_rslora": false
33
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af0056cca38075f99af329e5e893a2c81ed98da72f2269696a74ed9eaca54163
3
+ size 50982842
checkpoint-426/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: openlm-research/open_llama_3b_v2
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 0.9.0
checkpoint-426/adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "openlm-research/open_llama_3b_v2",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 32,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 8,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "gate_proj",
23
+ "down_proj",
24
+ "v_proj",
25
+ "q_proj",
26
+ "k_proj",
27
+ "o_proj",
28
+ "up_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_dora": false,
32
+ "use_rslora": false
33
+ }
checkpoint-426/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d88e78235d4ddc5b7b52ec7c76c652dddb06497132271c71f235151532f514c
3
+ size 50899792
checkpoint-426/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91970764b9b2e5f4f61f66d13fd4b7b95cff7d8ec6db8dc97320a10274f584a5
3
+ size 101919290
checkpoint-426/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0bcc534a49e53a439e836bf0ead81c29a4130b6a355c1c6306ce7f03ebe7a39
3
+ size 14244
checkpoint-426/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6fc1721e320fabfbdec907863b2c7ea1066f8dbf85bf217fd3d2e030ecb0239
3
+ size 1064
checkpoint-426/trainer_state.json ADDED
@@ -0,0 +1,3035 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 107,
6
+ "global_step": 426,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "grad_norm": 0.8741932511329651,
14
+ "learning_rate": 1e-05,
15
+ "loss": 1.2567,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0,
20
+ "eval_loss": 1.3469510078430176,
21
+ "eval_runtime": 5.3003,
22
+ "eval_samples_per_second": 18.867,
23
+ "eval_steps_per_second": 18.867,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.0,
28
+ "grad_norm": 0.7848138809204102,
29
+ "learning_rate": 2e-05,
30
+ "loss": 1.3328,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.01,
35
+ "grad_norm": 1.0692198276519775,
36
+ "learning_rate": 3e-05,
37
+ "loss": 1.6569,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.01,
42
+ "grad_norm": 1.4229260683059692,
43
+ "learning_rate": 4e-05,
44
+ "loss": 1.5493,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.01,
49
+ "grad_norm": 0.6837282180786133,
50
+ "learning_rate": 5e-05,
51
+ "loss": 1.4342,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.01,
56
+ "grad_norm": 1.1194649934768677,
57
+ "learning_rate": 6e-05,
58
+ "loss": 1.2668,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.02,
63
+ "grad_norm": 0.954695463180542,
64
+ "learning_rate": 7e-05,
65
+ "loss": 1.4721,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.02,
70
+ "grad_norm": 0.8204368352890015,
71
+ "learning_rate": 8e-05,
72
+ "loss": 1.4054,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.02,
77
+ "grad_norm": 0.8432589769363403,
78
+ "learning_rate": 9e-05,
79
+ "loss": 1.2849,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.02,
84
+ "grad_norm": 0.7272113561630249,
85
+ "learning_rate": 0.0001,
86
+ "loss": 1.1438,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.03,
91
+ "grad_norm": 0.8135901093482971,
92
+ "learning_rate": 0.00011000000000000002,
93
+ "loss": 1.4665,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.03,
98
+ "grad_norm": 0.8113470673561096,
99
+ "learning_rate": 0.00012,
100
+ "loss": 0.9749,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.03,
105
+ "grad_norm": 1.3105953931808472,
106
+ "learning_rate": 0.00013000000000000002,
107
+ "loss": 1.5133,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.03,
112
+ "grad_norm": 1.0281662940979004,
113
+ "learning_rate": 0.00014,
114
+ "loss": 1.1509,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.04,
119
+ "grad_norm": 2.1005992889404297,
120
+ "learning_rate": 0.00015000000000000001,
121
+ "loss": 1.2748,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.04,
126
+ "grad_norm": 1.453407645225525,
127
+ "learning_rate": 0.00016,
128
+ "loss": 1.3313,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.04,
133
+ "grad_norm": 1.0521585941314697,
134
+ "learning_rate": 0.00017,
135
+ "loss": 1.2977,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.04,
140
+ "grad_norm": 1.0728052854537964,
141
+ "learning_rate": 0.00018,
142
+ "loss": 1.322,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.04,
147
+ "grad_norm": 0.8539354205131531,
148
+ "learning_rate": 0.00019,
149
+ "loss": 1.2053,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.05,
154
+ "grad_norm": 1.6902265548706055,
155
+ "learning_rate": 0.0002,
156
+ "loss": 1.1924,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.05,
161
+ "grad_norm": 1.3770757913589478,
162
+ "learning_rate": 0.00019999928710990412,
163
+ "loss": 1.2286,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.05,
168
+ "grad_norm": 1.358694314956665,
169
+ "learning_rate": 0.00019999714844978078,
170
+ "loss": 1.3196,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.05,
175
+ "grad_norm": 1.4592664241790771,
176
+ "learning_rate": 0.0001999935840501225,
177
+ "loss": 1.5923,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.06,
182
+ "grad_norm": 1.122499942779541,
183
+ "learning_rate": 0.0001999885939617498,
184
+ "loss": 1.3107,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.06,
189
+ "grad_norm": 1.0040143728256226,
190
+ "learning_rate": 0.0001999821782558104,
191
+ "loss": 1.316,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.06,
196
+ "grad_norm": 1.0741703510284424,
197
+ "learning_rate": 0.00019997433702377817,
198
+ "loss": 1.2527,
199
+ "step": 26
200
+ },
201
+ {
202
+ "epoch": 0.06,
203
+ "grad_norm": 0.9978523850440979,
204
+ "learning_rate": 0.00019996507037745183,
205
+ "loss": 1.1989,
206
+ "step": 27
207
+ },
208
+ {
209
+ "epoch": 0.07,
210
+ "grad_norm": 1.002176284790039,
211
+ "learning_rate": 0.00019995437844895334,
212
+ "loss": 1.0503,
213
+ "step": 28
214
+ },
215
+ {
216
+ "epoch": 0.07,
217
+ "grad_norm": 1.0028811693191528,
218
+ "learning_rate": 0.0001999422613907262,
219
+ "loss": 1.356,
220
+ "step": 29
221
+ },
222
+ {
223
+ "epoch": 0.07,
224
+ "grad_norm": 1.3226864337921143,
225
+ "learning_rate": 0.0001999287193755329,
226
+ "loss": 1.2571,
227
+ "step": 30
228
+ },
229
+ {
230
+ "epoch": 0.07,
231
+ "grad_norm": 0.905536949634552,
232
+ "learning_rate": 0.00019991375259645293,
233
+ "loss": 1.1576,
234
+ "step": 31
235
+ },
236
+ {
237
+ "epoch": 0.08,
238
+ "grad_norm": 1.2652262449264526,
239
+ "learning_rate": 0.00019989736126687963,
240
+ "loss": 1.1792,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 0.08,
245
+ "grad_norm": 1.0161558389663696,
246
+ "learning_rate": 0.00019987954562051725,
247
+ "loss": 1.0074,
248
+ "step": 33
249
+ },
250
+ {
251
+ "epoch": 0.08,
252
+ "grad_norm": 0.9903879761695862,
253
+ "learning_rate": 0.00019986030591137783,
254
+ "loss": 1.196,
255
+ "step": 34
256
+ },
257
+ {
258
+ "epoch": 0.08,
259
+ "grad_norm": 1.3282291889190674,
260
+ "learning_rate": 0.0001998396424137773,
261
+ "loss": 1.5831,
262
+ "step": 35
263
+ },
264
+ {
265
+ "epoch": 0.08,
266
+ "grad_norm": 1.0442458391189575,
267
+ "learning_rate": 0.00019981755542233177,
268
+ "loss": 0.9708,
269
+ "step": 36
270
+ },
271
+ {
272
+ "epoch": 0.09,
273
+ "grad_norm": 0.9892172813415527,
274
+ "learning_rate": 0.0001997940452519531,
275
+ "loss": 1.1873,
276
+ "step": 37
277
+ },
278
+ {
279
+ "epoch": 0.09,
280
+ "grad_norm": 1.6204959154129028,
281
+ "learning_rate": 0.0001997691122378447,
282
+ "loss": 1.725,
283
+ "step": 38
284
+ },
285
+ {
286
+ "epoch": 0.09,
287
+ "grad_norm": 0.9563732147216797,
288
+ "learning_rate": 0.00019974275673549654,
289
+ "loss": 1.513,
290
+ "step": 39
291
+ },
292
+ {
293
+ "epoch": 0.09,
294
+ "grad_norm": 1.225378155708313,
295
+ "learning_rate": 0.00019971497912068013,
296
+ "loss": 1.1298,
297
+ "step": 40
298
+ },
299
+ {
300
+ "epoch": 0.1,
301
+ "grad_norm": 0.8867512941360474,
302
+ "learning_rate": 0.00019968577978944323,
303
+ "loss": 1.2413,
304
+ "step": 41
305
+ },
306
+ {
307
+ "epoch": 0.1,
308
+ "grad_norm": 0.9609911441802979,
309
+ "learning_rate": 0.0001996551591581041,
310
+ "loss": 1.2217,
311
+ "step": 42
312
+ },
313
+ {
314
+ "epoch": 0.1,
315
+ "grad_norm": 0.8636968731880188,
316
+ "learning_rate": 0.0001996231176632456,
317
+ "loss": 1.5268,
318
+ "step": 43
319
+ },
320
+ {
321
+ "epoch": 0.1,
322
+ "grad_norm": 0.9208036065101624,
323
+ "learning_rate": 0.00019958965576170908,
324
+ "loss": 1.1154,
325
+ "step": 44
326
+ },
327
+ {
328
+ "epoch": 0.11,
329
+ "grad_norm": 0.8316241502761841,
330
+ "learning_rate": 0.00019955477393058773,
331
+ "loss": 1.0891,
332
+ "step": 45
333
+ },
334
+ {
335
+ "epoch": 0.11,
336
+ "grad_norm": 1.0851703882217407,
337
+ "learning_rate": 0.0001995184726672197,
338
+ "loss": 1.237,
339
+ "step": 46
340
+ },
341
+ {
342
+ "epoch": 0.11,
343
+ "grad_norm": 1.2032215595245361,
344
+ "learning_rate": 0.00019948075248918124,
345
+ "loss": 1.3444,
346
+ "step": 47
347
+ },
348
+ {
349
+ "epoch": 0.11,
350
+ "grad_norm": 0.8556870818138123,
351
+ "learning_rate": 0.00019944161393427922,
352
+ "loss": 0.9632,
353
+ "step": 48
354
+ },
355
+ {
356
+ "epoch": 0.12,
357
+ "grad_norm": 1.038156270980835,
358
+ "learning_rate": 0.00019940105756054337,
359
+ "loss": 1.3897,
360
+ "step": 49
361
+ },
362
+ {
363
+ "epoch": 0.12,
364
+ "grad_norm": 1.1046299934387207,
365
+ "learning_rate": 0.00019935908394621844,
366
+ "loss": 1.0211,
367
+ "step": 50
368
+ },
369
+ {
370
+ "epoch": 0.12,
371
+ "grad_norm": 1.1632884740829468,
372
+ "learning_rate": 0.00019931569368975588,
373
+ "loss": 1.3098,
374
+ "step": 51
375
+ },
376
+ {
377
+ "epoch": 0.12,
378
+ "grad_norm": 0.9915144443511963,
379
+ "learning_rate": 0.0001992708874098054,
380
+ "loss": 1.1708,
381
+ "step": 52
382
+ },
383
+ {
384
+ "epoch": 0.12,
385
+ "grad_norm": 1.1974948644638062,
386
+ "learning_rate": 0.00019922466574520608,
387
+ "loss": 1.248,
388
+ "step": 53
389
+ },
390
+ {
391
+ "epoch": 0.13,
392
+ "grad_norm": 1.123138189315796,
393
+ "learning_rate": 0.00019917702935497725,
394
+ "loss": 0.8789,
395
+ "step": 54
396
+ },
397
+ {
398
+ "epoch": 0.13,
399
+ "grad_norm": 0.7720706462860107,
400
+ "learning_rate": 0.00019912797891830908,
401
+ "loss": 1.2278,
402
+ "step": 55
403
+ },
404
+ {
405
+ "epoch": 0.13,
406
+ "grad_norm": 1.171324610710144,
407
+ "learning_rate": 0.00019907751513455302,
408
+ "loss": 1.419,
409
+ "step": 56
410
+ },
411
+ {
412
+ "epoch": 0.13,
413
+ "grad_norm": 1.1821049451828003,
414
+ "learning_rate": 0.00019902563872321172,
415
+ "loss": 1.3281,
416
+ "step": 57
417
+ },
418
+ {
419
+ "epoch": 0.14,
420
+ "grad_norm": 0.8871707320213318,
421
+ "learning_rate": 0.00019897235042392873,
422
+ "loss": 1.1431,
423
+ "step": 58
424
+ },
425
+ {
426
+ "epoch": 0.14,
427
+ "grad_norm": 0.9106453657150269,
428
+ "learning_rate": 0.0001989176509964781,
429
+ "loss": 1.0687,
430
+ "step": 59
431
+ },
432
+ {
433
+ "epoch": 0.14,
434
+ "grad_norm": 0.8794414401054382,
435
+ "learning_rate": 0.00019886154122075343,
436
+ "loss": 1.3627,
437
+ "step": 60
438
+ },
439
+ {
440
+ "epoch": 0.14,
441
+ "grad_norm": 0.9249592423439026,
442
+ "learning_rate": 0.00019880402189675678,
443
+ "loss": 0.5962,
444
+ "step": 61
445
+ },
446
+ {
447
+ "epoch": 0.15,
448
+ "grad_norm": 0.8355573415756226,
449
+ "learning_rate": 0.00019874509384458725,
450
+ "loss": 1.2576,
451
+ "step": 62
452
+ },
453
+ {
454
+ "epoch": 0.15,
455
+ "grad_norm": 1.3829615116119385,
456
+ "learning_rate": 0.0001986847579044294,
457
+ "loss": 1.3844,
458
+ "step": 63
459
+ },
460
+ {
461
+ "epoch": 0.15,
462
+ "grad_norm": 0.7890944480895996,
463
+ "learning_rate": 0.00019862301493654108,
464
+ "loss": 0.9504,
465
+ "step": 64
466
+ },
467
+ {
468
+ "epoch": 0.15,
469
+ "grad_norm": 0.9988391995429993,
470
+ "learning_rate": 0.00019855986582124126,
471
+ "loss": 1.1127,
472
+ "step": 65
473
+ },
474
+ {
475
+ "epoch": 0.15,
476
+ "grad_norm": 1.024064302444458,
477
+ "learning_rate": 0.00019849531145889758,
478
+ "loss": 1.0418,
479
+ "step": 66
480
+ },
481
+ {
482
+ "epoch": 0.16,
483
+ "grad_norm": 1.1652387380599976,
484
+ "learning_rate": 0.0001984293527699133,
485
+ "loss": 1.0524,
486
+ "step": 67
487
+ },
488
+ {
489
+ "epoch": 0.16,
490
+ "grad_norm": 0.8396044969558716,
491
+ "learning_rate": 0.00019836199069471437,
492
+ "loss": 1.1829,
493
+ "step": 68
494
+ },
495
+ {
496
+ "epoch": 0.16,
497
+ "grad_norm": 0.9767330884933472,
498
+ "learning_rate": 0.00019829322619373588,
499
+ "loss": 1.1652,
500
+ "step": 69
501
+ },
502
+ {
503
+ "epoch": 0.16,
504
+ "grad_norm": 0.7999225854873657,
505
+ "learning_rate": 0.00019822306024740852,
506
+ "loss": 1.1075,
507
+ "step": 70
508
+ },
509
+ {
510
+ "epoch": 0.17,
511
+ "grad_norm": 0.9757010340690613,
512
+ "learning_rate": 0.00019815149385614444,
513
+ "loss": 1.3074,
514
+ "step": 71
515
+ },
516
+ {
517
+ "epoch": 0.17,
518
+ "grad_norm": 0.9027532339096069,
519
+ "learning_rate": 0.00019807852804032305,
520
+ "loss": 1.308,
521
+ "step": 72
522
+ },
523
+ {
524
+ "epoch": 0.17,
525
+ "grad_norm": 1.5158909559249878,
526
+ "learning_rate": 0.0001980041638402765,
527
+ "loss": 1.1594,
528
+ "step": 73
529
+ },
530
+ {
531
+ "epoch": 0.17,
532
+ "grad_norm": 0.8618407249450684,
533
+ "learning_rate": 0.00019792840231627482,
534
+ "loss": 0.7077,
535
+ "step": 74
536
+ },
537
+ {
538
+ "epoch": 0.18,
539
+ "grad_norm": 1.0307233333587646,
540
+ "learning_rate": 0.00019785124454851084,
541
+ "loss": 1.0812,
542
+ "step": 75
543
+ },
544
+ {
545
+ "epoch": 0.18,
546
+ "grad_norm": 0.8295727968215942,
547
+ "learning_rate": 0.00019777269163708468,
548
+ "loss": 1.0412,
549
+ "step": 76
550
+ },
551
+ {
552
+ "epoch": 0.18,
553
+ "grad_norm": 1.0772101879119873,
554
+ "learning_rate": 0.00019769274470198827,
555
+ "loss": 1.1484,
556
+ "step": 77
557
+ },
558
+ {
559
+ "epoch": 0.18,
560
+ "grad_norm": 1.0130198001861572,
561
+ "learning_rate": 0.0001976114048830891,
562
+ "loss": 1.0704,
563
+ "step": 78
564
+ },
565
+ {
566
+ "epoch": 0.19,
567
+ "grad_norm": 0.6028400659561157,
568
+ "learning_rate": 0.00019752867334011423,
569
+ "loss": 0.6347,
570
+ "step": 79
571
+ },
572
+ {
573
+ "epoch": 0.19,
574
+ "grad_norm": 0.8858622312545776,
575
+ "learning_rate": 0.0001974445512526336,
576
+ "loss": 1.4117,
577
+ "step": 80
578
+ },
579
+ {
580
+ "epoch": 0.19,
581
+ "grad_norm": 0.9046239852905273,
582
+ "learning_rate": 0.00019735903982004324,
583
+ "loss": 1.0355,
584
+ "step": 81
585
+ },
586
+ {
587
+ "epoch": 0.19,
588
+ "grad_norm": 0.987149715423584,
589
+ "learning_rate": 0.00019727214026154827,
590
+ "loss": 1.117,
591
+ "step": 82
592
+ },
593
+ {
594
+ "epoch": 0.19,
595
+ "grad_norm": 1.066720962524414,
596
+ "learning_rate": 0.0001971838538161454,
597
+ "loss": 1.4394,
598
+ "step": 83
599
+ },
600
+ {
601
+ "epoch": 0.2,
602
+ "grad_norm": 0.7880568504333496,
603
+ "learning_rate": 0.0001970941817426052,
604
+ "loss": 1.0591,
605
+ "step": 84
606
+ },
607
+ {
608
+ "epoch": 0.2,
609
+ "grad_norm": 0.8709908723831177,
610
+ "learning_rate": 0.00019700312531945442,
611
+ "loss": 0.8653,
612
+ "step": 85
613
+ },
614
+ {
615
+ "epoch": 0.2,
616
+ "grad_norm": 0.8909516930580139,
617
+ "learning_rate": 0.00019691068584495742,
618
+ "loss": 1.0539,
619
+ "step": 86
620
+ },
621
+ {
622
+ "epoch": 0.2,
623
+ "grad_norm": 0.726899266242981,
624
+ "learning_rate": 0.000196816864637098,
625
+ "loss": 1.0426,
626
+ "step": 87
627
+ },
628
+ {
629
+ "epoch": 0.21,
630
+ "grad_norm": 0.9136834144592285,
631
+ "learning_rate": 0.00019672166303356028,
632
+ "loss": 1.0121,
633
+ "step": 88
634
+ },
635
+ {
636
+ "epoch": 0.21,
637
+ "grad_norm": 0.8233316540718079,
638
+ "learning_rate": 0.0001966250823917099,
639
+ "loss": 1.1974,
640
+ "step": 89
641
+ },
642
+ {
643
+ "epoch": 0.21,
644
+ "grad_norm": 0.8916105628013611,
645
+ "learning_rate": 0.0001965271240885745,
646
+ "loss": 1.2969,
647
+ "step": 90
648
+ },
649
+ {
650
+ "epoch": 0.21,
651
+ "grad_norm": 0.7402650713920593,
652
+ "learning_rate": 0.00019642778952082426,
653
+ "loss": 1.0409,
654
+ "step": 91
655
+ },
656
+ {
657
+ "epoch": 0.22,
658
+ "grad_norm": 1.036402702331543,
659
+ "learning_rate": 0.00019632708010475165,
660
+ "loss": 1.1482,
661
+ "step": 92
662
+ },
663
+ {
664
+ "epoch": 0.22,
665
+ "grad_norm": 1.50504469871521,
666
+ "learning_rate": 0.00019622499727625162,
667
+ "loss": 1.3788,
668
+ "step": 93
669
+ },
670
+ {
671
+ "epoch": 0.22,
672
+ "grad_norm": 0.7590145468711853,
673
+ "learning_rate": 0.0001961215424908009,
674
+ "loss": 1.0139,
675
+ "step": 94
676
+ },
677
+ {
678
+ "epoch": 0.22,
679
+ "grad_norm": 0.8763208389282227,
680
+ "learning_rate": 0.00019601671722343738,
681
+ "loss": 1.066,
682
+ "step": 95
683
+ },
684
+ {
685
+ "epoch": 0.23,
686
+ "grad_norm": 1.0625308752059937,
687
+ "learning_rate": 0.00019591052296873888,
688
+ "loss": 1.1032,
689
+ "step": 96
690
+ },
691
+ {
692
+ "epoch": 0.23,
693
+ "grad_norm": 0.7704355716705322,
694
+ "learning_rate": 0.00019580296124080212,
695
+ "loss": 0.8728,
696
+ "step": 97
697
+ },
698
+ {
699
+ "epoch": 0.23,
700
+ "grad_norm": 0.8164972066879272,
701
+ "learning_rate": 0.0001956940335732209,
702
+ "loss": 0.8879,
703
+ "step": 98
704
+ },
705
+ {
706
+ "epoch": 0.23,
707
+ "grad_norm": 1.114343285560608,
708
+ "learning_rate": 0.0001955837415190643,
709
+ "loss": 1.3132,
710
+ "step": 99
711
+ },
712
+ {
713
+ "epoch": 0.23,
714
+ "grad_norm": 0.8190547227859497,
715
+ "learning_rate": 0.00019547208665085457,
716
+ "loss": 1.324,
717
+ "step": 100
718
+ },
719
+ {
720
+ "epoch": 0.24,
721
+ "grad_norm": 1.0214807987213135,
722
+ "learning_rate": 0.00019535907056054475,
723
+ "loss": 1.0961,
724
+ "step": 101
725
+ },
726
+ {
727
+ "epoch": 0.24,
728
+ "grad_norm": 1.0679683685302734,
729
+ "learning_rate": 0.00019524469485949583,
730
+ "loss": 1.5574,
731
+ "step": 102
732
+ },
733
+ {
734
+ "epoch": 0.24,
735
+ "grad_norm": 0.7177500128746033,
736
+ "learning_rate": 0.00019512896117845392,
737
+ "loss": 1.1553,
738
+ "step": 103
739
+ },
740
+ {
741
+ "epoch": 0.24,
742
+ "grad_norm": 1.2570964097976685,
743
+ "learning_rate": 0.00019501187116752693,
744
+ "loss": 1.2929,
745
+ "step": 104
746
+ },
747
+ {
748
+ "epoch": 0.25,
749
+ "grad_norm": 0.8858779668807983,
750
+ "learning_rate": 0.000194893426496161,
751
+ "loss": 1.2218,
752
+ "step": 105
753
+ },
754
+ {
755
+ "epoch": 0.25,
756
+ "grad_norm": 0.9762778282165527,
757
+ "learning_rate": 0.00019477362885311682,
758
+ "loss": 0.9456,
759
+ "step": 106
760
+ },
761
+ {
762
+ "epoch": 0.25,
763
+ "grad_norm": 0.8851660490036011,
764
+ "learning_rate": 0.00019465247994644545,
765
+ "loss": 1.0032,
766
+ "step": 107
767
+ },
768
+ {
769
+ "epoch": 0.25,
770
+ "eval_loss": 1.1362618207931519,
771
+ "eval_runtime": 5.3254,
772
+ "eval_samples_per_second": 18.778,
773
+ "eval_steps_per_second": 18.778,
774
+ "step": 107
775
+ },
776
+ {
777
+ "epoch": 0.25,
778
+ "grad_norm": 0.8778185844421387,
779
+ "learning_rate": 0.00019452998150346401,
780
+ "loss": 1.1764,
781
+ "step": 108
782
+ },
783
+ {
784
+ "epoch": 0.26,
785
+ "grad_norm": 0.8865760564804077,
786
+ "learning_rate": 0.00019440613527073105,
787
+ "loss": 1.0644,
788
+ "step": 109
789
+ },
790
+ {
791
+ "epoch": 0.26,
792
+ "grad_norm": 0.8576034903526306,
793
+ "learning_rate": 0.00019428094301402162,
794
+ "loss": 1.0943,
795
+ "step": 110
796
+ },
797
+ {
798
+ "epoch": 0.26,
799
+ "grad_norm": 0.810203492641449,
800
+ "learning_rate": 0.00019415440651830208,
801
+ "loss": 1.2353,
802
+ "step": 111
803
+ },
804
+ {
805
+ "epoch": 0.26,
806
+ "grad_norm": 1.1911653280258179,
807
+ "learning_rate": 0.00019402652758770475,
808
+ "loss": 1.215,
809
+ "step": 112
810
+ },
811
+ {
812
+ "epoch": 0.27,
813
+ "grad_norm": 0.5166463851928711,
814
+ "learning_rate": 0.00019389730804550211,
815
+ "loss": 0.4519,
816
+ "step": 113
817
+ },
818
+ {
819
+ "epoch": 0.27,
820
+ "grad_norm": 0.983464241027832,
821
+ "learning_rate": 0.00019376674973408075,
822
+ "loss": 1.3189,
823
+ "step": 114
824
+ },
825
+ {
826
+ "epoch": 0.27,
827
+ "grad_norm": 0.7697935700416565,
828
+ "learning_rate": 0.00019363485451491524,
829
+ "loss": 1.0372,
830
+ "step": 115
831
+ },
832
+ {
833
+ "epoch": 0.27,
834
+ "grad_norm": 0.8599738478660583,
835
+ "learning_rate": 0.0001935016242685415,
836
+ "loss": 1.1381,
837
+ "step": 116
838
+ },
839
+ {
840
+ "epoch": 0.27,
841
+ "grad_norm": 1.0430530309677124,
842
+ "learning_rate": 0.00019336706089452996,
843
+ "loss": 1.2332,
844
+ "step": 117
845
+ },
846
+ {
847
+ "epoch": 0.28,
848
+ "grad_norm": 1.163251280784607,
849
+ "learning_rate": 0.0001932311663114586,
850
+ "loss": 1.1588,
851
+ "step": 118
852
+ },
853
+ {
854
+ "epoch": 0.28,
855
+ "grad_norm": 0.8196917176246643,
856
+ "learning_rate": 0.0001930939424568854,
857
+ "loss": 1.1114,
858
+ "step": 119
859
+ },
860
+ {
861
+ "epoch": 0.28,
862
+ "grad_norm": 0.8848841786384583,
863
+ "learning_rate": 0.00019295539128732093,
864
+ "loss": 1.0458,
865
+ "step": 120
866
+ },
867
+ {
868
+ "epoch": 0.28,
869
+ "grad_norm": 0.9288797974586487,
870
+ "learning_rate": 0.00019281551477820036,
871
+ "loss": 0.7388,
872
+ "step": 121
873
+ },
874
+ {
875
+ "epoch": 0.29,
876
+ "grad_norm": 0.8119339942932129,
877
+ "learning_rate": 0.00019267431492385521,
878
+ "loss": 1.1095,
879
+ "step": 122
880
+ },
881
+ {
882
+ "epoch": 0.29,
883
+ "grad_norm": 0.9211128354072571,
884
+ "learning_rate": 0.00019253179373748504,
885
+ "loss": 1.3183,
886
+ "step": 123
887
+ },
888
+ {
889
+ "epoch": 0.29,
890
+ "grad_norm": 0.9682132601737976,
891
+ "learning_rate": 0.0001923879532511287,
892
+ "loss": 1.3786,
893
+ "step": 124
894
+ },
895
+ {
896
+ "epoch": 0.29,
897
+ "grad_norm": 0.9330196976661682,
898
+ "learning_rate": 0.00019224279551563532,
899
+ "loss": 1.4051,
900
+ "step": 125
901
+ },
902
+ {
903
+ "epoch": 0.3,
904
+ "grad_norm": 0.7206214070320129,
905
+ "learning_rate": 0.0001920963226006352,
906
+ "loss": 0.8213,
907
+ "step": 126
908
+ },
909
+ {
910
+ "epoch": 0.3,
911
+ "grad_norm": 0.6096452474594116,
912
+ "learning_rate": 0.0001919485365945101,
913
+ "loss": 0.5982,
914
+ "step": 127
915
+ },
916
+ {
917
+ "epoch": 0.3,
918
+ "grad_norm": 1.0045711994171143,
919
+ "learning_rate": 0.00019179943960436358,
920
+ "loss": 1.1399,
921
+ "step": 128
922
+ },
923
+ {
924
+ "epoch": 0.3,
925
+ "grad_norm": 0.8744232058525085,
926
+ "learning_rate": 0.00019164903375599112,
927
+ "loss": 1.0176,
928
+ "step": 129
929
+ },
930
+ {
931
+ "epoch": 0.31,
932
+ "grad_norm": 0.8323287963867188,
933
+ "learning_rate": 0.00019149732119384943,
934
+ "loss": 1.2937,
935
+ "step": 130
936
+ },
937
+ {
938
+ "epoch": 0.31,
939
+ "grad_norm": 0.9033424854278564,
940
+ "learning_rate": 0.00019134430408102615,
941
+ "loss": 1.3108,
942
+ "step": 131
943
+ },
944
+ {
945
+ "epoch": 0.31,
946
+ "grad_norm": 0.7392603158950806,
947
+ "learning_rate": 0.00019118998459920902,
948
+ "loss": 1.0297,
949
+ "step": 132
950
+ },
951
+ {
952
+ "epoch": 0.31,
953
+ "grad_norm": 1.136338710784912,
954
+ "learning_rate": 0.0001910343649486546,
955
+ "loss": 1.3037,
956
+ "step": 133
957
+ },
958
+ {
959
+ "epoch": 0.31,
960
+ "grad_norm": 0.8202427625656128,
961
+ "learning_rate": 0.00019087744734815708,
962
+ "loss": 0.9239,
963
+ "step": 134
964
+ },
965
+ {
966
+ "epoch": 0.32,
967
+ "grad_norm": 1.039093255996704,
968
+ "learning_rate": 0.0001907192340350165,
969
+ "loss": 1.2387,
970
+ "step": 135
971
+ },
972
+ {
973
+ "epoch": 0.32,
974
+ "grad_norm": 1.1009947061538696,
975
+ "learning_rate": 0.00019055972726500695,
976
+ "loss": 1.0234,
977
+ "step": 136
978
+ },
979
+ {
980
+ "epoch": 0.32,
981
+ "grad_norm": 1.057837724685669,
982
+ "learning_rate": 0.00019039892931234435,
983
+ "loss": 1.4308,
984
+ "step": 137
985
+ },
986
+ {
987
+ "epoch": 0.32,
988
+ "grad_norm": 0.8715041279792786,
989
+ "learning_rate": 0.00019023684246965406,
990
+ "loss": 1.0642,
991
+ "step": 138
992
+ },
993
+ {
994
+ "epoch": 0.33,
995
+ "grad_norm": 1.3314340114593506,
996
+ "learning_rate": 0.00019007346904793818,
997
+ "loss": 1.1097,
998
+ "step": 139
999
+ },
1000
+ {
1001
+ "epoch": 0.33,
1002
+ "grad_norm": 0.6808525919914246,
1003
+ "learning_rate": 0.00018990881137654258,
1004
+ "loss": 0.9254,
1005
+ "step": 140
1006
+ },
1007
+ {
1008
+ "epoch": 0.33,
1009
+ "grad_norm": 0.8727401494979858,
1010
+ "learning_rate": 0.00018974287180312377,
1011
+ "loss": 1.1062,
1012
+ "step": 141
1013
+ },
1014
+ {
1015
+ "epoch": 0.33,
1016
+ "grad_norm": 1.0826424360275269,
1017
+ "learning_rate": 0.00018957565269361531,
1018
+ "loss": 1.1528,
1019
+ "step": 142
1020
+ },
1021
+ {
1022
+ "epoch": 0.34,
1023
+ "grad_norm": 0.8825279474258423,
1024
+ "learning_rate": 0.00018940715643219407,
1025
+ "loss": 1.2208,
1026
+ "step": 143
1027
+ },
1028
+ {
1029
+ "epoch": 0.34,
1030
+ "grad_norm": 0.8955380320549011,
1031
+ "learning_rate": 0.00018923738542124644,
1032
+ "loss": 1.0918,
1033
+ "step": 144
1034
+ },
1035
+ {
1036
+ "epoch": 0.34,
1037
+ "grad_norm": 1.0863996744155884,
1038
+ "learning_rate": 0.00018906634208133385,
1039
+ "loss": 1.2153,
1040
+ "step": 145
1041
+ },
1042
+ {
1043
+ "epoch": 0.34,
1044
+ "grad_norm": 1.0089964866638184,
1045
+ "learning_rate": 0.00018889402885115833,
1046
+ "loss": 1.0796,
1047
+ "step": 146
1048
+ },
1049
+ {
1050
+ "epoch": 0.35,
1051
+ "grad_norm": 0.9210363626480103,
1052
+ "learning_rate": 0.0001887204481875278,
1053
+ "loss": 0.8502,
1054
+ "step": 147
1055
+ },
1056
+ {
1057
+ "epoch": 0.35,
1058
+ "grad_norm": 0.9592724442481995,
1059
+ "learning_rate": 0.000188545602565321,
1060
+ "loss": 1.4313,
1061
+ "step": 148
1062
+ },
1063
+ {
1064
+ "epoch": 0.35,
1065
+ "grad_norm": 1.2299224138259888,
1066
+ "learning_rate": 0.00018836949447745215,
1067
+ "loss": 1.1074,
1068
+ "step": 149
1069
+ },
1070
+ {
1071
+ "epoch": 0.35,
1072
+ "grad_norm": 1.1486583948135376,
1073
+ "learning_rate": 0.0001881921264348355,
1074
+ "loss": 1.3576,
1075
+ "step": 150
1076
+ },
1077
+ {
1078
+ "epoch": 0.35,
1079
+ "grad_norm": 1.1912083625793457,
1080
+ "learning_rate": 0.00018801350096634946,
1081
+ "loss": 1.343,
1082
+ "step": 151
1083
+ },
1084
+ {
1085
+ "epoch": 0.36,
1086
+ "grad_norm": 0.8830162882804871,
1087
+ "learning_rate": 0.00018783362061880062,
1088
+ "loss": 1.6139,
1089
+ "step": 152
1090
+ },
1091
+ {
1092
+ "epoch": 0.36,
1093
+ "grad_norm": 1.0919363498687744,
1094
+ "learning_rate": 0.00018765248795688726,
1095
+ "loss": 1.4051,
1096
+ "step": 153
1097
+ },
1098
+ {
1099
+ "epoch": 0.36,
1100
+ "grad_norm": 0.8009780049324036,
1101
+ "learning_rate": 0.00018747010556316305,
1102
+ "loss": 1.4095,
1103
+ "step": 154
1104
+ },
1105
+ {
1106
+ "epoch": 0.36,
1107
+ "grad_norm": 0.964438796043396,
1108
+ "learning_rate": 0.00018728647603800003,
1109
+ "loss": 1.1634,
1110
+ "step": 155
1111
+ },
1112
+ {
1113
+ "epoch": 0.37,
1114
+ "grad_norm": 0.9883137941360474,
1115
+ "learning_rate": 0.00018710160199955156,
1116
+ "loss": 1.1904,
1117
+ "step": 156
1118
+ },
1119
+ {
1120
+ "epoch": 0.37,
1121
+ "grad_norm": 0.8936368227005005,
1122
+ "learning_rate": 0.0001869154860837151,
1123
+ "loss": 1.2264,
1124
+ "step": 157
1125
+ },
1126
+ {
1127
+ "epoch": 0.37,
1128
+ "grad_norm": 0.6435540914535522,
1129
+ "learning_rate": 0.0001867281309440945,
1130
+ "loss": 0.8426,
1131
+ "step": 158
1132
+ },
1133
+ {
1134
+ "epoch": 0.37,
1135
+ "grad_norm": 0.7036202549934387,
1136
+ "learning_rate": 0.00018653953925196225,
1137
+ "loss": 0.8162,
1138
+ "step": 159
1139
+ },
1140
+ {
1141
+ "epoch": 0.38,
1142
+ "grad_norm": 0.7669593095779419,
1143
+ "learning_rate": 0.0001863497136962213,
1144
+ "loss": 0.9143,
1145
+ "step": 160
1146
+ },
1147
+ {
1148
+ "epoch": 0.38,
1149
+ "grad_norm": 0.8047689199447632,
1150
+ "learning_rate": 0.00018615865698336684,
1151
+ "loss": 1.1911,
1152
+ "step": 161
1153
+ },
1154
+ {
1155
+ "epoch": 0.38,
1156
+ "grad_norm": 1.1324609518051147,
1157
+ "learning_rate": 0.00018596637183744763,
1158
+ "loss": 1.064,
1159
+ "step": 162
1160
+ },
1161
+ {
1162
+ "epoch": 0.38,
1163
+ "grad_norm": 0.8058610558509827,
1164
+ "learning_rate": 0.00018577286100002723,
1165
+ "loss": 0.7428,
1166
+ "step": 163
1167
+ },
1168
+ {
1169
+ "epoch": 0.38,
1170
+ "grad_norm": 0.8588782548904419,
1171
+ "learning_rate": 0.00018557812723014476,
1172
+ "loss": 0.8801,
1173
+ "step": 164
1174
+ },
1175
+ {
1176
+ "epoch": 0.39,
1177
+ "grad_norm": 1.0751081705093384,
1178
+ "learning_rate": 0.00018538217330427582,
1179
+ "loss": 1.3674,
1180
+ "step": 165
1181
+ },
1182
+ {
1183
+ "epoch": 0.39,
1184
+ "grad_norm": 0.791789174079895,
1185
+ "learning_rate": 0.00018518500201629258,
1186
+ "loss": 1.0103,
1187
+ "step": 166
1188
+ },
1189
+ {
1190
+ "epoch": 0.39,
1191
+ "grad_norm": 0.8154894709587097,
1192
+ "learning_rate": 0.00018498661617742426,
1193
+ "loss": 1.1219,
1194
+ "step": 167
1195
+ },
1196
+ {
1197
+ "epoch": 0.39,
1198
+ "grad_norm": 1.3946795463562012,
1199
+ "learning_rate": 0.00018478701861621686,
1200
+ "loss": 1.0725,
1201
+ "step": 168
1202
+ },
1203
+ {
1204
+ "epoch": 0.4,
1205
+ "grad_norm": 0.9187031388282776,
1206
+ "learning_rate": 0.00018458621217849286,
1207
+ "loss": 1.2674,
1208
+ "step": 169
1209
+ },
1210
+ {
1211
+ "epoch": 0.4,
1212
+ "grad_norm": 0.9884739518165588,
1213
+ "learning_rate": 0.00018438419972731067,
1214
+ "loss": 1.3507,
1215
+ "step": 170
1216
+ },
1217
+ {
1218
+ "epoch": 0.4,
1219
+ "grad_norm": 1.4417808055877686,
1220
+ "learning_rate": 0.0001841809841429238,
1221
+ "loss": 1.129,
1222
+ "step": 171
1223
+ },
1224
+ {
1225
+ "epoch": 0.4,
1226
+ "grad_norm": 1.0408543348312378,
1227
+ "learning_rate": 0.0001839765683227398,
1228
+ "loss": 1.2038,
1229
+ "step": 172
1230
+ },
1231
+ {
1232
+ "epoch": 0.41,
1233
+ "grad_norm": 1.2746024131774902,
1234
+ "learning_rate": 0.00018377095518127897,
1235
+ "loss": 1.2916,
1236
+ "step": 173
1237
+ },
1238
+ {
1239
+ "epoch": 0.41,
1240
+ "grad_norm": 0.996474027633667,
1241
+ "learning_rate": 0.00018356414765013267,
1242
+ "loss": 1.3041,
1243
+ "step": 174
1244
+ },
1245
+ {
1246
+ "epoch": 0.41,
1247
+ "grad_norm": 0.9435645341873169,
1248
+ "learning_rate": 0.00018335614867792183,
1249
+ "loss": 1.3457,
1250
+ "step": 175
1251
+ },
1252
+ {
1253
+ "epoch": 0.41,
1254
+ "grad_norm": 1.0813288688659668,
1255
+ "learning_rate": 0.00018314696123025454,
1256
+ "loss": 1.2323,
1257
+ "step": 176
1258
+ },
1259
+ {
1260
+ "epoch": 0.42,
1261
+ "grad_norm": 1.1004307270050049,
1262
+ "learning_rate": 0.00018293658828968397,
1263
+ "loss": 1.3084,
1264
+ "step": 177
1265
+ },
1266
+ {
1267
+ "epoch": 0.42,
1268
+ "grad_norm": 0.7818973660469055,
1269
+ "learning_rate": 0.00018272503285566587,
1270
+ "loss": 0.88,
1271
+ "step": 178
1272
+ },
1273
+ {
1274
+ "epoch": 0.42,
1275
+ "grad_norm": 0.8897396326065063,
1276
+ "learning_rate": 0.00018251229794451567,
1277
+ "loss": 1.0124,
1278
+ "step": 179
1279
+ },
1280
+ {
1281
+ "epoch": 0.42,
1282
+ "grad_norm": 1.0572400093078613,
1283
+ "learning_rate": 0.00018229838658936564,
1284
+ "loss": 1.4603,
1285
+ "step": 180
1286
+ },
1287
+ {
1288
+ "epoch": 0.42,
1289
+ "grad_norm": 0.8974701166152954,
1290
+ "learning_rate": 0.0001820833018401215,
1291
+ "loss": 1.1961,
1292
+ "step": 181
1293
+ },
1294
+ {
1295
+ "epoch": 0.43,
1296
+ "grad_norm": 0.8860751390457153,
1297
+ "learning_rate": 0.00018186704676341898,
1298
+ "loss": 0.9779,
1299
+ "step": 182
1300
+ },
1301
+ {
1302
+ "epoch": 0.43,
1303
+ "grad_norm": 0.7719995975494385,
1304
+ "learning_rate": 0.00018164962444258014,
1305
+ "loss": 1.1156,
1306
+ "step": 183
1307
+ },
1308
+ {
1309
+ "epoch": 0.43,
1310
+ "grad_norm": 1.0823787450790405,
1311
+ "learning_rate": 0.0001814310379775694,
1312
+ "loss": 0.959,
1313
+ "step": 184
1314
+ },
1315
+ {
1316
+ "epoch": 0.43,
1317
+ "grad_norm": 0.9932149052619934,
1318
+ "learning_rate": 0.00018121129048494922,
1319
+ "loss": 1.358,
1320
+ "step": 185
1321
+ },
1322
+ {
1323
+ "epoch": 0.44,
1324
+ "grad_norm": 0.7363601326942444,
1325
+ "learning_rate": 0.00018099038509783582,
1326
+ "loss": 1.2639,
1327
+ "step": 186
1328
+ },
1329
+ {
1330
+ "epoch": 0.44,
1331
+ "grad_norm": 1.0355418920516968,
1332
+ "learning_rate": 0.0001807683249658545,
1333
+ "loss": 1.2566,
1334
+ "step": 187
1335
+ },
1336
+ {
1337
+ "epoch": 0.44,
1338
+ "grad_norm": 0.8746327757835388,
1339
+ "learning_rate": 0.0001805451132550946,
1340
+ "loss": 1.2159,
1341
+ "step": 188
1342
+ },
1343
+ {
1344
+ "epoch": 0.44,
1345
+ "grad_norm": 0.9230121374130249,
1346
+ "learning_rate": 0.00018032075314806448,
1347
+ "loss": 1.1717,
1348
+ "step": 189
1349
+ },
1350
+ {
1351
+ "epoch": 0.45,
1352
+ "grad_norm": 0.8293251991271973,
1353
+ "learning_rate": 0.00018009524784364615,
1354
+ "loss": 1.1053,
1355
+ "step": 190
1356
+ },
1357
+ {
1358
+ "epoch": 0.45,
1359
+ "grad_norm": 1.8819063901901245,
1360
+ "learning_rate": 0.00017986860055704953,
1361
+ "loss": 1.4713,
1362
+ "step": 191
1363
+ },
1364
+ {
1365
+ "epoch": 0.45,
1366
+ "grad_norm": 0.843971312046051,
1367
+ "learning_rate": 0.00017964081451976672,
1368
+ "loss": 1.175,
1369
+ "step": 192
1370
+ },
1371
+ {
1372
+ "epoch": 0.45,
1373
+ "grad_norm": 1.1449857950210571,
1374
+ "learning_rate": 0.00017941189297952597,
1375
+ "loss": 1.0097,
1376
+ "step": 193
1377
+ },
1378
+ {
1379
+ "epoch": 0.46,
1380
+ "grad_norm": 0.8204749226570129,
1381
+ "learning_rate": 0.0001791818392002452,
1382
+ "loss": 1.0383,
1383
+ "step": 194
1384
+ },
1385
+ {
1386
+ "epoch": 0.46,
1387
+ "grad_norm": 1.0437519550323486,
1388
+ "learning_rate": 0.00017895065646198567,
1389
+ "loss": 1.4455,
1390
+ "step": 195
1391
+ },
1392
+ {
1393
+ "epoch": 0.46,
1394
+ "grad_norm": 0.803774356842041,
1395
+ "learning_rate": 0.00017871834806090501,
1396
+ "loss": 0.9266,
1397
+ "step": 196
1398
+ },
1399
+ {
1400
+ "epoch": 0.46,
1401
+ "grad_norm": 0.991162121295929,
1402
+ "learning_rate": 0.00017848491730921046,
1403
+ "loss": 0.9433,
1404
+ "step": 197
1405
+ },
1406
+ {
1407
+ "epoch": 0.46,
1408
+ "grad_norm": 0.9293928146362305,
1409
+ "learning_rate": 0.00017825036753511144,
1410
+ "loss": 1.2432,
1411
+ "step": 198
1412
+ },
1413
+ {
1414
+ "epoch": 0.47,
1415
+ "grad_norm": 0.6806849241256714,
1416
+ "learning_rate": 0.0001780147020827721,
1417
+ "loss": 0.696,
1418
+ "step": 199
1419
+ },
1420
+ {
1421
+ "epoch": 0.47,
1422
+ "grad_norm": 1.2757548093795776,
1423
+ "learning_rate": 0.00017777792431226383,
1424
+ "loss": 1.3426,
1425
+ "step": 200
1426
+ },
1427
+ {
1428
+ "epoch": 0.47,
1429
+ "grad_norm": 0.8645375370979309,
1430
+ "learning_rate": 0.00017754003759951715,
1431
+ "loss": 1.0345,
1432
+ "step": 201
1433
+ },
1434
+ {
1435
+ "epoch": 0.47,
1436
+ "grad_norm": 1.0262008905410767,
1437
+ "learning_rate": 0.0001773010453362737,
1438
+ "loss": 0.935,
1439
+ "step": 202
1440
+ },
1441
+ {
1442
+ "epoch": 0.48,
1443
+ "grad_norm": 1.225273609161377,
1444
+ "learning_rate": 0.00017706095093003785,
1445
+ "loss": 1.1271,
1446
+ "step": 203
1447
+ },
1448
+ {
1449
+ "epoch": 0.48,
1450
+ "grad_norm": 0.9024125337600708,
1451
+ "learning_rate": 0.00017681975780402807,
1452
+ "loss": 1.1307,
1453
+ "step": 204
1454
+ },
1455
+ {
1456
+ "epoch": 0.48,
1457
+ "grad_norm": 0.9035881161689758,
1458
+ "learning_rate": 0.00017657746939712815,
1459
+ "loss": 1.3217,
1460
+ "step": 205
1461
+ },
1462
+ {
1463
+ "epoch": 0.48,
1464
+ "grad_norm": 2.1178483963012695,
1465
+ "learning_rate": 0.00017633408916383826,
1466
+ "loss": 1.4955,
1467
+ "step": 206
1468
+ },
1469
+ {
1470
+ "epoch": 0.49,
1471
+ "grad_norm": 0.826454222202301,
1472
+ "learning_rate": 0.00017608962057422549,
1473
+ "loss": 1.187,
1474
+ "step": 207
1475
+ },
1476
+ {
1477
+ "epoch": 0.49,
1478
+ "grad_norm": 0.8255906701087952,
1479
+ "learning_rate": 0.00017584406711387463,
1480
+ "loss": 1.0733,
1481
+ "step": 208
1482
+ },
1483
+ {
1484
+ "epoch": 0.49,
1485
+ "grad_norm": 0.9498797059059143,
1486
+ "learning_rate": 0.0001755974322838382,
1487
+ "loss": 1.3054,
1488
+ "step": 209
1489
+ },
1490
+ {
1491
+ "epoch": 0.49,
1492
+ "grad_norm": 0.7860575914382935,
1493
+ "learning_rate": 0.00017534971960058685,
1494
+ "loss": 1.0231,
1495
+ "step": 210
1496
+ },
1497
+ {
1498
+ "epoch": 0.5,
1499
+ "grad_norm": 0.905441403388977,
1500
+ "learning_rate": 0.00017510093259595885,
1501
+ "loss": 1.2928,
1502
+ "step": 211
1503
+ },
1504
+ {
1505
+ "epoch": 0.5,
1506
+ "grad_norm": 1.0108212232589722,
1507
+ "learning_rate": 0.00017485107481711012,
1508
+ "loss": 0.8964,
1509
+ "step": 212
1510
+ },
1511
+ {
1512
+ "epoch": 0.5,
1513
+ "grad_norm": 1.036566972732544,
1514
+ "learning_rate": 0.00017460014982646334,
1515
+ "loss": 1.4823,
1516
+ "step": 213
1517
+ },
1518
+ {
1519
+ "epoch": 0.5,
1520
+ "grad_norm": 0.8670862913131714,
1521
+ "learning_rate": 0.00017434816120165728,
1522
+ "loss": 1.0994,
1523
+ "step": 214
1524
+ },
1525
+ {
1526
+ "epoch": 0.5,
1527
+ "eval_loss": 1.1271697282791138,
1528
+ "eval_runtime": 4.9762,
1529
+ "eval_samples_per_second": 20.096,
1530
+ "eval_steps_per_second": 20.096,
1531
+ "step": 214
1532
+ },
1533
+ {
1534
+ "epoch": 0.5,
1535
+ "grad_norm": 0.9359840750694275,
1536
+ "learning_rate": 0.00017409511253549593,
1537
+ "loss": 1.1552,
1538
+ "step": 215
1539
+ },
1540
+ {
1541
+ "epoch": 0.51,
1542
+ "grad_norm": 1.0469551086425781,
1543
+ "learning_rate": 0.00017384100743589697,
1544
+ "loss": 1.1175,
1545
+ "step": 216
1546
+ },
1547
+ {
1548
+ "epoch": 0.51,
1549
+ "grad_norm": 0.8635923266410828,
1550
+ "learning_rate": 0.0001735858495258406,
1551
+ "loss": 0.9823,
1552
+ "step": 217
1553
+ },
1554
+ {
1555
+ "epoch": 0.51,
1556
+ "grad_norm": 1.1676996946334839,
1557
+ "learning_rate": 0.00017332964244331776,
1558
+ "loss": 1.2903,
1559
+ "step": 218
1560
+ },
1561
+ {
1562
+ "epoch": 0.51,
1563
+ "grad_norm": 0.9774354696273804,
1564
+ "learning_rate": 0.00017307238984127832,
1565
+ "loss": 1.1928,
1566
+ "step": 219
1567
+ },
1568
+ {
1569
+ "epoch": 0.52,
1570
+ "grad_norm": 1.0486751794815063,
1571
+ "learning_rate": 0.00017281409538757883,
1572
+ "loss": 1.039,
1573
+ "step": 220
1574
+ },
1575
+ {
1576
+ "epoch": 0.52,
1577
+ "grad_norm": 1.0949512720108032,
1578
+ "learning_rate": 0.00017255476276493056,
1579
+ "loss": 1.148,
1580
+ "step": 221
1581
+ },
1582
+ {
1583
+ "epoch": 0.52,
1584
+ "grad_norm": 0.8077650666236877,
1585
+ "learning_rate": 0.0001722943956708466,
1586
+ "loss": 1.1376,
1587
+ "step": 222
1588
+ },
1589
+ {
1590
+ "epoch": 0.52,
1591
+ "grad_norm": 1.0595574378967285,
1592
+ "learning_rate": 0.00017203299781758943,
1593
+ "loss": 1.0757,
1594
+ "step": 223
1595
+ },
1596
+ {
1597
+ "epoch": 0.53,
1598
+ "grad_norm": 0.813774049282074,
1599
+ "learning_rate": 0.00017177057293211784,
1600
+ "loss": 1.2645,
1601
+ "step": 224
1602
+ },
1603
+ {
1604
+ "epoch": 0.53,
1605
+ "grad_norm": 0.8764140009880066,
1606
+ "learning_rate": 0.0001715071247560339,
1607
+ "loss": 0.9552,
1608
+ "step": 225
1609
+ },
1610
+ {
1611
+ "epoch": 0.53,
1612
+ "grad_norm": 0.9136344194412231,
1613
+ "learning_rate": 0.0001712426570455295,
1614
+ "loss": 1.1841,
1615
+ "step": 226
1616
+ },
1617
+ {
1618
+ "epoch": 0.53,
1619
+ "grad_norm": 0.8742187023162842,
1620
+ "learning_rate": 0.00017097717357133284,
1621
+ "loss": 1.0314,
1622
+ "step": 227
1623
+ },
1624
+ {
1625
+ "epoch": 0.54,
1626
+ "grad_norm": 0.8309169411659241,
1627
+ "learning_rate": 0.00017071067811865476,
1628
+ "loss": 0.9842,
1629
+ "step": 228
1630
+ },
1631
+ {
1632
+ "epoch": 0.54,
1633
+ "grad_norm": 0.8644968867301941,
1634
+ "learning_rate": 0.00017044317448713461,
1635
+ "loss": 1.3819,
1636
+ "step": 229
1637
+ },
1638
+ {
1639
+ "epoch": 0.54,
1640
+ "grad_norm": 0.8510339260101318,
1641
+ "learning_rate": 0.0001701746664907862,
1642
+ "loss": 1.2385,
1643
+ "step": 230
1644
+ },
1645
+ {
1646
+ "epoch": 0.54,
1647
+ "grad_norm": 0.8174643516540527,
1648
+ "learning_rate": 0.00016990515795794334,
1649
+ "loss": 0.9789,
1650
+ "step": 231
1651
+ },
1652
+ {
1653
+ "epoch": 0.54,
1654
+ "grad_norm": 0.9340826272964478,
1655
+ "learning_rate": 0.0001696346527312053,
1656
+ "loss": 1.2472,
1657
+ "step": 232
1658
+ },
1659
+ {
1660
+ "epoch": 0.55,
1661
+ "grad_norm": 0.9614835977554321,
1662
+ "learning_rate": 0.00016936315466738205,
1663
+ "loss": 1.1588,
1664
+ "step": 233
1665
+ },
1666
+ {
1667
+ "epoch": 0.55,
1668
+ "grad_norm": 1.1464625597000122,
1669
+ "learning_rate": 0.00016909066763743912,
1670
+ "loss": 0.8365,
1671
+ "step": 234
1672
+ },
1673
+ {
1674
+ "epoch": 0.55,
1675
+ "grad_norm": 0.8775334358215332,
1676
+ "learning_rate": 0.00016881719552644273,
1677
+ "loss": 1.1143,
1678
+ "step": 235
1679
+ },
1680
+ {
1681
+ "epoch": 0.55,
1682
+ "grad_norm": 0.9431893825531006,
1683
+ "learning_rate": 0.00016854274223350397,
1684
+ "loss": 1.362,
1685
+ "step": 236
1686
+ },
1687
+ {
1688
+ "epoch": 0.56,
1689
+ "grad_norm": 0.7953469157218933,
1690
+ "learning_rate": 0.0001682673116717236,
1691
+ "loss": 1.1568,
1692
+ "step": 237
1693
+ },
1694
+ {
1695
+ "epoch": 0.56,
1696
+ "grad_norm": 0.7517049908638,
1697
+ "learning_rate": 0.00016799090776813597,
1698
+ "loss": 0.9274,
1699
+ "step": 238
1700
+ },
1701
+ {
1702
+ "epoch": 0.56,
1703
+ "grad_norm": 0.796934187412262,
1704
+ "learning_rate": 0.00016771353446365318,
1705
+ "loss": 0.8641,
1706
+ "step": 239
1707
+ },
1708
+ {
1709
+ "epoch": 0.56,
1710
+ "grad_norm": 0.7946231961250305,
1711
+ "learning_rate": 0.00016743519571300888,
1712
+ "loss": 1.0518,
1713
+ "step": 240
1714
+ },
1715
+ {
1716
+ "epoch": 0.57,
1717
+ "grad_norm": 1.0859878063201904,
1718
+ "learning_rate": 0.00016715589548470185,
1719
+ "loss": 1.1815,
1720
+ "step": 241
1721
+ },
1722
+ {
1723
+ "epoch": 0.57,
1724
+ "grad_norm": 0.7418296933174133,
1725
+ "learning_rate": 0.00016687563776093941,
1726
+ "loss": 1.0321,
1727
+ "step": 242
1728
+ },
1729
+ {
1730
+ "epoch": 0.57,
1731
+ "grad_norm": 0.8161245584487915,
1732
+ "learning_rate": 0.00016659442653758064,
1733
+ "loss": 1.0931,
1734
+ "step": 243
1735
+ },
1736
+ {
1737
+ "epoch": 0.57,
1738
+ "grad_norm": 0.7787612080574036,
1739
+ "learning_rate": 0.00016631226582407952,
1740
+ "loss": 1.2239,
1741
+ "step": 244
1742
+ },
1743
+ {
1744
+ "epoch": 0.58,
1745
+ "grad_norm": 0.7161651849746704,
1746
+ "learning_rate": 0.00016602915964342757,
1747
+ "loss": 1.1104,
1748
+ "step": 245
1749
+ },
1750
+ {
1751
+ "epoch": 0.58,
1752
+ "grad_norm": 0.786612331867218,
1753
+ "learning_rate": 0.00016574511203209667,
1754
+ "loss": 1.2486,
1755
+ "step": 246
1756
+ },
1757
+ {
1758
+ "epoch": 0.58,
1759
+ "grad_norm": 0.8251045942306519,
1760
+ "learning_rate": 0.00016546012703998138,
1761
+ "loss": 1.2358,
1762
+ "step": 247
1763
+ },
1764
+ {
1765
+ "epoch": 0.58,
1766
+ "grad_norm": 0.8045319318771362,
1767
+ "learning_rate": 0.00016517420873034123,
1768
+ "loss": 0.8145,
1769
+ "step": 248
1770
+ },
1771
+ {
1772
+ "epoch": 0.58,
1773
+ "grad_norm": 0.8730091452598572,
1774
+ "learning_rate": 0.0001648873611797429,
1775
+ "loss": 0.8832,
1776
+ "step": 249
1777
+ },
1778
+ {
1779
+ "epoch": 0.59,
1780
+ "grad_norm": 0.9003087878227234,
1781
+ "learning_rate": 0.00016459958847800187,
1782
+ "loss": 1.1149,
1783
+ "step": 250
1784
+ },
1785
+ {
1786
+ "epoch": 0.59,
1787
+ "grad_norm": 1.0912461280822754,
1788
+ "learning_rate": 0.00016431089472812444,
1789
+ "loss": 1.0439,
1790
+ "step": 251
1791
+ },
1792
+ {
1793
+ "epoch": 0.59,
1794
+ "grad_norm": 0.7999249696731567,
1795
+ "learning_rate": 0.00016402128404624882,
1796
+ "loss": 0.9821,
1797
+ "step": 252
1798
+ },
1799
+ {
1800
+ "epoch": 0.59,
1801
+ "grad_norm": 1.0122705698013306,
1802
+ "learning_rate": 0.00016373076056158675,
1803
+ "loss": 1.2302,
1804
+ "step": 253
1805
+ },
1806
+ {
1807
+ "epoch": 0.6,
1808
+ "grad_norm": 0.6447519659996033,
1809
+ "learning_rate": 0.00016343932841636456,
1810
+ "loss": 0.6079,
1811
+ "step": 254
1812
+ },
1813
+ {
1814
+ "epoch": 0.6,
1815
+ "grad_norm": 0.7757092118263245,
1816
+ "learning_rate": 0.00016314699176576402,
1817
+ "loss": 1.0092,
1818
+ "step": 255
1819
+ },
1820
+ {
1821
+ "epoch": 0.6,
1822
+ "grad_norm": 0.7445678114891052,
1823
+ "learning_rate": 0.00016285375477786322,
1824
+ "loss": 0.684,
1825
+ "step": 256
1826
+ },
1827
+ {
1828
+ "epoch": 0.6,
1829
+ "grad_norm": 1.241065263748169,
1830
+ "learning_rate": 0.000162559621633577,
1831
+ "loss": 1.0321,
1832
+ "step": 257
1833
+ },
1834
+ {
1835
+ "epoch": 0.61,
1836
+ "grad_norm": 1.1429563760757446,
1837
+ "learning_rate": 0.00016226459652659753,
1838
+ "loss": 1.1635,
1839
+ "step": 258
1840
+ },
1841
+ {
1842
+ "epoch": 0.61,
1843
+ "grad_norm": 0.7441573739051819,
1844
+ "learning_rate": 0.0001619686836633343,
1845
+ "loss": 0.9685,
1846
+ "step": 259
1847
+ },
1848
+ {
1849
+ "epoch": 0.61,
1850
+ "grad_norm": 1.3199349641799927,
1851
+ "learning_rate": 0.00016167188726285434,
1852
+ "loss": 1.3159,
1853
+ "step": 260
1854
+ },
1855
+ {
1856
+ "epoch": 0.61,
1857
+ "grad_norm": 0.8082245588302612,
1858
+ "learning_rate": 0.00016137421155682183,
1859
+ "loss": 1.317,
1860
+ "step": 261
1861
+ },
1862
+ {
1863
+ "epoch": 0.62,
1864
+ "grad_norm": 0.9036356210708618,
1865
+ "learning_rate": 0.0001610756607894382,
1866
+ "loss": 0.8672,
1867
+ "step": 262
1868
+ },
1869
+ {
1870
+ "epoch": 0.62,
1871
+ "grad_norm": 0.9773459434509277,
1872
+ "learning_rate": 0.00016077623921738102,
1873
+ "loss": 1.1405,
1874
+ "step": 263
1875
+ },
1876
+ {
1877
+ "epoch": 0.62,
1878
+ "grad_norm": 0.9840144515037537,
1879
+ "learning_rate": 0.00016047595110974376,
1880
+ "loss": 1.4167,
1881
+ "step": 264
1882
+ },
1883
+ {
1884
+ "epoch": 0.62,
1885
+ "grad_norm": 1.0358545780181885,
1886
+ "learning_rate": 0.0001601748007479748,
1887
+ "loss": 1.196,
1888
+ "step": 265
1889
+ },
1890
+ {
1891
+ "epoch": 0.62,
1892
+ "grad_norm": 0.7097404599189758,
1893
+ "learning_rate": 0.0001598727924258164,
1894
+ "loss": 0.791,
1895
+ "step": 266
1896
+ },
1897
+ {
1898
+ "epoch": 0.63,
1899
+ "grad_norm": 1.7330995798110962,
1900
+ "learning_rate": 0.00015956993044924334,
1901
+ "loss": 1.4283,
1902
+ "step": 267
1903
+ },
1904
+ {
1905
+ "epoch": 0.63,
1906
+ "grad_norm": 0.7444025278091431,
1907
+ "learning_rate": 0.0001592662191364017,
1908
+ "loss": 0.7525,
1909
+ "step": 268
1910
+ },
1911
+ {
1912
+ "epoch": 0.63,
1913
+ "grad_norm": 0.9818642139434814,
1914
+ "learning_rate": 0.0001589616628175472,
1915
+ "loss": 1.2417,
1916
+ "step": 269
1917
+ },
1918
+ {
1919
+ "epoch": 0.63,
1920
+ "grad_norm": 0.9218468070030212,
1921
+ "learning_rate": 0.00015865626583498355,
1922
+ "loss": 1.1316,
1923
+ "step": 270
1924
+ },
1925
+ {
1926
+ "epoch": 0.64,
1927
+ "grad_norm": 0.9644055366516113,
1928
+ "learning_rate": 0.00015835003254300039,
1929
+ "loss": 1.2594,
1930
+ "step": 271
1931
+ },
1932
+ {
1933
+ "epoch": 0.64,
1934
+ "grad_norm": 0.8228254914283752,
1935
+ "learning_rate": 0.00015804296730781135,
1936
+ "loss": 1.2481,
1937
+ "step": 272
1938
+ },
1939
+ {
1940
+ "epoch": 0.64,
1941
+ "grad_norm": 1.0708152055740356,
1942
+ "learning_rate": 0.00015773507450749172,
1943
+ "loss": 1.107,
1944
+ "step": 273
1945
+ },
1946
+ {
1947
+ "epoch": 0.64,
1948
+ "grad_norm": 1.1122934818267822,
1949
+ "learning_rate": 0.00015742635853191608,
1950
+ "loss": 0.8714,
1951
+ "step": 274
1952
+ },
1953
+ {
1954
+ "epoch": 0.65,
1955
+ "grad_norm": 0.8141905665397644,
1956
+ "learning_rate": 0.00015711682378269565,
1957
+ "loss": 0.9943,
1958
+ "step": 275
1959
+ },
1960
+ {
1961
+ "epoch": 0.65,
1962
+ "grad_norm": 0.8955541253089905,
1963
+ "learning_rate": 0.00015680647467311557,
1964
+ "loss": 1.3176,
1965
+ "step": 276
1966
+ },
1967
+ {
1968
+ "epoch": 0.65,
1969
+ "grad_norm": 1.1133729219436646,
1970
+ "learning_rate": 0.000156495315628072,
1971
+ "loss": 1.2602,
1972
+ "step": 277
1973
+ },
1974
+ {
1975
+ "epoch": 0.65,
1976
+ "grad_norm": 0.8733439445495605,
1977
+ "learning_rate": 0.00015618335108400893,
1978
+ "loss": 1.3639,
1979
+ "step": 278
1980
+ },
1981
+ {
1982
+ "epoch": 0.65,
1983
+ "grad_norm": 0.8614795804023743,
1984
+ "learning_rate": 0.00015587058548885505,
1985
+ "loss": 1.1905,
1986
+ "step": 279
1987
+ },
1988
+ {
1989
+ "epoch": 0.66,
1990
+ "grad_norm": 0.8306368589401245,
1991
+ "learning_rate": 0.00015555702330196023,
1992
+ "loss": 1.1978,
1993
+ "step": 280
1994
+ },
1995
+ {
1996
+ "epoch": 0.66,
1997
+ "grad_norm": 0.8460854887962341,
1998
+ "learning_rate": 0.00015524266899403206,
1999
+ "loss": 0.9872,
2000
+ "step": 281
2001
+ },
2002
+ {
2003
+ "epoch": 0.66,
2004
+ "grad_norm": 0.8452059626579285,
2005
+ "learning_rate": 0.000154927527047072,
2006
+ "loss": 0.979,
2007
+ "step": 282
2008
+ },
2009
+ {
2010
+ "epoch": 0.66,
2011
+ "grad_norm": 0.8805731534957886,
2012
+ "learning_rate": 0.00015461160195431148,
2013
+ "loss": 1.2885,
2014
+ "step": 283
2015
+ },
2016
+ {
2017
+ "epoch": 0.67,
2018
+ "grad_norm": 0.9095639586448669,
2019
+ "learning_rate": 0.0001542948982201479,
2020
+ "loss": 1.1156,
2021
+ "step": 284
2022
+ },
2023
+ {
2024
+ "epoch": 0.67,
2025
+ "grad_norm": 0.9862900376319885,
2026
+ "learning_rate": 0.00015397742036008034,
2027
+ "loss": 1.1571,
2028
+ "step": 285
2029
+ },
2030
+ {
2031
+ "epoch": 0.67,
2032
+ "grad_norm": 0.9344744086265564,
2033
+ "learning_rate": 0.0001536591729006453,
2034
+ "loss": 1.2204,
2035
+ "step": 286
2036
+ },
2037
+ {
2038
+ "epoch": 0.67,
2039
+ "grad_norm": 1.0605379343032837,
2040
+ "learning_rate": 0.00015334016037935196,
2041
+ "loss": 1.3048,
2042
+ "step": 287
2043
+ },
2044
+ {
2045
+ "epoch": 0.68,
2046
+ "grad_norm": 0.9844763278961182,
2047
+ "learning_rate": 0.0001530203873446177,
2048
+ "loss": 1.0035,
2049
+ "step": 288
2050
+ },
2051
+ {
2052
+ "epoch": 0.68,
2053
+ "grad_norm": 0.767954409122467,
2054
+ "learning_rate": 0.0001526998583557031,
2055
+ "loss": 0.9023,
2056
+ "step": 289
2057
+ },
2058
+ {
2059
+ "epoch": 0.68,
2060
+ "grad_norm": 1.0622146129608154,
2061
+ "learning_rate": 0.000152378577982647,
2062
+ "loss": 1.4837,
2063
+ "step": 290
2064
+ },
2065
+ {
2066
+ "epoch": 0.68,
2067
+ "grad_norm": 0.9536969065666199,
2068
+ "learning_rate": 0.0001520565508062013,
2069
+ "loss": 1.0948,
2070
+ "step": 291
2071
+ },
2072
+ {
2073
+ "epoch": 0.69,
2074
+ "grad_norm": 0.9654991030693054,
2075
+ "learning_rate": 0.00015173378141776568,
2076
+ "loss": 1.1913,
2077
+ "step": 292
2078
+ },
2079
+ {
2080
+ "epoch": 0.69,
2081
+ "grad_norm": 0.8208710551261902,
2082
+ "learning_rate": 0.00015141027441932216,
2083
+ "loss": 1.1435,
2084
+ "step": 293
2085
+ },
2086
+ {
2087
+ "epoch": 0.69,
2088
+ "grad_norm": 0.9273961186408997,
2089
+ "learning_rate": 0.0001510860344233695,
2090
+ "loss": 1.0845,
2091
+ "step": 294
2092
+ },
2093
+ {
2094
+ "epoch": 0.69,
2095
+ "grad_norm": 1.0316227674484253,
2096
+ "learning_rate": 0.00015076106605285724,
2097
+ "loss": 1.4532,
2098
+ "step": 295
2099
+ },
2100
+ {
2101
+ "epoch": 0.69,
2102
+ "grad_norm": 1.0121437311172485,
2103
+ "learning_rate": 0.00015043537394112007,
2104
+ "loss": 0.8687,
2105
+ "step": 296
2106
+ },
2107
+ {
2108
+ "epoch": 0.7,
2109
+ "grad_norm": 1.0713882446289062,
2110
+ "learning_rate": 0.00015010896273181165,
2111
+ "loss": 1.1097,
2112
+ "step": 297
2113
+ },
2114
+ {
2115
+ "epoch": 0.7,
2116
+ "grad_norm": 0.8149722814559937,
2117
+ "learning_rate": 0.00014978183707883827,
2118
+ "loss": 0.8682,
2119
+ "step": 298
2120
+ },
2121
+ {
2122
+ "epoch": 0.7,
2123
+ "grad_norm": 0.7118079662322998,
2124
+ "learning_rate": 0.00014945400164629278,
2125
+ "loss": 0.9225,
2126
+ "step": 299
2127
+ },
2128
+ {
2129
+ "epoch": 0.7,
2130
+ "grad_norm": 1.1042624711990356,
2131
+ "learning_rate": 0.00014912546110838775,
2132
+ "loss": 1.4279,
2133
+ "step": 300
2134
+ },
2135
+ {
2136
+ "epoch": 0.71,
2137
+ "grad_norm": 0.947619616985321,
2138
+ "learning_rate": 0.00014879622014938915,
2139
+ "loss": 1.0544,
2140
+ "step": 301
2141
+ },
2142
+ {
2143
+ "epoch": 0.71,
2144
+ "grad_norm": 0.9065904021263123,
2145
+ "learning_rate": 0.00014846628346354933,
2146
+ "loss": 1.1642,
2147
+ "step": 302
2148
+ },
2149
+ {
2150
+ "epoch": 0.71,
2151
+ "grad_norm": 0.9430320262908936,
2152
+ "learning_rate": 0.00014813565575504022,
2153
+ "loss": 1.2182,
2154
+ "step": 303
2155
+ },
2156
+ {
2157
+ "epoch": 0.71,
2158
+ "grad_norm": 0.8739117980003357,
2159
+ "learning_rate": 0.00014780434173788617,
2160
+ "loss": 1.0176,
2161
+ "step": 304
2162
+ },
2163
+ {
2164
+ "epoch": 0.72,
2165
+ "grad_norm": 0.853125274181366,
2166
+ "learning_rate": 0.00014747234613589685,
2167
+ "loss": 1.1827,
2168
+ "step": 305
2169
+ },
2170
+ {
2171
+ "epoch": 0.72,
2172
+ "grad_norm": 1.6718727350234985,
2173
+ "learning_rate": 0.0001471396736825998,
2174
+ "loss": 1.2665,
2175
+ "step": 306
2176
+ },
2177
+ {
2178
+ "epoch": 0.72,
2179
+ "grad_norm": 0.8566248416900635,
2180
+ "learning_rate": 0.00014680632912117286,
2181
+ "loss": 1.2231,
2182
+ "step": 307
2183
+ },
2184
+ {
2185
+ "epoch": 0.72,
2186
+ "grad_norm": 0.6841180324554443,
2187
+ "learning_rate": 0.00014647231720437686,
2188
+ "loss": 0.9366,
2189
+ "step": 308
2190
+ },
2191
+ {
2192
+ "epoch": 0.73,
2193
+ "grad_norm": 0.9140876531600952,
2194
+ "learning_rate": 0.00014613764269448751,
2195
+ "loss": 1.0711,
2196
+ "step": 309
2197
+ },
2198
+ {
2199
+ "epoch": 0.73,
2200
+ "grad_norm": 0.9394497275352478,
2201
+ "learning_rate": 0.00014580231036322768,
2202
+ "loss": 1.1159,
2203
+ "step": 310
2204
+ },
2205
+ {
2206
+ "epoch": 0.73,
2207
+ "grad_norm": 1.1066112518310547,
2208
+ "learning_rate": 0.00014546632499169937,
2209
+ "loss": 1.3487,
2210
+ "step": 311
2211
+ },
2212
+ {
2213
+ "epoch": 0.73,
2214
+ "grad_norm": 0.9925751090049744,
2215
+ "learning_rate": 0.00014512969137031538,
2216
+ "loss": 1.1207,
2217
+ "step": 312
2218
+ },
2219
+ {
2220
+ "epoch": 0.73,
2221
+ "grad_norm": 0.9642359018325806,
2222
+ "learning_rate": 0.0001447924142987312,
2223
+ "loss": 1.3772,
2224
+ "step": 313
2225
+ },
2226
+ {
2227
+ "epoch": 0.74,
2228
+ "grad_norm": 0.6977396607398987,
2229
+ "learning_rate": 0.0001444544985857766,
2230
+ "loss": 0.8517,
2231
+ "step": 314
2232
+ },
2233
+ {
2234
+ "epoch": 0.74,
2235
+ "grad_norm": 1.033882737159729,
2236
+ "learning_rate": 0.00014411594904938682,
2237
+ "loss": 1.0644,
2238
+ "step": 315
2239
+ },
2240
+ {
2241
+ "epoch": 0.74,
2242
+ "grad_norm": 1.020871877670288,
2243
+ "learning_rate": 0.00014377677051653404,
2244
+ "loss": 1.2026,
2245
+ "step": 316
2246
+ },
2247
+ {
2248
+ "epoch": 0.74,
2249
+ "grad_norm": 1.059812068939209,
2250
+ "learning_rate": 0.0001434369678231587,
2251
+ "loss": 1.4181,
2252
+ "step": 317
2253
+ },
2254
+ {
2255
+ "epoch": 0.75,
2256
+ "grad_norm": 0.8130291104316711,
2257
+ "learning_rate": 0.00014309654581410024,
2258
+ "loss": 1.0691,
2259
+ "step": 318
2260
+ },
2261
+ {
2262
+ "epoch": 0.75,
2263
+ "grad_norm": 0.8362820148468018,
2264
+ "learning_rate": 0.00014275550934302823,
2265
+ "loss": 1.0053,
2266
+ "step": 319
2267
+ },
2268
+ {
2269
+ "epoch": 0.75,
2270
+ "grad_norm": 0.9266586899757385,
2271
+ "learning_rate": 0.0001424138632723731,
2272
+ "loss": 1.1313,
2273
+ "step": 320
2274
+ },
2275
+ {
2276
+ "epoch": 0.75,
2277
+ "grad_norm": 1.0162605047225952,
2278
+ "learning_rate": 0.00014207161247325691,
2279
+ "loss": 1.3518,
2280
+ "step": 321
2281
+ },
2282
+ {
2283
+ "epoch": 0.75,
2284
+ "eval_loss": 1.114696741104126,
2285
+ "eval_runtime": 5.1062,
2286
+ "eval_samples_per_second": 19.584,
2287
+ "eval_steps_per_second": 19.584,
2288
+ "step": 321
2289
+ },
2290
+ {
2291
+ "epoch": 0.76,
2292
+ "grad_norm": 1.0078846216201782,
2293
+ "learning_rate": 0.00014172876182542372,
2294
+ "loss": 1.0446,
2295
+ "step": 322
2296
+ },
2297
+ {
2298
+ "epoch": 0.76,
2299
+ "grad_norm": 1.2844680547714233,
2300
+ "learning_rate": 0.00014138531621717018,
2301
+ "loss": 1.4105,
2302
+ "step": 323
2303
+ },
2304
+ {
2305
+ "epoch": 0.76,
2306
+ "grad_norm": 1.0380208492279053,
2307
+ "learning_rate": 0.0001410412805452757,
2308
+ "loss": 1.4212,
2309
+ "step": 324
2310
+ },
2311
+ {
2312
+ "epoch": 0.76,
2313
+ "grad_norm": 0.8037036061286926,
2314
+ "learning_rate": 0.00014069665971493274,
2315
+ "loss": 0.8392,
2316
+ "step": 325
2317
+ },
2318
+ {
2319
+ "epoch": 0.77,
2320
+ "grad_norm": 0.9248948693275452,
2321
+ "learning_rate": 0.00014035145863967692,
2322
+ "loss": 1.3121,
2323
+ "step": 326
2324
+ },
2325
+ {
2326
+ "epoch": 0.77,
2327
+ "grad_norm": 0.8579298853874207,
2328
+ "learning_rate": 0.0001400056822413167,
2329
+ "loss": 1.1128,
2330
+ "step": 327
2331
+ },
2332
+ {
2333
+ "epoch": 0.77,
2334
+ "grad_norm": 1.0605120658874512,
2335
+ "learning_rate": 0.0001396593354498635,
2336
+ "loss": 1.543,
2337
+ "step": 328
2338
+ },
2339
+ {
2340
+ "epoch": 0.77,
2341
+ "grad_norm": 0.9975443482398987,
2342
+ "learning_rate": 0.0001393124232034613,
2343
+ "loss": 1.1178,
2344
+ "step": 329
2345
+ },
2346
+ {
2347
+ "epoch": 0.77,
2348
+ "grad_norm": 0.8115065693855286,
2349
+ "learning_rate": 0.0001389649504483162,
2350
+ "loss": 1.1937,
2351
+ "step": 330
2352
+ },
2353
+ {
2354
+ "epoch": 0.78,
2355
+ "grad_norm": 0.7796252369880676,
2356
+ "learning_rate": 0.00013861692213862584,
2357
+ "loss": 1.1886,
2358
+ "step": 331
2359
+ },
2360
+ {
2361
+ "epoch": 0.78,
2362
+ "grad_norm": 1.0133821964263916,
2363
+ "learning_rate": 0.000138268343236509,
2364
+ "loss": 1.4973,
2365
+ "step": 332
2366
+ },
2367
+ {
2368
+ "epoch": 0.78,
2369
+ "grad_norm": 0.9557147026062012,
2370
+ "learning_rate": 0.00013791921871193457,
2371
+ "loss": 1.4592,
2372
+ "step": 333
2373
+ },
2374
+ {
2375
+ "epoch": 0.78,
2376
+ "grad_norm": 0.9763726592063904,
2377
+ "learning_rate": 0.00013756955354265085,
2378
+ "loss": 0.8502,
2379
+ "step": 334
2380
+ },
2381
+ {
2382
+ "epoch": 0.79,
2383
+ "grad_norm": 0.8208116888999939,
2384
+ "learning_rate": 0.00013721935271411464,
2385
+ "loss": 1.1601,
2386
+ "step": 335
2387
+ },
2388
+ {
2389
+ "epoch": 0.79,
2390
+ "grad_norm": 1.3176727294921875,
2391
+ "learning_rate": 0.0001368686212194199,
2392
+ "loss": 1.1715,
2393
+ "step": 336
2394
+ },
2395
+ {
2396
+ "epoch": 0.79,
2397
+ "grad_norm": 1.2329626083374023,
2398
+ "learning_rate": 0.00013651736405922686,
2399
+ "loss": 1.3426,
2400
+ "step": 337
2401
+ },
2402
+ {
2403
+ "epoch": 0.79,
2404
+ "grad_norm": 0.9947068691253662,
2405
+ "learning_rate": 0.0001361655862416905,
2406
+ "loss": 1.0623,
2407
+ "step": 338
2408
+ },
2409
+ {
2410
+ "epoch": 0.8,
2411
+ "grad_norm": 1.176267147064209,
2412
+ "learning_rate": 0.00013581329278238927,
2413
+ "loss": 1.1281,
2414
+ "step": 339
2415
+ },
2416
+ {
2417
+ "epoch": 0.8,
2418
+ "grad_norm": 0.909443736076355,
2419
+ "learning_rate": 0.00013546048870425356,
2420
+ "loss": 1.2623,
2421
+ "step": 340
2422
+ },
2423
+ {
2424
+ "epoch": 0.8,
2425
+ "grad_norm": 0.8919989466667175,
2426
+ "learning_rate": 0.000135107179037494,
2427
+ "loss": 1.2652,
2428
+ "step": 341
2429
+ },
2430
+ {
2431
+ "epoch": 0.8,
2432
+ "grad_norm": 0.7781542539596558,
2433
+ "learning_rate": 0.00013475336881952986,
2434
+ "loss": 0.9857,
2435
+ "step": 342
2436
+ },
2437
+ {
2438
+ "epoch": 0.81,
2439
+ "grad_norm": 0.9232913851737976,
2440
+ "learning_rate": 0.00013439906309491712,
2441
+ "loss": 1.0923,
2442
+ "step": 343
2443
+ },
2444
+ {
2445
+ "epoch": 0.81,
2446
+ "grad_norm": 1.1160950660705566,
2447
+ "learning_rate": 0.0001340442669152766,
2448
+ "loss": 1.3445,
2449
+ "step": 344
2450
+ },
2451
+ {
2452
+ "epoch": 0.81,
2453
+ "grad_norm": 1.084597110748291,
2454
+ "learning_rate": 0.000133688985339222,
2455
+ "loss": 1.7647,
2456
+ "step": 345
2457
+ },
2458
+ {
2459
+ "epoch": 0.81,
2460
+ "grad_norm": 0.8420549631118774,
2461
+ "learning_rate": 0.0001333332234322876,
2462
+ "loss": 1.1342,
2463
+ "step": 346
2464
+ },
2465
+ {
2466
+ "epoch": 0.81,
2467
+ "grad_norm": 1.0362187623977661,
2468
+ "learning_rate": 0.0001329769862668563,
2469
+ "loss": 1.0779,
2470
+ "step": 347
2471
+ },
2472
+ {
2473
+ "epoch": 0.82,
2474
+ "grad_norm": 0.902492344379425,
2475
+ "learning_rate": 0.00013262027892208694,
2476
+ "loss": 1.1121,
2477
+ "step": 348
2478
+ },
2479
+ {
2480
+ "epoch": 0.82,
2481
+ "grad_norm": 1.4322317838668823,
2482
+ "learning_rate": 0.0001322631064838422,
2483
+ "loss": 1.5474,
2484
+ "step": 349
2485
+ },
2486
+ {
2487
+ "epoch": 0.82,
2488
+ "grad_norm": 0.8751888275146484,
2489
+ "learning_rate": 0.00013190547404461598,
2490
+ "loss": 1.2055,
2491
+ "step": 350
2492
+ },
2493
+ {
2494
+ "epoch": 0.82,
2495
+ "grad_norm": 0.9157432913780212,
2496
+ "learning_rate": 0.0001315473867034608,
2497
+ "loss": 1.3176,
2498
+ "step": 351
2499
+ },
2500
+ {
2501
+ "epoch": 0.83,
2502
+ "grad_norm": 0.7300966382026672,
2503
+ "learning_rate": 0.0001311888495659149,
2504
+ "loss": 0.9548,
2505
+ "step": 352
2506
+ },
2507
+ {
2508
+ "epoch": 0.83,
2509
+ "grad_norm": 1.0954256057739258,
2510
+ "learning_rate": 0.0001308298677439299,
2511
+ "loss": 1.1649,
2512
+ "step": 353
2513
+ },
2514
+ {
2515
+ "epoch": 0.83,
2516
+ "grad_norm": 1.0646469593048096,
2517
+ "learning_rate": 0.00013047044635579747,
2518
+ "loss": 1.3597,
2519
+ "step": 354
2520
+ },
2521
+ {
2522
+ "epoch": 0.83,
2523
+ "grad_norm": 0.7668378949165344,
2524
+ "learning_rate": 0.00013011059052607656,
2525
+ "loss": 1.1246,
2526
+ "step": 355
2527
+ },
2528
+ {
2529
+ "epoch": 0.84,
2530
+ "grad_norm": 0.9135538339614868,
2531
+ "learning_rate": 0.00012975030538552032,
2532
+ "loss": 1.0189,
2533
+ "step": 356
2534
+ },
2535
+ {
2536
+ "epoch": 0.84,
2537
+ "grad_norm": 0.7841051816940308,
2538
+ "learning_rate": 0.00012938959607100288,
2539
+ "loss": 1.1396,
2540
+ "step": 357
2541
+ },
2542
+ {
2543
+ "epoch": 0.84,
2544
+ "grad_norm": 0.9529784321784973,
2545
+ "learning_rate": 0.00012902846772544624,
2546
+ "loss": 1.4681,
2547
+ "step": 358
2548
+ },
2549
+ {
2550
+ "epoch": 0.84,
2551
+ "grad_norm": 0.8711650967597961,
2552
+ "learning_rate": 0.00012866692549774682,
2553
+ "loss": 0.9842,
2554
+ "step": 359
2555
+ },
2556
+ {
2557
+ "epoch": 0.85,
2558
+ "grad_norm": 0.9562662839889526,
2559
+ "learning_rate": 0.00012830497454270205,
2560
+ "loss": 1.3051,
2561
+ "step": 360
2562
+ },
2563
+ {
2564
+ "epoch": 0.85,
2565
+ "grad_norm": 1.0756105184555054,
2566
+ "learning_rate": 0.00012794262002093697,
2567
+ "loss": 1.3275,
2568
+ "step": 361
2569
+ },
2570
+ {
2571
+ "epoch": 0.85,
2572
+ "grad_norm": 0.7915710806846619,
2573
+ "learning_rate": 0.0001275798670988306,
2574
+ "loss": 1.0035,
2575
+ "step": 362
2576
+ },
2577
+ {
2578
+ "epoch": 0.85,
2579
+ "grad_norm": 0.9524595737457275,
2580
+ "learning_rate": 0.0001272167209484422,
2581
+ "loss": 1.2083,
2582
+ "step": 363
2583
+ },
2584
+ {
2585
+ "epoch": 0.85,
2586
+ "grad_norm": 1.4926435947418213,
2587
+ "learning_rate": 0.0001268531867474377,
2588
+ "loss": 1.3218,
2589
+ "step": 364
2590
+ },
2591
+ {
2592
+ "epoch": 0.86,
2593
+ "grad_norm": 1.2689683437347412,
2594
+ "learning_rate": 0.00012648926967901567,
2595
+ "loss": 2.7813,
2596
+ "step": 365
2597
+ },
2598
+ {
2599
+ "epoch": 0.86,
2600
+ "grad_norm": 0.8361314535140991,
2601
+ "learning_rate": 0.00012612497493183364,
2602
+ "loss": 1.124,
2603
+ "step": 366
2604
+ },
2605
+ {
2606
+ "epoch": 0.86,
2607
+ "grad_norm": 1.2996618747711182,
2608
+ "learning_rate": 0.00012576030769993393,
2609
+ "loss": 1.3745,
2610
+ "step": 367
2611
+ },
2612
+ {
2613
+ "epoch": 0.86,
2614
+ "grad_norm": 0.8248890042304993,
2615
+ "learning_rate": 0.0001253952731826697,
2616
+ "loss": 1.1971,
2617
+ "step": 368
2618
+ },
2619
+ {
2620
+ "epoch": 0.87,
2621
+ "grad_norm": 0.8044300079345703,
2622
+ "learning_rate": 0.00012502987658463075,
2623
+ "loss": 1.1508,
2624
+ "step": 369
2625
+ },
2626
+ {
2627
+ "epoch": 0.87,
2628
+ "grad_norm": 1.196742057800293,
2629
+ "learning_rate": 0.00012466412311556952,
2630
+ "loss": 0.9868,
2631
+ "step": 370
2632
+ },
2633
+ {
2634
+ "epoch": 0.87,
2635
+ "grad_norm": 0.9415065050125122,
2636
+ "learning_rate": 0.0001242980179903264,
2637
+ "loss": 1.046,
2638
+ "step": 371
2639
+ },
2640
+ {
2641
+ "epoch": 0.87,
2642
+ "grad_norm": 1.049695611000061,
2643
+ "learning_rate": 0.0001239315664287558,
2644
+ "loss": 0.9927,
2645
+ "step": 372
2646
+ },
2647
+ {
2648
+ "epoch": 0.88,
2649
+ "grad_norm": 0.8266507387161255,
2650
+ "learning_rate": 0.00012356477365565148,
2651
+ "loss": 0.8879,
2652
+ "step": 373
2653
+ },
2654
+ {
2655
+ "epoch": 0.88,
2656
+ "grad_norm": 0.9163070321083069,
2657
+ "learning_rate": 0.0001231976449006721,
2658
+ "loss": 1.1214,
2659
+ "step": 374
2660
+ },
2661
+ {
2662
+ "epoch": 0.88,
2663
+ "grad_norm": 1.01756751537323,
2664
+ "learning_rate": 0.00012283018539826685,
2665
+ "loss": 1.1644,
2666
+ "step": 375
2667
+ },
2668
+ {
2669
+ "epoch": 0.88,
2670
+ "grad_norm": 0.901319682598114,
2671
+ "learning_rate": 0.00012246240038760043,
2672
+ "loss": 1.1985,
2673
+ "step": 376
2674
+ },
2675
+ {
2676
+ "epoch": 0.88,
2677
+ "grad_norm": 0.9721381664276123,
2678
+ "learning_rate": 0.00012209429511247864,
2679
+ "loss": 1.1199,
2680
+ "step": 377
2681
+ },
2682
+ {
2683
+ "epoch": 0.89,
2684
+ "grad_norm": 0.8883329033851624,
2685
+ "learning_rate": 0.0001217258748212737,
2686
+ "loss": 1.3431,
2687
+ "step": 378
2688
+ },
2689
+ {
2690
+ "epoch": 0.89,
2691
+ "grad_norm": 1.0698317289352417,
2692
+ "learning_rate": 0.00012135714476684903,
2693
+ "loss": 1.3173,
2694
+ "step": 379
2695
+ },
2696
+ {
2697
+ "epoch": 0.89,
2698
+ "grad_norm": 0.8664084076881409,
2699
+ "learning_rate": 0.00012098811020648475,
2700
+ "loss": 1.0441,
2701
+ "step": 380
2702
+ },
2703
+ {
2704
+ "epoch": 0.89,
2705
+ "grad_norm": 0.9194340109825134,
2706
+ "learning_rate": 0.00012061877640180255,
2707
+ "loss": 1.152,
2708
+ "step": 381
2709
+ },
2710
+ {
2711
+ "epoch": 0.9,
2712
+ "grad_norm": 0.9599464535713196,
2713
+ "learning_rate": 0.00012024914861869063,
2714
+ "loss": 1.1115,
2715
+ "step": 382
2716
+ },
2717
+ {
2718
+ "epoch": 0.9,
2719
+ "grad_norm": 0.9990159273147583,
2720
+ "learning_rate": 0.00011987923212722872,
2721
+ "loss": 1.2534,
2722
+ "step": 383
2723
+ },
2724
+ {
2725
+ "epoch": 0.9,
2726
+ "grad_norm": 0.8435646891593933,
2727
+ "learning_rate": 0.00011950903220161285,
2728
+ "loss": 1.1752,
2729
+ "step": 384
2730
+ },
2731
+ {
2732
+ "epoch": 0.9,
2733
+ "grad_norm": 1.0376098155975342,
2734
+ "learning_rate": 0.00011913855412008023,
2735
+ "loss": 1.4716,
2736
+ "step": 385
2737
+ },
2738
+ {
2739
+ "epoch": 0.91,
2740
+ "grad_norm": 1.3249186277389526,
2741
+ "learning_rate": 0.00011876780316483401,
2742
+ "loss": 1.211,
2743
+ "step": 386
2744
+ },
2745
+ {
2746
+ "epoch": 0.91,
2747
+ "grad_norm": 1.378393292427063,
2748
+ "learning_rate": 0.00011839678462196784,
2749
+ "loss": 1.0357,
2750
+ "step": 387
2751
+ },
2752
+ {
2753
+ "epoch": 0.91,
2754
+ "grad_norm": 0.7574142217636108,
2755
+ "learning_rate": 0.0001180255037813906,
2756
+ "loss": 0.4137,
2757
+ "step": 388
2758
+ },
2759
+ {
2760
+ "epoch": 0.91,
2761
+ "grad_norm": 0.7813417911529541,
2762
+ "learning_rate": 0.00011765396593675097,
2763
+ "loss": 1.1776,
2764
+ "step": 389
2765
+ },
2766
+ {
2767
+ "epoch": 0.92,
2768
+ "grad_norm": 0.8787057995796204,
2769
+ "learning_rate": 0.00011728217638536197,
2770
+ "loss": 1.1352,
2771
+ "step": 390
2772
+ },
2773
+ {
2774
+ "epoch": 0.92,
2775
+ "grad_norm": 0.9643175005912781,
2776
+ "learning_rate": 0.00011691014042812536,
2777
+ "loss": 1.3089,
2778
+ "step": 391
2779
+ },
2780
+ {
2781
+ "epoch": 0.92,
2782
+ "grad_norm": 0.9101107716560364,
2783
+ "learning_rate": 0.00011653786336945614,
2784
+ "loss": 1.0639,
2785
+ "step": 392
2786
+ },
2787
+ {
2788
+ "epoch": 0.92,
2789
+ "grad_norm": 1.018091082572937,
2790
+ "learning_rate": 0.00011616535051720685,
2791
+ "loss": 0.9938,
2792
+ "step": 393
2793
+ },
2794
+ {
2795
+ "epoch": 0.92,
2796
+ "grad_norm": 0.9708930253982544,
2797
+ "learning_rate": 0.00011579260718259197,
2798
+ "loss": 0.8004,
2799
+ "step": 394
2800
+ },
2801
+ {
2802
+ "epoch": 0.93,
2803
+ "grad_norm": 0.8909386396408081,
2804
+ "learning_rate": 0.00011541963868011212,
2805
+ "loss": 1.2997,
2806
+ "step": 395
2807
+ },
2808
+ {
2809
+ "epoch": 0.93,
2810
+ "grad_norm": 1.0622750520706177,
2811
+ "learning_rate": 0.00011504645032747832,
2812
+ "loss": 1.0235,
2813
+ "step": 396
2814
+ },
2815
+ {
2816
+ "epoch": 0.93,
2817
+ "grad_norm": 0.8857365250587463,
2818
+ "learning_rate": 0.00011467304744553618,
2819
+ "loss": 0.8382,
2820
+ "step": 397
2821
+ },
2822
+ {
2823
+ "epoch": 0.93,
2824
+ "grad_norm": 0.8980242013931274,
2825
+ "learning_rate": 0.00011429943535819005,
2826
+ "loss": 1.0877,
2827
+ "step": 398
2828
+ },
2829
+ {
2830
+ "epoch": 0.94,
2831
+ "grad_norm": 1.1426031589508057,
2832
+ "learning_rate": 0.00011392561939232706,
2833
+ "loss": 1.3496,
2834
+ "step": 399
2835
+ },
2836
+ {
2837
+ "epoch": 0.94,
2838
+ "grad_norm": 1.0347543954849243,
2839
+ "learning_rate": 0.0001135516048777412,
2840
+ "loss": 1.6309,
2841
+ "step": 400
2842
+ },
2843
+ {
2844
+ "epoch": 0.94,
2845
+ "grad_norm": 1.0121687650680542,
2846
+ "learning_rate": 0.00011317739714705731,
2847
+ "loss": 1.2256,
2848
+ "step": 401
2849
+ },
2850
+ {
2851
+ "epoch": 0.94,
2852
+ "grad_norm": 0.8863442540168762,
2853
+ "learning_rate": 0.0001128030015356551,
2854
+ "loss": 0.8687,
2855
+ "step": 402
2856
+ },
2857
+ {
2858
+ "epoch": 0.95,
2859
+ "grad_norm": 0.7622981667518616,
2860
+ "learning_rate": 0.00011242842338159309,
2861
+ "loss": 0.7564,
2862
+ "step": 403
2863
+ },
2864
+ {
2865
+ "epoch": 0.95,
2866
+ "grad_norm": 0.9527961015701294,
2867
+ "learning_rate": 0.0001120536680255323,
2868
+ "loss": 1.0593,
2869
+ "step": 404
2870
+ },
2871
+ {
2872
+ "epoch": 0.95,
2873
+ "grad_norm": 1.3481955528259277,
2874
+ "learning_rate": 0.00011167874081066045,
2875
+ "loss": 1.2279,
2876
+ "step": 405
2877
+ },
2878
+ {
2879
+ "epoch": 0.95,
2880
+ "grad_norm": 0.8665672540664673,
2881
+ "learning_rate": 0.00011130364708261552,
2882
+ "loss": 1.1677,
2883
+ "step": 406
2884
+ },
2885
+ {
2886
+ "epoch": 0.96,
2887
+ "grad_norm": 1.217490553855896,
2888
+ "learning_rate": 0.0001109283921894095,
2889
+ "loss": 1.2617,
2890
+ "step": 407
2891
+ },
2892
+ {
2893
+ "epoch": 0.96,
2894
+ "grad_norm": 0.8935596942901611,
2895
+ "learning_rate": 0.00011055298148135236,
2896
+ "loss": 1.1184,
2897
+ "step": 408
2898
+ },
2899
+ {
2900
+ "epoch": 0.96,
2901
+ "grad_norm": 0.8513955473899841,
2902
+ "learning_rate": 0.00011017742031097563,
2903
+ "loss": 1.2705,
2904
+ "step": 409
2905
+ },
2906
+ {
2907
+ "epoch": 0.96,
2908
+ "grad_norm": 1.0295133590698242,
2909
+ "learning_rate": 0.0001098017140329561,
2910
+ "loss": 1.1966,
2911
+ "step": 410
2912
+ },
2913
+ {
2914
+ "epoch": 0.96,
2915
+ "grad_norm": 1.1029167175292969,
2916
+ "learning_rate": 0.0001094258680040394,
2917
+ "loss": 1.4887,
2918
+ "step": 411
2919
+ },
2920
+ {
2921
+ "epoch": 0.97,
2922
+ "grad_norm": 0.9045723080635071,
2923
+ "learning_rate": 0.0001090498875829638,
2924
+ "loss": 1.1461,
2925
+ "step": 412
2926
+ },
2927
+ {
2928
+ "epoch": 0.97,
2929
+ "grad_norm": 0.8317312002182007,
2930
+ "learning_rate": 0.00010867377813038366,
2931
+ "loss": 1.136,
2932
+ "step": 413
2933
+ },
2934
+ {
2935
+ "epoch": 0.97,
2936
+ "grad_norm": 1.0023647546768188,
2937
+ "learning_rate": 0.00010829754500879308,
2938
+ "loss": 1.1123,
2939
+ "step": 414
2940
+ },
2941
+ {
2942
+ "epoch": 0.97,
2943
+ "grad_norm": 0.9197617769241333,
2944
+ "learning_rate": 0.00010792119358244939,
2945
+ "loss": 1.2792,
2946
+ "step": 415
2947
+ },
2948
+ {
2949
+ "epoch": 0.98,
2950
+ "grad_norm": 0.9892452955245972,
2951
+ "learning_rate": 0.00010754472921729661,
2952
+ "loss": 1.634,
2953
+ "step": 416
2954
+ },
2955
+ {
2956
+ "epoch": 0.98,
2957
+ "grad_norm": 0.8005648255348206,
2958
+ "learning_rate": 0.00010716815728088912,
2959
+ "loss": 0.7168,
2960
+ "step": 417
2961
+ },
2962
+ {
2963
+ "epoch": 0.98,
2964
+ "grad_norm": 1.1989247798919678,
2965
+ "learning_rate": 0.00010679148314231504,
2966
+ "loss": 1.2882,
2967
+ "step": 418
2968
+ },
2969
+ {
2970
+ "epoch": 0.98,
2971
+ "grad_norm": 0.7820172905921936,
2972
+ "learning_rate": 0.00010641471217211958,
2973
+ "loss": 1.1125,
2974
+ "step": 419
2975
+ },
2976
+ {
2977
+ "epoch": 0.99,
2978
+ "grad_norm": 1.352563500404358,
2979
+ "learning_rate": 0.00010603784974222861,
2980
+ "loss": 0.9641,
2981
+ "step": 420
2982
+ },
2983
+ {
2984
+ "epoch": 0.99,
2985
+ "grad_norm": 0.8966504335403442,
2986
+ "learning_rate": 0.000105660901225872,
2987
+ "loss": 1.1155,
2988
+ "step": 421
2989
+ },
2990
+ {
2991
+ "epoch": 0.99,
2992
+ "grad_norm": 0.8722444176673889,
2993
+ "learning_rate": 0.00010528387199750707,
2994
+ "loss": 1.3011,
2995
+ "step": 422
2996
+ },
2997
+ {
2998
+ "epoch": 0.99,
2999
+ "grad_norm": 0.8678218722343445,
3000
+ "learning_rate": 0.00010490676743274181,
3001
+ "loss": 1.2912,
3002
+ "step": 423
3003
+ },
3004
+ {
3005
+ "epoch": 1.0,
3006
+ "grad_norm": 0.8596826791763306,
3007
+ "learning_rate": 0.00010452959290825846,
3008
+ "loss": 1.3792,
3009
+ "step": 424
3010
+ },
3011
+ {
3012
+ "epoch": 1.0,
3013
+ "grad_norm": 0.777655303478241,
3014
+ "learning_rate": 0.00010415235380173662,
3015
+ "loss": 0.9992,
3016
+ "step": 425
3017
+ },
3018
+ {
3019
+ "epoch": 1.0,
3020
+ "grad_norm": 0.7913762331008911,
3021
+ "learning_rate": 0.00010377505549177682,
3022
+ "loss": 0.8813,
3023
+ "step": 426
3024
+ }
3025
+ ],
3026
+ "logging_steps": 1,
3027
+ "max_steps": 852,
3028
+ "num_input_tokens_seen": 0,
3029
+ "num_train_epochs": 2,
3030
+ "save_steps": 426,
3031
+ "total_flos": 7754585188270080.0,
3032
+ "train_batch_size": 1,
3033
+ "trial_name": null,
3034
+ "trial_params": null
3035
+ }
checkpoint-426/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a88d9833ec2589b59141f1c93c82d94c94fbeb0ecfb4fa977032e0f7f6fd339
3
+ size 5624
checkpoint-852/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: openlm-research/open_llama_3b_v2
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 0.9.0
checkpoint-852/adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "openlm-research/open_llama_3b_v2",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 32,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 8,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "gate_proj",
23
+ "down_proj",
24
+ "v_proj",
25
+ "q_proj",
26
+ "k_proj",
27
+ "o_proj",
28
+ "up_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_dora": false,
32
+ "use_rslora": false
33
+ }
checkpoint-852/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7903f7bfdf9468d2fd89546cc5673712b457f9aec2dd6fc604e50884578ea9f
3
+ size 50899792
checkpoint-852/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94c840d7d87ccddb2ce294831e4e9bbda71c234d64a346bd22ca5c390096a8aa
3
+ size 101919290
checkpoint-852/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f953a10686edd67b9d7c36b5439b185a57a5c11c3bd125fd4823dcf7499eda9c
3
+ size 14244
checkpoint-852/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47aed3f9ab91b9295d1b086f046a3f3a20b19295893c3cd84e641de0f1b4ecfa
3
+ size 1064
checkpoint-852/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-852/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a88d9833ec2589b59141f1c93c82d94c94fbeb0ecfb4fa977032e0f7f6fd339
3
+ size 5624
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openlm-research/open_llama_3b_v2",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 3200,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 8640,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 26,
18
+ "num_key_value_heads": 32,
19
+ "pad_token_id": 0,
20
+ "pretraining_tp": 1,
21
+ "quantization_config": {
22
+ "_load_in_4bit": true,
23
+ "_load_in_8bit": false,
24
+ "bnb_4bit_compute_dtype": "float16",
25
+ "bnb_4bit_quant_type": "nf4",
26
+ "bnb_4bit_use_double_quant": true,
27
+ "llm_int8_enable_fp32_cpu_offload": false,
28
+ "llm_int8_has_fp16_weight": false,
29
+ "llm_int8_skip_modules": null,
30
+ "llm_int8_threshold": 6.0,
31
+ "load_in_4bit": true,
32
+ "load_in_8bit": false,
33
+ "quant_method": "bitsandbytes"
34
+ },
35
+ "rms_norm_eps": 1e-06,
36
+ "rope_scaling": null,
37
+ "rope_theta": 10000.0,
38
+ "tie_word_embeddings": false,
39
+ "torch_dtype": "float16",
40
+ "transformers_version": "4.38.2",
41
+ "use_cache": false,
42
+ "vocab_size": 32000
43
+ }
runs/Mar10_09-02-34_451e0eacc3ea/events.out.tfevents.1710061354.451e0eacc3ea.39.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae71449a093d1cf53cdbddc1c3e0f9b1c808a5a592eb6504553bac03edd74704
3
+ size 137460
runs/Mar10_09-15-58_451e0eacc3ea/events.out.tfevents.1710062158.451e0eacc3ea.175.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8adc6cc7c71b705370feb812353d826c104c24f3d29b22961524f1ca3b7fd24
3
+ size 187601
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91b289e85fa20fd375d8b33dc12f77616f18abc6359804471d1fafcb425fecb8
3
+ size 511574
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 2048,
36
+ "pad_token": "</s>",
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false,
42
+ "use_fast": true
43
+ }