Upload folder using huggingface_hub

checkpoint-800/README.md

@@ -0,0 +1,202 @@
+---
+base_model: ibm-granite/granite-3.2-2b-instruct
+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 0.14.0

checkpoint-800/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ibm-granite/granite-3.2-2b-instruct",
+  "bias": "none",
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.2,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-800/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:067ae12c5a04efb227cee4ce9a1a62b4c08cc71d5555a58046cbbfd8df39d8b4
+size 136358080

checkpoint-800/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|end_of_role|>": 49153,
+  "<|start_of_role|>": 49152,
+  "<|tool_call|>": 49154
+}

checkpoint-800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:017ea081fa3fb966fa69e0db5e534bd5bef99f49e381dca2585097d940a930b5
+size 70430610

checkpoint-800/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3243c4e3916aa7ad2c673654ee5639edef3c9ce21b80c530ac54c0d95ae9a3f9
+size 14244

checkpoint-800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8238e2c3eee78d29beacbb4b284f2182de6e43e8277417be67741217651c762d
+size 1064

checkpoint-800/special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    "<|start_of_role|>",
+    "<|end_of_role|>",
+    "<|tool_call|>"
+  ],
+  "bos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>",
+  "unk_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-800/tokenizer_config.json

@@ -0,0 +1,199 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49152": {
+      "content": "<|start_of_role|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49153": {
+      "content": "<|end_of_role|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49154": {
+      "content": "<|tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|start_of_role|>",
+    "<|end_of_role|>",
+    "<|tool_call|>"
+  ],
+  "bos_token": "<|end_of_text|>",
+  "chat_template": "{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"Knowledge Cutoff Date: April 2024.\nToday's Date: \" + strftime_now('%B %d, %Y') + \".\nYou are Granite, developed by IBM.\" %}\n    {%- if tools and documents %}\n        {%- set system_message = system_message + \" You are a helpful AI assistant with access to the following tools. When a tool is required to answer the user's query, respond with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.\n\nWrite the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.\" %}\n    {%- elif tools %}\n        {%- set system_message = system_message + \" You are a helpful AI assistant with access to the following tools. When a tool is required to answer the user's query, respond with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.\" %}\n    {%- elif documents %}\n        {%- set system_message = system_message + \" Write the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.\" %}\n    {%- elif thinking %}\n    {%- set system_message = system_message + \" You are a helpful AI assistant.\nRespond to every user query in a comprehensive and detailed way. You can write down your thoughts and reasoning process before responding. In the thought process, engage in a comprehensive cycle of analysis, summarization, exploration, reassessment, reflection, backtracing, and iteration to develop well-considered thinking process. In the response section, based on various attempts, explorations, and reflections from the thoughts section, systematically present the final solution that you deem correct. The response should summarize the thought process. Write your thoughts after 'Here is my thought process:' and write your response after 'Here is my response:' for each user query.\" %}\n    {%- else %}\n        {%- set system_message = system_message + \" You are a helpful AI assistant.\" %}    \n    {%- endif %}\n    {%- if 'citations' in controls and documents %}\n        {%- set system_message = system_message + '\n\nIn your response, use the symbols <co> and </co> to indicate when a fact comes from a document in the search result, e.g <co>0</co> for a fact from document 0. Afterwards, list all the citations with their corresponding documents in an ordered list.' %}\n    {%- endif %}\n    {%- if 'hallucinations' in controls and documents %}\n        {%- set system_message = system_message + '\n\nFinally, after the response is written, include a numbered list of sentences from the response that are potentially hallucinated and not based in the documents.' %}\n    {%- endif %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n{{- '<|start_of_role|>system<|end_of_role|>' + system_message + '<|end_of_text|>\n' }}\n{%- if tools %}\n    {{- '<|start_of_role|>tools<|end_of_role|>' }}\n    {{- tools | tojson(indent=4) }}\n    {{- '<|end_of_text|>\n' }}\n{%- endif %}\n{%- if documents %}\n    {{- '<|start_of_role|>documents<|end_of_role|>' }}\n    {%- for document in documents %}\n        {{- 'Document ' + loop.index0 | string + '\n' }}\n        {{- document['text'] }}\n        {%- if not loop.last %}\n            {{- '\n\n'}}\n        {%- endif%}\n    {%- endfor %}\n    {{- '<|end_of_text|>\n' }}\n{%- endif %}\n{%- for message in loop_messages %}\n    {{- '<|start_of_role|>' + message['role'] + '<|end_of_role|>' + message['content'] + '<|end_of_text|>\n' }}\n    {%- if loop.last and add_generation_prompt %}\n        {{- '<|start_of_role|>assistant' }}\n            {%- if controls %}\n                {{- ' ' + controls | tojson()}}\n            {%- endif %}\n        {{- '<|end_of_role|>' }}\n    {%- endif %}\n{%- endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 9223372036854775807,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|end_of_text|>",
+  "vocab_size": 49152
+}

checkpoint-800/trainer_state.json

@@ -0,0 +1,1233 @@
+{
+  "best_metric": 0.6271193027496338,
+  "best_model_checkpoint": "./Granite3.2-2B-NF4-lora-FP16/checkpoint-650",
+  "epoch": 3.789598108747045,
+  "eval_steps": 10,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04728132387706856,
+      "grad_norm": 87.26045989990234,
+      "learning_rate": 8.293838862559242e-08,
+      "loss": 8.5102,
+      "step": 10
+    },
+    {
+      "epoch": 0.04728132387706856,
+      "eval_loss": 1.651900291442871,
+      "eval_runtime": 189.2938,
+      "eval_samples_per_second": 7.914,
+      "eval_steps_per_second": 7.914,
+      "step": 10
+    },
+    {
+      "epoch": 0.09456264775413711,
+      "grad_norm": NaN,
+      "learning_rate": 1.3033175355450237e-07,
+      "loss": 10.2287,
+      "step": 20
+    },
+    {
+      "epoch": 0.09456264775413711,
+      "eval_loss": 1.648614525794983,
+      "eval_runtime": 191.1258,
+      "eval_samples_per_second": 7.838,
+      "eval_steps_per_second": 7.838,
+      "step": 20
+    },
+    {
+      "epoch": 0.14184397163120568,
+      "grad_norm": NaN,
+      "learning_rate": 2.014218009478673e-07,
+      "loss": 8.1147,
+      "step": 30
+    },
+    {
+      "epoch": 0.14184397163120568,
+      "eval_loss": 1.6365329027175903,
+      "eval_runtime": 191.126,
+      "eval_samples_per_second": 7.838,
+      "eval_steps_per_second": 7.838,
+      "step": 30
+    },
+    {
+      "epoch": 0.18912529550827423,
+      "grad_norm": 93.69634246826172,
+      "learning_rate": 2.843601895734597e-07,
+      "loss": 8.9379,
+      "step": 40
+    },
+    {
+      "epoch": 0.18912529550827423,
+      "eval_loss": 1.6096875667572021,
+      "eval_runtime": 191.0567,
+      "eval_samples_per_second": 7.841,
+      "eval_steps_per_second": 7.841,
+      "step": 40
+    },
+    {
+      "epoch": 0.2364066193853428,
+      "grad_norm": 52.54499435424805,
+      "learning_rate": 3.5545023696682467e-07,
+      "loss": 8.8021,
+      "step": 50
+    },
+    {
+      "epoch": 0.2364066193853428,
+      "eval_loss": 1.5783013105392456,
+      "eval_runtime": 190.3143,
+      "eval_samples_per_second": 7.871,
+      "eval_steps_per_second": 7.871,
+      "step": 50
+    },
+    {
+      "epoch": 0.28368794326241137,
+      "grad_norm": 0.0,
+      "learning_rate": 3.9099526066350717e-07,
+      "loss": 8.3498,
+      "step": 60
+    },
+    {
+      "epoch": 0.28368794326241137,
+      "eval_loss": 1.5635849237442017,
+      "eval_runtime": 189.6366,
+      "eval_samples_per_second": 7.899,
+      "eval_steps_per_second": 7.899,
+      "step": 60
+    },
+    {
+      "epoch": 0.3309692671394799,
+      "grad_norm": NaN,
+      "learning_rate": 4.383886255924171e-07,
+      "loss": 8.3163,
+      "step": 70
+    },
+    {
+      "epoch": 0.3309692671394799,
+      "eval_loss": 1.548291563987732,
+      "eval_runtime": 187.6384,
+      "eval_samples_per_second": 7.983,
+      "eval_steps_per_second": 7.983,
+      "step": 70
+    },
+    {
+      "epoch": 0.37825059101654845,
+      "grad_norm": 0.0,
+      "learning_rate": 5.09478672985782e-07,
+      "loss": 7.9849,
+      "step": 80
+    },
+    {
+      "epoch": 0.37825059101654845,
+      "eval_loss": 1.53183114528656,
+      "eval_runtime": 191.207,
+      "eval_samples_per_second": 7.834,
+      "eval_steps_per_second": 7.834,
+      "step": 80
+    },
+    {
+      "epoch": 0.425531914893617,
+      "grad_norm": 0.0,
+      "learning_rate": 6.161137440758294e-07,
+      "loss": 7.082,
+      "step": 90
+    },
+    {
+      "epoch": 0.425531914893617,
+      "eval_loss": 1.5181553363800049,
+      "eval_runtime": 190.4139,
+      "eval_samples_per_second": 7.867,
+      "eval_steps_per_second": 7.867,
+      "step": 90
+    },
+    {
+      "epoch": 0.4728132387706856,
+      "grad_norm": 0.0,
+      "learning_rate": 7.227488151658768e-07,
+      "loss": 7.1551,
+      "step": 100
+    },
+    {
+      "epoch": 0.4728132387706856,
+      "eval_loss": 1.5116242170333862,
+      "eval_runtime": 190.4531,
+      "eval_samples_per_second": 7.865,
+      "eval_steps_per_second": 7.865,
+      "step": 100
+    },
+    {
+      "epoch": 0.5200945626477541,
+      "grad_norm": 0.0,
+      "learning_rate": 8.056872037914692e-07,
+      "loss": 7.913,
+      "step": 110
+    },
+    {
+      "epoch": 0.5200945626477541,
+      "eval_loss": 1.5087770223617554,
+      "eval_runtime": 189.9529,
+      "eval_samples_per_second": 7.886,
+      "eval_steps_per_second": 7.886,
+      "step": 110
+    },
+    {
+      "epoch": 0.5673758865248227,
+      "grad_norm": 0.0,
+      "learning_rate": 8.886255924170617e-07,
+      "loss": 8.1934,
+      "step": 120
+    },
+    {
+      "epoch": 0.5673758865248227,
+      "eval_loss": 1.5076136589050293,
+      "eval_runtime": 188.2808,
+      "eval_samples_per_second": 7.956,
+      "eval_steps_per_second": 7.956,
+      "step": 120
+    },
+    {
+      "epoch": 0.6146572104018913,
+      "grad_norm": NaN,
+      "learning_rate": 9.360189573459716e-07,
+      "loss": 7.6321,
+      "step": 130
+    },
+    {
+      "epoch": 0.6146572104018913,
+      "eval_loss": 1.506999135017395,
+      "eval_runtime": 189.8831,
+      "eval_samples_per_second": 7.889,
+      "eval_steps_per_second": 7.889,
+      "step": 130
+    },
+    {
+      "epoch": 0.6619385342789598,
+      "grad_norm": NaN,
+      "learning_rate": 9.95260663507109e-07,
+      "loss": 7.2685,
+      "step": 140
+    },
+    {
+      "epoch": 0.6619385342789598,
+      "eval_loss": 1.5065042972564697,
+      "eval_runtime": 187.3951,
+      "eval_samples_per_second": 7.994,
+      "eval_steps_per_second": 7.994,
+      "step": 140
+    },
+    {
+      "epoch": 0.7092198581560284,
+      "grad_norm": NaN,
+      "learning_rate": 1.042654028436019e-06,
+      "loss": 7.8588,
+      "step": 150
+    },
+    {
+      "epoch": 0.7092198581560284,
+      "eval_loss": 1.5062100887298584,
+      "eval_runtime": 188.4095,
+      "eval_samples_per_second": 7.951,
+      "eval_steps_per_second": 7.951,
+      "step": 150
+    },
+    {
+      "epoch": 0.7565011820330969,
+      "grad_norm": 0.0,
+      "learning_rate": 1.1137440758293839e-06,
+      "loss": 7.6134,
+      "step": 160
+    },
+    {
+      "epoch": 0.7565011820330969,
+      "eval_loss": 1.5061581134796143,
+      "eval_runtime": 189.1523,
+      "eval_samples_per_second": 7.92,
+      "eval_steps_per_second": 7.92,
+      "step": 160
+    },
+    {
+      "epoch": 0.8037825059101655,
+      "grad_norm": NaN,
+      "learning_rate": 1.161137440758294e-06,
+      "loss": 7.2664,
+      "step": 170
+    },
+    {
+      "epoch": 0.8037825059101655,
+      "eval_loss": 1.5059285163879395,
+      "eval_runtime": 188.6762,
+      "eval_samples_per_second": 7.94,
+      "eval_steps_per_second": 7.94,
+      "step": 170
+    },
+    {
+      "epoch": 0.851063829787234,
+      "grad_norm": NaN,
+      "learning_rate": 1.2559241706161137e-06,
+      "loss": 7.4329,
+      "step": 180
+    },
+    {
+      "epoch": 0.851063829787234,
+      "eval_loss": 1.5059077739715576,
+      "eval_runtime": 187.6795,
+      "eval_samples_per_second": 7.982,
+      "eval_steps_per_second": 7.982,
+      "step": 180
+    },
+    {
+      "epoch": 0.8983451536643026,
+      "grad_norm": NaN,
+      "learning_rate": 1.3151658767772512e-06,
+      "loss": 7.6408,
+      "step": 190
+    },
+    {
+      "epoch": 0.8983451536643026,
+      "eval_loss": 1.5057716369628906,
+      "eval_runtime": 189.3117,
+      "eval_samples_per_second": 7.913,
+      "eval_steps_per_second": 7.913,
+      "step": 190
+    },
+    {
+      "epoch": 0.9456264775413712,
+      "grad_norm": 0.0,
+      "learning_rate": 1.4099526066350713e-06,
+      "loss": 7.3045,
+      "step": 200
+    },
+    {
+      "epoch": 0.9456264775413712,
+      "eval_loss": 1.5058767795562744,
+      "eval_runtime": 188.469,
+      "eval_samples_per_second": 7.948,
+      "eval_steps_per_second": 7.948,
+      "step": 200
+    },
+    {
+      "epoch": 0.9929078014184397,
+      "grad_norm": NaN,
+      "learning_rate": 1.4810426540284362e-06,
+      "loss": 7.5174,
+      "step": 210
+    },
+    {
+      "epoch": 0.9929078014184397,
+      "eval_loss": 1.5057271718978882,
+      "eval_runtime": 189.4647,
+      "eval_samples_per_second": 7.906,
+      "eval_steps_per_second": 7.906,
+      "step": 210
+    },
+    {
+      "epoch": 1.037825059101655,
+      "grad_norm": 0.0,
+      "learning_rate": 1.5165876777251187e-06,
+      "loss": 6.3875,
+      "step": 220
+    },
+    {
+      "epoch": 1.037825059101655,
+      "eval_loss": 1.5058012008666992,
+      "eval_runtime": 191.0237,
+      "eval_samples_per_second": 7.842,
+      "eval_steps_per_second": 7.842,
+      "step": 220
+    },
+    {
+      "epoch": 1.0851063829787233,
+      "grad_norm": 0.0,
+      "learning_rate": 1.5758293838862558e-06,
+      "loss": 8.4706,
+      "step": 230
+    },
+    {
+      "epoch": 1.0851063829787233,
+      "eval_loss": 1.5058584213256836,
+      "eval_runtime": 188.0372,
+      "eval_samples_per_second": 7.967,
+      "eval_steps_per_second": 7.967,
+      "step": 230
+    },
+    {
+      "epoch": 1.132387706855792,
+      "grad_norm": NaN,
+      "learning_rate": 1.6232227488151662e-06,
+      "loss": 8.065,
+      "step": 240
+    },
+    {
+      "epoch": 1.132387706855792,
+      "eval_loss": 1.505755066871643,
+      "eval_runtime": 187.7724,
+      "eval_samples_per_second": 7.978,
+      "eval_steps_per_second": 7.978,
+      "step": 240
+    },
+    {
+      "epoch": 1.1796690307328606,
+      "grad_norm": 0.0,
+      "learning_rate": 1.670616113744076e-06,
+      "loss": 7.5316,
+      "step": 250
+    },
+    {
+      "epoch": 1.1796690307328606,
+      "eval_loss": 1.5057827234268188,
+      "eval_runtime": 188.7924,
+      "eval_samples_per_second": 7.935,
+      "eval_steps_per_second": 7.935,
+      "step": 250
+    },
+    {
+      "epoch": 1.226950354609929,
+      "grad_norm": NaN,
+      "learning_rate": 1.7417061611374408e-06,
+      "loss": 7.5248,
+      "step": 260
+    },
+    {
+      "epoch": 1.226950354609929,
+      "eval_loss": 1.5058114528656006,
+      "eval_runtime": 187.4552,
+      "eval_samples_per_second": 7.991,
+      "eval_steps_per_second": 7.991,
+      "step": 260
+    },
+    {
+      "epoch": 1.2742316784869976,
+      "grad_norm": NaN,
+      "learning_rate": 1.8009478672985784e-06,
+      "loss": 7.4775,
+      "step": 270
+    },
+    {
+      "epoch": 1.2742316784869976,
+      "eval_loss": 1.505687952041626,
+      "eval_runtime": 188.978,
+      "eval_samples_per_second": 7.927,
+      "eval_steps_per_second": 7.927,
+      "step": 270
+    },
+    {
+      "epoch": 1.3215130023640662,
+      "grad_norm": NaN,
+      "learning_rate": 1.8957345971563982e-06,
+      "loss": 7.6242,
+      "step": 280
+    },
+    {
+      "epoch": 1.3215130023640662,
+      "eval_loss": 1.505746603012085,
+      "eval_runtime": 188.9548,
+      "eval_samples_per_second": 7.928,
+      "eval_steps_per_second": 7.928,
+      "step": 280
+    },
+    {
+      "epoch": 1.3687943262411348,
+      "grad_norm": NaN,
+      "learning_rate": 1.9549763033175357e-06,
+      "loss": 7.3763,
+      "step": 290
+    },
+    {
+      "epoch": 1.3687943262411348,
+      "eval_loss": 1.505776286125183,
+      "eval_runtime": 204.2212,
+      "eval_samples_per_second": 7.335,
+      "eval_steps_per_second": 7.335,
+      "step": 290
+    },
+    {
+      "epoch": 1.4160756501182032,
+      "grad_norm": NaN,
+      "learning_rate": 1.990521327014218e-06,
+      "loss": 7.8478,
+      "step": 300
+    },
+    {
+      "epoch": 1.4160756501182032,
+      "eval_loss": 1.5056565999984741,
+      "eval_runtime": 200.9197,
+      "eval_samples_per_second": 7.456,
+      "eval_steps_per_second": 7.456,
+      "step": 300
+    },
+    {
+      "epoch": 1.4633569739952719,
+      "grad_norm": 0.0,
+      "learning_rate": 2.073459715639811e-06,
+      "loss": 7.8697,
+      "step": 310
+    },
+    {
+      "epoch": 1.4633569739952719,
+      "eval_loss": 1.5057348012924194,
+      "eval_runtime": 189.629,
+      "eval_samples_per_second": 7.9,
+      "eval_steps_per_second": 7.9,
+      "step": 310
+    },
+    {
+      "epoch": 1.5106382978723403,
+      "grad_norm": 0.0,
+      "learning_rate": 2.156398104265403e-06,
+      "loss": 7.2537,
+      "step": 320
+    },
+    {
+      "epoch": 1.5106382978723403,
+      "eval_loss": 1.5058965682983398,
+      "eval_runtime": 188.6635,
+      "eval_samples_per_second": 7.94,
+      "eval_steps_per_second": 7.94,
+      "step": 320
+    },
+    {
+      "epoch": 1.557919621749409,
+      "grad_norm": 0.0,
+      "learning_rate": 2.251184834123223e-06,
+      "loss": 7.2557,
+      "step": 330
+    },
+    {
+      "epoch": 1.557919621749409,
+      "eval_loss": 1.5058610439300537,
+      "eval_runtime": 187.4881,
+      "eval_samples_per_second": 7.99,
+      "eval_steps_per_second": 7.99,
+      "step": 330
+    },
+    {
+      "epoch": 1.6052009456264775,
+      "grad_norm": NaN,
+      "learning_rate": 2.3104265402843605e-06,
+      "loss": 7.5409,
+      "step": 340
+    },
+    {
+      "epoch": 1.6052009456264775,
+      "eval_loss": 1.505786418914795,
+      "eval_runtime": 187.3837,
+      "eval_samples_per_second": 7.994,
+      "eval_steps_per_second": 7.994,
+      "step": 340
+    },
+    {
+      "epoch": 1.6524822695035462,
+      "grad_norm": NaN,
+      "learning_rate": 2.381516587677725e-06,
+      "loss": 7.6392,
+      "step": 350
+    },
+    {
+      "epoch": 1.6524822695035462,
+      "eval_loss": 1.505786418914795,
+      "eval_runtime": 196.9848,
+      "eval_samples_per_second": 7.605,
+      "eval_steps_per_second": 7.605,
+      "step": 350
+    },
+    {
+      "epoch": 1.6997635933806148,
+      "grad_norm": NaN,
+      "learning_rate": 2.4289099526066355e-06,
+      "loss": 7.937,
+      "step": 360
+    },
+    {
+      "epoch": 1.6997635933806148,
+      "eval_loss": 1.505786418914795,
+      "eval_runtime": 188.7817,
+      "eval_samples_per_second": 7.935,
+      "eval_steps_per_second": 7.935,
+      "step": 360
+    },
+    {
+      "epoch": 1.7470449172576832,
+      "grad_norm": NaN,
+      "learning_rate": 2.5e-06,
+      "loss": 6.7999,
+      "step": 370
+    },
+    {
+      "epoch": 1.7470449172576832,
+      "eval_loss": 1.505786418914795,
+      "eval_runtime": 187.9736,
+      "eval_samples_per_second": 7.969,
+      "eval_steps_per_second": 7.969,
+      "step": 370
+    },
+    {
+      "epoch": 1.7943262411347518,
+      "grad_norm": NaN,
+      "learning_rate": 2.5592417061611373e-06,
+      "loss": 8.5177,
+      "step": 380
+    },
+    {
+      "epoch": 1.7943262411347518,
+      "eval_loss": 1.505786418914795,
+      "eval_runtime": 187.9063,
+      "eval_samples_per_second": 7.972,
+      "eval_steps_per_second": 7.972,
+      "step": 380
+    },
+    {
+      "epoch": 1.8416075650118202,
+      "grad_norm": NaN,
+      "learning_rate": 2.606635071090048e-06,
+      "loss": 7.7415,
+      "step": 390
+    },
+    {
+      "epoch": 1.8416075650118202,
+      "eval_loss": 1.505786418914795,
+      "eval_runtime": 187.7579,
+      "eval_samples_per_second": 7.978,
+      "eval_steps_per_second": 7.978,
+      "step": 390
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": NaN,
+      "learning_rate": 2.68957345971564e-06,
+      "loss": 7.7509,
+      "step": 400
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "eval_loss": 1.505786418914795,
+      "eval_runtime": 187.7192,
+      "eval_samples_per_second": 7.98,
+      "eval_steps_per_second": 7.98,
+      "step": 400
+    },
+    {
+      "epoch": 1.9361702127659575,
+      "grad_norm": NaN,
+      "learning_rate": 2.7488151658767775e-06,
+      "loss": 7.1524,
+      "step": 410
+    },
+    {
+      "epoch": 1.9361702127659575,
+      "eval_loss": 1.505786418914795,
+      "eval_runtime": 187.5663,
+      "eval_samples_per_second": 7.987,
+      "eval_steps_per_second": 7.987,
+      "step": 410
+    },
+    {
+      "epoch": 1.983451536643026,
+      "grad_norm": NaN,
+      "learning_rate": 2.7962085308056874e-06,
+      "loss": 7.3399,
+      "step": 420
+    },
+    {
+      "epoch": 1.983451536643026,
+      "eval_loss": 1.505786418914795,
+      "eval_runtime": 200.9294,
+      "eval_samples_per_second": 7.455,
+      "eval_steps_per_second": 7.455,
+      "step": 420
+    },
+    {
+      "epoch": 2.028368794326241,
+      "grad_norm": NaN,
+      "learning_rate": 2.8791469194312797e-06,
+      "loss": 6.7778,
+      "step": 430
+    },
+    {
+      "epoch": 2.028368794326241,
+      "eval_loss": 1.505786418914795,
+      "eval_runtime": 187.6432,
+      "eval_samples_per_second": 7.983,
+      "eval_steps_per_second": 7.983,
+      "step": 430
+    },
+    {
+      "epoch": 2.07565011820331,
+      "grad_norm": NaN,
+      "learning_rate": 2.9620853080568724e-06,
+      "loss": 7.3263,
+      "step": 440
+    },
+    {
+      "epoch": 2.07565011820331,
+      "eval_loss": 1.505786418914795,
+      "eval_runtime": 187.7825,
+      "eval_samples_per_second": 7.977,
+      "eval_steps_per_second": 7.977,
+      "step": 440
+    },
+    {
+      "epoch": 2.1229314420803784,
+      "grad_norm": NaN,
+      "learning_rate": 3.0450236966824647e-06,
+      "loss": 6.9175,
+      "step": 450
+    },
+    {
+      "epoch": 2.1229314420803784,
+      "eval_loss": 1.505786418914795,
+      "eval_runtime": 187.2013,
+      "eval_samples_per_second": 8.002,
+      "eval_steps_per_second": 8.002,
+      "step": 450
+    },
+    {
+      "epoch": 2.1702127659574466,
+      "grad_norm": NaN,
+      "learning_rate": 3.0924170616113746e-06,
+      "loss": 8.1551,
+      "step": 460
+    },
+    {
+      "epoch": 2.1702127659574466,
+      "eval_loss": 1.505786418914795,
+      "eval_runtime": 187.4539,
+      "eval_samples_per_second": 7.991,
+      "eval_steps_per_second": 7.991,
+      "step": 460
+    },
+    {
+      "epoch": 2.2174940898345152,
+      "grad_norm": NaN,
+      "learning_rate": 3.1516587677725117e-06,
+      "loss": 8.1098,
+      "step": 470
+    },
+    {
+      "epoch": 2.2174940898345152,
+      "eval_loss": 1.505786418914795,
+      "eval_runtime": 187.9635,
+      "eval_samples_per_second": 7.97,
+      "eval_steps_per_second": 7.97,
+      "step": 470
+    },
+    {
+      "epoch": 2.264775413711584,
+      "grad_norm": NaN,
+      "learning_rate": 3.2109004739336496e-06,
+      "loss": 8.3371,
+      "step": 480
+    },
+    {
+      "epoch": 2.264775413711584,
+      "eval_loss": 1.505786418914795,
+      "eval_runtime": 193.023,
+      "eval_samples_per_second": 7.761,
+      "eval_steps_per_second": 7.761,
+      "step": 480
+    },
+    {
+      "epoch": 2.3120567375886525,
+      "grad_norm": NaN,
+      "learning_rate": 3.3056872037914695e-06,
+      "loss": 7.1629,
+      "step": 490
+    },
+    {
+      "epoch": 2.3120567375886525,
+      "eval_loss": 1.505786418914795,
+      "eval_runtime": 189.1352,
+      "eval_samples_per_second": 7.92,
+      "eval_steps_per_second": 7.92,
+      "step": 490
+    },
+    {
+      "epoch": 2.359338061465721,
+      "grad_norm": NaN,
+      "learning_rate": 3.3767772511848346e-06,
+      "loss": 7.8394,
+      "step": 500
+    },
+    {
+      "epoch": 2.359338061465721,
+      "eval_loss": 1.505786418914795,
+      "eval_runtime": 189.5805,
+      "eval_samples_per_second": 7.902,
+      "eval_steps_per_second": 7.902,
+      "step": 500
+    },
+    {
+      "epoch": 2.4066193853427897,
+      "grad_norm": NaN,
+      "learning_rate": 3.4241706161137446e-06,
+      "loss": 7.1466,
+      "step": 510
+    },
+    {
+      "epoch": 2.4066193853427897,
+      "eval_loss": 1.505786418914795,
+      "eval_runtime": 199.2319,
+      "eval_samples_per_second": 7.519,
+      "eval_steps_per_second": 7.519,
+      "step": 510
+    },
+    {
+      "epoch": 2.453900709219858,
+      "grad_norm": NaN,
+      "learning_rate": 3.4834123222748817e-06,
+      "loss": 7.5045,
+      "step": 520
+    },
+    {
+      "epoch": 2.453900709219858,
+      "eval_loss": 1.505786418914795,
+      "eval_runtime": 197.5354,
+      "eval_samples_per_second": 7.583,
+      "eval_steps_per_second": 7.583,
+      "step": 520
+    },
+    {
+      "epoch": 2.5011820330969265,
+      "grad_norm": NaN,
+      "learning_rate": 3.5426540284360196e-06,
+      "loss": 7.4143,
+      "step": 530
+    },
+    {
+      "epoch": 2.5011820330969265,
+      "eval_loss": 1.505786418914795,
+      "eval_runtime": 188.3058,
+      "eval_samples_per_second": 7.955,
+      "eval_steps_per_second": 7.955,
+      "step": 530
+    },
+    {
+      "epoch": 2.548463356973995,
+      "grad_norm": NaN,
+      "learning_rate": 3.625592417061612e-06,
+      "loss": 7.6097,
+      "step": 540
+    },
+    {
+      "epoch": 2.548463356973995,
+      "eval_loss": 1.505786418914795,
+      "eval_runtime": 192.9892,
+      "eval_samples_per_second": 7.762,
+      "eval_steps_per_second": 7.762,
+      "step": 540
+    },
+    {
+      "epoch": 2.595744680851064,
+      "grad_norm": NaN,
+      "learning_rate": 3.708530805687204e-06,
+      "loss": 7.0607,
+      "step": 550
+    },
+    {
+      "epoch": 2.595744680851064,
+      "eval_loss": 1.505786418914795,
+      "eval_runtime": 189.7776,
+      "eval_samples_per_second": 7.893,
+      "eval_steps_per_second": 7.893,
+      "step": 550
+    },
+    {
+      "epoch": 2.6430260047281324,
+      "grad_norm": NaN,
+      "learning_rate": 3.7677725118483417e-06,
+      "loss": 7.485,
+      "step": 560
+    },
+    {
+      "epoch": 2.6430260047281324,
+      "eval_loss": 1.505786418914795,
+      "eval_runtime": 190.8152,
+      "eval_samples_per_second": 7.851,
+      "eval_steps_per_second": 7.851,
+      "step": 560
+    },
+    {
+      "epoch": 2.690307328605201,
+      "grad_norm": NaN,
+      "learning_rate": 3.850710900473934e-06,
+      "loss": 7.1815,
+      "step": 570
+    },
+    {
+      "epoch": 2.690307328605201,
+      "eval_loss": 1.505786418914795,
+      "eval_runtime": 192.3642,
+      "eval_samples_per_second": 7.787,
+      "eval_steps_per_second": 7.787,
+      "step": 570
+    },
+    {
+      "epoch": 2.7375886524822697,
+      "grad_norm": NaN,
+      "learning_rate": 3.9099526066350715e-06,
+      "loss": 7.7287,
+      "step": 580
+    },
+    {
+      "epoch": 2.7375886524822697,
+      "eval_loss": 1.505786418914795,
+      "eval_runtime": 192.4745,
+      "eval_samples_per_second": 7.783,
+      "eval_steps_per_second": 7.783,
+      "step": 580
+    },
+    {
+      "epoch": 2.784869976359338,
+      "grad_norm": NaN,
+      "learning_rate": 4.0165876777251185e-06,
+      "loss": 7.2689,
+      "step": 590
+    },
+    {
+      "epoch": 2.784869976359338,
+      "eval_loss": 1.505786418914795,
+      "eval_runtime": 191.8231,
+      "eval_samples_per_second": 7.809,
+      "eval_steps_per_second": 7.809,
+      "step": 590
+    },
+    {
+      "epoch": 2.8321513002364065,
+      "grad_norm": NaN,
+      "learning_rate": 4.052132701421802e-06,
+      "loss": 7.844,
+      "step": 600
+    },
+    {
+      "epoch": 2.8321513002364065,
+      "eval_loss": 1.505786418914795,
+      "eval_runtime": 193.4448,
+      "eval_samples_per_second": 7.744,
+      "eval_steps_per_second": 7.744,
+      "step": 600
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 31.39480209350586,
+      "learning_rate": 4.123222748815166e-06,
+      "loss": 6.0041,
+      "step": 610
+    },
+    {
+      "epoch": 2.888888888888889,
+      "eval_loss": 0.8467056155204773,
+      "eval_runtime": 201.1866,
+      "eval_samples_per_second": 7.446,
+      "eval_steps_per_second": 7.446,
+      "step": 610
+    },
+    {
+      "epoch": 2.9361702127659575,
+      "grad_norm": NaN,
+      "learning_rate": 4.194312796208531e-06,
+      "loss": 2.5635,
+      "step": 620
+    },
+    {
+      "epoch": 2.9361702127659575,
+      "eval_loss": 0.7216377854347229,
+      "eval_runtime": 188.6215,
+      "eval_samples_per_second": 7.942,
+      "eval_steps_per_second": 7.942,
+      "step": 620
+    },
+    {
+      "epoch": 2.983451536643026,
+      "grad_norm": 5.911599159240723,
+      "learning_rate": 4.265402843601897e-06,
+      "loss": 1.8933,
+      "step": 630
+    },
+    {
+      "epoch": 2.983451536643026,
+      "eval_loss": 0.6720291972160339,
+      "eval_runtime": 191.8114,
+      "eval_samples_per_second": 7.81,
+      "eval_steps_per_second": 7.81,
+      "step": 630
+    },
+    {
+      "epoch": 3.033096926713948,
+      "grad_norm": 0.8963627219200134,
+      "learning_rate": 4.360189573459716e-06,
+      "loss": 1.8142,
+      "step": 640
+    },
+    {
+      "epoch": 3.033096926713948,
+      "eval_loss": 0.632388174533844,
+      "eval_runtime": 190.4463,
+      "eval_samples_per_second": 7.866,
+      "eval_steps_per_second": 7.866,
+      "step": 640
+    },
+    {
+      "epoch": 3.0803782505910164,
+      "grad_norm": 1.0507489442825317,
+      "learning_rate": 4.443127962085308e-06,
+      "loss": 1.8062,
+      "step": 650
+    },
+    {
+      "epoch": 3.0803782505910164,
+      "eval_loss": 0.6271193027496338,
+      "eval_runtime": 190.8235,
+      "eval_samples_per_second": 7.85,
+      "eval_steps_per_second": 7.85,
+      "step": 650
+    },
+    {
+      "epoch": 3.127659574468085,
+      "grad_norm": 1.2229665517807007,
+      "learning_rate": 4.561611374407583e-06,
+      "loss": 1.8038,
+      "step": 660
+    },
+    {
+      "epoch": 3.127659574468085,
+      "eval_loss": 0.6392990946769714,
+      "eval_runtime": 189.5871,
+      "eval_samples_per_second": 7.901,
+      "eval_steps_per_second": 7.901,
+      "step": 660
+    },
+    {
+      "epoch": 3.1749408983451537,
+      "grad_norm": 1.3551545143127441,
+      "learning_rate": 4.656398104265403e-06,
+      "loss": 1.7994,
+      "step": 670
+    },
+    {
+      "epoch": 3.1749408983451537,
+      "eval_loss": 0.6542360186576843,
+      "eval_runtime": 192.7671,
+      "eval_samples_per_second": 7.771,
+      "eval_steps_per_second": 7.771,
+      "step": 670
+    },
+    {
+      "epoch": 3.2222222222222223,
+      "grad_norm": 0.25800448656082153,
+      "learning_rate": 4.76303317535545e-06,
+      "loss": 1.8652,
+      "step": 680
+    },
+    {
+      "epoch": 3.2222222222222223,
+      "eval_loss": 0.6668521165847778,
+      "eval_runtime": 195.2941,
+      "eval_samples_per_second": 7.67,
+      "eval_steps_per_second": 7.67,
+      "step": 680
+    },
+    {
+      "epoch": 3.269503546099291,
+      "grad_norm": 0.2729438245296478,
+      "learning_rate": 4.881516587677725e-06,
+      "loss": 1.7835,
+      "step": 690
+    },
+    {
+      "epoch": 3.269503546099291,
+      "eval_loss": 0.6744400262832642,
+      "eval_runtime": 196.4651,
+      "eval_samples_per_second": 7.625,
+      "eval_steps_per_second": 7.625,
+      "step": 690
+    },
+    {
+      "epoch": 3.3167848699763596,
+      "grad_norm": 0.001072466024197638,
+      "learning_rate": 4.976303317535545e-06,
+      "loss": 1.9284,
+      "step": 700
+    },
+    {
+      "epoch": 3.3167848699763596,
+      "eval_loss": 0.6774776577949524,
+      "eval_runtime": 189.0513,
+      "eval_samples_per_second": 7.924,
+      "eval_steps_per_second": 7.924,
+      "step": 700
+    },
+    {
+      "epoch": 3.3640661938534278,
+      "grad_norm": 0.0,
+      "learning_rate": 5.082938388625592e-06,
+      "loss": 1.7848,
+      "step": 710
+    },
+    {
+      "epoch": 3.3640661938534278,
+      "eval_loss": 0.6789966821670532,
+      "eval_runtime": 187.9092,
+      "eval_samples_per_second": 7.972,
+      "eval_steps_per_second": 7.972,
+      "step": 710
+    },
+    {
+      "epoch": 3.4113475177304964,
+      "grad_norm": 0.0,
+      "learning_rate": 5.201421800947868e-06,
+      "loss": 1.8963,
+      "step": 720
+    },
+    {
+      "epoch": 3.4113475177304964,
+      "eval_loss": 0.6796472668647766,
+      "eval_runtime": 202.3055,
+      "eval_samples_per_second": 7.405,
+      "eval_steps_per_second": 7.405,
+      "step": 720
+    },
+    {
+      "epoch": 3.458628841607565,
+      "grad_norm": 0.0,
+      "learning_rate": 5.319905213270142e-06,
+      "loss": 1.8163,
+      "step": 730
+    },
+    {
+      "epoch": 3.458628841607565,
+      "eval_loss": 0.6799014806747437,
+      "eval_runtime": 188.6933,
+      "eval_samples_per_second": 7.939,
+      "eval_steps_per_second": 7.939,
+      "step": 730
+    },
+    {
+      "epoch": 3.5059101654846336,
+      "grad_norm": 0.0,
+      "learning_rate": 5.438388625592418e-06,
+      "loss": 1.8742,
+      "step": 740
+    },
+    {
+      "epoch": 3.5059101654846336,
+      "eval_loss": 0.6799649000167847,
+      "eval_runtime": 191.0673,
+      "eval_samples_per_second": 7.84,
+      "eval_steps_per_second": 7.84,
+      "step": 740
+    },
+    {
+      "epoch": 3.5531914893617023,
+      "grad_norm": 0.0,
+      "learning_rate": 5.5568720379146925e-06,
+      "loss": 1.8309,
+      "step": 750
+    },
+    {
+      "epoch": 3.5531914893617023,
+      "eval_loss": 0.6799895167350769,
+      "eval_runtime": 190.2596,
+      "eval_samples_per_second": 7.873,
+      "eval_steps_per_second": 7.873,
+      "step": 750
+    },
+    {
+      "epoch": 3.6004728132387704,
+      "grad_norm": 0.0,
+      "learning_rate": 5.651658767772512e-06,
+      "loss": 1.9419,
+      "step": 760
+    },
+    {
+      "epoch": 3.6004728132387704,
+      "eval_loss": 0.6800009608268738,
+      "eval_runtime": 189.9752,
+      "eval_samples_per_second": 7.885,
+      "eval_steps_per_second": 7.885,
+      "step": 760
+    },
+    {
+      "epoch": 3.6477541371158395,
+      "grad_norm": 0.0,
+      "learning_rate": 5.734597156398105e-06,
+      "loss": 2.0215,
+      "step": 770
+    },
+    {
+      "epoch": 3.6477541371158395,
+      "eval_loss": 0.680011510848999,
+      "eval_runtime": 197.5866,
+      "eval_samples_per_second": 7.581,
+      "eval_steps_per_second": 7.581,
+      "step": 770
+    },
+    {
+      "epoch": 3.6950354609929077,
+      "grad_norm": 0.0,
+      "learning_rate": 5.829383886255925e-06,
+      "loss": 1.9827,
+      "step": 780
+    },
+    {
+      "epoch": 3.6950354609929077,
+      "eval_loss": 0.6800098419189453,
+      "eval_runtime": 187.6296,
+      "eval_samples_per_second": 7.984,
+      "eval_steps_per_second": 7.984,
+      "step": 780
+    },
+    {
+      "epoch": 3.7423167848699763,
+      "grad_norm": 0.0,
+      "learning_rate": 5.924170616113745e-06,
+      "loss": 1.9726,
+      "step": 790
+    },
+    {
+      "epoch": 3.7423167848699763,
+      "eval_loss": 0.6800153255462646,
+      "eval_runtime": 191.5237,
+      "eval_samples_per_second": 7.821,
+      "eval_steps_per_second": 7.821,
+      "step": 790
+    },
+    {
+      "epoch": 3.789598108747045,
+      "grad_norm": 0.0,
+      "learning_rate": 6.042654028436019e-06,
+      "loss": 1.8562,
+      "step": 800
+    },
+    {
+      "epoch": 3.789598108747045,
+      "eval_loss": 0.6799952983856201,
+      "eval_runtime": 195.1911,
+      "eval_samples_per_second": 7.675,
+      "eval_steps_per_second": 7.675,
+      "step": 800
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 4220,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "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": 3.87159893571797e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e817479fc5e4c98026c1e18a920b437c0cc9da7987ef5cf23619791a63461de
+size 5368