Upload folder using huggingface_hub

README.md

@@ -0,0 +1,155 @@
+---
+license: bigcode-openrail-m
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: bigcode/starcoder
+model-index:
+- name: lora-out
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<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)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.0`
+```yaml
+base_model: bigcode/starcoder # this can be swapped for mdel model when the model is released
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+is_llama_derived_model: false
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: /workspace/axolotl-mdel/mtg.txt # change this to where your dataset is
+    type: completion # change this to 'alpaca' if you are using alpaca
+
+lora_modules_to_save:
+  - embed_tokens
+  - lm_head
+
+dataset_prepared_path:
+val_set_size: 0.05
+output_dir: ./lora-out
+
+sequence_len: 4096 # this can be tweaked for efficiency
+sample_packing: true
+pad_to_sequence_len: true
+
+adapter: lora
+lora_model_dir:
+lora_r: 32
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+
+wandb_project: mtg-starcoder-experiement-cleaner # give this a name
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 2 # this can be tweaked for efficiency
+micro_batch_size: 1 # this can be tweaked for efficiency
+num_epochs: 1 # this can be experimented with
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+train_on_inputs: true
+group_by_length: false
+bf16: true
+fp16: false
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: false #true
+s2_attention:
+
+warmup_steps: 10 # this can be tweaked for efficiency
+evals_per_epoch: 10 # this can be tweaked for efficiency
+eval_table_size:
+eval_table_max_new_tokens: 128
+saves_per_epoch: 1 
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  pad_token: "<|endoftext|>" # I need to talk with Huu/Taishi about this
+  eos_token: "<|endoftext|>"
+
+```
+
+</details><br>
+
+# lora-out
+
+This model is a fine-tuned version of [bigcode/starcoder](https://huggingface.co/bigcode/starcoder) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7371
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 2
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 4.0386        | 0.0   | 1    | 3.7331          |
+| 1.8941        | 0.1   | 25   | 1.6178          |
+| 1.0615        | 0.21  | 50   | 0.9739          |
+| 0.9228        | 0.31  | 75   | 0.8470          |
+| 0.8614        | 0.41  | 100  | 0.8104          |
+| 0.8562        | 0.52  | 125  | 0.7776          |
+| 0.7939        | 0.62  | 150  | 0.7530          |
+| 0.7714        | 0.73  | 175  | 0.7430          |
+| 0.7999        | 0.83  | 200  | 0.7389          |
+| 0.8647        | 0.93  | 225  | 0.7371          |
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.37.0
+- Pytorch 2.1.2+cu118
+- Datasets 2.16.1
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,30 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "bigcode/starcoder",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_attn",
+    "c_proj",
+    "c_fc"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39056333c77bfb87a464b7c756991323eebfaa3db8427c922c6ca687dae7c3cc
+size 824951054

checkpoint-241/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: bigcode/starcoder
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- 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. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+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).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+### Framework versions
+
+- PEFT 0.7.1

checkpoint-241/adapter_config.json

@@ -0,0 +1,30 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "bigcode/starcoder",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_attn",
+    "c_proj",
+    "c_fc"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-241/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1100244c5ce1010dae5f4532a7333dd17e8c899338710a1620ca400543e55d35
+size 824878800

checkpoint-241/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8fe4084ae2efade499fce3fc2f6eae5771f99586917f5c3cdff2f4ca6f783de
+size 826822552

checkpoint-241/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f24e00645cc08087bf206cfd932ba5f0fece885d758b0fc1e9060d777e7eebef
+size 14244

checkpoint-241/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5939dffaffa27516a665d7288c4418204f16cc2c1fee3d39b441522b0b2ae897
+size 1064

checkpoint-241/trainer_state.json

@@ -0,0 +1,1547 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 25,
+  "global_step": 241,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 2e-05,
+      "loss": 4.0386,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 3.7331418991088867,
+      "eval_runtime": 31.7985,
+      "eval_samples_per_second": 42.423,
+      "eval_steps_per_second": 42.423,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4e-05,
+      "loss": 4.0197,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6e-05,
+      "loss": 3.923,
+      "step": 3
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 8e-05,
+      "loss": 3.8825,
+      "step": 4
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0001,
+      "loss": 3.7663,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00012,
+      "loss": 3.4309,
+      "step": 6
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00014,
+      "loss": 3.2986,
+      "step": 7
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00016,
+      "loss": 3.1106,
+      "step": 8
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00018,
+      "loss": 3.0555,
+      "step": 9
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0002,
+      "loss": 2.8894,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00019999075218579183,
+      "loss": 2.7674,
+      "step": 11
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00019996301045360873,
+      "loss": 2.6985,
+      "step": 12
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0001999167799344583,
+      "loss": 2.7367,
+      "step": 13
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00019985206917896563,
+      "loss": 2.6074,
+      "step": 14
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00019976889015579165,
+      "loss": 2.5426,
+      "step": 15
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019966725824941932,
+      "loss": 2.4266,
+      "step": 16
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019954719225730847,
+      "loss": 2.4288,
+      "step": 17
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019940871438641882,
+      "loss": 2.3498,
+      "step": 18
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00019925185024910277,
+      "loss": 2.383,
+      "step": 19
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00019907662885836836,
+      "loss": 2.304,
+      "step": 20
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00019888308262251285,
+      "loss": 2.2202,
+      "step": 21
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0001986712473391289,
+      "loss": 2.1988,
+      "step": 22
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00019844116218848334,
+      "loss": 2.0964,
+      "step": 23
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00019819286972627066,
+      "loss": 1.8888,
+      "step": 24
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00019792641587574212,
+      "loss": 1.8941,
+      "step": 25
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 1.6177802085876465,
+      "eval_runtime": 32.4612,
+      "eval_samples_per_second": 41.557,
+      "eval_steps_per_second": 41.557,
+      "step": 25
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00019764184991921178,
+      "loss": 1.8308,
+      "step": 26
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0001973392244889415,
+      "loss": 1.6953,
+      "step": 27
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00019701859555740648,
+      "loss": 1.6846,
+      "step": 28
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00019668002242694238,
+      "loss": 1.6546,
+      "step": 29
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00019632356771877735,
+      "loss": 1.5143,
+      "step": 30
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00019594929736144976,
+      "loss": 1.5162,
+      "step": 31
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0001955572805786141,
+      "loss": 1.5521,
+      "step": 32
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00019514758987623784,
+      "loss": 1.382,
+      "step": 33
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000194720301029191,
+      "loss": 1.3927,
+      "step": 34
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00019427549306723097,
+      "loss": 1.3969,
+      "step": 35
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0001938132482603856,
+      "loss": 1.327,
+      "step": 36
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0001933336521037367,
+      "loss": 1.3012,
+      "step": 37
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00019283679330160726,
+      "loss": 1.2846,
+      "step": 38
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00019232276375115515,
+      "loss": 1.1911,
+      "step": 39
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00019179165852537596,
+      "loss": 1.3068,
+      "step": 40
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00019124357585551872,
+      "loss": 1.172,
+      "step": 41
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00019067861711291744,
+      "loss": 1.1701,
+      "step": 42
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0001900968867902419,
+      "loss": 1.2153,
+      "step": 43
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000189498492482171,
+      "loss": 1.2069,
+      "step": 44
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00018888354486549237,
+      "loss": 1.1386,
+      "step": 45
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00018825215767863214,
+      "loss": 1.188,
+      "step": 46
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0001876044477006183,
+      "loss": 1.081,
+      "step": 47
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00018694053472948156,
+      "loss": 1.1138,
+      "step": 48
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00018626054156009806,
+      "loss": 1.1209,
+      "step": 49
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00018556459396147775,
+      "loss": 1.0615,
+      "step": 50
+    },
+    {
+      "epoch": 0.21,
+      "eval_loss": 0.9739040732383728,
+      "eval_runtime": 32.5014,
+      "eval_samples_per_second": 41.506,
+      "eval_steps_per_second": 41.506,
+      "step": 50
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00018485282065350235,
+      "loss": 1.0427,
+      "step": 51
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00018412535328311814,
+      "loss": 1.0302,
+      "step": 52
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0001833823263999867,
+      "loss": 1.0702,
+      "step": 53
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0001826238774315995,
+      "loss": 1.0953,
+      "step": 54
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00018185014665785936,
+      "loss": 1.051,
+      "step": 55
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00018106127718513516,
+      "loss": 1.0492,
+      "step": 56
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00018025741491979326,
+      "loss": 1.0026,
+      "step": 57
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00017943870854121124,
+      "loss": 1.015,
+      "step": 58
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00017860530947427875,
+      "loss": 0.9858,
+      "step": 59
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00017775737186139038,
+      "loss": 1.057,
+      "step": 60
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0001768950525339362,
+      "loss": 0.9989,
+      "step": 61
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00017601851098329483,
+      "loss": 1.0269,
+      "step": 62
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00017512790933133437,
+      "loss": 0.9407,
+      "step": 63
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.000174223412300427,
+      "loss": 1.0122,
+      "step": 64
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00017330518718298264,
+      "loss": 0.9799,
+      "step": 65
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00017237340381050703,
+      "loss": 0.9827,
+      "step": 66
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00017142823452219038,
+      "loss": 0.9264,
+      "step": 67
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00017046985413303215,
+      "loss": 0.982,
+      "step": 68
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00016949843990150796,
+      "loss": 0.995,
+      "step": 69
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00016851417149678444,
+      "loss": 0.949,
+      "step": 70
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00016751723096548835,
+      "loss": 0.9733,
+      "step": 71
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00016650780269803587,
+      "loss": 0.9465,
+      "step": 72
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00016548607339452853,
+      "loss": 0.9639,
+      "step": 73
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00016445223203022166,
+      "loss": 0.9159,
+      "step": 74
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00016340646982057247,
+      "loss": 0.9228,
+      "step": 75
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 0.8469665050506592,
+      "eval_runtime": 32.5025,
+      "eval_samples_per_second": 41.504,
+      "eval_steps_per_second": 41.504,
+      "step": 75
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00016234898018587337,
+      "loss": 0.9526,
+      "step": 76
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0001612799587154777,
+      "loss": 0.9272,
+      "step": 77
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00016019960313162434,
+      "loss": 0.9204,
+      "step": 78
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00015910811325286768,
+      "loss": 1.0185,
+      "step": 79
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00015800569095711982,
+      "loss": 0.9675,
+      "step": 80
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00015689254014431225,
+      "loss": 0.9504,
+      "step": 81
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00015576886669868296,
+      "loss": 0.9555,
+      "step": 82
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00015463487845069707,
+      "loss": 0.9131,
+      "step": 83
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00015349078513860726,
+      "loss": 3.3474,
+      "step": 84
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00015233679836966122,
+      "loss": 0.9042,
+      "step": 85
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0001511731315809637,
+      "loss": 0.9409,
+      "step": 86
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.9692,
+      "step": 87
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00014881762060482814,
+      "loss": 0.9186,
+      "step": 88
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0001476262120839475,
+      "loss": 0.9448,
+      "step": 89
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00014642599479585105,
+      "loss": 0.917,
+      "step": 90
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00014521719072826858,
+      "loss": 0.9023,
+      "step": 91
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0001440000234571087,
+      "loss": 0.8668,
+      "step": 92
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0001427747181051071,
+      "loss": 0.9481,
+      "step": 93
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00014154150130018866,
+      "loss": 0.9152,
+      "step": 94
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00014030060113355116,
+      "loss": 0.9099,
+      "step": 95
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00013905224711747844,
+      "loss": 0.9107,
+      "step": 96
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00013779667014289065,
+      "loss": 0.8976,
+      "step": 97
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00013653410243663952,
+      "loss": 0.8903,
+      "step": 98
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00013526477751855644,
+      "loss": 0.8592,
+      "step": 99
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00013398893015826167,
+      "loss": 0.8614,
+      "step": 100
+    },
+    {
+      "epoch": 0.41,
+      "eval_loss": 0.8104140162467957,
+      "eval_runtime": 32.7643,
+      "eval_samples_per_second": 41.173,
+      "eval_steps_per_second": 41.173,
+      "step": 100
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00013270679633174218,
+      "loss": 0.9136,
+      "step": 101
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00013141861317770626,
+      "loss": 0.9266,
+      "step": 102
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00013012461895372344,
+      "loss": 0.8899,
+      "step": 103
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0001288250529921571,
+      "loss": 0.8543,
+      "step": 104
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00012752015565589852,
+      "loss": 0.8738,
+      "step": 105
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00012621016829391022,
+      "loss": 0.8649,
+      "step": 106
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00012489533319658702,
+      "loss": 0.8579,
+      "step": 107
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00012357589355094275,
+      "loss": 0.8752,
+      "step": 108
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00012225209339563145,
+      "loss": 0.908,
+      "step": 109
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00012092417757581085,
+      "loss": 0.8645,
+      "step": 110
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00011959239169785667,
+      "loss": 0.8811,
+      "step": 111
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00011825698208393619,
+      "loss": 0.8492,
+      "step": 112
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00011691819572644939,
+      "loss": 0.8998,
+      "step": 113
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0001155762802423463,
+      "loss": 0.8174,
+      "step": 114
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00011423148382732853,
+      "loss": 0.8516,
+      "step": 115
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0001128840552099439,
+      "loss": 0.8899,
+      "step": 116
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00011153424360558267,
+      "loss": 0.8683,
+      "step": 117
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00011018229867038356,
+      "loss": 0.841,
+      "step": 118
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00010882847045505808,
+      "loss": 0.8126,
+      "step": 119
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00010747300935864243,
+      "loss": 0.8781,
+      "step": 120
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00010611616608218429,
+      "loss": 0.8716,
+      "step": 121
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00010475819158237425,
+      "loss": 0.8288,
+      "step": 122
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00010339933702512979,
+      "loss": 0.8418,
+      "step": 123
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00010203985373914056,
+      "loss": 0.8574,
+      "step": 124
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00010067999316938347,
+      "loss": 0.8562,
+      "step": 125
+    },
+    {
+      "epoch": 0.52,
+      "eval_loss": 0.777643084526062,
+      "eval_runtime": 32.674,
+      "eval_samples_per_second": 41.287,
+      "eval_steps_per_second": 41.287,
+      "step": 125
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.932000683061653e-05,
+      "loss": 0.8407,
+      "step": 126
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.79601462608595e-05,
+      "loss": 0.8131,
+      "step": 127
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.660066297487022e-05,
+      "loss": 0.8564,
+      "step": 128
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.524180841762577e-05,
+      "loss": 0.8282,
+      "step": 129
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.388383391781575e-05,
+      "loss": 0.8353,
+      "step": 130
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.252699064135758e-05,
+      "loss": 0.7829,
+      "step": 131
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.117152954494194e-05,
+      "loss": 0.8683,
+      "step": 132
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.981770132961649e-05,
+      "loss": 0.8246,
+      "step": 133
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.846575639441732e-05,
+      "loss": 0.8414,
+      "step": 134
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.711594479005614e-05,
+      "loss": 0.8093,
+      "step": 135
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.57685161726715e-05,
+      "loss": 0.8633,
+      "step": 136
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.442371975765368e-05,
+      "loss": 0.861,
+      "step": 137
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.308180427355062e-05,
+      "loss": 0.8212,
+      "step": 138
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.174301791606385e-05,
+      "loss": 0.7889,
+      "step": 139
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.040760830214333e-05,
+      "loss": 0.8207,
+      "step": 140
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.907582242418916e-05,
+      "loss": 0.8163,
+      "step": 141
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.774790660436858e-05,
+      "loss": 0.8603,
+      "step": 142
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.642410644905726e-05,
+      "loss": 0.8745,
+      "step": 143
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.510466680341301e-05,
+      "loss": 0.8254,
+      "step": 144
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.378983170608982e-05,
+      "loss": 0.7949,
+      "step": 145
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.24798443441015e-05,
+      "loss": 0.837,
+      "step": 146
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.117494700784292e-05,
+      "loss": 0.8211,
+      "step": 147
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.98753810462766e-05,
+      "loss": 0.8267,
+      "step": 148
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.858138682229376e-05,
+      "loss": 0.819,
+      "step": 149
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.729320366825784e-05,
+      "loss": 0.7939,
+      "step": 150
+    },
+    {
+      "epoch": 0.62,
+      "eval_loss": 0.753038763999939,
+      "eval_runtime": 32.7487,
+      "eval_samples_per_second": 41.192,
+      "eval_steps_per_second": 41.192,
+      "step": 150
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.601106984173835e-05,
+      "loss": 0.8429,
+      "step": 151
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.47352224814436e-05,
+      "loss": 0.7932,
+      "step": 152
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.34658975633605e-05,
+      "loss": 0.7522,
+      "step": 153
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.220332985710936e-05,
+      "loss": 0.8002,
+      "step": 154
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.094775288252157e-05,
+      "loss": 0.7934,
+      "step": 155
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.969939886644884e-05,
+      "loss": 0.7772,
+      "step": 156
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.845849869981137e-05,
+      "loss": 0.8183,
+      "step": 157
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.7225281894892935e-05,
+      "loss": 0.8265,
+      "step": 158
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.599997654289129e-05,
+      "loss": 0.8557,
+      "step": 159
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.478280927173145e-05,
+      "loss": 0.8062,
+      "step": 160
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.357400520414898e-05,
+      "loss": 0.8418,
+      "step": 161
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.2373787916052486e-05,
+      "loss": 0.8169,
+      "step": 162
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.11823793951719e-05,
+      "loss": 0.8194,
+      "step": 163
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.8218,
+      "step": 164
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.882686841903628e-05,
+      "loss": 0.8385,
+      "step": 165
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.7663201630338816e-05,
+      "loss": 0.803,
+      "step": 166
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.650921486139278e-05,
+      "loss": 0.7703,
+      "step": 167
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.5365121549302914e-05,
+      "loss": 0.821,
+      "step": 168
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.423113330131707e-05,
+      "loss": 0.813,
+      "step": 169
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.310745985568778e-05,
+      "loss": 0.7596,
+      "step": 170
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.19943090428802e-05,
+      "loss": 0.781,
+      "step": 171
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.089188674713236e-05,
+      "loss": 0.8146,
+      "step": 172
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.980039686837568e-05,
+      "loss": 0.8185,
+      "step": 173
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.872004128452231e-05,
+      "loss": 0.7865,
+      "step": 174
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.7651019814126654e-05,
+      "loss": 0.7714,
+      "step": 175
+    },
+    {
+      "epoch": 0.73,
+      "eval_loss": 0.7429953813552856,
+      "eval_runtime": 32.5067,
+      "eval_samples_per_second": 41.499,
+      "eval_steps_per_second": 41.499,
+      "step": 175
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.6593530179427535e-05,
+      "loss": 0.8393,
+      "step": 176
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.554776796977836e-05,
+      "loss": 0.7994,
+      "step": 177
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.45139266054715e-05,
+      "loss": 0.8316,
+      "step": 178
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.3492197301964145e-05,
+      "loss": 0.774,
+      "step": 179
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.248276903451171e-05,
+      "loss": 0.8276,
+      "step": 180
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.1485828503215585e-05,
+      "loss": 0.8111,
+      "step": 181
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.0501560098492056e-05,
+      "loss": 0.8084,
+      "step": 182
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.9530145866967895e-05,
+      "loss": 0.7886,
+      "step": 183
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.8571765477809643e-05,
+      "loss": 0.8145,
+      "step": 184
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.7626596189492983e-05,
+      "loss": 0.8078,
+      "step": 185
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.669481281701739e-05,
+      "loss": 0.817,
+      "step": 186
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.5776587699573006e-05,
+      "loss": 0.8176,
+      "step": 187
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.487209066866565e-05,
+      "loss": 0.8207,
+      "step": 188
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.3981489016705205e-05,
+      "loss": 0.7963,
+      "step": 189
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.3104947466063787e-05,
+      "loss": 0.8191,
+      "step": 190
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.2242628138609623e-05,
+      "loss": 0.7866,
+      "step": 191
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.139469052572127e-05,
+      "loss": 0.7864,
+      "step": 192
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.0561291458788733e-05,
+      "loss": 0.7627,
+      "step": 193
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.9742585080206755e-05,
+      "loss": 0.8242,
+      "step": 194
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.893872281486486e-05,
+      "loss": 0.7887,
+      "step": 195
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.8149853342140645e-05,
+      "loss": 0.8096,
+      "step": 196
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7376122568400532e-05,
+      "loss": 0.7973,
+      "step": 197
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6617673600013296e-05,
+      "loss": 0.8113,
+      "step": 198
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.587464671688187e-05,
+      "loss": 0.8113,
+      "step": 199
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.5147179346497664e-05,
+      "loss": 0.7999,
+      "step": 200
+    },
+    {
+      "epoch": 0.83,
+      "eval_loss": 0.7389363646507263,
+      "eval_runtime": 32.4951,
+      "eval_samples_per_second": 41.514,
+      "eval_steps_per_second": 41.514,
+      "step": 200
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.443540603852227e-05,
+      "loss": 0.8259,
+      "step": 201
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.373945843990192e-05,
+      "loss": 0.7476,
+      "step": 202
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3059465270518468e-05,
+      "loss": 0.8456,
+      "step": 203
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.2395552299381741e-05,
+      "loss": 0.7892,
+      "step": 204
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1747842321367886e-05,
+      "loss": 0.806,
+      "step": 205
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1116455134507664e-05,
+      "loss": 0.8261,
+      "step": 206
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0501507517829012e-05,
+      "loss": 0.7824,
+      "step": 207
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.903113209758096e-06,
+      "loss": 0.7844,
+      "step": 208
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.321382887082563e-06,
+      "loss": 0.8263,
+      "step": 209
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.756424144481312e-06,
+      "loss": 0.7956,
+      "step": 210
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.208341474624071e-06,
+      "loss": 0.7837,
+      "step": 211
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.677236248844855e-06,
+      "loss": 0.8052,
+      "step": 212
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.163206698392744e-06,
+      "loss": 0.7991,
+      "step": 213
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.666347896263325e-06,
+      "loss": 0.7617,
+      "step": 214
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.186751739614405e-06,
+      "loss": 0.7845,
+      "step": 215
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.724506932769014e-06,
+      "loss": 0.8269,
+      "step": 216
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.27969897080901e-06,
+      "loss": 0.7921,
+      "step": 217
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.8524101237621635e-06,
+      "loss": 0.7987,
+      "step": 218
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.442719421385922e-06,
+      "loss": 0.8054,
+      "step": 219
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.050702638550275e-06,
+      "loss": 0.8617,
+      "step": 220
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.6764322812226415e-06,
+      "loss": 0.7809,
+      "step": 221
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.319977573057642e-06,
+      "loss": 0.7665,
+      "step": 222
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.9814044425935606e-06,
+      "loss": 0.821,
+      "step": 223
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.6607755110584887e-06,
+      "loss": 0.8062,
+      "step": 224
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.3581500807882462e-06,
+      "loss": 0.8647,
+      "step": 225
+    },
+    {
+      "epoch": 0.93,
+      "eval_loss": 0.7371375560760498,
+      "eval_runtime": 32.4942,
+      "eval_samples_per_second": 41.515,
+      "eval_steps_per_second": 41.515,
+      "step": 225
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.073584124257899e-06,
+      "loss": 0.7942,
+      "step": 226
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.8071302737293295e-06,
+      "loss": 0.7546,
+      "step": 227
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.5588378115166669e-06,
+      "loss": 0.8232,
+      "step": 228
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.3287526608711131e-06,
+      "loss": 0.8385,
+      "step": 229
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1169173774871478e-06,
+      "loss": 0.8162,
+      "step": 230
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.233711416316571e-07,
+      "loss": 0.8246,
+      "step": 231
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.481497508972312e-07,
+      "loss": 0.7929,
+      "step": 232
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.912856135812051e-07,
+      "loss": 0.8086,
+      "step": 233
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.5280774269154115e-07,
+      "loss": 0.809,
+      "step": 234
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.3274175058067846e-07,
+      "loss": 0.8029,
+      "step": 235
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.311098442083659e-07,
+      "loss": 0.8179,
+      "step": 236
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.4793082103435885e-07,
+      "loss": 0.7883,
+      "step": 237
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 8.322006554171146e-08,
+      "loss": 0.8049,
+      "step": 238
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.6989546391297256e-08,
+      "loss": 0.7787,
+      "step": 239
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.24781420816867e-09,
+      "loss": 0.7801,
+      "step": 240
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 0.7948,
+      "step": 241
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 241,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 1.8452595906655027e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-241/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01fe87b2aca5e1c430604a86027ac937102b57790fef7a34f9b60c1a8cc201e9
+size 5240

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "bigcode/starcoder",
+  "activation_function": "gelu",
+  "architectures": [
+    "GPTBigCodeForCausalLM"
+  ],
+  "attention_softmax_in_fp32": true,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "inference_runner": 0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_batch_size": null,
+  "max_sequence_length": null,
+  "model_type": "gpt_bigcode",
+  "multi_query": true,
+  "n_embd": 6144,
+  "n_head": 48,
+  "n_inner": 24576,
+  "n_layer": 40,
+  "n_positions": 8192,
+  "pad_key_length": true,
+  "pre_allocate_kv_cache": false,
+  "resid_pdrop": 0.1,
+  "scale_attention_softmax_in_fp32": true,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0",
+  "use_cache": false,
+  "validate_runner_input": true,
+  "vocab_size": 49152
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,186 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}