Add files using upload-large-folder tool

README.md

@@ -1,3 +1,202 @@
----
-license: mit
----
+---
+base_model: naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-0.5B
+library_name: peft
+---
+
+# 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 0.15.2

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-0.5B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c55a734c5984211e0ca53d517c2555c9da07b10514f3d91090cb00bf01b0d7d9
+size 39366152

added_tokens.json

@@ -0,0 +1,35 @@
+{
+  "<EMAIL>": 110521,
+  "<KEY>": 110522,
+  "<NAME>": 110520,
+  "<PASSWORD>": 110523,
+  "<code_to_intermediate>": 110502,
+  "<empty_output>": 110501,
+  "<file_sep>": 110492,
+  "<intermediate_to_code>": 110503,
+  "<issue_closed>": 110495,
+  "<issue_comment>": 110494,
+  "<issue_start>": 110493,
+  "<jupyter_code>": 110498,
+  "<jupyter_output>": 110499,
+  "<jupyter_script>": 110500,
+  "<jupyter_start>": 110496,
+  "<jupyter_text>": 110497,
+  "<pr>": 110504,
+  "<pr_base>": 110507,
+  "<pr_base_code>": 110509,
+  "<pr_comment>": 110512,
+  "<pr_diff>": 110510,
+  "<pr_diff_hunk>": 110511,
+  "<pr_diff_hunk_comment_line>": 110519,
+  "<pr_event_id>": 110513,
+  "<pr_file>": 110508,
+  "<pr_in_reply_to_comment_id>": 110518,
+  "<pr_in_reply_to_review_id>": 110517,
+  "<pr_is_merged>": 110506,
+  "<pr_review>": 110514,
+  "<pr_review_comment>": 110516,
+  "<pr_review_state>": 110515,
+  "<pr_status>": 110505,
+  "<repo_name>": 110491
+}

chat_template.jinja

@@ -0,0 +1,4 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

checkpoint-1400/README.md

@@ -0,0 +1,202 @@
+---
+base_model: naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-0.5B
+library_name: peft
+---
+
+# 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 0.15.2

checkpoint-1400/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-0.5B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1400/added_tokens.json

@@ -0,0 +1,35 @@
+{
+  "<EMAIL>": 110521,
+  "<KEY>": 110522,
+  "<NAME>": 110520,
+  "<PASSWORD>": 110523,
+  "<code_to_intermediate>": 110502,
+  "<empty_output>": 110501,
+  "<file_sep>": 110492,
+  "<intermediate_to_code>": 110503,
+  "<issue_closed>": 110495,
+  "<issue_comment>": 110494,
+  "<issue_start>": 110493,
+  "<jupyter_code>": 110498,
+  "<jupyter_output>": 110499,
+  "<jupyter_script>": 110500,
+  "<jupyter_start>": 110496,
+  "<jupyter_text>": 110497,
+  "<pr>": 110504,
+  "<pr_base>": 110507,
+  "<pr_base_code>": 110509,
+  "<pr_comment>": 110512,
+  "<pr_diff>": 110510,
+  "<pr_diff_hunk>": 110511,
+  "<pr_diff_hunk_comment_line>": 110519,
+  "<pr_event_id>": 110513,
+  "<pr_file>": 110508,
+  "<pr_in_reply_to_comment_id>": 110518,
+  "<pr_in_reply_to_review_id>": 110517,
+  "<pr_is_merged>": 110506,
+  "<pr_review>": 110514,
+  "<pr_review_comment>": 110516,
+  "<pr_review_state>": 110515,
+  "<pr_status>": 110505,
+  "<repo_name>": 110491
+}

checkpoint-1400/chat_template.jinja

@@ -0,0 +1,4 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

checkpoint-1400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:234ba2ba854e17783128a343692bbffa9b7636ddfe7803957b3de9cafbbfa181
+size 14244

checkpoint-1400/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baba31a5e5063037a5c811de9cb04bc62c6c5f0f5fe6720b7d681afe6500d4c1
+size 988

checkpoint-1400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a99f5161179e9875eb1f7c51a56f0abffd0bb8aa424e3dd8b137233de0bb7117
+size 1064

checkpoint-1400/special_tokens_map.json

@@ -0,0 +1,86 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|endofprompt|>",
+    "<|_unuse_missing_100256|>",
+    "<|_unuse_missing_100261|>",
+    "<|_unuse_missing_100262|>",
+    "<|_unuse_missing_100263|>",
+    "<|_unuse_missing_100264|>",
+    "<|_unuse_missing_100265|>",
+    "<|_unuse_missing_100266|>",
+    "<|_unuse_missing_100267|>",
+    "<|_unuse_missing_100268|>",
+    "<|_unuse_missing_100269|>",
+    "<|_unuse_missing_100270|>",
+    "<|_unuse_missing_100271|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|stop|>",
+    "<|endofturn|>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endofturn|>",
+    "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
+  }
+}

checkpoint-1400/tokenizer_config.json

@@ -0,0 +1,501 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100256": {
+      "content": "<|_unuse_missing_100256|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100257": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100261": {
+      "content": "<|_unuse_missing_100261|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100262": {
+      "content": "<|_unuse_missing_100262|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100263": {
+      "content": "<|_unuse_missing_100263|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100264": {
+      "content": "<|_unuse_missing_100264|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|_unuse_missing_100265|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<|_unuse_missing_100266|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100267": {
+      "content": "<|_unuse_missing_100267|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100268": {
+      "content": "<|_unuse_missing_100268|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100269": {
+      "content": "<|_unuse_missing_100269|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100270": {
+      "content": "<|_unuse_missing_100270|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100271": {
+      "content": "<|_unuse_missing_100271|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100272": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100273": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100274": {
+      "content": "<|stop|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100275": {
+      "content": "<|endofturn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110491": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110492": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110493": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110494": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110495": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110496": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110497": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110498": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110499": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110500": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110501": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110502": {
+      "content": "<code_to_intermediate>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110503": {
+      "content": "<intermediate_to_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110504": {
+      "content": "<pr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110505": {
+      "content": "<pr_status>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110506": {
+      "content": "<pr_is_merged>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110507": {
+      "content": "<pr_base>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110508": {
+      "content": "<pr_file>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110509": {
+      "content": "<pr_base_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110510": {
+      "content": "<pr_diff>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110511": {
+      "content": "<pr_diff_hunk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110512": {
+      "content": "<pr_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110513": {
+      "content": "<pr_event_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110514": {
+      "content": "<pr_review>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110515": {
+      "content": "<pr_review_state>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110516": {
+      "content": "<pr_review_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110517": {
+      "content": "<pr_in_reply_to_review_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110518": {
+      "content": "<pr_in_reply_to_comment_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110519": {
+      "content": "<pr_diff_hunk_comment_line>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110520": {
+      "content": "<NAME>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110521": {
+      "content": "<EMAIL>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110522": {
+      "content": "<KEY>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110523": {
+      "content": "<PASSWORD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|endofprompt|>",
+    "<|_unuse_missing_100256|>",
+    "<|_unuse_missing_100261|>",
+    "<|_unuse_missing_100262|>",
+    "<|_unuse_missing_100263|>",
+    "<|_unuse_missing_100264|>",
+    "<|_unuse_missing_100265|>",
+    "<|_unuse_missing_100266|>",
+    "<|_unuse_missing_100267|>",
+    "<|_unuse_missing_100268|>",
+    "<|_unuse_missing_100269|>",
+    "<|_unuse_missing_100270|>",
+    "<|_unuse_missing_100271|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|stop|>",
+    "<|endofturn|>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endofturn|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-1400/trainer_state.json

@@ -0,0 +1,1364 @@
+{
+  "best_global_step": 1400,
+  "best_metric": 2.0077672004699707,
+  "best_model_checkpoint": "/content/drive/MyDrive/hyperclova-deobfuscation-lora/checkpoint-1400",
+  "epoch": 2.487111111111111,
+  "eval_steps": 200,
+  "global_step": 1400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.017777777777777778,
+      "grad_norm": 3.4749701023101807,
+      "learning_rate": 9e-06,
+      "loss": 4.1724,
+      "mean_token_accuracy": 0.3504906162619591,
+      "num_tokens": 22106.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 2.8458425998687744,
+      "learning_rate": 1.9e-05,
+      "loss": 3.9226,
+      "mean_token_accuracy": 0.3695666640996933,
+      "num_tokens": 44943.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 2.1938765048980713,
+      "learning_rate": 2.9e-05,
+      "loss": 3.6554,
+      "mean_token_accuracy": 0.4290380232036114,
+      "num_tokens": 67397.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 2.4278910160064697,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 3.303,
+      "mean_token_accuracy": 0.4723150283098221,
+      "num_tokens": 89803.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 1.7704142332077026,
+      "learning_rate": 4.9e-05,
+      "loss": 3.0041,
+      "mean_token_accuracy": 0.5115502133965493,
+      "num_tokens": 112364.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 1.5662821531295776,
+      "learning_rate": 5.9e-05,
+      "loss": 2.8013,
+      "mean_token_accuracy": 0.5329545043408871,
+      "num_tokens": 134028.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.12444444444444444,
+      "grad_norm": 1.5833848714828491,
+      "learning_rate": 6.9e-05,
+      "loss": 2.7291,
+      "mean_token_accuracy": 0.5422534577548503,
+      "num_tokens": 156703.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 1.8611595630645752,
+      "learning_rate": 7.900000000000001e-05,
+      "loss": 2.634,
+      "mean_token_accuracy": 0.5519127860665322,
+      "num_tokens": 178986.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.6170870065689087,
+      "learning_rate": 8.900000000000001e-05,
+      "loss": 2.6625,
+      "mean_token_accuracy": 0.5462300412356853,
+      "num_tokens": 201989.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 1.6247450113296509,
+      "learning_rate": 9.900000000000001e-05,
+      "loss": 2.5605,
+      "mean_token_accuracy": 0.5585827864706516,
+      "num_tokens": 223936.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.19555555555555557,
+      "grad_norm": 1.9383138418197632,
+      "learning_rate": 9.943360604153557e-05,
+      "loss": 2.5267,
+      "mean_token_accuracy": 0.563772913813591,
+      "num_tokens": 246101.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 1.875457763671875,
+      "learning_rate": 9.880427942101952e-05,
+      "loss": 2.5302,
+      "mean_token_accuracy": 0.562754824012518,
+      "num_tokens": 269187.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.2311111111111111,
+      "grad_norm": 1.6430569887161255,
+      "learning_rate": 9.817495280050347e-05,
+      "loss": 2.4479,
+      "mean_token_accuracy": 0.57414620667696,
+      "num_tokens": 291454.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 1.5991843938827515,
+      "learning_rate": 9.754562617998742e-05,
+      "loss": 2.4567,
+      "mean_token_accuracy": 0.5693153299391269,
+      "num_tokens": 314204.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 1.6487599611282349,
+      "learning_rate": 9.691629955947136e-05,
+      "loss": 2.4023,
+      "mean_token_accuracy": 0.5750032790005207,
+      "num_tokens": 337167.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 1.7035490274429321,
+      "learning_rate": 9.628697293895532e-05,
+      "loss": 2.4605,
+      "mean_token_accuracy": 0.5642550930380821,
+      "num_tokens": 360272.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.3022222222222222,
+      "grad_norm": 1.7211060523986816,
+      "learning_rate": 9.565764631843927e-05,
+      "loss": 2.3518,
+      "mean_token_accuracy": 0.5882908716797829,
+      "num_tokens": 382779.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.804926872253418,
+      "learning_rate": 9.502831969792323e-05,
+      "loss": 2.3712,
+      "mean_token_accuracy": 0.5805290326476097,
+      "num_tokens": 405438.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.3377777777777778,
+      "grad_norm": 1.849165678024292,
+      "learning_rate": 9.439899307740719e-05,
+      "loss": 2.4117,
+      "mean_token_accuracy": 0.5730262331664562,
+      "num_tokens": 428660.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 1.9137722253799438,
+      "learning_rate": 9.376966645689114e-05,
+      "loss": 2.3453,
+      "mean_token_accuracy": 0.5850483477115631,
+      "num_tokens": 450808.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "eval_loss": 2.345125436782837,
+      "eval_mean_token_accuracy": 0.5849845852851868,
+      "eval_num_tokens": 450808.0,
+      "eval_runtime": 30.3938,
+      "eval_samples_per_second": 32.901,
+      "eval_steps_per_second": 8.225,
+      "step": 200
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 1.7743253707885742,
+      "learning_rate": 9.314033983637508e-05,
+      "loss": 2.3494,
+      "mean_token_accuracy": 0.5811792358756065,
+      "num_tokens": 473434.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "grad_norm": 1.7797266244888306,
+      "learning_rate": 9.251101321585903e-05,
+      "loss": 2.3866,
+      "mean_token_accuracy": 0.5789428137242794,
+      "num_tokens": 496482.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.4088888888888889,
+      "grad_norm": 1.79751455783844,
+      "learning_rate": 9.188168659534298e-05,
+      "loss": 2.3453,
+      "mean_token_accuracy": 0.584120100736618,
+      "num_tokens": 519379.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 1.7770854234695435,
+      "learning_rate": 9.125235997482694e-05,
+      "loss": 2.355,
+      "mean_token_accuracy": 0.5805074371397495,
+      "num_tokens": 542631.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 1.7118644714355469,
+      "learning_rate": 9.06230333543109e-05,
+      "loss": 2.3288,
+      "mean_token_accuracy": 0.5817694693803788,
+      "num_tokens": 565400.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "grad_norm": 1.837351679801941,
+      "learning_rate": 8.999370673379485e-05,
+      "loss": 2.25,
+      "mean_token_accuracy": 0.594706054031849,
+      "num_tokens": 588003.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.8128186464309692,
+      "learning_rate": 8.93643801132788e-05,
+      "loss": 2.2712,
+      "mean_token_accuracy": 0.5904596522450447,
+      "num_tokens": 610974.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 1.8761178255081177,
+      "learning_rate": 8.873505349276275e-05,
+      "loss": 2.3144,
+      "mean_token_accuracy": 0.5835936337709426,
+      "num_tokens": 634093.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.5155555555555555,
+      "grad_norm": 1.7195324897766113,
+      "learning_rate": 8.81057268722467e-05,
+      "loss": 2.2206,
+      "mean_token_accuracy": 0.604982428252697,
+      "num_tokens": 656188.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 1.8294283151626587,
+      "learning_rate": 8.747640025173064e-05,
+      "loss": 2.255,
+      "mean_token_accuracy": 0.5953361228108406,
+      "num_tokens": 678769.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.5511111111111111,
+      "grad_norm": 1.7993453741073608,
+      "learning_rate": 8.68470736312146e-05,
+      "loss": 2.2312,
+      "mean_token_accuracy": 0.6017149150371551,
+      "num_tokens": 701734.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 1.7603346109390259,
+      "learning_rate": 8.621774701069856e-05,
+      "loss": 2.2124,
+      "mean_token_accuracy": 0.6003566391766071,
+      "num_tokens": 724815.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 1.7591211795806885,
+      "learning_rate": 8.558842039018251e-05,
+      "loss": 2.2208,
+      "mean_token_accuracy": 0.6021837159991265,
+      "num_tokens": 746903.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "grad_norm": 2.150559186935425,
+      "learning_rate": 8.495909376966647e-05,
+      "loss": 2.2122,
+      "mean_token_accuracy": 0.6015113711357116,
+      "num_tokens": 768982.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 1.6258208751678467,
+      "learning_rate": 8.432976714915042e-05,
+      "loss": 2.225,
+      "mean_token_accuracy": 0.6034559831023216,
+      "num_tokens": 791061.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.710488200187683,
+      "learning_rate": 8.370044052863437e-05,
+      "loss": 2.2123,
+      "mean_token_accuracy": 0.6031243965029717,
+      "num_tokens": 813112.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.6577777777777778,
+      "grad_norm": 1.9046748876571655,
+      "learning_rate": 8.307111390811831e-05,
+      "loss": 2.2185,
+      "mean_token_accuracy": 0.6007313683629036,
+      "num_tokens": 835469.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "grad_norm": 1.9116525650024414,
+      "learning_rate": 8.244178728760226e-05,
+      "loss": 2.2382,
+      "mean_token_accuracy": 0.5930798187851906,
+      "num_tokens": 857795.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 1.8034720420837402,
+      "learning_rate": 8.181246066708622e-05,
+      "loss": 2.191,
+      "mean_token_accuracy": 0.6052505746483803,
+      "num_tokens": 879659.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 1.8932994604110718,
+      "learning_rate": 8.118313404657017e-05,
+      "loss": 2.1755,
+      "mean_token_accuracy": 0.6076797977089882,
+      "num_tokens": 902240.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "eval_loss": 2.188769817352295,
+      "eval_mean_token_accuracy": 0.6060388499498367,
+      "eval_num_tokens": 902240.0,
+      "eval_runtime": 29.9448,
+      "eval_samples_per_second": 33.395,
+      "eval_steps_per_second": 8.349,
+      "step": 400
+    },
+    {
+      "epoch": 0.7288888888888889,
+      "grad_norm": 1.7485570907592773,
+      "learning_rate": 8.055380742605413e-05,
+      "loss": 2.2019,
+      "mean_token_accuracy": 0.6058685064315796,
+      "num_tokens": 925091.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 1.818544864654541,
+      "learning_rate": 7.992448080553809e-05,
+      "loss": 2.2313,
+      "mean_token_accuracy": 0.5964938789606095,
+      "num_tokens": 948151.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.7644444444444445,
+      "grad_norm": 1.796096682548523,
+      "learning_rate": 7.929515418502203e-05,
+      "loss": 2.141,
+      "mean_token_accuracy": 0.6135336428880691,
+      "num_tokens": 970339.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 1.7699111700057983,
+      "learning_rate": 7.866582756450598e-05,
+      "loss": 2.1904,
+      "mean_token_accuracy": 0.6022625803947449,
+      "num_tokens": 993552.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.906336784362793,
+      "learning_rate": 7.803650094398993e-05,
+      "loss": 2.2017,
+      "mean_token_accuracy": 0.602821895480156,
+      "num_tokens": 1015564.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.8177777777777778,
+      "grad_norm": 1.9261703491210938,
+      "learning_rate": 7.740717432347388e-05,
+      "loss": 2.1101,
+      "mean_token_accuracy": 0.6158386886119842,
+      "num_tokens": 1037721.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.8355555555555556,
+      "grad_norm": 1.7876946926116943,
+      "learning_rate": 7.677784770295784e-05,
+      "loss": 2.1866,
+      "mean_token_accuracy": 0.6046899721026421,
+      "num_tokens": 1060627.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 1.8447351455688477,
+      "learning_rate": 7.61485210824418e-05,
+      "loss": 2.1564,
+      "mean_token_accuracy": 0.6088386848568916,
+      "num_tokens": 1082672.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.8711111111111111,
+      "grad_norm": 1.7662327289581299,
+      "learning_rate": 7.551919446192575e-05,
+      "loss": 2.1566,
+      "mean_token_accuracy": 0.6086945086717606,
+      "num_tokens": 1104857.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.807004451751709,
+      "learning_rate": 7.48898678414097e-05,
+      "loss": 2.166,
+      "mean_token_accuracy": 0.605591855943203,
+      "num_tokens": 1127612.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 1.895982265472412,
+      "learning_rate": 7.426054122089365e-05,
+      "loss": 2.1645,
+      "mean_token_accuracy": 0.606428450345993,
+      "num_tokens": 1150411.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 1.8196443319320679,
+      "learning_rate": 7.36312146003776e-05,
+      "loss": 2.1878,
+      "mean_token_accuracy": 0.6036446511745452,
+      "num_tokens": 1172683.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.9422222222222222,
+      "grad_norm": 1.7809892892837524,
+      "learning_rate": 7.300188797986154e-05,
+      "loss": 2.0691,
+      "mean_token_accuracy": 0.6235968723893166,
+      "num_tokens": 1194160.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.774588704109192,
+      "learning_rate": 7.23725613593455e-05,
+      "loss": 2.1057,
+      "mean_token_accuracy": 0.6202786311507225,
+      "num_tokens": 1215760.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 1.8483060598373413,
+      "learning_rate": 7.174323473882946e-05,
+      "loss": 2.1634,
+      "mean_token_accuracy": 0.6098488807678223,
+      "num_tokens": 1238191.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "grad_norm": 1.9268509149551392,
+      "learning_rate": 7.111390811831341e-05,
+      "loss": 2.136,
+      "mean_token_accuracy": 0.6116517767310142,
+      "num_tokens": 1260429.0,
+      "step": 560
+    },
+    {
+      "epoch": 1.0124444444444445,
+      "grad_norm": 1.7296037673950195,
+      "learning_rate": 7.048458149779737e-05,
+      "loss": 2.0938,
+      "mean_token_accuracy": 0.6153759768134669,
+      "num_tokens": 1281232.0,
+      "step": 570
+    },
+    {
+      "epoch": 1.0302222222222222,
+      "grad_norm": 1.8975368738174438,
+      "learning_rate": 6.985525487728132e-05,
+      "loss": 2.0172,
+      "mean_token_accuracy": 0.6284284889698029,
+      "num_tokens": 1304130.0,
+      "step": 580
+    },
+    {
+      "epoch": 1.048,
+      "grad_norm": 1.8282201290130615,
+      "learning_rate": 6.922592825676527e-05,
+      "loss": 1.9979,
+      "mean_token_accuracy": 0.6334663733839989,
+      "num_tokens": 1326753.0,
+      "step": 590
+    },
+    {
+      "epoch": 1.0657777777777777,
+      "grad_norm": 1.7836159467697144,
+      "learning_rate": 6.859660163624921e-05,
+      "loss": 2.0058,
+      "mean_token_accuracy": 0.6304456666111946,
+      "num_tokens": 1348985.0,
+      "step": 600
+    },
+    {
+      "epoch": 1.0657777777777777,
+      "eval_loss": 2.114622116088867,
+      "eval_mean_token_accuracy": 0.6162020459175109,
+      "eval_num_tokens": 1348985.0,
+      "eval_runtime": 30.8226,
+      "eval_samples_per_second": 32.444,
+      "eval_steps_per_second": 8.111,
+      "step": 600
+    },
+    {
+      "epoch": 1.0835555555555556,
+      "grad_norm": 1.7529979944229126,
+      "learning_rate": 6.796727501573316e-05,
+      "loss": 2.0084,
+      "mean_token_accuracy": 0.6300177469849586,
+      "num_tokens": 1371318.0,
+      "step": 610
+    },
+    {
+      "epoch": 1.1013333333333333,
+      "grad_norm": 1.897518277168274,
+      "learning_rate": 6.733794839521712e-05,
+      "loss": 2.0348,
+      "mean_token_accuracy": 0.6270109280943871,
+      "num_tokens": 1393816.0,
+      "step": 620
+    },
+    {
+      "epoch": 1.1191111111111112,
+      "grad_norm": 1.9589266777038574,
+      "learning_rate": 6.670862177470107e-05,
+      "loss": 2.0377,
+      "mean_token_accuracy": 0.6255080983042717,
+      "num_tokens": 1416529.0,
+      "step": 630
+    },
+    {
+      "epoch": 1.1368888888888888,
+      "grad_norm": 1.933893084526062,
+      "learning_rate": 6.607929515418503e-05,
+      "loss": 2.0548,
+      "mean_token_accuracy": 0.6250210508704186,
+      "num_tokens": 1438970.0,
+      "step": 640
+    },
+    {
+      "epoch": 1.1546666666666667,
+      "grad_norm": 1.8967244625091553,
+      "learning_rate": 6.544996853366899e-05,
+      "loss": 2.0309,
+      "mean_token_accuracy": 0.6257808804512024,
+      "num_tokens": 1461324.0,
+      "step": 650
+    },
+    {
+      "epoch": 1.1724444444444444,
+      "grad_norm": 2.01849365234375,
+      "learning_rate": 6.482064191315293e-05,
+      "loss": 2.0737,
+      "mean_token_accuracy": 0.6156815335154533,
+      "num_tokens": 1484246.0,
+      "step": 660
+    },
+    {
+      "epoch": 1.1902222222222223,
+      "grad_norm": 1.8661456108093262,
+      "learning_rate": 6.419131529263688e-05,
+      "loss": 2.0632,
+      "mean_token_accuracy": 0.6184948399662972,
+      "num_tokens": 1507305.0,
+      "step": 670
+    },
+    {
+      "epoch": 1.208,
+      "grad_norm": 1.8781774044036865,
+      "learning_rate": 6.356198867212083e-05,
+      "loss": 2.0029,
+      "mean_token_accuracy": 0.6336544677615166,
+      "num_tokens": 1529082.0,
+      "step": 680
+    },
+    {
+      "epoch": 1.2257777777777779,
+      "grad_norm": 1.8406771421432495,
+      "learning_rate": 6.293266205160478e-05,
+      "loss": 2.0102,
+      "mean_token_accuracy": 0.6291820913553238,
+      "num_tokens": 1551159.0,
+      "step": 690
+    },
+    {
+      "epoch": 1.2435555555555555,
+      "grad_norm": 1.829233169555664,
+      "learning_rate": 6.230333543108874e-05,
+      "loss": 2.0396,
+      "mean_token_accuracy": 0.6300060883164406,
+      "num_tokens": 1573348.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.2613333333333334,
+      "grad_norm": 1.9671298265457153,
+      "learning_rate": 6.167400881057269e-05,
+      "loss": 2.0326,
+      "mean_token_accuracy": 0.6287923157215118,
+      "num_tokens": 1595989.0,
+      "step": 710
+    },
+    {
+      "epoch": 1.279111111111111,
+      "grad_norm": 2.0840771198272705,
+      "learning_rate": 6.104468219005665e-05,
+      "loss": 2.0659,
+      "mean_token_accuracy": 0.628783118724823,
+      "num_tokens": 1617895.0,
+      "step": 720
+    },
+    {
+      "epoch": 1.2968888888888888,
+      "grad_norm": 2.056278944015503,
+      "learning_rate": 6.04153555695406e-05,
+      "loss": 2.0177,
+      "mean_token_accuracy": 0.627280455827713,
+      "num_tokens": 1640415.0,
+      "step": 730
+    },
+    {
+      "epoch": 1.3146666666666667,
+      "grad_norm": 1.9183000326156616,
+      "learning_rate": 5.978602894902454e-05,
+      "loss": 1.9958,
+      "mean_token_accuracy": 0.631256802380085,
+      "num_tokens": 1662713.0,
+      "step": 740
+    },
+    {
+      "epoch": 1.3324444444444445,
+      "grad_norm": 2.005032777786255,
+      "learning_rate": 5.9156702328508496e-05,
+      "loss": 2.0164,
+      "mean_token_accuracy": 0.631276798248291,
+      "num_tokens": 1684783.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.3502222222222222,
+      "grad_norm": 1.8667700290679932,
+      "learning_rate": 5.852737570799245e-05,
+      "loss": 2.0295,
+      "mean_token_accuracy": 0.6288824707269669,
+      "num_tokens": 1706623.0,
+      "step": 760
+    },
+    {
+      "epoch": 1.3679999999999999,
+      "grad_norm": 2.123706817626953,
+      "learning_rate": 5.78980490874764e-05,
+      "loss": 2.0513,
+      "mean_token_accuracy": 0.6215401113033294,
+      "num_tokens": 1729494.0,
+      "step": 770
+    },
+    {
+      "epoch": 1.3857777777777778,
+      "grad_norm": 1.9470572471618652,
+      "learning_rate": 5.7268722466960356e-05,
+      "loss": 2.0179,
+      "mean_token_accuracy": 0.630026438832283,
+      "num_tokens": 1752045.0,
+      "step": 780
+    },
+    {
+      "epoch": 1.4035555555555557,
+      "grad_norm": 1.8666447401046753,
+      "learning_rate": 5.663939584644431e-05,
+      "loss": 2.035,
+      "mean_token_accuracy": 0.6255004242062568,
+      "num_tokens": 1775601.0,
+      "step": 790
+    },
+    {
+      "epoch": 1.4213333333333333,
+      "grad_norm": 1.8963086605072021,
+      "learning_rate": 5.601006922592826e-05,
+      "loss": 2.0004,
+      "mean_token_accuracy": 0.6287154361605645,
+      "num_tokens": 1798633.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.4213333333333333,
+      "eval_loss": 2.071798324584961,
+      "eval_mean_token_accuracy": 0.6222149915695191,
+      "eval_num_tokens": 1798633.0,
+      "eval_runtime": 30.3161,
+      "eval_samples_per_second": 32.986,
+      "eval_steps_per_second": 8.246,
+      "step": 800
+    },
+    {
+      "epoch": 1.439111111111111,
+      "grad_norm": 1.9529728889465332,
+      "learning_rate": 5.5380742605412216e-05,
+      "loss": 1.9781,
+      "mean_token_accuracy": 0.6329582959413529,
+      "num_tokens": 1820656.0,
+      "step": 810
+    },
+    {
+      "epoch": 1.456888888888889,
+      "grad_norm": 1.9527575969696045,
+      "learning_rate": 5.475141598489616e-05,
+      "loss": 2.0212,
+      "mean_token_accuracy": 0.6298958778381347,
+      "num_tokens": 1842871.0,
+      "step": 820
+    },
+    {
+      "epoch": 1.4746666666666668,
+      "grad_norm": 1.7937837839126587,
+      "learning_rate": 5.4122089364380114e-05,
+      "loss": 1.9904,
+      "mean_token_accuracy": 0.635308350622654,
+      "num_tokens": 1865652.0,
+      "step": 830
+    },
+    {
+      "epoch": 1.4924444444444445,
+      "grad_norm": 1.888289213180542,
+      "learning_rate": 5.349276274386407e-05,
+      "loss": 2.0129,
+      "mean_token_accuracy": 0.6266900539398194,
+      "num_tokens": 1888455.0,
+      "step": 840
+    },
+    {
+      "epoch": 1.5102222222222221,
+      "grad_norm": 2.0203657150268555,
+      "learning_rate": 5.286343612334802e-05,
+      "loss": 1.9766,
+      "mean_token_accuracy": 0.6383475095033646,
+      "num_tokens": 1910676.0,
+      "step": 850
+    },
+    {
+      "epoch": 1.528,
+      "grad_norm": 2.0756003856658936,
+      "learning_rate": 5.2234109502831975e-05,
+      "loss": 2.0257,
+      "mean_token_accuracy": 0.6280800834298134,
+      "num_tokens": 1933253.0,
+      "step": 860
+    },
+    {
+      "epoch": 1.545777777777778,
+      "grad_norm": 2.112074375152588,
+      "learning_rate": 5.160478288231593e-05,
+      "loss": 2.0314,
+      "mean_token_accuracy": 0.6242304086685181,
+      "num_tokens": 1955820.0,
+      "step": 870
+    },
+    {
+      "epoch": 1.5635555555555556,
+      "grad_norm": 1.9367856979370117,
+      "learning_rate": 5.097545626179988e-05,
+      "loss": 2.0112,
+      "mean_token_accuracy": 0.6305277988314628,
+      "num_tokens": 1978120.0,
+      "step": 880
+    },
+    {
+      "epoch": 1.5813333333333333,
+      "grad_norm": 1.991443395614624,
+      "learning_rate": 5.034612964128382e-05,
+      "loss": 1.9569,
+      "mean_token_accuracy": 0.6372233361005784,
+      "num_tokens": 2000508.0,
+      "step": 890
+    },
+    {
+      "epoch": 1.5991111111111111,
+      "grad_norm": 1.8759173154830933,
+      "learning_rate": 4.9716803020767784e-05,
+      "loss": 1.9894,
+      "mean_token_accuracy": 0.6314782112836838,
+      "num_tokens": 2023356.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.616888888888889,
+      "grad_norm": 1.8218945264816284,
+      "learning_rate": 4.908747640025173e-05,
+      "loss": 1.9459,
+      "mean_token_accuracy": 0.6442534357309342,
+      "num_tokens": 2045965.0,
+      "step": 910
+    },
+    {
+      "epoch": 1.6346666666666667,
+      "grad_norm": 1.9485502243041992,
+      "learning_rate": 4.845814977973568e-05,
+      "loss": 2.0177,
+      "mean_token_accuracy": 0.6231269478797913,
+      "num_tokens": 2069108.0,
+      "step": 920
+    },
+    {
+      "epoch": 1.6524444444444444,
+      "grad_norm": 1.9244948625564575,
+      "learning_rate": 4.782882315921964e-05,
+      "loss": 2.0259,
+      "mean_token_accuracy": 0.6279663592576981,
+      "num_tokens": 2091755.0,
+      "step": 930
+    },
+    {
+      "epoch": 1.6702222222222223,
+      "grad_norm": 1.9663888216018677,
+      "learning_rate": 4.719949653870359e-05,
+      "loss": 1.9896,
+      "mean_token_accuracy": 0.6341330617666244,
+      "num_tokens": 2114496.0,
+      "step": 940
+    },
+    {
+      "epoch": 1.688,
+      "grad_norm": 1.9700689315795898,
+      "learning_rate": 4.657016991818754e-05,
+      "loss": 2.0081,
+      "mean_token_accuracy": 0.629092475771904,
+      "num_tokens": 2137041.0,
+      "step": 950
+    },
+    {
+      "epoch": 1.7057777777777776,
+      "grad_norm": 1.9976369142532349,
+      "learning_rate": 4.594084329767149e-05,
+      "loss": 2.0177,
+      "mean_token_accuracy": 0.6279423177242279,
+      "num_tokens": 2159711.0,
+      "step": 960
+    },
+    {
+      "epoch": 1.7235555555555555,
+      "grad_norm": 1.9927507638931274,
+      "learning_rate": 4.531151667715545e-05,
+      "loss": 2.0111,
+      "mean_token_accuracy": 0.632372610270977,
+      "num_tokens": 2181675.0,
+      "step": 970
+    },
+    {
+      "epoch": 1.7413333333333334,
+      "grad_norm": 1.9318374395370483,
+      "learning_rate": 4.46821900566394e-05,
+      "loss": 1.9772,
+      "mean_token_accuracy": 0.6370243668556214,
+      "num_tokens": 2204671.0,
+      "step": 980
+    },
+    {
+      "epoch": 1.759111111111111,
+      "grad_norm": 1.8933532238006592,
+      "learning_rate": 4.405286343612335e-05,
+      "loss": 2.0098,
+      "mean_token_accuracy": 0.6229412123560906,
+      "num_tokens": 2227866.0,
+      "step": 990
+    },
+    {
+      "epoch": 1.7768888888888887,
+      "grad_norm": 2.063185930252075,
+      "learning_rate": 4.34235368156073e-05,
+      "loss": 1.9801,
+      "mean_token_accuracy": 0.6361721217632293,
+      "num_tokens": 2250379.0,
+      "step": 1000
+    },
+    {
+      "epoch": 1.7768888888888887,
+      "eval_loss": 2.036764621734619,
+      "eval_mean_token_accuracy": 0.6262071034908294,
+      "eval_num_tokens": 2250379.0,
+      "eval_runtime": 31.2979,
+      "eval_samples_per_second": 31.951,
+      "eval_steps_per_second": 7.988,
+      "step": 1000
+    },
+    {
+      "epoch": 1.7946666666666666,
+      "grad_norm": 1.9427729845046997,
+      "learning_rate": 4.2794210195091256e-05,
+      "loss": 2.0155,
+      "mean_token_accuracy": 0.6281099706888199,
+      "num_tokens": 2272999.0,
+      "step": 1010
+    },
+    {
+      "epoch": 1.8124444444444445,
+      "grad_norm": 1.842465877532959,
+      "learning_rate": 4.216488357457521e-05,
+      "loss": 1.9861,
+      "mean_token_accuracy": 0.6330478996038437,
+      "num_tokens": 2295110.0,
+      "step": 1020
+    },
+    {
+      "epoch": 1.8302222222222222,
+      "grad_norm": 1.8547931909561157,
+      "learning_rate": 4.1535556954059154e-05,
+      "loss": 1.9617,
+      "mean_token_accuracy": 0.6373973488807678,
+      "num_tokens": 2317432.0,
+      "step": 1030
+    },
+    {
+      "epoch": 1.8479999999999999,
+      "grad_norm": 1.8283085823059082,
+      "learning_rate": 4.090623033354311e-05,
+      "loss": 1.9987,
+      "mean_token_accuracy": 0.6286273017525673,
+      "num_tokens": 2340305.0,
+      "step": 1040
+    },
+    {
+      "epoch": 1.8657777777777778,
+      "grad_norm": 1.9289031028747559,
+      "learning_rate": 4.0276903713027065e-05,
+      "loss": 2.0035,
+      "mean_token_accuracy": 0.6320135101675988,
+      "num_tokens": 2362746.0,
+      "step": 1050
+    },
+    {
+      "epoch": 1.8835555555555556,
+      "grad_norm": 1.8411505222320557,
+      "learning_rate": 3.9647577092511014e-05,
+      "loss": 1.9697,
+      "mean_token_accuracy": 0.6332684755325317,
+      "num_tokens": 2385647.0,
+      "step": 1060
+    },
+    {
+      "epoch": 1.9013333333333333,
+      "grad_norm": 2.0083494186401367,
+      "learning_rate": 3.901825047199496e-05,
+      "loss": 1.987,
+      "mean_token_accuracy": 0.627101382613182,
+      "num_tokens": 2408732.0,
+      "step": 1070
+    },
+    {
+      "epoch": 1.919111111111111,
+      "grad_norm": 2.150812864303589,
+      "learning_rate": 3.838892385147892e-05,
+      "loss": 1.9642,
+      "mean_token_accuracy": 0.6350547641515731,
+      "num_tokens": 2431137.0,
+      "step": 1080
+    },
+    {
+      "epoch": 1.9368888888888889,
+      "grad_norm": 1.9779438972473145,
+      "learning_rate": 3.7759597230962874e-05,
+      "loss": 1.9249,
+      "mean_token_accuracy": 0.6438971221446991,
+      "num_tokens": 2453517.0,
+      "step": 1090
+    },
+    {
+      "epoch": 1.9546666666666668,
+      "grad_norm": 2.0672504901885986,
+      "learning_rate": 3.7130270610446823e-05,
+      "loss": 1.9679,
+      "mean_token_accuracy": 0.6345437586307525,
+      "num_tokens": 2475737.0,
+      "step": 1100
+    },
+    {
+      "epoch": 1.9724444444444444,
+      "grad_norm": 1.9778350591659546,
+      "learning_rate": 3.650094398993077e-05,
+      "loss": 1.9733,
+      "mean_token_accuracy": 0.6329764410853386,
+      "num_tokens": 2497880.0,
+      "step": 1110
+    },
+    {
+      "epoch": 1.9902222222222221,
+      "grad_norm": 2.014357328414917,
+      "learning_rate": 3.587161736941473e-05,
+      "loss": 1.9714,
+      "mean_token_accuracy": 0.635537999868393,
+      "num_tokens": 2519974.0,
+      "step": 1120
+    },
+    {
+      "epoch": 2.007111111111111,
+      "grad_norm": 1.9104490280151367,
+      "learning_rate": 3.5242290748898684e-05,
+      "loss": 1.8849,
+      "mean_token_accuracy": 0.6536890221269507,
+      "num_tokens": 2540296.0,
+      "step": 1130
+    },
+    {
+      "epoch": 2.024888888888889,
+      "grad_norm": 2.0223166942596436,
+      "learning_rate": 3.461296412838263e-05,
+      "loss": 1.8811,
+      "mean_token_accuracy": 0.6483465373516083,
+      "num_tokens": 2561919.0,
+      "step": 1140
+    },
+    {
+      "epoch": 2.042666666666667,
+      "grad_norm": 1.8120856285095215,
+      "learning_rate": 3.398363750786658e-05,
+      "loss": 1.9212,
+      "mean_token_accuracy": 0.6420063003897667,
+      "num_tokens": 2584915.0,
+      "step": 1150
+    },
+    {
+      "epoch": 2.0604444444444443,
+      "grad_norm": 1.9729136228561401,
+      "learning_rate": 3.335431088735054e-05,
+      "loss": 1.8851,
+      "mean_token_accuracy": 0.6519104614853859,
+      "num_tokens": 2606857.0,
+      "step": 1160
+    },
+    {
+      "epoch": 2.078222222222222,
+      "grad_norm": 2.1263654232025146,
+      "learning_rate": 3.272498426683449e-05,
+      "loss": 1.8905,
+      "mean_token_accuracy": 0.6453483879566193,
+      "num_tokens": 2629737.0,
+      "step": 1170
+    },
+    {
+      "epoch": 2.096,
+      "grad_norm": 1.9857081174850464,
+      "learning_rate": 3.209565764631844e-05,
+      "loss": 1.8381,
+      "mean_token_accuracy": 0.653864786028862,
+      "num_tokens": 2651936.0,
+      "step": 1180
+    },
+    {
+      "epoch": 2.113777777777778,
+      "grad_norm": 1.9701604843139648,
+      "learning_rate": 3.146633102580239e-05,
+      "loss": 1.9133,
+      "mean_token_accuracy": 0.6435931533575058,
+      "num_tokens": 2675241.0,
+      "step": 1190
+    },
+    {
+      "epoch": 2.1315555555555554,
+      "grad_norm": 1.9061148166656494,
+      "learning_rate": 3.0837004405286347e-05,
+      "loss": 1.8832,
+      "mean_token_accuracy": 0.6495110660791397,
+      "num_tokens": 2698219.0,
+      "step": 1200
+    },
+    {
+      "epoch": 2.1315555555555554,
+      "eval_loss": 2.020338296890259,
+      "eval_mean_token_accuracy": 0.6295755279064178,
+      "eval_num_tokens": 2698219.0,
+      "eval_runtime": 30.7487,
+      "eval_samples_per_second": 32.522,
+      "eval_steps_per_second": 8.13,
+      "step": 1200
+    },
+    {
+      "epoch": 2.1493333333333333,
+      "grad_norm": 2.1164379119873047,
+      "learning_rate": 3.02076777847703e-05,
+      "loss": 1.8986,
+      "mean_token_accuracy": 0.6449921384453774,
+      "num_tokens": 2721580.0,
+      "step": 1210
+    },
+    {
+      "epoch": 2.167111111111111,
+      "grad_norm": 1.9740287065505981,
+      "learning_rate": 2.9578351164254248e-05,
+      "loss": 1.8953,
+      "mean_token_accuracy": 0.648700350522995,
+      "num_tokens": 2744110.0,
+      "step": 1220
+    },
+    {
+      "epoch": 2.1848888888888887,
+      "grad_norm": 1.9970844984054565,
+      "learning_rate": 2.89490245437382e-05,
+      "loss": 1.8693,
+      "mean_token_accuracy": 0.6546828895807266,
+      "num_tokens": 2765844.0,
+      "step": 1230
+    },
+    {
+      "epoch": 2.2026666666666666,
+      "grad_norm": 2.06357479095459,
+      "learning_rate": 2.8319697923222156e-05,
+      "loss": 1.8775,
+      "mean_token_accuracy": 0.6484791278839112,
+      "num_tokens": 2788070.0,
+      "step": 1240
+    },
+    {
+      "epoch": 2.2204444444444444,
+      "grad_norm": 1.9746241569519043,
+      "learning_rate": 2.7690371302706108e-05,
+      "loss": 1.9117,
+      "mean_token_accuracy": 0.6470579236745835,
+      "num_tokens": 2810964.0,
+      "step": 1250
+    },
+    {
+      "epoch": 2.2382222222222223,
+      "grad_norm": 2.1169064044952393,
+      "learning_rate": 2.7061044682190057e-05,
+      "loss": 1.8684,
+      "mean_token_accuracy": 0.6524357482790947,
+      "num_tokens": 2833176.0,
+      "step": 1260
+    },
+    {
+      "epoch": 2.2560000000000002,
+      "grad_norm": 2.0234525203704834,
+      "learning_rate": 2.643171806167401e-05,
+      "loss": 1.9089,
+      "mean_token_accuracy": 0.6425125360488891,
+      "num_tokens": 2855440.0,
+      "step": 1270
+    },
+    {
+      "epoch": 2.2737777777777777,
+      "grad_norm": 2.0508742332458496,
+      "learning_rate": 2.5802391441157965e-05,
+      "loss": 1.8463,
+      "mean_token_accuracy": 0.6541648581624031,
+      "num_tokens": 2877713.0,
+      "step": 1280
+    },
+    {
+      "epoch": 2.2915555555555556,
+      "grad_norm": 1.863732099533081,
+      "learning_rate": 2.517306482064191e-05,
+      "loss": 1.8953,
+      "mean_token_accuracy": 0.6487652212381363,
+      "num_tokens": 2899934.0,
+      "step": 1290
+    },
+    {
+      "epoch": 2.3093333333333335,
+      "grad_norm": 2.148881196975708,
+      "learning_rate": 2.4543738200125866e-05,
+      "loss": 1.8937,
+      "mean_token_accuracy": 0.6466890797019005,
+      "num_tokens": 2923244.0,
+      "step": 1300
+    },
+    {
+      "epoch": 2.327111111111111,
+      "grad_norm": 2.0562210083007812,
+      "learning_rate": 2.391441157960982e-05,
+      "loss": 1.8776,
+      "mean_token_accuracy": 0.648098886013031,
+      "num_tokens": 2945580.0,
+      "step": 1310
+    },
+    {
+      "epoch": 2.344888888888889,
+      "grad_norm": 1.9801143407821655,
+      "learning_rate": 2.328508495909377e-05,
+      "loss": 1.8718,
+      "mean_token_accuracy": 0.6436786696314811,
+      "num_tokens": 2969470.0,
+      "step": 1320
+    },
+    {
+      "epoch": 2.3626666666666667,
+      "grad_norm": 2.244140863418579,
+      "learning_rate": 2.2655758338577723e-05,
+      "loss": 1.871,
+      "mean_token_accuracy": 0.6460510939359665,
+      "num_tokens": 2991982.0,
+      "step": 1330
+    },
+    {
+      "epoch": 2.3804444444444446,
+      "grad_norm": 1.993152379989624,
+      "learning_rate": 2.2026431718061676e-05,
+      "loss": 1.8909,
+      "mean_token_accuracy": 0.6495360463857651,
+      "num_tokens": 3014206.0,
+      "step": 1340
+    },
+    {
+      "epoch": 2.398222222222222,
+      "grad_norm": 1.974604606628418,
+      "learning_rate": 2.1397105097545628e-05,
+      "loss": 1.843,
+      "mean_token_accuracy": 0.6507977247238159,
+      "num_tokens": 3036651.0,
+      "step": 1350
+    },
+    {
+      "epoch": 2.416,
+      "grad_norm": 1.9981292486190796,
+      "learning_rate": 2.0767778477029577e-05,
+      "loss": 1.8775,
+      "mean_token_accuracy": 0.6513748601078987,
+      "num_tokens": 3058745.0,
+      "step": 1360
+    },
+    {
+      "epoch": 2.433777777777778,
+      "grad_norm": 2.1414084434509277,
+      "learning_rate": 2.0138451856513533e-05,
+      "loss": 1.8904,
+      "mean_token_accuracy": 0.6470720157027244,
+      "num_tokens": 3081726.0,
+      "step": 1370
+    },
+    {
+      "epoch": 2.4515555555555557,
+      "grad_norm": 2.157397747039795,
+      "learning_rate": 1.950912523599748e-05,
+      "loss": 1.8711,
+      "mean_token_accuracy": 0.6492032095789909,
+      "num_tokens": 3104292.0,
+      "step": 1380
+    },
+    {
+      "epoch": 2.469333333333333,
+      "grad_norm": 2.0714213848114014,
+      "learning_rate": 1.8879798615481437e-05,
+      "loss": 1.8845,
+      "mean_token_accuracy": 0.6478913977742196,
+      "num_tokens": 3126334.0,
+      "step": 1390
+    },
+    {
+      "epoch": 2.487111111111111,
+      "grad_norm": 2.1000311374664307,
+      "learning_rate": 1.8250471994965386e-05,
+      "loss": 1.9088,
+      "mean_token_accuracy": 0.6414603188633918,
+      "num_tokens": 3149845.0,
+      "step": 1400
+    },
+    {
+      "epoch": 2.487111111111111,
+      "eval_loss": 2.0077672004699707,
+      "eval_mean_token_accuracy": 0.63226633644104,
+      "eval_num_tokens": 3149845.0,
+      "eval_runtime": 30.4714,
+      "eval_samples_per_second": 32.818,
+      "eval_steps_per_second": 8.204,
+      "step": 1400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1689,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1090406995533824e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eceb4430d91d4336dfb8665bee3ec27bf48bbaee43f0bde2d77c967c54bed50b
+size 5624

checkpoint-1600/README.md

@@ -0,0 +1,202 @@
+---
+base_model: naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-0.5B
+library_name: peft
+---
+
+# 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 0.15.2

checkpoint-1600/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-0.5B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1600/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c55a734c5984211e0ca53d517c2555c9da07b10514f3d91090cb00bf01b0d7d9
+size 39366152

checkpoint-1600/added_tokens.json

@@ -0,0 +1,35 @@
+{
+  "<EMAIL>": 110521,
+  "<KEY>": 110522,
+  "<NAME>": 110520,
+  "<PASSWORD>": 110523,
+  "<code_to_intermediate>": 110502,
+  "<empty_output>": 110501,
+  "<file_sep>": 110492,
+  "<intermediate_to_code>": 110503,
+  "<issue_closed>": 110495,
+  "<issue_comment>": 110494,
+  "<issue_start>": 110493,
+  "<jupyter_code>": 110498,
+  "<jupyter_output>": 110499,
+  "<jupyter_script>": 110500,
+  "<jupyter_start>": 110496,
+  "<jupyter_text>": 110497,
+  "<pr>": 110504,
+  "<pr_base>": 110507,
+  "<pr_base_code>": 110509,
+  "<pr_comment>": 110512,
+  "<pr_diff>": 110510,
+  "<pr_diff_hunk>": 110511,
+  "<pr_diff_hunk_comment_line>": 110519,
+  "<pr_event_id>": 110513,
+  "<pr_file>": 110508,
+  "<pr_in_reply_to_comment_id>": 110518,
+  "<pr_in_reply_to_review_id>": 110517,
+  "<pr_is_merged>": 110506,
+  "<pr_review>": 110514,
+  "<pr_review_comment>": 110516,
+  "<pr_review_state>": 110515,
+  "<pr_status>": 110505,
+  "<repo_name>": 110491
+}

checkpoint-1600/chat_template.jinja

@@ -0,0 +1,4 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

checkpoint-1600/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1b428ae58168f86e967bd5b1dbcf44997a0624fd2ad300fb0174bcd12f6a6c0
+size 78925378

checkpoint-1600/special_tokens_map.json

@@ -0,0 +1,86 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|endofprompt|>",
+    "<|_unuse_missing_100256|>",
+    "<|_unuse_missing_100261|>",
+    "<|_unuse_missing_100262|>",
+    "<|_unuse_missing_100263|>",
+    "<|_unuse_missing_100264|>",
+    "<|_unuse_missing_100265|>",
+    "<|_unuse_missing_100266|>",
+    "<|_unuse_missing_100267|>",
+    "<|_unuse_missing_100268|>",
+    "<|_unuse_missing_100269|>",
+    "<|_unuse_missing_100270|>",
+    "<|_unuse_missing_100271|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|stop|>",
+    "<|endofturn|>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endofturn|>",
+    "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
+  }
+}

checkpoint-1600/tokenizer_config.json

@@ -0,0 +1,501 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100256": {
+      "content": "<|_unuse_missing_100256|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100257": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100261": {
+      "content": "<|_unuse_missing_100261|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100262": {
+      "content": "<|_unuse_missing_100262|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100263": {
+      "content": "<|_unuse_missing_100263|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100264": {
+      "content": "<|_unuse_missing_100264|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|_unuse_missing_100265|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<|_unuse_missing_100266|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100267": {
+      "content": "<|_unuse_missing_100267|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100268": {
+      "content": "<|_unuse_missing_100268|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100269": {
+      "content": "<|_unuse_missing_100269|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100270": {
+      "content": "<|_unuse_missing_100270|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100271": {
+      "content": "<|_unuse_missing_100271|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100272": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100273": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100274": {
+      "content": "<|stop|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100275": {
+      "content": "<|endofturn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110491": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110492": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110493": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110494": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110495": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110496": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110497": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110498": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110499": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110500": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110501": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110502": {
+      "content": "<code_to_intermediate>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110503": {
+      "content": "<intermediate_to_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110504": {
+      "content": "<pr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110505": {
+      "content": "<pr_status>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110506": {
+      "content": "<pr_is_merged>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110507": {
+      "content": "<pr_base>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110508": {
+      "content": "<pr_file>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110509": {
+      "content": "<pr_base_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110510": {
+      "content": "<pr_diff>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110511": {
+      "content": "<pr_diff_hunk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110512": {
+      "content": "<pr_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110513": {
+      "content": "<pr_event_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110514": {
+      "content": "<pr_review>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110515": {
+      "content": "<pr_review_state>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110516": {
+      "content": "<pr_review_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110517": {
+      "content": "<pr_in_reply_to_review_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110518": {
+      "content": "<pr_in_reply_to_comment_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110519": {
+      "content": "<pr_diff_hunk_comment_line>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110520": {
+      "content": "<NAME>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110521": {
+      "content": "<EMAIL>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110522": {
+      "content": "<KEY>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110523": {
+      "content": "<PASSWORD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|endofprompt|>",
+    "<|_unuse_missing_100256|>",
+    "<|_unuse_missing_100261|>",
+    "<|_unuse_missing_100262|>",
+    "<|_unuse_missing_100263|>",
+    "<|_unuse_missing_100264|>",
+    "<|_unuse_missing_100265|>",
+    "<|_unuse_missing_100266|>",
+    "<|_unuse_missing_100267|>",
+    "<|_unuse_missing_100268|>",
+    "<|_unuse_missing_100269|>",
+    "<|_unuse_missing_100270|>",
+    "<|_unuse_missing_100271|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|stop|>",
+    "<|endofturn|>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endofturn|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-1600/trainer_state.json

@@ -0,0 +1,1554 @@
+{
+  "best_global_step": 1600,
+  "best_metric": 1.9988627433776855,
+  "best_model_checkpoint": "/content/drive/MyDrive/hyperclova-deobfuscation-lora/checkpoint-1600",
+  "epoch": 2.8426666666666667,
+  "eval_steps": 200,
+  "global_step": 1600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.017777777777777778,
+      "grad_norm": 3.4749701023101807,
+      "learning_rate": 9e-06,
+      "loss": 4.1724,
+      "mean_token_accuracy": 0.3504906162619591,
+      "num_tokens": 22106.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 2.8458425998687744,
+      "learning_rate": 1.9e-05,
+      "loss": 3.9226,
+      "mean_token_accuracy": 0.3695666640996933,
+      "num_tokens": 44943.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 2.1938765048980713,
+      "learning_rate": 2.9e-05,
+      "loss": 3.6554,
+      "mean_token_accuracy": 0.4290380232036114,
+      "num_tokens": 67397.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 2.4278910160064697,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 3.303,
+      "mean_token_accuracy": 0.4723150283098221,
+      "num_tokens": 89803.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 1.7704142332077026,
+      "learning_rate": 4.9e-05,
+      "loss": 3.0041,
+      "mean_token_accuracy": 0.5115502133965493,
+      "num_tokens": 112364.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 1.5662821531295776,
+      "learning_rate": 5.9e-05,
+      "loss": 2.8013,
+      "mean_token_accuracy": 0.5329545043408871,
+      "num_tokens": 134028.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.12444444444444444,
+      "grad_norm": 1.5833848714828491,
+      "learning_rate": 6.9e-05,
+      "loss": 2.7291,
+      "mean_token_accuracy": 0.5422534577548503,
+      "num_tokens": 156703.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 1.8611595630645752,
+      "learning_rate": 7.900000000000001e-05,
+      "loss": 2.634,
+      "mean_token_accuracy": 0.5519127860665322,
+      "num_tokens": 178986.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.6170870065689087,
+      "learning_rate": 8.900000000000001e-05,
+      "loss": 2.6625,
+      "mean_token_accuracy": 0.5462300412356853,
+      "num_tokens": 201989.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 1.6247450113296509,
+      "learning_rate": 9.900000000000001e-05,
+      "loss": 2.5605,
+      "mean_token_accuracy": 0.5585827864706516,
+      "num_tokens": 223936.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.19555555555555557,
+      "grad_norm": 1.9383138418197632,
+      "learning_rate": 9.943360604153557e-05,
+      "loss": 2.5267,
+      "mean_token_accuracy": 0.563772913813591,
+      "num_tokens": 246101.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 1.875457763671875,
+      "learning_rate": 9.880427942101952e-05,
+      "loss": 2.5302,
+      "mean_token_accuracy": 0.562754824012518,
+      "num_tokens": 269187.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.2311111111111111,
+      "grad_norm": 1.6430569887161255,
+      "learning_rate": 9.817495280050347e-05,
+      "loss": 2.4479,
+      "mean_token_accuracy": 0.57414620667696,
+      "num_tokens": 291454.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 1.5991843938827515,
+      "learning_rate": 9.754562617998742e-05,
+      "loss": 2.4567,
+      "mean_token_accuracy": 0.5693153299391269,
+      "num_tokens": 314204.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 1.6487599611282349,
+      "learning_rate": 9.691629955947136e-05,
+      "loss": 2.4023,
+      "mean_token_accuracy": 0.5750032790005207,
+      "num_tokens": 337167.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 1.7035490274429321,
+      "learning_rate": 9.628697293895532e-05,
+      "loss": 2.4605,
+      "mean_token_accuracy": 0.5642550930380821,
+      "num_tokens": 360272.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.3022222222222222,
+      "grad_norm": 1.7211060523986816,
+      "learning_rate": 9.565764631843927e-05,
+      "loss": 2.3518,
+      "mean_token_accuracy": 0.5882908716797829,
+      "num_tokens": 382779.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.804926872253418,
+      "learning_rate": 9.502831969792323e-05,
+      "loss": 2.3712,
+      "mean_token_accuracy": 0.5805290326476097,
+      "num_tokens": 405438.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.3377777777777778,
+      "grad_norm": 1.849165678024292,
+      "learning_rate": 9.439899307740719e-05,
+      "loss": 2.4117,
+      "mean_token_accuracy": 0.5730262331664562,
+      "num_tokens": 428660.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 1.9137722253799438,
+      "learning_rate": 9.376966645689114e-05,
+      "loss": 2.3453,
+      "mean_token_accuracy": 0.5850483477115631,
+      "num_tokens": 450808.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "eval_loss": 2.345125436782837,
+      "eval_mean_token_accuracy": 0.5849845852851868,
+      "eval_num_tokens": 450808.0,
+      "eval_runtime": 30.3938,
+      "eval_samples_per_second": 32.901,
+      "eval_steps_per_second": 8.225,
+      "step": 200
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 1.7743253707885742,
+      "learning_rate": 9.314033983637508e-05,
+      "loss": 2.3494,
+      "mean_token_accuracy": 0.5811792358756065,
+      "num_tokens": 473434.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "grad_norm": 1.7797266244888306,
+      "learning_rate": 9.251101321585903e-05,
+      "loss": 2.3866,
+      "mean_token_accuracy": 0.5789428137242794,
+      "num_tokens": 496482.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.4088888888888889,
+      "grad_norm": 1.79751455783844,
+      "learning_rate": 9.188168659534298e-05,
+      "loss": 2.3453,
+      "mean_token_accuracy": 0.584120100736618,
+      "num_tokens": 519379.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 1.7770854234695435,
+      "learning_rate": 9.125235997482694e-05,
+      "loss": 2.355,
+      "mean_token_accuracy": 0.5805074371397495,
+      "num_tokens": 542631.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 1.7118644714355469,
+      "learning_rate": 9.06230333543109e-05,
+      "loss": 2.3288,
+      "mean_token_accuracy": 0.5817694693803788,
+      "num_tokens": 565400.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "grad_norm": 1.837351679801941,
+      "learning_rate": 8.999370673379485e-05,
+      "loss": 2.25,
+      "mean_token_accuracy": 0.594706054031849,
+      "num_tokens": 588003.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.8128186464309692,
+      "learning_rate": 8.93643801132788e-05,
+      "loss": 2.2712,
+      "mean_token_accuracy": 0.5904596522450447,
+      "num_tokens": 610974.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 1.8761178255081177,
+      "learning_rate": 8.873505349276275e-05,
+      "loss": 2.3144,
+      "mean_token_accuracy": 0.5835936337709426,
+      "num_tokens": 634093.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.5155555555555555,
+      "grad_norm": 1.7195324897766113,
+      "learning_rate": 8.81057268722467e-05,
+      "loss": 2.2206,
+      "mean_token_accuracy": 0.604982428252697,
+      "num_tokens": 656188.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 1.8294283151626587,
+      "learning_rate": 8.747640025173064e-05,
+      "loss": 2.255,
+      "mean_token_accuracy": 0.5953361228108406,
+      "num_tokens": 678769.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.5511111111111111,
+      "grad_norm": 1.7993453741073608,
+      "learning_rate": 8.68470736312146e-05,
+      "loss": 2.2312,
+      "mean_token_accuracy": 0.6017149150371551,
+      "num_tokens": 701734.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 1.7603346109390259,
+      "learning_rate": 8.621774701069856e-05,
+      "loss": 2.2124,
+      "mean_token_accuracy": 0.6003566391766071,
+      "num_tokens": 724815.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 1.7591211795806885,
+      "learning_rate": 8.558842039018251e-05,
+      "loss": 2.2208,
+      "mean_token_accuracy": 0.6021837159991265,
+      "num_tokens": 746903.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "grad_norm": 2.150559186935425,
+      "learning_rate": 8.495909376966647e-05,
+      "loss": 2.2122,
+      "mean_token_accuracy": 0.6015113711357116,
+      "num_tokens": 768982.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 1.6258208751678467,
+      "learning_rate": 8.432976714915042e-05,
+      "loss": 2.225,
+      "mean_token_accuracy": 0.6034559831023216,
+      "num_tokens": 791061.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.710488200187683,
+      "learning_rate": 8.370044052863437e-05,
+      "loss": 2.2123,
+      "mean_token_accuracy": 0.6031243965029717,
+      "num_tokens": 813112.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.6577777777777778,
+      "grad_norm": 1.9046748876571655,
+      "learning_rate": 8.307111390811831e-05,
+      "loss": 2.2185,
+      "mean_token_accuracy": 0.6007313683629036,
+      "num_tokens": 835469.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "grad_norm": 1.9116525650024414,
+      "learning_rate": 8.244178728760226e-05,
+      "loss": 2.2382,
+      "mean_token_accuracy": 0.5930798187851906,
+      "num_tokens": 857795.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 1.8034720420837402,
+      "learning_rate": 8.181246066708622e-05,
+      "loss": 2.191,
+      "mean_token_accuracy": 0.6052505746483803,
+      "num_tokens": 879659.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 1.8932994604110718,
+      "learning_rate": 8.118313404657017e-05,
+      "loss": 2.1755,
+      "mean_token_accuracy": 0.6076797977089882,
+      "num_tokens": 902240.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "eval_loss": 2.188769817352295,
+      "eval_mean_token_accuracy": 0.6060388499498367,
+      "eval_num_tokens": 902240.0,
+      "eval_runtime": 29.9448,
+      "eval_samples_per_second": 33.395,
+      "eval_steps_per_second": 8.349,
+      "step": 400
+    },
+    {
+      "epoch": 0.7288888888888889,
+      "grad_norm": 1.7485570907592773,
+      "learning_rate": 8.055380742605413e-05,
+      "loss": 2.2019,
+      "mean_token_accuracy": 0.6058685064315796,
+      "num_tokens": 925091.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 1.818544864654541,
+      "learning_rate": 7.992448080553809e-05,
+      "loss": 2.2313,
+      "mean_token_accuracy": 0.5964938789606095,
+      "num_tokens": 948151.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.7644444444444445,
+      "grad_norm": 1.796096682548523,
+      "learning_rate": 7.929515418502203e-05,
+      "loss": 2.141,
+      "mean_token_accuracy": 0.6135336428880691,
+      "num_tokens": 970339.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 1.7699111700057983,
+      "learning_rate": 7.866582756450598e-05,
+      "loss": 2.1904,
+      "mean_token_accuracy": 0.6022625803947449,
+      "num_tokens": 993552.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.906336784362793,
+      "learning_rate": 7.803650094398993e-05,
+      "loss": 2.2017,
+      "mean_token_accuracy": 0.602821895480156,
+      "num_tokens": 1015564.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.8177777777777778,
+      "grad_norm": 1.9261703491210938,
+      "learning_rate": 7.740717432347388e-05,
+      "loss": 2.1101,
+      "mean_token_accuracy": 0.6158386886119842,
+      "num_tokens": 1037721.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.8355555555555556,
+      "grad_norm": 1.7876946926116943,
+      "learning_rate": 7.677784770295784e-05,
+      "loss": 2.1866,
+      "mean_token_accuracy": 0.6046899721026421,
+      "num_tokens": 1060627.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 1.8447351455688477,
+      "learning_rate": 7.61485210824418e-05,
+      "loss": 2.1564,
+      "mean_token_accuracy": 0.6088386848568916,
+      "num_tokens": 1082672.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.8711111111111111,
+      "grad_norm": 1.7662327289581299,
+      "learning_rate": 7.551919446192575e-05,
+      "loss": 2.1566,
+      "mean_token_accuracy": 0.6086945086717606,
+      "num_tokens": 1104857.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.807004451751709,
+      "learning_rate": 7.48898678414097e-05,
+      "loss": 2.166,
+      "mean_token_accuracy": 0.605591855943203,
+      "num_tokens": 1127612.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 1.895982265472412,
+      "learning_rate": 7.426054122089365e-05,
+      "loss": 2.1645,
+      "mean_token_accuracy": 0.606428450345993,
+      "num_tokens": 1150411.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 1.8196443319320679,
+      "learning_rate": 7.36312146003776e-05,
+      "loss": 2.1878,
+      "mean_token_accuracy": 0.6036446511745452,
+      "num_tokens": 1172683.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.9422222222222222,
+      "grad_norm": 1.7809892892837524,
+      "learning_rate": 7.300188797986154e-05,
+      "loss": 2.0691,
+      "mean_token_accuracy": 0.6235968723893166,
+      "num_tokens": 1194160.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.774588704109192,
+      "learning_rate": 7.23725613593455e-05,
+      "loss": 2.1057,
+      "mean_token_accuracy": 0.6202786311507225,
+      "num_tokens": 1215760.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 1.8483060598373413,
+      "learning_rate": 7.174323473882946e-05,
+      "loss": 2.1634,
+      "mean_token_accuracy": 0.6098488807678223,
+      "num_tokens": 1238191.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "grad_norm": 1.9268509149551392,
+      "learning_rate": 7.111390811831341e-05,
+      "loss": 2.136,
+      "mean_token_accuracy": 0.6116517767310142,
+      "num_tokens": 1260429.0,
+      "step": 560
+    },
+    {
+      "epoch": 1.0124444444444445,
+      "grad_norm": 1.7296037673950195,
+      "learning_rate": 7.048458149779737e-05,
+      "loss": 2.0938,
+      "mean_token_accuracy": 0.6153759768134669,
+      "num_tokens": 1281232.0,
+      "step": 570
+    },
+    {
+      "epoch": 1.0302222222222222,
+      "grad_norm": 1.8975368738174438,
+      "learning_rate": 6.985525487728132e-05,
+      "loss": 2.0172,
+      "mean_token_accuracy": 0.6284284889698029,
+      "num_tokens": 1304130.0,
+      "step": 580
+    },
+    {
+      "epoch": 1.048,
+      "grad_norm": 1.8282201290130615,
+      "learning_rate": 6.922592825676527e-05,
+      "loss": 1.9979,
+      "mean_token_accuracy": 0.6334663733839989,
+      "num_tokens": 1326753.0,
+      "step": 590
+    },
+    {
+      "epoch": 1.0657777777777777,
+      "grad_norm": 1.7836159467697144,
+      "learning_rate": 6.859660163624921e-05,
+      "loss": 2.0058,
+      "mean_token_accuracy": 0.6304456666111946,
+      "num_tokens": 1348985.0,
+      "step": 600
+    },
+    {
+      "epoch": 1.0657777777777777,
+      "eval_loss": 2.114622116088867,
+      "eval_mean_token_accuracy": 0.6162020459175109,
+      "eval_num_tokens": 1348985.0,
+      "eval_runtime": 30.8226,
+      "eval_samples_per_second": 32.444,
+      "eval_steps_per_second": 8.111,
+      "step": 600
+    },
+    {
+      "epoch": 1.0835555555555556,
+      "grad_norm": 1.7529979944229126,
+      "learning_rate": 6.796727501573316e-05,
+      "loss": 2.0084,
+      "mean_token_accuracy": 0.6300177469849586,
+      "num_tokens": 1371318.0,
+      "step": 610
+    },
+    {
+      "epoch": 1.1013333333333333,
+      "grad_norm": 1.897518277168274,
+      "learning_rate": 6.733794839521712e-05,
+      "loss": 2.0348,
+      "mean_token_accuracy": 0.6270109280943871,
+      "num_tokens": 1393816.0,
+      "step": 620
+    },
+    {
+      "epoch": 1.1191111111111112,
+      "grad_norm": 1.9589266777038574,
+      "learning_rate": 6.670862177470107e-05,
+      "loss": 2.0377,
+      "mean_token_accuracy": 0.6255080983042717,
+      "num_tokens": 1416529.0,
+      "step": 630
+    },
+    {
+      "epoch": 1.1368888888888888,
+      "grad_norm": 1.933893084526062,
+      "learning_rate": 6.607929515418503e-05,
+      "loss": 2.0548,
+      "mean_token_accuracy": 0.6250210508704186,
+      "num_tokens": 1438970.0,
+      "step": 640
+    },
+    {
+      "epoch": 1.1546666666666667,
+      "grad_norm": 1.8967244625091553,
+      "learning_rate": 6.544996853366899e-05,
+      "loss": 2.0309,
+      "mean_token_accuracy": 0.6257808804512024,
+      "num_tokens": 1461324.0,
+      "step": 650
+    },
+    {
+      "epoch": 1.1724444444444444,
+      "grad_norm": 2.01849365234375,
+      "learning_rate": 6.482064191315293e-05,
+      "loss": 2.0737,
+      "mean_token_accuracy": 0.6156815335154533,
+      "num_tokens": 1484246.0,
+      "step": 660
+    },
+    {
+      "epoch": 1.1902222222222223,
+      "grad_norm": 1.8661456108093262,
+      "learning_rate": 6.419131529263688e-05,
+      "loss": 2.0632,
+      "mean_token_accuracy": 0.6184948399662972,
+      "num_tokens": 1507305.0,
+      "step": 670
+    },
+    {
+      "epoch": 1.208,
+      "grad_norm": 1.8781774044036865,
+      "learning_rate": 6.356198867212083e-05,
+      "loss": 2.0029,
+      "mean_token_accuracy": 0.6336544677615166,
+      "num_tokens": 1529082.0,
+      "step": 680
+    },
+    {
+      "epoch": 1.2257777777777779,
+      "grad_norm": 1.8406771421432495,
+      "learning_rate": 6.293266205160478e-05,
+      "loss": 2.0102,
+      "mean_token_accuracy": 0.6291820913553238,
+      "num_tokens": 1551159.0,
+      "step": 690
+    },
+    {
+      "epoch": 1.2435555555555555,
+      "grad_norm": 1.829233169555664,
+      "learning_rate": 6.230333543108874e-05,
+      "loss": 2.0396,
+      "mean_token_accuracy": 0.6300060883164406,
+      "num_tokens": 1573348.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.2613333333333334,
+      "grad_norm": 1.9671298265457153,
+      "learning_rate": 6.167400881057269e-05,
+      "loss": 2.0326,
+      "mean_token_accuracy": 0.6287923157215118,
+      "num_tokens": 1595989.0,
+      "step": 710
+    },
+    {
+      "epoch": 1.279111111111111,
+      "grad_norm": 2.0840771198272705,
+      "learning_rate": 6.104468219005665e-05,
+      "loss": 2.0659,
+      "mean_token_accuracy": 0.628783118724823,
+      "num_tokens": 1617895.0,
+      "step": 720
+    },
+    {
+      "epoch": 1.2968888888888888,
+      "grad_norm": 2.056278944015503,
+      "learning_rate": 6.04153555695406e-05,
+      "loss": 2.0177,
+      "mean_token_accuracy": 0.627280455827713,
+      "num_tokens": 1640415.0,
+      "step": 730
+    },
+    {
+      "epoch": 1.3146666666666667,
+      "grad_norm": 1.9183000326156616,
+      "learning_rate": 5.978602894902454e-05,
+      "loss": 1.9958,
+      "mean_token_accuracy": 0.631256802380085,
+      "num_tokens": 1662713.0,
+      "step": 740
+    },
+    {
+      "epoch": 1.3324444444444445,
+      "grad_norm": 2.005032777786255,
+      "learning_rate": 5.9156702328508496e-05,
+      "loss": 2.0164,
+      "mean_token_accuracy": 0.631276798248291,
+      "num_tokens": 1684783.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.3502222222222222,
+      "grad_norm": 1.8667700290679932,
+      "learning_rate": 5.852737570799245e-05,
+      "loss": 2.0295,
+      "mean_token_accuracy": 0.6288824707269669,
+      "num_tokens": 1706623.0,
+      "step": 760
+    },
+    {
+      "epoch": 1.3679999999999999,
+      "grad_norm": 2.123706817626953,
+      "learning_rate": 5.78980490874764e-05,
+      "loss": 2.0513,
+      "mean_token_accuracy": 0.6215401113033294,
+      "num_tokens": 1729494.0,
+      "step": 770
+    },
+    {
+      "epoch": 1.3857777777777778,
+      "grad_norm": 1.9470572471618652,
+      "learning_rate": 5.7268722466960356e-05,
+      "loss": 2.0179,
+      "mean_token_accuracy": 0.630026438832283,
+      "num_tokens": 1752045.0,
+      "step": 780
+    },
+    {
+      "epoch": 1.4035555555555557,
+      "grad_norm": 1.8666447401046753,
+      "learning_rate": 5.663939584644431e-05,
+      "loss": 2.035,
+      "mean_token_accuracy": 0.6255004242062568,
+      "num_tokens": 1775601.0,
+      "step": 790
+    },
+    {
+      "epoch": 1.4213333333333333,
+      "grad_norm": 1.8963086605072021,
+      "learning_rate": 5.601006922592826e-05,
+      "loss": 2.0004,
+      "mean_token_accuracy": 0.6287154361605645,
+      "num_tokens": 1798633.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.4213333333333333,
+      "eval_loss": 2.071798324584961,
+      "eval_mean_token_accuracy": 0.6222149915695191,
+      "eval_num_tokens": 1798633.0,
+      "eval_runtime": 30.3161,
+      "eval_samples_per_second": 32.986,
+      "eval_steps_per_second": 8.246,
+      "step": 800
+    },
+    {
+      "epoch": 1.439111111111111,
+      "grad_norm": 1.9529728889465332,
+      "learning_rate": 5.5380742605412216e-05,
+      "loss": 1.9781,
+      "mean_token_accuracy": 0.6329582959413529,
+      "num_tokens": 1820656.0,
+      "step": 810
+    },
+    {
+      "epoch": 1.456888888888889,
+      "grad_norm": 1.9527575969696045,
+      "learning_rate": 5.475141598489616e-05,
+      "loss": 2.0212,
+      "mean_token_accuracy": 0.6298958778381347,
+      "num_tokens": 1842871.0,
+      "step": 820
+    },
+    {
+      "epoch": 1.4746666666666668,
+      "grad_norm": 1.7937837839126587,
+      "learning_rate": 5.4122089364380114e-05,
+      "loss": 1.9904,
+      "mean_token_accuracy": 0.635308350622654,
+      "num_tokens": 1865652.0,
+      "step": 830
+    },
+    {
+      "epoch": 1.4924444444444445,
+      "grad_norm": 1.888289213180542,
+      "learning_rate": 5.349276274386407e-05,
+      "loss": 2.0129,
+      "mean_token_accuracy": 0.6266900539398194,
+      "num_tokens": 1888455.0,
+      "step": 840
+    },
+    {
+      "epoch": 1.5102222222222221,
+      "grad_norm": 2.0203657150268555,
+      "learning_rate": 5.286343612334802e-05,
+      "loss": 1.9766,
+      "mean_token_accuracy": 0.6383475095033646,
+      "num_tokens": 1910676.0,
+      "step": 850
+    },
+    {
+      "epoch": 1.528,
+      "grad_norm": 2.0756003856658936,
+      "learning_rate": 5.2234109502831975e-05,
+      "loss": 2.0257,
+      "mean_token_accuracy": 0.6280800834298134,
+      "num_tokens": 1933253.0,
+      "step": 860
+    },
+    {
+      "epoch": 1.545777777777778,
+      "grad_norm": 2.112074375152588,
+      "learning_rate": 5.160478288231593e-05,
+      "loss": 2.0314,
+      "mean_token_accuracy": 0.6242304086685181,
+      "num_tokens": 1955820.0,
+      "step": 870
+    },
+    {
+      "epoch": 1.5635555555555556,
+      "grad_norm": 1.9367856979370117,
+      "learning_rate": 5.097545626179988e-05,
+      "loss": 2.0112,
+      "mean_token_accuracy": 0.6305277988314628,
+      "num_tokens": 1978120.0,
+      "step": 880
+    },
+    {
+      "epoch": 1.5813333333333333,
+      "grad_norm": 1.991443395614624,
+      "learning_rate": 5.034612964128382e-05,
+      "loss": 1.9569,
+      "mean_token_accuracy": 0.6372233361005784,
+      "num_tokens": 2000508.0,
+      "step": 890
+    },
+    {
+      "epoch": 1.5991111111111111,
+      "grad_norm": 1.8759173154830933,
+      "learning_rate": 4.9716803020767784e-05,
+      "loss": 1.9894,
+      "mean_token_accuracy": 0.6314782112836838,
+      "num_tokens": 2023356.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.616888888888889,
+      "grad_norm": 1.8218945264816284,
+      "learning_rate": 4.908747640025173e-05,
+      "loss": 1.9459,
+      "mean_token_accuracy": 0.6442534357309342,
+      "num_tokens": 2045965.0,
+      "step": 910
+    },
+    {
+      "epoch": 1.6346666666666667,
+      "grad_norm": 1.9485502243041992,
+      "learning_rate": 4.845814977973568e-05,
+      "loss": 2.0177,
+      "mean_token_accuracy": 0.6231269478797913,
+      "num_tokens": 2069108.0,
+      "step": 920
+    },
+    {
+      "epoch": 1.6524444444444444,
+      "grad_norm": 1.9244948625564575,
+      "learning_rate": 4.782882315921964e-05,
+      "loss": 2.0259,
+      "mean_token_accuracy": 0.6279663592576981,
+      "num_tokens": 2091755.0,
+      "step": 930
+    },
+    {
+      "epoch": 1.6702222222222223,
+      "grad_norm": 1.9663888216018677,
+      "learning_rate": 4.719949653870359e-05,
+      "loss": 1.9896,
+      "mean_token_accuracy": 0.6341330617666244,
+      "num_tokens": 2114496.0,
+      "step": 940
+    },
+    {
+      "epoch": 1.688,
+      "grad_norm": 1.9700689315795898,
+      "learning_rate": 4.657016991818754e-05,
+      "loss": 2.0081,
+      "mean_token_accuracy": 0.629092475771904,
+      "num_tokens": 2137041.0,
+      "step": 950
+    },
+    {
+      "epoch": 1.7057777777777776,
+      "grad_norm": 1.9976369142532349,
+      "learning_rate": 4.594084329767149e-05,
+      "loss": 2.0177,
+      "mean_token_accuracy": 0.6279423177242279,
+      "num_tokens": 2159711.0,
+      "step": 960
+    },
+    {
+      "epoch": 1.7235555555555555,
+      "grad_norm": 1.9927507638931274,
+      "learning_rate": 4.531151667715545e-05,
+      "loss": 2.0111,
+      "mean_token_accuracy": 0.632372610270977,
+      "num_tokens": 2181675.0,
+      "step": 970
+    },
+    {
+      "epoch": 1.7413333333333334,
+      "grad_norm": 1.9318374395370483,
+      "learning_rate": 4.46821900566394e-05,
+      "loss": 1.9772,
+      "mean_token_accuracy": 0.6370243668556214,
+      "num_tokens": 2204671.0,
+      "step": 980
+    },
+    {
+      "epoch": 1.759111111111111,
+      "grad_norm": 1.8933532238006592,
+      "learning_rate": 4.405286343612335e-05,
+      "loss": 2.0098,
+      "mean_token_accuracy": 0.6229412123560906,
+      "num_tokens": 2227866.0,
+      "step": 990
+    },
+    {
+      "epoch": 1.7768888888888887,
+      "grad_norm": 2.063185930252075,
+      "learning_rate": 4.34235368156073e-05,
+      "loss": 1.9801,
+      "mean_token_accuracy": 0.6361721217632293,
+      "num_tokens": 2250379.0,
+      "step": 1000
+    },
+    {
+      "epoch": 1.7768888888888887,
+      "eval_loss": 2.036764621734619,
+      "eval_mean_token_accuracy": 0.6262071034908294,
+      "eval_num_tokens": 2250379.0,
+      "eval_runtime": 31.2979,
+      "eval_samples_per_second": 31.951,
+      "eval_steps_per_second": 7.988,
+      "step": 1000
+    },
+    {
+      "epoch": 1.7946666666666666,
+      "grad_norm": 1.9427729845046997,
+      "learning_rate": 4.2794210195091256e-05,
+      "loss": 2.0155,
+      "mean_token_accuracy": 0.6281099706888199,
+      "num_tokens": 2272999.0,
+      "step": 1010
+    },
+    {
+      "epoch": 1.8124444444444445,
+      "grad_norm": 1.842465877532959,
+      "learning_rate": 4.216488357457521e-05,
+      "loss": 1.9861,
+      "mean_token_accuracy": 0.6330478996038437,
+      "num_tokens": 2295110.0,
+      "step": 1020
+    },
+    {
+      "epoch": 1.8302222222222222,
+      "grad_norm": 1.8547931909561157,
+      "learning_rate": 4.1535556954059154e-05,
+      "loss": 1.9617,
+      "mean_token_accuracy": 0.6373973488807678,
+      "num_tokens": 2317432.0,
+      "step": 1030
+    },
+    {
+      "epoch": 1.8479999999999999,
+      "grad_norm": 1.8283085823059082,
+      "learning_rate": 4.090623033354311e-05,
+      "loss": 1.9987,
+      "mean_token_accuracy": 0.6286273017525673,
+      "num_tokens": 2340305.0,
+      "step": 1040
+    },
+    {
+      "epoch": 1.8657777777777778,
+      "grad_norm": 1.9289031028747559,
+      "learning_rate": 4.0276903713027065e-05,
+      "loss": 2.0035,
+      "mean_token_accuracy": 0.6320135101675988,
+      "num_tokens": 2362746.0,
+      "step": 1050
+    },
+    {
+      "epoch": 1.8835555555555556,
+      "grad_norm": 1.8411505222320557,
+      "learning_rate": 3.9647577092511014e-05,
+      "loss": 1.9697,
+      "mean_token_accuracy": 0.6332684755325317,
+      "num_tokens": 2385647.0,
+      "step": 1060
+    },
+    {
+      "epoch": 1.9013333333333333,
+      "grad_norm": 2.0083494186401367,
+      "learning_rate": 3.901825047199496e-05,
+      "loss": 1.987,
+      "mean_token_accuracy": 0.627101382613182,
+      "num_tokens": 2408732.0,
+      "step": 1070
+    },
+    {
+      "epoch": 1.919111111111111,
+      "grad_norm": 2.150812864303589,
+      "learning_rate": 3.838892385147892e-05,
+      "loss": 1.9642,
+      "mean_token_accuracy": 0.6350547641515731,
+      "num_tokens": 2431137.0,
+      "step": 1080
+    },
+    {
+      "epoch": 1.9368888888888889,
+      "grad_norm": 1.9779438972473145,
+      "learning_rate": 3.7759597230962874e-05,
+      "loss": 1.9249,
+      "mean_token_accuracy": 0.6438971221446991,
+      "num_tokens": 2453517.0,
+      "step": 1090
+    },
+    {
+      "epoch": 1.9546666666666668,
+      "grad_norm": 2.0672504901885986,
+      "learning_rate": 3.7130270610446823e-05,
+      "loss": 1.9679,
+      "mean_token_accuracy": 0.6345437586307525,
+      "num_tokens": 2475737.0,
+      "step": 1100
+    },
+    {
+      "epoch": 1.9724444444444444,
+      "grad_norm": 1.9778350591659546,
+      "learning_rate": 3.650094398993077e-05,
+      "loss": 1.9733,
+      "mean_token_accuracy": 0.6329764410853386,
+      "num_tokens": 2497880.0,
+      "step": 1110
+    },
+    {
+      "epoch": 1.9902222222222221,
+      "grad_norm": 2.014357328414917,
+      "learning_rate": 3.587161736941473e-05,
+      "loss": 1.9714,
+      "mean_token_accuracy": 0.635537999868393,
+      "num_tokens": 2519974.0,
+      "step": 1120
+    },
+    {
+      "epoch": 2.007111111111111,
+      "grad_norm": 1.9104490280151367,
+      "learning_rate": 3.5242290748898684e-05,
+      "loss": 1.8849,
+      "mean_token_accuracy": 0.6536890221269507,
+      "num_tokens": 2540296.0,
+      "step": 1130
+    },
+    {
+      "epoch": 2.024888888888889,
+      "grad_norm": 2.0223166942596436,
+      "learning_rate": 3.461296412838263e-05,
+      "loss": 1.8811,
+      "mean_token_accuracy": 0.6483465373516083,
+      "num_tokens": 2561919.0,
+      "step": 1140
+    },
+    {
+      "epoch": 2.042666666666667,
+      "grad_norm": 1.8120856285095215,
+      "learning_rate": 3.398363750786658e-05,
+      "loss": 1.9212,
+      "mean_token_accuracy": 0.6420063003897667,
+      "num_tokens": 2584915.0,
+      "step": 1150
+    },
+    {
+      "epoch": 2.0604444444444443,
+      "grad_norm": 1.9729136228561401,
+      "learning_rate": 3.335431088735054e-05,
+      "loss": 1.8851,
+      "mean_token_accuracy": 0.6519104614853859,
+      "num_tokens": 2606857.0,
+      "step": 1160
+    },
+    {
+      "epoch": 2.078222222222222,
+      "grad_norm": 2.1263654232025146,
+      "learning_rate": 3.272498426683449e-05,
+      "loss": 1.8905,
+      "mean_token_accuracy": 0.6453483879566193,
+      "num_tokens": 2629737.0,
+      "step": 1170
+    },
+    {
+      "epoch": 2.096,
+      "grad_norm": 1.9857081174850464,
+      "learning_rate": 3.209565764631844e-05,
+      "loss": 1.8381,
+      "mean_token_accuracy": 0.653864786028862,
+      "num_tokens": 2651936.0,
+      "step": 1180
+    },
+    {
+      "epoch": 2.113777777777778,
+      "grad_norm": 1.9701604843139648,
+      "learning_rate": 3.146633102580239e-05,
+      "loss": 1.9133,
+      "mean_token_accuracy": 0.6435931533575058,
+      "num_tokens": 2675241.0,
+      "step": 1190
+    },
+    {
+      "epoch": 2.1315555555555554,
+      "grad_norm": 1.9061148166656494,
+      "learning_rate": 3.0837004405286347e-05,
+      "loss": 1.8832,
+      "mean_token_accuracy": 0.6495110660791397,
+      "num_tokens": 2698219.0,
+      "step": 1200
+    },
+    {
+      "epoch": 2.1315555555555554,
+      "eval_loss": 2.020338296890259,
+      "eval_mean_token_accuracy": 0.6295755279064178,
+      "eval_num_tokens": 2698219.0,
+      "eval_runtime": 30.7487,
+      "eval_samples_per_second": 32.522,
+      "eval_steps_per_second": 8.13,
+      "step": 1200
+    },
+    {
+      "epoch": 2.1493333333333333,
+      "grad_norm": 2.1164379119873047,
+      "learning_rate": 3.02076777847703e-05,
+      "loss": 1.8986,
+      "mean_token_accuracy": 0.6449921384453774,
+      "num_tokens": 2721580.0,
+      "step": 1210
+    },
+    {
+      "epoch": 2.167111111111111,
+      "grad_norm": 1.9740287065505981,
+      "learning_rate": 2.9578351164254248e-05,
+      "loss": 1.8953,
+      "mean_token_accuracy": 0.648700350522995,
+      "num_tokens": 2744110.0,
+      "step": 1220
+    },
+    {
+      "epoch": 2.1848888888888887,
+      "grad_norm": 1.9970844984054565,
+      "learning_rate": 2.89490245437382e-05,
+      "loss": 1.8693,
+      "mean_token_accuracy": 0.6546828895807266,
+      "num_tokens": 2765844.0,
+      "step": 1230
+    },
+    {
+      "epoch": 2.2026666666666666,
+      "grad_norm": 2.06357479095459,
+      "learning_rate": 2.8319697923222156e-05,
+      "loss": 1.8775,
+      "mean_token_accuracy": 0.6484791278839112,
+      "num_tokens": 2788070.0,
+      "step": 1240
+    },
+    {
+      "epoch": 2.2204444444444444,
+      "grad_norm": 1.9746241569519043,
+      "learning_rate": 2.7690371302706108e-05,
+      "loss": 1.9117,
+      "mean_token_accuracy": 0.6470579236745835,
+      "num_tokens": 2810964.0,
+      "step": 1250
+    },
+    {
+      "epoch": 2.2382222222222223,
+      "grad_norm": 2.1169064044952393,
+      "learning_rate": 2.7061044682190057e-05,
+      "loss": 1.8684,
+      "mean_token_accuracy": 0.6524357482790947,
+      "num_tokens": 2833176.0,
+      "step": 1260
+    },
+    {
+      "epoch": 2.2560000000000002,
+      "grad_norm": 2.0234525203704834,
+      "learning_rate": 2.643171806167401e-05,
+      "loss": 1.9089,
+      "mean_token_accuracy": 0.6425125360488891,
+      "num_tokens": 2855440.0,
+      "step": 1270
+    },
+    {
+      "epoch": 2.2737777777777777,
+      "grad_norm": 2.0508742332458496,
+      "learning_rate": 2.5802391441157965e-05,
+      "loss": 1.8463,
+      "mean_token_accuracy": 0.6541648581624031,
+      "num_tokens": 2877713.0,
+      "step": 1280
+    },
+    {
+      "epoch": 2.2915555555555556,
+      "grad_norm": 1.863732099533081,
+      "learning_rate": 2.517306482064191e-05,
+      "loss": 1.8953,
+      "mean_token_accuracy": 0.6487652212381363,
+      "num_tokens": 2899934.0,
+      "step": 1290
+    },
+    {
+      "epoch": 2.3093333333333335,
+      "grad_norm": 2.148881196975708,
+      "learning_rate": 2.4543738200125866e-05,
+      "loss": 1.8937,
+      "mean_token_accuracy": 0.6466890797019005,
+      "num_tokens": 2923244.0,
+      "step": 1300
+    },
+    {
+      "epoch": 2.327111111111111,
+      "grad_norm": 2.0562210083007812,
+      "learning_rate": 2.391441157960982e-05,
+      "loss": 1.8776,
+      "mean_token_accuracy": 0.648098886013031,
+      "num_tokens": 2945580.0,
+      "step": 1310
+    },
+    {
+      "epoch": 2.344888888888889,
+      "grad_norm": 1.9801143407821655,
+      "learning_rate": 2.328508495909377e-05,
+      "loss": 1.8718,
+      "mean_token_accuracy": 0.6436786696314811,
+      "num_tokens": 2969470.0,
+      "step": 1320
+    },
+    {
+      "epoch": 2.3626666666666667,
+      "grad_norm": 2.244140863418579,
+      "learning_rate": 2.2655758338577723e-05,
+      "loss": 1.871,
+      "mean_token_accuracy": 0.6460510939359665,
+      "num_tokens": 2991982.0,
+      "step": 1330
+    },
+    {
+      "epoch": 2.3804444444444446,
+      "grad_norm": 1.993152379989624,
+      "learning_rate": 2.2026431718061676e-05,
+      "loss": 1.8909,
+      "mean_token_accuracy": 0.6495360463857651,
+      "num_tokens": 3014206.0,
+      "step": 1340
+    },
+    {
+      "epoch": 2.398222222222222,
+      "grad_norm": 1.974604606628418,
+      "learning_rate": 2.1397105097545628e-05,
+      "loss": 1.843,
+      "mean_token_accuracy": 0.6507977247238159,
+      "num_tokens": 3036651.0,
+      "step": 1350
+    },
+    {
+      "epoch": 2.416,
+      "grad_norm": 1.9981292486190796,
+      "learning_rate": 2.0767778477029577e-05,
+      "loss": 1.8775,
+      "mean_token_accuracy": 0.6513748601078987,
+      "num_tokens": 3058745.0,
+      "step": 1360
+    },
+    {
+      "epoch": 2.433777777777778,
+      "grad_norm": 2.1414084434509277,
+      "learning_rate": 2.0138451856513533e-05,
+      "loss": 1.8904,
+      "mean_token_accuracy": 0.6470720157027244,
+      "num_tokens": 3081726.0,
+      "step": 1370
+    },
+    {
+      "epoch": 2.4515555555555557,
+      "grad_norm": 2.157397747039795,
+      "learning_rate": 1.950912523599748e-05,
+      "loss": 1.8711,
+      "mean_token_accuracy": 0.6492032095789909,
+      "num_tokens": 3104292.0,
+      "step": 1380
+    },
+    {
+      "epoch": 2.469333333333333,
+      "grad_norm": 2.0714213848114014,
+      "learning_rate": 1.8879798615481437e-05,
+      "loss": 1.8845,
+      "mean_token_accuracy": 0.6478913977742196,
+      "num_tokens": 3126334.0,
+      "step": 1390
+    },
+    {
+      "epoch": 2.487111111111111,
+      "grad_norm": 2.1000311374664307,
+      "learning_rate": 1.8250471994965386e-05,
+      "loss": 1.9088,
+      "mean_token_accuracy": 0.6414603188633918,
+      "num_tokens": 3149845.0,
+      "step": 1400
+    },
+    {
+      "epoch": 2.487111111111111,
+      "eval_loss": 2.0077672004699707,
+      "eval_mean_token_accuracy": 0.63226633644104,
+      "eval_num_tokens": 3149845.0,
+      "eval_runtime": 30.4714,
+      "eval_samples_per_second": 32.818,
+      "eval_steps_per_second": 8.204,
+      "step": 1400
+    },
+    {
+      "epoch": 2.504888888888889,
+      "grad_norm": 1.9947516918182373,
+      "learning_rate": 1.7621145374449342e-05,
+      "loss": 1.8948,
+      "mean_token_accuracy": 0.6480994567275047,
+      "num_tokens": 3172117.0,
+      "step": 1410
+    },
+    {
+      "epoch": 2.522666666666667,
+      "grad_norm": 2.0749399662017822,
+      "learning_rate": 1.699181875393329e-05,
+      "loss": 1.8821,
+      "mean_token_accuracy": 0.6532607778906823,
+      "num_tokens": 3194261.0,
+      "step": 1420
+    },
+    {
+      "epoch": 2.5404444444444443,
+      "grad_norm": 2.021650552749634,
+      "learning_rate": 1.6362492133417247e-05,
+      "loss": 1.7886,
+      "mean_token_accuracy": 0.6606403380632401,
+      "num_tokens": 3216455.0,
+      "step": 1430
+    },
+    {
+      "epoch": 2.558222222222222,
+      "grad_norm": 2.041862726211548,
+      "learning_rate": 1.5733165512901195e-05,
+      "loss": 1.9171,
+      "mean_token_accuracy": 0.6459932029247284,
+      "num_tokens": 3238359.0,
+      "step": 1440
+    },
+    {
+      "epoch": 2.576,
+      "grad_norm": 1.9248042106628418,
+      "learning_rate": 1.510383889238515e-05,
+      "loss": 1.9163,
+      "mean_token_accuracy": 0.6407139167189598,
+      "num_tokens": 3261568.0,
+      "step": 1450
+    },
+    {
+      "epoch": 2.5937777777777775,
+      "grad_norm": 2.2711341381073,
+      "learning_rate": 1.44745122718691e-05,
+      "loss": 1.9086,
+      "mean_token_accuracy": 0.6399997368454933,
+      "num_tokens": 3284517.0,
+      "step": 1460
+    },
+    {
+      "epoch": 2.6115555555555554,
+      "grad_norm": 2.2452495098114014,
+      "learning_rate": 1.3845185651353054e-05,
+      "loss": 1.8712,
+      "mean_token_accuracy": 0.649416595697403,
+      "num_tokens": 3306623.0,
+      "step": 1470
+    },
+    {
+      "epoch": 2.6293333333333333,
+      "grad_norm": 1.9956483840942383,
+      "learning_rate": 1.3215859030837005e-05,
+      "loss": 1.8503,
+      "mean_token_accuracy": 0.6563126415014267,
+      "num_tokens": 3329270.0,
+      "step": 1480
+    },
+    {
+      "epoch": 2.647111111111111,
+      "grad_norm": 2.000636100769043,
+      "learning_rate": 1.2586532410320955e-05,
+      "loss": 1.8668,
+      "mean_token_accuracy": 0.6488404273986816,
+      "num_tokens": 3352533.0,
+      "step": 1490
+    },
+    {
+      "epoch": 2.664888888888889,
+      "grad_norm": 2.1857969760894775,
+      "learning_rate": 1.195720578980491e-05,
+      "loss": 1.8487,
+      "mean_token_accuracy": 0.6583347156643867,
+      "num_tokens": 3374132.0,
+      "step": 1500
+    },
+    {
+      "epoch": 2.6826666666666665,
+      "grad_norm": 1.9961498975753784,
+      "learning_rate": 1.1327879169288862e-05,
+      "loss": 1.9102,
+      "mean_token_accuracy": 0.6406741261482238,
+      "num_tokens": 3397176.0,
+      "step": 1510
+    },
+    {
+      "epoch": 2.7004444444444444,
+      "grad_norm": 2.1003425121307373,
+      "learning_rate": 1.0698552548772814e-05,
+      "loss": 1.8477,
+      "mean_token_accuracy": 0.6532559394836426,
+      "num_tokens": 3418961.0,
+      "step": 1520
+    },
+    {
+      "epoch": 2.7182222222222223,
+      "grad_norm": 2.024757146835327,
+      "learning_rate": 1.0069225928256766e-05,
+      "loss": 1.8602,
+      "mean_token_accuracy": 0.6530294433236122,
+      "num_tokens": 3441815.0,
+      "step": 1530
+    },
+    {
+      "epoch": 2.7359999999999998,
+      "grad_norm": 1.9595909118652344,
+      "learning_rate": 9.439899307740719e-06,
+      "loss": 1.8787,
+      "mean_token_accuracy": 0.6477272987365723,
+      "num_tokens": 3464582.0,
+      "step": 1540
+    },
+    {
+      "epoch": 2.7537777777777777,
+      "grad_norm": 1.9734858274459839,
+      "learning_rate": 8.810572687224671e-06,
+      "loss": 1.8385,
+      "mean_token_accuracy": 0.656038624048233,
+      "num_tokens": 3486694.0,
+      "step": 1550
+    },
+    {
+      "epoch": 2.7715555555555556,
+      "grad_norm": 2.0039222240448,
+      "learning_rate": 8.181246066708623e-06,
+      "loss": 1.8825,
+      "mean_token_accuracy": 0.6516638934612274,
+      "num_tokens": 3508908.0,
+      "step": 1560
+    },
+    {
+      "epoch": 2.7893333333333334,
+      "grad_norm": 2.040252685546875,
+      "learning_rate": 7.551919446192575e-06,
+      "loss": 1.8168,
+      "mean_token_accuracy": 0.6596024230122566,
+      "num_tokens": 3530306.0,
+      "step": 1570
+    },
+    {
+      "epoch": 2.8071111111111113,
+      "grad_norm": 2.2906384468078613,
+      "learning_rate": 6.922592825676527e-06,
+      "loss": 1.9023,
+      "mean_token_accuracy": 0.643904159963131,
+      "num_tokens": 3552880.0,
+      "step": 1580
+    },
+    {
+      "epoch": 2.824888888888889,
+      "grad_norm": 1.9195839166641235,
+      "learning_rate": 6.293266205160478e-06,
+      "loss": 1.8941,
+      "mean_token_accuracy": 0.648286484181881,
+      "num_tokens": 3575800.0,
+      "step": 1590
+    },
+    {
+      "epoch": 2.8426666666666667,
+      "grad_norm": 2.044443368911743,
+      "learning_rate": 5.663939584644431e-06,
+      "loss": 1.8881,
+      "mean_token_accuracy": 0.652445487678051,
+      "num_tokens": 3598214.0,
+      "step": 1600
+    },
+    {
+      "epoch": 2.8426666666666667,
+      "eval_loss": 1.9988627433776855,
+      "eval_mean_token_accuracy": 0.6337166538238526,
+      "eval_num_tokens": 3598214.0,
+      "eval_runtime": 30.1548,
+      "eval_samples_per_second": 33.162,
+      "eval_steps_per_second": 8.291,
+      "step": 1600
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1689,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2669174249603072e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1689/README.md

@@ -0,0 +1,202 @@
+---
+base_model: naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-0.5B
+library_name: peft
+---
+
+# 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 0.15.2

checkpoint-1689/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-0.5B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1689/added_tokens.json

@@ -0,0 +1,35 @@
+{
+  "<EMAIL>": 110521,
+  "<KEY>": 110522,
+  "<NAME>": 110520,
+  "<PASSWORD>": 110523,
+  "<code_to_intermediate>": 110502,
+  "<empty_output>": 110501,
+  "<file_sep>": 110492,
+  "<intermediate_to_code>": 110503,
+  "<issue_closed>": 110495,
+  "<issue_comment>": 110494,
+  "<issue_start>": 110493,
+  "<jupyter_code>": 110498,
+  "<jupyter_output>": 110499,
+  "<jupyter_script>": 110500,
+  "<jupyter_start>": 110496,
+  "<jupyter_text>": 110497,
+  "<pr>": 110504,
+  "<pr_base>": 110507,
+  "<pr_base_code>": 110509,
+  "<pr_comment>": 110512,
+  "<pr_diff>": 110510,
+  "<pr_diff_hunk>": 110511,
+  "<pr_diff_hunk_comment_line>": 110519,
+  "<pr_event_id>": 110513,
+  "<pr_file>": 110508,
+  "<pr_in_reply_to_comment_id>": 110518,
+  "<pr_in_reply_to_review_id>": 110517,
+  "<pr_is_merged>": 110506,
+  "<pr_review>": 110514,
+  "<pr_review_comment>": 110516,
+  "<pr_review_state>": 110515,
+  "<pr_status>": 110505,
+  "<repo_name>": 110491
+}

checkpoint-1689/chat_template.jinja

@@ -0,0 +1,4 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

checkpoint-1689/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8e4809df8f7107a5f01170ea92659e2d802dc98538b6ea3a14af789d42642eb
+size 78925378

checkpoint-1689/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:622064fb68e7107ee7b349ab074bd33170144438520452d68e43e21e6486d978
+size 14244

checkpoint-1689/special_tokens_map.json

@@ -0,0 +1,86 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|endofprompt|>",
+    "<|_unuse_missing_100256|>",
+    "<|_unuse_missing_100261|>",
+    "<|_unuse_missing_100262|>",
+    "<|_unuse_missing_100263|>",
+    "<|_unuse_missing_100264|>",
+    "<|_unuse_missing_100265|>",
+    "<|_unuse_missing_100266|>",
+    "<|_unuse_missing_100267|>",
+    "<|_unuse_missing_100268|>",
+    "<|_unuse_missing_100269|>",
+    "<|_unuse_missing_100270|>",
+    "<|_unuse_missing_100271|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|stop|>",
+    "<|endofturn|>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endofturn|>",
+    "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
+  }
+}

checkpoint-1689/tokenizer_config.json

@@ -0,0 +1,501 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100256": {
+      "content": "<|_unuse_missing_100256|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100257": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100261": {
+      "content": "<|_unuse_missing_100261|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100262": {
+      "content": "<|_unuse_missing_100262|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100263": {
+      "content": "<|_unuse_missing_100263|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100264": {
+      "content": "<|_unuse_missing_100264|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|_unuse_missing_100265|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<|_unuse_missing_100266|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100267": {
+      "content": "<|_unuse_missing_100267|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100268": {
+      "content": "<|_unuse_missing_100268|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100269": {
+      "content": "<|_unuse_missing_100269|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100270": {
+      "content": "<|_unuse_missing_100270|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100271": {
+      "content": "<|_unuse_missing_100271|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100272": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100273": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100274": {
+      "content": "<|stop|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100275": {
+      "content": "<|endofturn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110491": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110492": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110493": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110494": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110495": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110496": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110497": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110498": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110499": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110500": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110501": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110502": {
+      "content": "<code_to_intermediate>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110503": {
+      "content": "<intermediate_to_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110504": {
+      "content": "<pr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110505": {
+      "content": "<pr_status>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110506": {
+      "content": "<pr_is_merged>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110507": {
+      "content": "<pr_base>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110508": {
+      "content": "<pr_file>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110509": {
+      "content": "<pr_base_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110510": {
+      "content": "<pr_diff>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110511": {
+      "content": "<pr_diff_hunk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110512": {
+      "content": "<pr_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110513": {
+      "content": "<pr_event_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110514": {
+      "content": "<pr_review>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110515": {
+      "content": "<pr_review_state>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110516": {
+      "content": "<pr_review_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110517": {
+      "content": "<pr_in_reply_to_review_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110518": {
+      "content": "<pr_in_reply_to_comment_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110519": {
+      "content": "<pr_diff_hunk_comment_line>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110520": {
+      "content": "<NAME>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110521": {
+      "content": "<EMAIL>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110522": {
+      "content": "<KEY>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110523": {
+      "content": "<PASSWORD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|endofprompt|>",
+    "<|_unuse_missing_100256|>",
+    "<|_unuse_missing_100261|>",
+    "<|_unuse_missing_100262|>",
+    "<|_unuse_missing_100263|>",
+    "<|_unuse_missing_100264|>",
+    "<|_unuse_missing_100265|>",
+    "<|_unuse_missing_100266|>",
+    "<|_unuse_missing_100267|>",
+    "<|_unuse_missing_100268|>",
+    "<|_unuse_missing_100269|>",
+    "<|_unuse_missing_100270|>",
+    "<|_unuse_missing_100271|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|stop|>",
+    "<|endofturn|>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endofturn|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-1689/trainer_state.json

@@ -0,0 +1,1626 @@
+{
+  "best_global_step": 1600,
+  "best_metric": 1.9988627433776855,
+  "best_model_checkpoint": "/content/drive/MyDrive/hyperclova-deobfuscation-lora/checkpoint-1600",
+  "epoch": 3.0,
+  "eval_steps": 200,
+  "global_step": 1689,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.017777777777777778,
+      "grad_norm": 3.4749701023101807,
+      "learning_rate": 9e-06,
+      "loss": 4.1724,
+      "mean_token_accuracy": 0.3504906162619591,
+      "num_tokens": 22106.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 2.8458425998687744,
+      "learning_rate": 1.9e-05,
+      "loss": 3.9226,
+      "mean_token_accuracy": 0.3695666640996933,
+      "num_tokens": 44943.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 2.1938765048980713,
+      "learning_rate": 2.9e-05,
+      "loss": 3.6554,
+      "mean_token_accuracy": 0.4290380232036114,
+      "num_tokens": 67397.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 2.4278910160064697,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 3.303,
+      "mean_token_accuracy": 0.4723150283098221,
+      "num_tokens": 89803.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 1.7704142332077026,
+      "learning_rate": 4.9e-05,
+      "loss": 3.0041,
+      "mean_token_accuracy": 0.5115502133965493,
+      "num_tokens": 112364.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 1.5662821531295776,
+      "learning_rate": 5.9e-05,
+      "loss": 2.8013,
+      "mean_token_accuracy": 0.5329545043408871,
+      "num_tokens": 134028.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.12444444444444444,
+      "grad_norm": 1.5833848714828491,
+      "learning_rate": 6.9e-05,
+      "loss": 2.7291,
+      "mean_token_accuracy": 0.5422534577548503,
+      "num_tokens": 156703.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 1.8611595630645752,
+      "learning_rate": 7.900000000000001e-05,
+      "loss": 2.634,
+      "mean_token_accuracy": 0.5519127860665322,
+      "num_tokens": 178986.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.6170870065689087,
+      "learning_rate": 8.900000000000001e-05,
+      "loss": 2.6625,
+      "mean_token_accuracy": 0.5462300412356853,
+      "num_tokens": 201989.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 1.6247450113296509,
+      "learning_rate": 9.900000000000001e-05,
+      "loss": 2.5605,
+      "mean_token_accuracy": 0.5585827864706516,
+      "num_tokens": 223936.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.19555555555555557,
+      "grad_norm": 1.9383138418197632,
+      "learning_rate": 9.943360604153557e-05,
+      "loss": 2.5267,
+      "mean_token_accuracy": 0.563772913813591,
+      "num_tokens": 246101.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 1.875457763671875,
+      "learning_rate": 9.880427942101952e-05,
+      "loss": 2.5302,
+      "mean_token_accuracy": 0.562754824012518,
+      "num_tokens": 269187.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.2311111111111111,
+      "grad_norm": 1.6430569887161255,
+      "learning_rate": 9.817495280050347e-05,
+      "loss": 2.4479,
+      "mean_token_accuracy": 0.57414620667696,
+      "num_tokens": 291454.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 1.5991843938827515,
+      "learning_rate": 9.754562617998742e-05,
+      "loss": 2.4567,
+      "mean_token_accuracy": 0.5693153299391269,
+      "num_tokens": 314204.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 1.6487599611282349,
+      "learning_rate": 9.691629955947136e-05,
+      "loss": 2.4023,
+      "mean_token_accuracy": 0.5750032790005207,
+      "num_tokens": 337167.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 1.7035490274429321,
+      "learning_rate": 9.628697293895532e-05,
+      "loss": 2.4605,
+      "mean_token_accuracy": 0.5642550930380821,
+      "num_tokens": 360272.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.3022222222222222,
+      "grad_norm": 1.7211060523986816,
+      "learning_rate": 9.565764631843927e-05,
+      "loss": 2.3518,
+      "mean_token_accuracy": 0.5882908716797829,
+      "num_tokens": 382779.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.804926872253418,
+      "learning_rate": 9.502831969792323e-05,
+      "loss": 2.3712,
+      "mean_token_accuracy": 0.5805290326476097,
+      "num_tokens": 405438.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.3377777777777778,
+      "grad_norm": 1.849165678024292,
+      "learning_rate": 9.439899307740719e-05,
+      "loss": 2.4117,
+      "mean_token_accuracy": 0.5730262331664562,
+      "num_tokens": 428660.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 1.9137722253799438,
+      "learning_rate": 9.376966645689114e-05,
+      "loss": 2.3453,
+      "mean_token_accuracy": 0.5850483477115631,
+      "num_tokens": 450808.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "eval_loss": 2.345125436782837,
+      "eval_mean_token_accuracy": 0.5849845852851868,
+      "eval_num_tokens": 450808.0,
+      "eval_runtime": 30.3938,
+      "eval_samples_per_second": 32.901,
+      "eval_steps_per_second": 8.225,
+      "step": 200
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 1.7743253707885742,
+      "learning_rate": 9.314033983637508e-05,
+      "loss": 2.3494,
+      "mean_token_accuracy": 0.5811792358756065,
+      "num_tokens": 473434.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "grad_norm": 1.7797266244888306,
+      "learning_rate": 9.251101321585903e-05,
+      "loss": 2.3866,
+      "mean_token_accuracy": 0.5789428137242794,
+      "num_tokens": 496482.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.4088888888888889,
+      "grad_norm": 1.79751455783844,
+      "learning_rate": 9.188168659534298e-05,
+      "loss": 2.3453,
+      "mean_token_accuracy": 0.584120100736618,
+      "num_tokens": 519379.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 1.7770854234695435,
+      "learning_rate": 9.125235997482694e-05,
+      "loss": 2.355,
+      "mean_token_accuracy": 0.5805074371397495,
+      "num_tokens": 542631.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 1.7118644714355469,
+      "learning_rate": 9.06230333543109e-05,
+      "loss": 2.3288,
+      "mean_token_accuracy": 0.5817694693803788,
+      "num_tokens": 565400.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "grad_norm": 1.837351679801941,
+      "learning_rate": 8.999370673379485e-05,
+      "loss": 2.25,
+      "mean_token_accuracy": 0.594706054031849,
+      "num_tokens": 588003.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.8128186464309692,
+      "learning_rate": 8.93643801132788e-05,
+      "loss": 2.2712,
+      "mean_token_accuracy": 0.5904596522450447,
+      "num_tokens": 610974.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 1.8761178255081177,
+      "learning_rate": 8.873505349276275e-05,
+      "loss": 2.3144,
+      "mean_token_accuracy": 0.5835936337709426,
+      "num_tokens": 634093.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.5155555555555555,
+      "grad_norm": 1.7195324897766113,
+      "learning_rate": 8.81057268722467e-05,
+      "loss": 2.2206,
+      "mean_token_accuracy": 0.604982428252697,
+      "num_tokens": 656188.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 1.8294283151626587,
+      "learning_rate": 8.747640025173064e-05,
+      "loss": 2.255,
+      "mean_token_accuracy": 0.5953361228108406,
+      "num_tokens": 678769.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.5511111111111111,
+      "grad_norm": 1.7993453741073608,
+      "learning_rate": 8.68470736312146e-05,
+      "loss": 2.2312,
+      "mean_token_accuracy": 0.6017149150371551,
+      "num_tokens": 701734.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 1.7603346109390259,
+      "learning_rate": 8.621774701069856e-05,
+      "loss": 2.2124,
+      "mean_token_accuracy": 0.6003566391766071,
+      "num_tokens": 724815.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 1.7591211795806885,
+      "learning_rate": 8.558842039018251e-05,
+      "loss": 2.2208,
+      "mean_token_accuracy": 0.6021837159991265,
+      "num_tokens": 746903.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "grad_norm": 2.150559186935425,
+      "learning_rate": 8.495909376966647e-05,
+      "loss": 2.2122,
+      "mean_token_accuracy": 0.6015113711357116,
+      "num_tokens": 768982.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 1.6258208751678467,
+      "learning_rate": 8.432976714915042e-05,
+      "loss": 2.225,
+      "mean_token_accuracy": 0.6034559831023216,
+      "num_tokens": 791061.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.710488200187683,
+      "learning_rate": 8.370044052863437e-05,
+      "loss": 2.2123,
+      "mean_token_accuracy": 0.6031243965029717,
+      "num_tokens": 813112.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.6577777777777778,
+      "grad_norm": 1.9046748876571655,
+      "learning_rate": 8.307111390811831e-05,
+      "loss": 2.2185,
+      "mean_token_accuracy": 0.6007313683629036,
+      "num_tokens": 835469.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "grad_norm": 1.9116525650024414,
+      "learning_rate": 8.244178728760226e-05,
+      "loss": 2.2382,
+      "mean_token_accuracy": 0.5930798187851906,
+      "num_tokens": 857795.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 1.8034720420837402,
+      "learning_rate": 8.181246066708622e-05,
+      "loss": 2.191,
+      "mean_token_accuracy": 0.6052505746483803,
+      "num_tokens": 879659.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 1.8932994604110718,
+      "learning_rate": 8.118313404657017e-05,
+      "loss": 2.1755,
+      "mean_token_accuracy": 0.6076797977089882,
+      "num_tokens": 902240.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "eval_loss": 2.188769817352295,
+      "eval_mean_token_accuracy": 0.6060388499498367,
+      "eval_num_tokens": 902240.0,
+      "eval_runtime": 29.9448,
+      "eval_samples_per_second": 33.395,
+      "eval_steps_per_second": 8.349,
+      "step": 400
+    },
+    {
+      "epoch": 0.7288888888888889,
+      "grad_norm": 1.7485570907592773,
+      "learning_rate": 8.055380742605413e-05,
+      "loss": 2.2019,
+      "mean_token_accuracy": 0.6058685064315796,
+      "num_tokens": 925091.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 1.818544864654541,
+      "learning_rate": 7.992448080553809e-05,
+      "loss": 2.2313,
+      "mean_token_accuracy": 0.5964938789606095,
+      "num_tokens": 948151.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.7644444444444445,
+      "grad_norm": 1.796096682548523,
+      "learning_rate": 7.929515418502203e-05,
+      "loss": 2.141,
+      "mean_token_accuracy": 0.6135336428880691,
+      "num_tokens": 970339.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 1.7699111700057983,
+      "learning_rate": 7.866582756450598e-05,
+      "loss": 2.1904,
+      "mean_token_accuracy": 0.6022625803947449,
+      "num_tokens": 993552.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.906336784362793,
+      "learning_rate": 7.803650094398993e-05,
+      "loss": 2.2017,
+      "mean_token_accuracy": 0.602821895480156,
+      "num_tokens": 1015564.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.8177777777777778,
+      "grad_norm": 1.9261703491210938,
+      "learning_rate": 7.740717432347388e-05,
+      "loss": 2.1101,
+      "mean_token_accuracy": 0.6158386886119842,
+      "num_tokens": 1037721.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.8355555555555556,
+      "grad_norm": 1.7876946926116943,
+      "learning_rate": 7.677784770295784e-05,
+      "loss": 2.1866,
+      "mean_token_accuracy": 0.6046899721026421,
+      "num_tokens": 1060627.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 1.8447351455688477,
+      "learning_rate": 7.61485210824418e-05,
+      "loss": 2.1564,
+      "mean_token_accuracy": 0.6088386848568916,
+      "num_tokens": 1082672.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.8711111111111111,
+      "grad_norm": 1.7662327289581299,
+      "learning_rate": 7.551919446192575e-05,
+      "loss": 2.1566,
+      "mean_token_accuracy": 0.6086945086717606,
+      "num_tokens": 1104857.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.807004451751709,
+      "learning_rate": 7.48898678414097e-05,
+      "loss": 2.166,
+      "mean_token_accuracy": 0.605591855943203,
+      "num_tokens": 1127612.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 1.895982265472412,
+      "learning_rate": 7.426054122089365e-05,
+      "loss": 2.1645,
+      "mean_token_accuracy": 0.606428450345993,
+      "num_tokens": 1150411.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 1.8196443319320679,
+      "learning_rate": 7.36312146003776e-05,
+      "loss": 2.1878,
+      "mean_token_accuracy": 0.6036446511745452,
+      "num_tokens": 1172683.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.9422222222222222,
+      "grad_norm": 1.7809892892837524,
+      "learning_rate": 7.300188797986154e-05,
+      "loss": 2.0691,
+      "mean_token_accuracy": 0.6235968723893166,
+      "num_tokens": 1194160.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.774588704109192,
+      "learning_rate": 7.23725613593455e-05,
+      "loss": 2.1057,
+      "mean_token_accuracy": 0.6202786311507225,
+      "num_tokens": 1215760.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 1.8483060598373413,
+      "learning_rate": 7.174323473882946e-05,
+      "loss": 2.1634,
+      "mean_token_accuracy": 0.6098488807678223,
+      "num_tokens": 1238191.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "grad_norm": 1.9268509149551392,
+      "learning_rate": 7.111390811831341e-05,
+      "loss": 2.136,
+      "mean_token_accuracy": 0.6116517767310142,
+      "num_tokens": 1260429.0,
+      "step": 560
+    },
+    {
+      "epoch": 1.0124444444444445,
+      "grad_norm": 1.7296037673950195,
+      "learning_rate": 7.048458149779737e-05,
+      "loss": 2.0938,
+      "mean_token_accuracy": 0.6153759768134669,
+      "num_tokens": 1281232.0,
+      "step": 570
+    },
+    {
+      "epoch": 1.0302222222222222,
+      "grad_norm": 1.8975368738174438,
+      "learning_rate": 6.985525487728132e-05,
+      "loss": 2.0172,
+      "mean_token_accuracy": 0.6284284889698029,
+      "num_tokens": 1304130.0,
+      "step": 580
+    },
+    {
+      "epoch": 1.048,
+      "grad_norm": 1.8282201290130615,
+      "learning_rate": 6.922592825676527e-05,
+      "loss": 1.9979,
+      "mean_token_accuracy": 0.6334663733839989,
+      "num_tokens": 1326753.0,
+      "step": 590
+    },
+    {
+      "epoch": 1.0657777777777777,
+      "grad_norm": 1.7836159467697144,
+      "learning_rate": 6.859660163624921e-05,
+      "loss": 2.0058,
+      "mean_token_accuracy": 0.6304456666111946,
+      "num_tokens": 1348985.0,
+      "step": 600
+    },
+    {
+      "epoch": 1.0657777777777777,
+      "eval_loss": 2.114622116088867,
+      "eval_mean_token_accuracy": 0.6162020459175109,
+      "eval_num_tokens": 1348985.0,
+      "eval_runtime": 30.8226,
+      "eval_samples_per_second": 32.444,
+      "eval_steps_per_second": 8.111,
+      "step": 600
+    },
+    {
+      "epoch": 1.0835555555555556,
+      "grad_norm": 1.7529979944229126,
+      "learning_rate": 6.796727501573316e-05,
+      "loss": 2.0084,
+      "mean_token_accuracy": 0.6300177469849586,
+      "num_tokens": 1371318.0,
+      "step": 610
+    },
+    {
+      "epoch": 1.1013333333333333,
+      "grad_norm": 1.897518277168274,
+      "learning_rate": 6.733794839521712e-05,
+      "loss": 2.0348,
+      "mean_token_accuracy": 0.6270109280943871,
+      "num_tokens": 1393816.0,
+      "step": 620
+    },
+    {
+      "epoch": 1.1191111111111112,
+      "grad_norm": 1.9589266777038574,
+      "learning_rate": 6.670862177470107e-05,
+      "loss": 2.0377,
+      "mean_token_accuracy": 0.6255080983042717,
+      "num_tokens": 1416529.0,
+      "step": 630
+    },
+    {
+      "epoch": 1.1368888888888888,
+      "grad_norm": 1.933893084526062,
+      "learning_rate": 6.607929515418503e-05,
+      "loss": 2.0548,
+      "mean_token_accuracy": 0.6250210508704186,
+      "num_tokens": 1438970.0,
+      "step": 640
+    },
+    {
+      "epoch": 1.1546666666666667,
+      "grad_norm": 1.8967244625091553,
+      "learning_rate": 6.544996853366899e-05,
+      "loss": 2.0309,
+      "mean_token_accuracy": 0.6257808804512024,
+      "num_tokens": 1461324.0,
+      "step": 650
+    },
+    {
+      "epoch": 1.1724444444444444,
+      "grad_norm": 2.01849365234375,
+      "learning_rate": 6.482064191315293e-05,
+      "loss": 2.0737,
+      "mean_token_accuracy": 0.6156815335154533,
+      "num_tokens": 1484246.0,
+      "step": 660
+    },
+    {
+      "epoch": 1.1902222222222223,
+      "grad_norm": 1.8661456108093262,
+      "learning_rate": 6.419131529263688e-05,
+      "loss": 2.0632,
+      "mean_token_accuracy": 0.6184948399662972,
+      "num_tokens": 1507305.0,
+      "step": 670
+    },
+    {
+      "epoch": 1.208,
+      "grad_norm": 1.8781774044036865,
+      "learning_rate": 6.356198867212083e-05,
+      "loss": 2.0029,
+      "mean_token_accuracy": 0.6336544677615166,
+      "num_tokens": 1529082.0,
+      "step": 680
+    },
+    {
+      "epoch": 1.2257777777777779,
+      "grad_norm": 1.8406771421432495,
+      "learning_rate": 6.293266205160478e-05,
+      "loss": 2.0102,
+      "mean_token_accuracy": 0.6291820913553238,
+      "num_tokens": 1551159.0,
+      "step": 690
+    },
+    {
+      "epoch": 1.2435555555555555,
+      "grad_norm": 1.829233169555664,
+      "learning_rate": 6.230333543108874e-05,
+      "loss": 2.0396,
+      "mean_token_accuracy": 0.6300060883164406,
+      "num_tokens": 1573348.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.2613333333333334,
+      "grad_norm": 1.9671298265457153,
+      "learning_rate": 6.167400881057269e-05,
+      "loss": 2.0326,
+      "mean_token_accuracy": 0.6287923157215118,
+      "num_tokens": 1595989.0,
+      "step": 710
+    },
+    {
+      "epoch": 1.279111111111111,
+      "grad_norm": 2.0840771198272705,
+      "learning_rate": 6.104468219005665e-05,
+      "loss": 2.0659,
+      "mean_token_accuracy": 0.628783118724823,
+      "num_tokens": 1617895.0,
+      "step": 720
+    },
+    {
+      "epoch": 1.2968888888888888,
+      "grad_norm": 2.056278944015503,
+      "learning_rate": 6.04153555695406e-05,
+      "loss": 2.0177,
+      "mean_token_accuracy": 0.627280455827713,
+      "num_tokens": 1640415.0,
+      "step": 730
+    },
+    {
+      "epoch": 1.3146666666666667,
+      "grad_norm": 1.9183000326156616,
+      "learning_rate": 5.978602894902454e-05,
+      "loss": 1.9958,
+      "mean_token_accuracy": 0.631256802380085,
+      "num_tokens": 1662713.0,
+      "step": 740
+    },
+    {
+      "epoch": 1.3324444444444445,
+      "grad_norm": 2.005032777786255,
+      "learning_rate": 5.9156702328508496e-05,
+      "loss": 2.0164,
+      "mean_token_accuracy": 0.631276798248291,
+      "num_tokens": 1684783.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.3502222222222222,
+      "grad_norm": 1.8667700290679932,
+      "learning_rate": 5.852737570799245e-05,
+      "loss": 2.0295,
+      "mean_token_accuracy": 0.6288824707269669,
+      "num_tokens": 1706623.0,
+      "step": 760
+    },
+    {
+      "epoch": 1.3679999999999999,
+      "grad_norm": 2.123706817626953,
+      "learning_rate": 5.78980490874764e-05,
+      "loss": 2.0513,
+      "mean_token_accuracy": 0.6215401113033294,
+      "num_tokens": 1729494.0,
+      "step": 770
+    },
+    {
+      "epoch": 1.3857777777777778,
+      "grad_norm": 1.9470572471618652,
+      "learning_rate": 5.7268722466960356e-05,
+      "loss": 2.0179,
+      "mean_token_accuracy": 0.630026438832283,
+      "num_tokens": 1752045.0,
+      "step": 780
+    },
+    {
+      "epoch": 1.4035555555555557,
+      "grad_norm": 1.8666447401046753,
+      "learning_rate": 5.663939584644431e-05,
+      "loss": 2.035,
+      "mean_token_accuracy": 0.6255004242062568,
+      "num_tokens": 1775601.0,
+      "step": 790
+    },
+    {
+      "epoch": 1.4213333333333333,
+      "grad_norm": 1.8963086605072021,
+      "learning_rate": 5.601006922592826e-05,
+      "loss": 2.0004,
+      "mean_token_accuracy": 0.6287154361605645,
+      "num_tokens": 1798633.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.4213333333333333,
+      "eval_loss": 2.071798324584961,
+      "eval_mean_token_accuracy": 0.6222149915695191,
+      "eval_num_tokens": 1798633.0,
+      "eval_runtime": 30.3161,
+      "eval_samples_per_second": 32.986,
+      "eval_steps_per_second": 8.246,
+      "step": 800
+    },
+    {
+      "epoch": 1.439111111111111,
+      "grad_norm": 1.9529728889465332,
+      "learning_rate": 5.5380742605412216e-05,
+      "loss": 1.9781,
+      "mean_token_accuracy": 0.6329582959413529,
+      "num_tokens": 1820656.0,
+      "step": 810
+    },
+    {
+      "epoch": 1.456888888888889,
+      "grad_norm": 1.9527575969696045,
+      "learning_rate": 5.475141598489616e-05,
+      "loss": 2.0212,
+      "mean_token_accuracy": 0.6298958778381347,
+      "num_tokens": 1842871.0,
+      "step": 820
+    },
+    {
+      "epoch": 1.4746666666666668,
+      "grad_norm": 1.7937837839126587,
+      "learning_rate": 5.4122089364380114e-05,
+      "loss": 1.9904,
+      "mean_token_accuracy": 0.635308350622654,
+      "num_tokens": 1865652.0,
+      "step": 830
+    },
+    {
+      "epoch": 1.4924444444444445,
+      "grad_norm": 1.888289213180542,
+      "learning_rate": 5.349276274386407e-05,
+      "loss": 2.0129,
+      "mean_token_accuracy": 0.6266900539398194,
+      "num_tokens": 1888455.0,
+      "step": 840
+    },
+    {
+      "epoch": 1.5102222222222221,
+      "grad_norm": 2.0203657150268555,
+      "learning_rate": 5.286343612334802e-05,
+      "loss": 1.9766,
+      "mean_token_accuracy": 0.6383475095033646,
+      "num_tokens": 1910676.0,
+      "step": 850
+    },
+    {
+      "epoch": 1.528,
+      "grad_norm": 2.0756003856658936,
+      "learning_rate": 5.2234109502831975e-05,
+      "loss": 2.0257,
+      "mean_token_accuracy": 0.6280800834298134,
+      "num_tokens": 1933253.0,
+      "step": 860
+    },
+    {
+      "epoch": 1.545777777777778,
+      "grad_norm": 2.112074375152588,
+      "learning_rate": 5.160478288231593e-05,
+      "loss": 2.0314,
+      "mean_token_accuracy": 0.6242304086685181,
+      "num_tokens": 1955820.0,
+      "step": 870
+    },
+    {
+      "epoch": 1.5635555555555556,
+      "grad_norm": 1.9367856979370117,
+      "learning_rate": 5.097545626179988e-05,
+      "loss": 2.0112,
+      "mean_token_accuracy": 0.6305277988314628,
+      "num_tokens": 1978120.0,
+      "step": 880
+    },
+    {
+      "epoch": 1.5813333333333333,
+      "grad_norm": 1.991443395614624,
+      "learning_rate": 5.034612964128382e-05,
+      "loss": 1.9569,
+      "mean_token_accuracy": 0.6372233361005784,
+      "num_tokens": 2000508.0,
+      "step": 890
+    },
+    {
+      "epoch": 1.5991111111111111,
+      "grad_norm": 1.8759173154830933,
+      "learning_rate": 4.9716803020767784e-05,
+      "loss": 1.9894,
+      "mean_token_accuracy": 0.6314782112836838,
+      "num_tokens": 2023356.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.616888888888889,
+      "grad_norm": 1.8218945264816284,
+      "learning_rate": 4.908747640025173e-05,
+      "loss": 1.9459,
+      "mean_token_accuracy": 0.6442534357309342,
+      "num_tokens": 2045965.0,
+      "step": 910
+    },
+    {
+      "epoch": 1.6346666666666667,
+      "grad_norm": 1.9485502243041992,
+      "learning_rate": 4.845814977973568e-05,
+      "loss": 2.0177,
+      "mean_token_accuracy": 0.6231269478797913,
+      "num_tokens": 2069108.0,
+      "step": 920
+    },
+    {
+      "epoch": 1.6524444444444444,
+      "grad_norm": 1.9244948625564575,
+      "learning_rate": 4.782882315921964e-05,
+      "loss": 2.0259,
+      "mean_token_accuracy": 0.6279663592576981,
+      "num_tokens": 2091755.0,
+      "step": 930
+    },
+    {
+      "epoch": 1.6702222222222223,
+      "grad_norm": 1.9663888216018677,
+      "learning_rate": 4.719949653870359e-05,
+      "loss": 1.9896,
+      "mean_token_accuracy": 0.6341330617666244,
+      "num_tokens": 2114496.0,
+      "step": 940
+    },
+    {
+      "epoch": 1.688,
+      "grad_norm": 1.9700689315795898,
+      "learning_rate": 4.657016991818754e-05,
+      "loss": 2.0081,
+      "mean_token_accuracy": 0.629092475771904,
+      "num_tokens": 2137041.0,
+      "step": 950
+    },
+    {
+      "epoch": 1.7057777777777776,
+      "grad_norm": 1.9976369142532349,
+      "learning_rate": 4.594084329767149e-05,
+      "loss": 2.0177,
+      "mean_token_accuracy": 0.6279423177242279,
+      "num_tokens": 2159711.0,
+      "step": 960
+    },
+    {
+      "epoch": 1.7235555555555555,
+      "grad_norm": 1.9927507638931274,
+      "learning_rate": 4.531151667715545e-05,
+      "loss": 2.0111,
+      "mean_token_accuracy": 0.632372610270977,
+      "num_tokens": 2181675.0,
+      "step": 970
+    },
+    {
+      "epoch": 1.7413333333333334,
+      "grad_norm": 1.9318374395370483,
+      "learning_rate": 4.46821900566394e-05,
+      "loss": 1.9772,
+      "mean_token_accuracy": 0.6370243668556214,
+      "num_tokens": 2204671.0,
+      "step": 980
+    },
+    {
+      "epoch": 1.759111111111111,
+      "grad_norm": 1.8933532238006592,
+      "learning_rate": 4.405286343612335e-05,
+      "loss": 2.0098,
+      "mean_token_accuracy": 0.6229412123560906,
+      "num_tokens": 2227866.0,
+      "step": 990
+    },
+    {
+      "epoch": 1.7768888888888887,
+      "grad_norm": 2.063185930252075,
+      "learning_rate": 4.34235368156073e-05,
+      "loss": 1.9801,
+      "mean_token_accuracy": 0.6361721217632293,
+      "num_tokens": 2250379.0,
+      "step": 1000
+    },
+    {
+      "epoch": 1.7768888888888887,
+      "eval_loss": 2.036764621734619,
+      "eval_mean_token_accuracy": 0.6262071034908294,
+      "eval_num_tokens": 2250379.0,
+      "eval_runtime": 31.2979,
+      "eval_samples_per_second": 31.951,
+      "eval_steps_per_second": 7.988,
+      "step": 1000
+    },
+    {
+      "epoch": 1.7946666666666666,
+      "grad_norm": 1.9427729845046997,
+      "learning_rate": 4.2794210195091256e-05,
+      "loss": 2.0155,
+      "mean_token_accuracy": 0.6281099706888199,
+      "num_tokens": 2272999.0,
+      "step": 1010
+    },
+    {
+      "epoch": 1.8124444444444445,
+      "grad_norm": 1.842465877532959,
+      "learning_rate": 4.216488357457521e-05,
+      "loss": 1.9861,
+      "mean_token_accuracy": 0.6330478996038437,
+      "num_tokens": 2295110.0,
+      "step": 1020
+    },
+    {
+      "epoch": 1.8302222222222222,
+      "grad_norm": 1.8547931909561157,
+      "learning_rate": 4.1535556954059154e-05,
+      "loss": 1.9617,
+      "mean_token_accuracy": 0.6373973488807678,
+      "num_tokens": 2317432.0,
+      "step": 1030
+    },
+    {
+      "epoch": 1.8479999999999999,
+      "grad_norm": 1.8283085823059082,
+      "learning_rate": 4.090623033354311e-05,
+      "loss": 1.9987,
+      "mean_token_accuracy": 0.6286273017525673,
+      "num_tokens": 2340305.0,
+      "step": 1040
+    },
+    {
+      "epoch": 1.8657777777777778,
+      "grad_norm": 1.9289031028747559,
+      "learning_rate": 4.0276903713027065e-05,
+      "loss": 2.0035,
+      "mean_token_accuracy": 0.6320135101675988,
+      "num_tokens": 2362746.0,
+      "step": 1050
+    },
+    {
+      "epoch": 1.8835555555555556,
+      "grad_norm": 1.8411505222320557,
+      "learning_rate": 3.9647577092511014e-05,
+      "loss": 1.9697,
+      "mean_token_accuracy": 0.6332684755325317,
+      "num_tokens": 2385647.0,
+      "step": 1060
+    },
+    {
+      "epoch": 1.9013333333333333,
+      "grad_norm": 2.0083494186401367,
+      "learning_rate": 3.901825047199496e-05,
+      "loss": 1.987,
+      "mean_token_accuracy": 0.627101382613182,
+      "num_tokens": 2408732.0,
+      "step": 1070
+    },
+    {
+      "epoch": 1.919111111111111,
+      "grad_norm": 2.150812864303589,
+      "learning_rate": 3.838892385147892e-05,
+      "loss": 1.9642,
+      "mean_token_accuracy": 0.6350547641515731,
+      "num_tokens": 2431137.0,
+      "step": 1080
+    },
+    {
+      "epoch": 1.9368888888888889,
+      "grad_norm": 1.9779438972473145,
+      "learning_rate": 3.7759597230962874e-05,
+      "loss": 1.9249,
+      "mean_token_accuracy": 0.6438971221446991,
+      "num_tokens": 2453517.0,
+      "step": 1090
+    },
+    {
+      "epoch": 1.9546666666666668,
+      "grad_norm": 2.0672504901885986,
+      "learning_rate": 3.7130270610446823e-05,
+      "loss": 1.9679,
+      "mean_token_accuracy": 0.6345437586307525,
+      "num_tokens": 2475737.0,
+      "step": 1100
+    },
+    {
+      "epoch": 1.9724444444444444,
+      "grad_norm": 1.9778350591659546,
+      "learning_rate": 3.650094398993077e-05,
+      "loss": 1.9733,
+      "mean_token_accuracy": 0.6329764410853386,
+      "num_tokens": 2497880.0,
+      "step": 1110
+    },
+    {
+      "epoch": 1.9902222222222221,
+      "grad_norm": 2.014357328414917,
+      "learning_rate": 3.587161736941473e-05,
+      "loss": 1.9714,
+      "mean_token_accuracy": 0.635537999868393,
+      "num_tokens": 2519974.0,
+      "step": 1120
+    },
+    {
+      "epoch": 2.007111111111111,
+      "grad_norm": 1.9104490280151367,
+      "learning_rate": 3.5242290748898684e-05,
+      "loss": 1.8849,
+      "mean_token_accuracy": 0.6536890221269507,
+      "num_tokens": 2540296.0,
+      "step": 1130
+    },
+    {
+      "epoch": 2.024888888888889,
+      "grad_norm": 2.0223166942596436,
+      "learning_rate": 3.461296412838263e-05,
+      "loss": 1.8811,
+      "mean_token_accuracy": 0.6483465373516083,
+      "num_tokens": 2561919.0,
+      "step": 1140
+    },
+    {
+      "epoch": 2.042666666666667,
+      "grad_norm": 1.8120856285095215,
+      "learning_rate": 3.398363750786658e-05,
+      "loss": 1.9212,
+      "mean_token_accuracy": 0.6420063003897667,
+      "num_tokens": 2584915.0,
+      "step": 1150
+    },
+    {
+      "epoch": 2.0604444444444443,
+      "grad_norm": 1.9729136228561401,
+      "learning_rate": 3.335431088735054e-05,
+      "loss": 1.8851,
+      "mean_token_accuracy": 0.6519104614853859,
+      "num_tokens": 2606857.0,
+      "step": 1160
+    },
+    {
+      "epoch": 2.078222222222222,
+      "grad_norm": 2.1263654232025146,
+      "learning_rate": 3.272498426683449e-05,
+      "loss": 1.8905,
+      "mean_token_accuracy": 0.6453483879566193,
+      "num_tokens": 2629737.0,
+      "step": 1170
+    },
+    {
+      "epoch": 2.096,
+      "grad_norm": 1.9857081174850464,
+      "learning_rate": 3.209565764631844e-05,
+      "loss": 1.8381,
+      "mean_token_accuracy": 0.653864786028862,
+      "num_tokens": 2651936.0,
+      "step": 1180
+    },
+    {
+      "epoch": 2.113777777777778,
+      "grad_norm": 1.9701604843139648,
+      "learning_rate": 3.146633102580239e-05,
+      "loss": 1.9133,
+      "mean_token_accuracy": 0.6435931533575058,
+      "num_tokens": 2675241.0,
+      "step": 1190
+    },
+    {
+      "epoch": 2.1315555555555554,
+      "grad_norm": 1.9061148166656494,
+      "learning_rate": 3.0837004405286347e-05,
+      "loss": 1.8832,
+      "mean_token_accuracy": 0.6495110660791397,
+      "num_tokens": 2698219.0,
+      "step": 1200
+    },
+    {
+      "epoch": 2.1315555555555554,
+      "eval_loss": 2.020338296890259,
+      "eval_mean_token_accuracy": 0.6295755279064178,
+      "eval_num_tokens": 2698219.0,
+      "eval_runtime": 30.7487,
+      "eval_samples_per_second": 32.522,
+      "eval_steps_per_second": 8.13,
+      "step": 1200
+    },
+    {
+      "epoch": 2.1493333333333333,
+      "grad_norm": 2.1164379119873047,
+      "learning_rate": 3.02076777847703e-05,
+      "loss": 1.8986,
+      "mean_token_accuracy": 0.6449921384453774,
+      "num_tokens": 2721580.0,
+      "step": 1210
+    },
+    {
+      "epoch": 2.167111111111111,
+      "grad_norm": 1.9740287065505981,
+      "learning_rate": 2.9578351164254248e-05,
+      "loss": 1.8953,
+      "mean_token_accuracy": 0.648700350522995,
+      "num_tokens": 2744110.0,
+      "step": 1220
+    },
+    {
+      "epoch": 2.1848888888888887,
+      "grad_norm": 1.9970844984054565,
+      "learning_rate": 2.89490245437382e-05,
+      "loss": 1.8693,
+      "mean_token_accuracy": 0.6546828895807266,
+      "num_tokens": 2765844.0,
+      "step": 1230
+    },
+    {
+      "epoch": 2.2026666666666666,
+      "grad_norm": 2.06357479095459,
+      "learning_rate": 2.8319697923222156e-05,
+      "loss": 1.8775,
+      "mean_token_accuracy": 0.6484791278839112,
+      "num_tokens": 2788070.0,
+      "step": 1240
+    },
+    {
+      "epoch": 2.2204444444444444,
+      "grad_norm": 1.9746241569519043,
+      "learning_rate": 2.7690371302706108e-05,
+      "loss": 1.9117,
+      "mean_token_accuracy": 0.6470579236745835,
+      "num_tokens": 2810964.0,
+      "step": 1250
+    },
+    {
+      "epoch": 2.2382222222222223,
+      "grad_norm": 2.1169064044952393,
+      "learning_rate": 2.7061044682190057e-05,
+      "loss": 1.8684,
+      "mean_token_accuracy": 0.6524357482790947,
+      "num_tokens": 2833176.0,
+      "step": 1260
+    },
+    {
+      "epoch": 2.2560000000000002,
+      "grad_norm": 2.0234525203704834,
+      "learning_rate": 2.643171806167401e-05,
+      "loss": 1.9089,
+      "mean_token_accuracy": 0.6425125360488891,
+      "num_tokens": 2855440.0,
+      "step": 1270
+    },
+    {
+      "epoch": 2.2737777777777777,
+      "grad_norm": 2.0508742332458496,
+      "learning_rate": 2.5802391441157965e-05,
+      "loss": 1.8463,
+      "mean_token_accuracy": 0.6541648581624031,
+      "num_tokens": 2877713.0,
+      "step": 1280
+    },
+    {
+      "epoch": 2.2915555555555556,
+      "grad_norm": 1.863732099533081,
+      "learning_rate": 2.517306482064191e-05,
+      "loss": 1.8953,
+      "mean_token_accuracy": 0.6487652212381363,
+      "num_tokens": 2899934.0,
+      "step": 1290
+    },
+    {
+      "epoch": 2.3093333333333335,
+      "grad_norm": 2.148881196975708,
+      "learning_rate": 2.4543738200125866e-05,
+      "loss": 1.8937,
+      "mean_token_accuracy": 0.6466890797019005,
+      "num_tokens": 2923244.0,
+      "step": 1300
+    },
+    {
+      "epoch": 2.327111111111111,
+      "grad_norm": 2.0562210083007812,
+      "learning_rate": 2.391441157960982e-05,
+      "loss": 1.8776,
+      "mean_token_accuracy": 0.648098886013031,
+      "num_tokens": 2945580.0,
+      "step": 1310
+    },
+    {
+      "epoch": 2.344888888888889,
+      "grad_norm": 1.9801143407821655,
+      "learning_rate": 2.328508495909377e-05,
+      "loss": 1.8718,
+      "mean_token_accuracy": 0.6436786696314811,
+      "num_tokens": 2969470.0,
+      "step": 1320
+    },
+    {
+      "epoch": 2.3626666666666667,
+      "grad_norm": 2.244140863418579,
+      "learning_rate": 2.2655758338577723e-05,
+      "loss": 1.871,
+      "mean_token_accuracy": 0.6460510939359665,
+      "num_tokens": 2991982.0,
+      "step": 1330
+    },
+    {
+      "epoch": 2.3804444444444446,
+      "grad_norm": 1.993152379989624,
+      "learning_rate": 2.2026431718061676e-05,
+      "loss": 1.8909,
+      "mean_token_accuracy": 0.6495360463857651,
+      "num_tokens": 3014206.0,
+      "step": 1340
+    },
+    {
+      "epoch": 2.398222222222222,
+      "grad_norm": 1.974604606628418,
+      "learning_rate": 2.1397105097545628e-05,
+      "loss": 1.843,
+      "mean_token_accuracy": 0.6507977247238159,
+      "num_tokens": 3036651.0,
+      "step": 1350
+    },
+    {
+      "epoch": 2.416,
+      "grad_norm": 1.9981292486190796,
+      "learning_rate": 2.0767778477029577e-05,
+      "loss": 1.8775,
+      "mean_token_accuracy": 0.6513748601078987,
+      "num_tokens": 3058745.0,
+      "step": 1360
+    },
+    {
+      "epoch": 2.433777777777778,
+      "grad_norm": 2.1414084434509277,
+      "learning_rate": 2.0138451856513533e-05,
+      "loss": 1.8904,
+      "mean_token_accuracy": 0.6470720157027244,
+      "num_tokens": 3081726.0,
+      "step": 1370
+    },
+    {
+      "epoch": 2.4515555555555557,
+      "grad_norm": 2.157397747039795,
+      "learning_rate": 1.950912523599748e-05,
+      "loss": 1.8711,
+      "mean_token_accuracy": 0.6492032095789909,
+      "num_tokens": 3104292.0,
+      "step": 1380
+    },
+    {
+      "epoch": 2.469333333333333,
+      "grad_norm": 2.0714213848114014,
+      "learning_rate": 1.8879798615481437e-05,
+      "loss": 1.8845,
+      "mean_token_accuracy": 0.6478913977742196,
+      "num_tokens": 3126334.0,
+      "step": 1390
+    },
+    {
+      "epoch": 2.487111111111111,
+      "grad_norm": 2.1000311374664307,
+      "learning_rate": 1.8250471994965386e-05,
+      "loss": 1.9088,
+      "mean_token_accuracy": 0.6414603188633918,
+      "num_tokens": 3149845.0,
+      "step": 1400
+    },
+    {
+      "epoch": 2.487111111111111,
+      "eval_loss": 2.0077672004699707,
+      "eval_mean_token_accuracy": 0.63226633644104,
+      "eval_num_tokens": 3149845.0,
+      "eval_runtime": 30.4714,
+      "eval_samples_per_second": 32.818,
+      "eval_steps_per_second": 8.204,
+      "step": 1400
+    },
+    {
+      "epoch": 2.504888888888889,
+      "grad_norm": 1.9947516918182373,
+      "learning_rate": 1.7621145374449342e-05,
+      "loss": 1.8948,
+      "mean_token_accuracy": 0.6480994567275047,
+      "num_tokens": 3172117.0,
+      "step": 1410
+    },
+    {
+      "epoch": 2.522666666666667,
+      "grad_norm": 2.0749399662017822,
+      "learning_rate": 1.699181875393329e-05,
+      "loss": 1.8821,
+      "mean_token_accuracy": 0.6532607778906823,
+      "num_tokens": 3194261.0,
+      "step": 1420
+    },
+    {
+      "epoch": 2.5404444444444443,
+      "grad_norm": 2.021650552749634,
+      "learning_rate": 1.6362492133417247e-05,
+      "loss": 1.7886,
+      "mean_token_accuracy": 0.6606403380632401,
+      "num_tokens": 3216455.0,
+      "step": 1430
+    },
+    {
+      "epoch": 2.558222222222222,
+      "grad_norm": 2.041862726211548,
+      "learning_rate": 1.5733165512901195e-05,
+      "loss": 1.9171,
+      "mean_token_accuracy": 0.6459932029247284,
+      "num_tokens": 3238359.0,
+      "step": 1440
+    },
+    {
+      "epoch": 2.576,
+      "grad_norm": 1.9248042106628418,
+      "learning_rate": 1.510383889238515e-05,
+      "loss": 1.9163,
+      "mean_token_accuracy": 0.6407139167189598,
+      "num_tokens": 3261568.0,
+      "step": 1450
+    },
+    {
+      "epoch": 2.5937777777777775,
+      "grad_norm": 2.2711341381073,
+      "learning_rate": 1.44745122718691e-05,
+      "loss": 1.9086,
+      "mean_token_accuracy": 0.6399997368454933,
+      "num_tokens": 3284517.0,
+      "step": 1460
+    },
+    {
+      "epoch": 2.6115555555555554,
+      "grad_norm": 2.2452495098114014,
+      "learning_rate": 1.3845185651353054e-05,
+      "loss": 1.8712,
+      "mean_token_accuracy": 0.649416595697403,
+      "num_tokens": 3306623.0,
+      "step": 1470
+    },
+    {
+      "epoch": 2.6293333333333333,
+      "grad_norm": 1.9956483840942383,
+      "learning_rate": 1.3215859030837005e-05,
+      "loss": 1.8503,
+      "mean_token_accuracy": 0.6563126415014267,
+      "num_tokens": 3329270.0,
+      "step": 1480
+    },
+    {
+      "epoch": 2.647111111111111,
+      "grad_norm": 2.000636100769043,
+      "learning_rate": 1.2586532410320955e-05,
+      "loss": 1.8668,
+      "mean_token_accuracy": 0.6488404273986816,
+      "num_tokens": 3352533.0,
+      "step": 1490
+    },
+    {
+      "epoch": 2.664888888888889,
+      "grad_norm": 2.1857969760894775,
+      "learning_rate": 1.195720578980491e-05,
+      "loss": 1.8487,
+      "mean_token_accuracy": 0.6583347156643867,
+      "num_tokens": 3374132.0,
+      "step": 1500
+    },
+    {
+      "epoch": 2.6826666666666665,
+      "grad_norm": 1.9961498975753784,
+      "learning_rate": 1.1327879169288862e-05,
+      "loss": 1.9102,
+      "mean_token_accuracy": 0.6406741261482238,
+      "num_tokens": 3397176.0,
+      "step": 1510
+    },
+    {
+      "epoch": 2.7004444444444444,
+      "grad_norm": 2.1003425121307373,
+      "learning_rate": 1.0698552548772814e-05,
+      "loss": 1.8477,
+      "mean_token_accuracy": 0.6532559394836426,
+      "num_tokens": 3418961.0,
+      "step": 1520
+    },
+    {
+      "epoch": 2.7182222222222223,
+      "grad_norm": 2.024757146835327,
+      "learning_rate": 1.0069225928256766e-05,
+      "loss": 1.8602,
+      "mean_token_accuracy": 0.6530294433236122,
+      "num_tokens": 3441815.0,
+      "step": 1530
+    },
+    {
+      "epoch": 2.7359999999999998,
+      "grad_norm": 1.9595909118652344,
+      "learning_rate": 9.439899307740719e-06,
+      "loss": 1.8787,
+      "mean_token_accuracy": 0.6477272987365723,
+      "num_tokens": 3464582.0,
+      "step": 1540
+    },
+    {
+      "epoch": 2.7537777777777777,
+      "grad_norm": 1.9734858274459839,
+      "learning_rate": 8.810572687224671e-06,
+      "loss": 1.8385,
+      "mean_token_accuracy": 0.656038624048233,
+      "num_tokens": 3486694.0,
+      "step": 1550
+    },
+    {
+      "epoch": 2.7715555555555556,
+      "grad_norm": 2.0039222240448,
+      "learning_rate": 8.181246066708623e-06,
+      "loss": 1.8825,
+      "mean_token_accuracy": 0.6516638934612274,
+      "num_tokens": 3508908.0,
+      "step": 1560
+    },
+    {
+      "epoch": 2.7893333333333334,
+      "grad_norm": 2.040252685546875,
+      "learning_rate": 7.551919446192575e-06,
+      "loss": 1.8168,
+      "mean_token_accuracy": 0.6596024230122566,
+      "num_tokens": 3530306.0,
+      "step": 1570
+    },
+    {
+      "epoch": 2.8071111111111113,
+      "grad_norm": 2.2906384468078613,
+      "learning_rate": 6.922592825676527e-06,
+      "loss": 1.9023,
+      "mean_token_accuracy": 0.643904159963131,
+      "num_tokens": 3552880.0,
+      "step": 1580
+    },
+    {
+      "epoch": 2.824888888888889,
+      "grad_norm": 1.9195839166641235,
+      "learning_rate": 6.293266205160478e-06,
+      "loss": 1.8941,
+      "mean_token_accuracy": 0.648286484181881,
+      "num_tokens": 3575800.0,
+      "step": 1590
+    },
+    {
+      "epoch": 2.8426666666666667,
+      "grad_norm": 2.044443368911743,
+      "learning_rate": 5.663939584644431e-06,
+      "loss": 1.8881,
+      "mean_token_accuracy": 0.652445487678051,
+      "num_tokens": 3598214.0,
+      "step": 1600
+    },
+    {
+      "epoch": 2.8426666666666667,
+      "eval_loss": 1.9988627433776855,
+      "eval_mean_token_accuracy": 0.6337166538238526,
+      "eval_num_tokens": 3598214.0,
+      "eval_runtime": 30.1548,
+      "eval_samples_per_second": 33.162,
+      "eval_steps_per_second": 8.291,
+      "step": 1600
+    },
+    {
+      "epoch": 2.8604444444444446,
+      "grad_norm": 1.9401663541793823,
+      "learning_rate": 5.034612964128383e-06,
+      "loss": 1.8622,
+      "mean_token_accuracy": 0.6543288782238961,
+      "num_tokens": 3620353.0,
+      "step": 1610
+    },
+    {
+      "epoch": 2.878222222222222,
+      "grad_norm": 2.042475700378418,
+      "learning_rate": 4.4052863436123355e-06,
+      "loss": 1.8698,
+      "mean_token_accuracy": 0.6504862099885941,
+      "num_tokens": 3642281.0,
+      "step": 1620
+    },
+    {
+      "epoch": 2.896,
+      "grad_norm": 2.1123745441436768,
+      "learning_rate": 3.7759597230962874e-06,
+      "loss": 1.8245,
+      "mean_token_accuracy": 0.6554929837584496,
+      "num_tokens": 3664853.0,
+      "step": 1630
+    },
+    {
+      "epoch": 2.913777777777778,
+      "grad_norm": 2.1008834838867188,
+      "learning_rate": 3.146633102580239e-06,
+      "loss": 1.9279,
+      "mean_token_accuracy": 0.6415353491902351,
+      "num_tokens": 3688123.0,
+      "step": 1640
+    },
+    {
+      "epoch": 2.9315555555555557,
+      "grad_norm": 2.181321382522583,
+      "learning_rate": 2.5173064820641916e-06,
+      "loss": 1.9278,
+      "mean_token_accuracy": 0.6381989911198616,
+      "num_tokens": 3710934.0,
+      "step": 1650
+    },
+    {
+      "epoch": 2.9493333333333336,
+      "grad_norm": 2.198791742324829,
+      "learning_rate": 1.8879798615481437e-06,
+      "loss": 1.9123,
+      "mean_token_accuracy": 0.6442625164985657,
+      "num_tokens": 3733298.0,
+      "step": 1660
+    },
+    {
+      "epoch": 2.967111111111111,
+      "grad_norm": 1.9645713567733765,
+      "learning_rate": 1.2586532410320958e-06,
+      "loss": 1.9192,
+      "mean_token_accuracy": 0.6413909658789635,
+      "num_tokens": 3755641.0,
+      "step": 1670
+    },
+    {
+      "epoch": 2.984888888888889,
+      "grad_norm": 2.202366590499878,
+      "learning_rate": 6.293266205160479e-07,
+      "loss": 1.8528,
+      "mean_token_accuracy": 0.6523260295391082,
+      "num_tokens": 3777938.0,
+      "step": 1680
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1689,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3370037644550144e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

special_tokens_map.json

@@ -0,0 +1,86 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|endofprompt|>",
+    "<|_unuse_missing_100256|>",
+    "<|_unuse_missing_100261|>",
+    "<|_unuse_missing_100262|>",
+    "<|_unuse_missing_100263|>",
+    "<|_unuse_missing_100264|>",
+    "<|_unuse_missing_100265|>",
+    "<|_unuse_missing_100266|>",
+    "<|_unuse_missing_100267|>",
+    "<|_unuse_missing_100268|>",
+    "<|_unuse_missing_100269|>",
+    "<|_unuse_missing_100270|>",
+    "<|_unuse_missing_100271|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|stop|>",
+    "<|endofturn|>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endofturn|>",
+    "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 +1,501 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100256": {
+      "content": "<|_unuse_missing_100256|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100257": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100261": {
+      "content": "<|_unuse_missing_100261|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100262": {
+      "content": "<|_unuse_missing_100262|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100263": {
+      "content": "<|_unuse_missing_100263|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100264": {
+      "content": "<|_unuse_missing_100264|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|_unuse_missing_100265|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<|_unuse_missing_100266|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100267": {
+      "content": "<|_unuse_missing_100267|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100268": {
+      "content": "<|_unuse_missing_100268|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100269": {
+      "content": "<|_unuse_missing_100269|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100270": {
+      "content": "<|_unuse_missing_100270|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100271": {
+      "content": "<|_unuse_missing_100271|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100272": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100273": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100274": {
+      "content": "<|stop|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100275": {
+      "content": "<|endofturn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110491": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110492": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110493": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110494": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110495": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110496": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110497": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110498": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110499": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110500": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110501": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110502": {
+      "content": "<code_to_intermediate>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110503": {
+      "content": "<intermediate_to_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110504": {
+      "content": "<pr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110505": {
+      "content": "<pr_status>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110506": {
+      "content": "<pr_is_merged>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110507": {
+      "content": "<pr_base>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110508": {
+      "content": "<pr_file>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110509": {
+      "content": "<pr_base_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110510": {
+      "content": "<pr_diff>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110511": {
+      "content": "<pr_diff_hunk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110512": {
+      "content": "<pr_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110513": {
+      "content": "<pr_event_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110514": {
+      "content": "<pr_review>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110515": {
+      "content": "<pr_review_state>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110516": {
+      "content": "<pr_review_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110517": {
+      "content": "<pr_in_reply_to_review_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110518": {
+      "content": "<pr_in_reply_to_comment_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110519": {
+      "content": "<pr_diff_hunk_comment_line>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110520": {
+      "content": "<NAME>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110521": {
+      "content": "<EMAIL>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110522": {
+      "content": "<KEY>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110523": {
+      "content": "<PASSWORD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|endofprompt|>",
+    "<|_unuse_missing_100256|>",
+    "<|_unuse_missing_100261|>",
+    "<|_unuse_missing_100262|>",
+    "<|_unuse_missing_100263|>",
+    "<|_unuse_missing_100264|>",
+    "<|_unuse_missing_100265|>",
+    "<|_unuse_missing_100266|>",
+    "<|_unuse_missing_100267|>",
+    "<|_unuse_missing_100268|>",
+    "<|_unuse_missing_100269|>",
+    "<|_unuse_missing_100270|>",
+    "<|_unuse_missing_100271|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|stop|>",
+    "<|endofturn|>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endofturn|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eceb4430d91d4336dfb8665bee3ec27bf48bbaee43f0bde2d77c967c54bed50b
+size 5624