Upload folder using huggingface_hub

README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: microsoft/Phi-3-mini-4k-instruct
+---
+
+# 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 0.11.1

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
+  "bias": "none",
+  "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": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "qkv_proj",
+    "gate_up_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1aeed342de05ad51c31b4a1fd22ccea120c55f4c998b0091b79a23244ae20d1
+size 201361312

added_tokens.json

@@ -0,0 +1,14 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010,
+  "eos_token": 32011
+}

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.4361294785211252,
+    "train_runtime": 852.0177,
+    "train_samples_per_second": 1.592,
+    "train_steps_per_second": 0.05
+}

checkpoint-40/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: microsoft/Phi-3-mini-4k-instruct
+---
+
+# 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 0.11.1

checkpoint-40/adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
+  "bias": "none",
+  "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": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "qkv_proj",
+    "gate_up_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-40/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b10a598d1619cd4846294601c7d1f85001b2be71daa4d79ed13c8f52d71860b7
+size 201361312

checkpoint-40/added_tokens.json

@@ -0,0 +1,14 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010,
+  "eos_token": 32011
+}

checkpoint-40/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb175472ad2be171f9605357c276abce58909e6860992bb2b1d5b3178c85243e
+size 402807738

checkpoint-40/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:403bdda7559c9704cffa76004d2deeb3082d540e084ee09663623ab16cb36629
+size 14180

checkpoint-40/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c6822969f5b9e1cabdf082f2757132f7704699742d4c808be8940bfaa38fb13
+size 1064

checkpoint-40/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-40/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

checkpoint-40/tokenizer_config.json

@@ -0,0 +1,139 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32011": {
+      "content": "eos_token",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-40/trainer_state.json

@@ -0,0 +1,633 @@
+{
+  "best_metric": 1.0443669557571411,
+  "best_model_checkpoint": "./output/checkpoints/2024-06-10_23-12-21/checkpoint-40",
+  "epoch": 0.9302325581395349,
+  "eval_steps": 1,
+  "global_step": 40,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.023255813953488372,
+      "grad_norm": 3.1748037338256836,
+      "learning_rate": 8e-05,
+      "loss": 5.1513,
+      "step": 1
+    },
+    {
+      "epoch": 0.023255813953488372,
+      "eval_loss": 5.098567485809326,
+      "eval_runtime": 10.4736,
+      "eval_samples_per_second": 11.171,
+      "eval_steps_per_second": 0.764,
+      "step": 1
+    },
+    {
+      "epoch": 0.046511627906976744,
+      "grad_norm": 3.149711847305298,
+      "learning_rate": 0.00016,
+      "loss": 5.1556,
+      "step": 2
+    },
+    {
+      "epoch": 0.046511627906976744,
+      "eval_loss": 4.689513683319092,
+      "eval_runtime": 10.5409,
+      "eval_samples_per_second": 11.1,
+      "eval_steps_per_second": 0.759,
+      "step": 2
+    },
+    {
+      "epoch": 0.06976744186046512,
+      "grad_norm": 3.1611013412475586,
+      "learning_rate": 0.00024,
+      "loss": 4.6255,
+      "step": 3
+    },
+    {
+      "epoch": 0.06976744186046512,
+      "eval_loss": 3.2834692001342773,
+      "eval_runtime": 10.5481,
+      "eval_samples_per_second": 11.092,
+      "eval_steps_per_second": 0.758,
+      "step": 3
+    },
+    {
+      "epoch": 0.09302325581395349,
+      "grad_norm": 3.4506750106811523,
+      "learning_rate": 0.00032,
+      "loss": 3.268,
+      "step": 4
+    },
+    {
+      "epoch": 0.09302325581395349,
+      "eval_loss": 2.105466604232788,
+      "eval_runtime": 10.6124,
+      "eval_samples_per_second": 11.025,
+      "eval_steps_per_second": 0.754,
+      "step": 4
+    },
+    {
+      "epoch": 0.11627906976744186,
+      "grad_norm": 2.139575719833374,
+      "learning_rate": 0.0004,
+      "loss": 2.0627,
+      "step": 5
+    },
+    {
+      "epoch": 0.11627906976744186,
+      "eval_loss": 1.586738109588623,
+      "eval_runtime": 10.5613,
+      "eval_samples_per_second": 11.078,
+      "eval_steps_per_second": 0.757,
+      "step": 5
+    },
+    {
+      "epoch": 0.13953488372093023,
+      "grad_norm": 1.1181566715240479,
+      "learning_rate": 0.00038947368421052633,
+      "loss": 1.5525,
+      "step": 6
+    },
+    {
+      "epoch": 0.13953488372093023,
+      "eval_loss": 1.442232608795166,
+      "eval_runtime": 10.458,
+      "eval_samples_per_second": 11.188,
+      "eval_steps_per_second": 0.765,
+      "step": 6
+    },
+    {
+      "epoch": 0.16279069767441862,
+      "grad_norm": 1.6108548641204834,
+      "learning_rate": 0.00037894736842105265,
+      "loss": 1.4249,
+      "step": 7
+    },
+    {
+      "epoch": 0.16279069767441862,
+      "eval_loss": 1.2906938791275024,
+      "eval_runtime": 10.5694,
+      "eval_samples_per_second": 11.07,
+      "eval_steps_per_second": 0.757,
+      "step": 7
+    },
+    {
+      "epoch": 0.18604651162790697,
+      "grad_norm": 0.19699308276176453,
+      "learning_rate": 0.00036842105263157896,
+      "loss": 1.2713,
+      "step": 8
+    },
+    {
+      "epoch": 0.18604651162790697,
+      "eval_loss": 1.2516891956329346,
+      "eval_runtime": 10.4427,
+      "eval_samples_per_second": 11.204,
+      "eval_steps_per_second": 0.766,
+      "step": 8
+    },
+    {
+      "epoch": 0.20930232558139536,
+      "grad_norm": 0.12418746948242188,
+      "learning_rate": 0.0003578947368421053,
+      "loss": 1.2447,
+      "step": 9
+    },
+    {
+      "epoch": 0.20930232558139536,
+      "eval_loss": 1.2212988138198853,
+      "eval_runtime": 10.4966,
+      "eval_samples_per_second": 11.146,
+      "eval_steps_per_second": 0.762,
+      "step": 9
+    },
+    {
+      "epoch": 0.23255813953488372,
+      "grad_norm": 0.10525760799646378,
+      "learning_rate": 0.0003473684210526316,
+      "loss": 1.2071,
+      "step": 10
+    },
+    {
+      "epoch": 0.23255813953488372,
+      "eval_loss": 1.1963647603988647,
+      "eval_runtime": 10.5914,
+      "eval_samples_per_second": 11.047,
+      "eval_steps_per_second": 0.755,
+      "step": 10
+    },
+    {
+      "epoch": 0.2558139534883721,
+      "grad_norm": 0.1781289279460907,
+      "learning_rate": 0.0003368421052631579,
+      "loss": 1.1832,
+      "step": 11
+    },
+    {
+      "epoch": 0.2558139534883721,
+      "eval_loss": 1.1730906963348389,
+      "eval_runtime": 10.565,
+      "eval_samples_per_second": 11.074,
+      "eval_steps_per_second": 0.757,
+      "step": 11
+    },
+    {
+      "epoch": 0.27906976744186046,
+      "grad_norm": 0.16088849306106567,
+      "learning_rate": 0.0003263157894736842,
+      "loss": 1.1447,
+      "step": 12
+    },
+    {
+      "epoch": 0.27906976744186046,
+      "eval_loss": 1.1521227359771729,
+      "eval_runtime": 10.5741,
+      "eval_samples_per_second": 11.065,
+      "eval_steps_per_second": 0.757,
+      "step": 12
+    },
+    {
+      "epoch": 0.3023255813953488,
+      "grad_norm": 0.11435263603925705,
+      "learning_rate": 0.00031578947368421053,
+      "loss": 1.1098,
+      "step": 13
+    },
+    {
+      "epoch": 0.3023255813953488,
+      "eval_loss": 1.131661295890808,
+      "eval_runtime": 10.5531,
+      "eval_samples_per_second": 11.087,
+      "eval_steps_per_second": 0.758,
+      "step": 13
+    },
+    {
+      "epoch": 0.32558139534883723,
+      "grad_norm": 0.0963783711194992,
+      "learning_rate": 0.0003052631578947369,
+      "loss": 1.1298,
+      "step": 14
+    },
+    {
+      "epoch": 0.32558139534883723,
+      "eval_loss": 1.115828275680542,
+      "eval_runtime": 10.5575,
+      "eval_samples_per_second": 11.082,
+      "eval_steps_per_second": 0.758,
+      "step": 14
+    },
+    {
+      "epoch": 0.3488372093023256,
+      "grad_norm": 0.0737914890050888,
+      "learning_rate": 0.00029473684210526316,
+      "loss": 1.0838,
+      "step": 15
+    },
+    {
+      "epoch": 0.3488372093023256,
+      "eval_loss": 1.1041659116744995,
+      "eval_runtime": 10.4999,
+      "eval_samples_per_second": 11.143,
+      "eval_steps_per_second": 0.762,
+      "step": 15
+    },
+    {
+      "epoch": 0.37209302325581395,
+      "grad_norm": 0.06079930067062378,
+      "learning_rate": 0.00028421052631578947,
+      "loss": 1.0878,
+      "step": 16
+    },
+    {
+      "epoch": 0.37209302325581395,
+      "eval_loss": 1.0959372520446777,
+      "eval_runtime": 10.5731,
+      "eval_samples_per_second": 11.066,
+      "eval_steps_per_second": 0.757,
+      "step": 16
+    },
+    {
+      "epoch": 0.3953488372093023,
+      "grad_norm": 0.05798230320215225,
+      "learning_rate": 0.0002736842105263158,
+      "loss": 1.0726,
+      "step": 17
+    },
+    {
+      "epoch": 0.3953488372093023,
+      "eval_loss": 1.0892282724380493,
+      "eval_runtime": 10.5989,
+      "eval_samples_per_second": 11.039,
+      "eval_steps_per_second": 0.755,
+      "step": 17
+    },
+    {
+      "epoch": 0.4186046511627907,
+      "grad_norm": 0.05506344139575958,
+      "learning_rate": 0.00026315789473684215,
+      "loss": 1.0643,
+      "step": 18
+    },
+    {
+      "epoch": 0.4186046511627907,
+      "eval_loss": 1.0838031768798828,
+      "eval_runtime": 10.583,
+      "eval_samples_per_second": 11.055,
+      "eval_steps_per_second": 0.756,
+      "step": 18
+    },
+    {
+      "epoch": 0.4418604651162791,
+      "grad_norm": 0.05198650062084198,
+      "learning_rate": 0.0002526315789473684,
+      "loss": 1.0661,
+      "step": 19
+    },
+    {
+      "epoch": 0.4418604651162791,
+      "eval_loss": 1.0791563987731934,
+      "eval_runtime": 10.5263,
+      "eval_samples_per_second": 11.115,
+      "eval_steps_per_second": 0.76,
+      "step": 19
+    },
+    {
+      "epoch": 0.46511627906976744,
+      "grad_norm": 0.051451779901981354,
+      "learning_rate": 0.00024210526315789475,
+      "loss": 1.062,
+      "step": 20
+    },
+    {
+      "epoch": 0.46511627906976744,
+      "eval_loss": 1.0747723579406738,
+      "eval_runtime": 10.5633,
+      "eval_samples_per_second": 11.076,
+      "eval_steps_per_second": 0.757,
+      "step": 20
+    },
+    {
+      "epoch": 0.4883720930232558,
+      "grad_norm": 0.04886360839009285,
+      "learning_rate": 0.00023157894736842107,
+      "loss": 1.0482,
+      "step": 21
+    },
+    {
+      "epoch": 0.4883720930232558,
+      "eval_loss": 1.0707547664642334,
+      "eval_runtime": 10.5723,
+      "eval_samples_per_second": 11.067,
+      "eval_steps_per_second": 0.757,
+      "step": 21
+    },
+    {
+      "epoch": 0.5116279069767442,
+      "grad_norm": 0.04511698707938194,
+      "learning_rate": 0.0002210526315789474,
+      "loss": 1.0526,
+      "step": 22
+    },
+    {
+      "epoch": 0.5116279069767442,
+      "eval_loss": 1.0674015283584595,
+      "eval_runtime": 10.5187,
+      "eval_samples_per_second": 11.123,
+      "eval_steps_per_second": 0.761,
+      "step": 22
+    },
+    {
+      "epoch": 0.5348837209302325,
+      "grad_norm": 0.049303531646728516,
+      "learning_rate": 0.0002105263157894737,
+      "loss": 1.0154,
+      "step": 23
+    },
+    {
+      "epoch": 0.5348837209302325,
+      "eval_loss": 1.0645886659622192,
+      "eval_runtime": 10.5824,
+      "eval_samples_per_second": 11.056,
+      "eval_steps_per_second": 0.756,
+      "step": 23
+    },
+    {
+      "epoch": 0.5581395348837209,
+      "grad_norm": 0.13970467448234558,
+      "learning_rate": 0.0002,
+      "loss": 1.0336,
+      "step": 24
+    },
+    {
+      "epoch": 0.5581395348837209,
+      "eval_loss": 1.0622761249542236,
+      "eval_runtime": 10.5378,
+      "eval_samples_per_second": 11.103,
+      "eval_steps_per_second": 0.759,
+      "step": 24
+    },
+    {
+      "epoch": 0.5813953488372093,
+      "grad_norm": 0.04498777911067009,
+      "learning_rate": 0.00018947368421052632,
+      "loss": 1.0727,
+      "step": 25
+    },
+    {
+      "epoch": 0.5813953488372093,
+      "eval_loss": 1.0603291988372803,
+      "eval_runtime": 10.5222,
+      "eval_samples_per_second": 11.119,
+      "eval_steps_per_second": 0.76,
+      "step": 25
+    },
+    {
+      "epoch": 0.6046511627906976,
+      "grad_norm": 0.04431827366352081,
+      "learning_rate": 0.00017894736842105264,
+      "loss": 1.035,
+      "step": 26
+    },
+    {
+      "epoch": 0.6046511627906976,
+      "eval_loss": 1.0584354400634766,
+      "eval_runtime": 10.5855,
+      "eval_samples_per_second": 11.053,
+      "eval_steps_per_second": 0.756,
+      "step": 26
+    },
+    {
+      "epoch": 0.627906976744186,
+      "grad_norm": 0.0488644503057003,
+      "learning_rate": 0.00016842105263157895,
+      "loss": 1.057,
+      "step": 27
+    },
+    {
+      "epoch": 0.627906976744186,
+      "eval_loss": 1.0564749240875244,
+      "eval_runtime": 10.5114,
+      "eval_samples_per_second": 11.131,
+      "eval_steps_per_second": 0.761,
+      "step": 27
+    },
+    {
+      "epoch": 0.6511627906976745,
+      "grad_norm": 0.04599970951676369,
+      "learning_rate": 0.00015789473684210527,
+      "loss": 1.0386,
+      "step": 28
+    },
+    {
+      "epoch": 0.6511627906976745,
+      "eval_loss": 1.0546391010284424,
+      "eval_runtime": 10.536,
+      "eval_samples_per_second": 11.105,
+      "eval_steps_per_second": 0.759,
+      "step": 28
+    },
+    {
+      "epoch": 0.6744186046511628,
+      "grad_norm": 0.04661059379577637,
+      "learning_rate": 0.00014736842105263158,
+      "loss": 1.0552,
+      "step": 29
+    },
+    {
+      "epoch": 0.6744186046511628,
+      "eval_loss": 1.0529735088348389,
+      "eval_runtime": 10.5645,
+      "eval_samples_per_second": 11.075,
+      "eval_steps_per_second": 0.757,
+      "step": 29
+    },
+    {
+      "epoch": 0.6976744186046512,
+      "grad_norm": 0.04191095009446144,
+      "learning_rate": 0.0001368421052631579,
+      "loss": 1.0261,
+      "step": 30
+    },
+    {
+      "epoch": 0.6976744186046512,
+      "eval_loss": 1.0515702962875366,
+      "eval_runtime": 10.5459,
+      "eval_samples_per_second": 11.094,
+      "eval_steps_per_second": 0.759,
+      "step": 30
+    },
+    {
+      "epoch": 0.7209302325581395,
+      "grad_norm": 0.04263598471879959,
+      "learning_rate": 0.0001263157894736842,
+      "loss": 1.0265,
+      "step": 31
+    },
+    {
+      "epoch": 0.7209302325581395,
+      "eval_loss": 1.0504158735275269,
+      "eval_runtime": 10.5618,
+      "eval_samples_per_second": 11.078,
+      "eval_steps_per_second": 0.757,
+      "step": 31
+    },
+    {
+      "epoch": 0.7441860465116279,
+      "grad_norm": 0.043207377195358276,
+      "learning_rate": 0.00011578947368421053,
+      "loss": 1.038,
+      "step": 32
+    },
+    {
+      "epoch": 0.7441860465116279,
+      "eval_loss": 1.049385905265808,
+      "eval_runtime": 10.5765,
+      "eval_samples_per_second": 11.062,
+      "eval_steps_per_second": 0.756,
+      "step": 32
+    },
+    {
+      "epoch": 0.7674418604651163,
+      "grad_norm": 0.0437220074236393,
+      "learning_rate": 0.00010526315789473685,
+      "loss": 1.0456,
+      "step": 33
+    },
+    {
+      "epoch": 0.7674418604651163,
+      "eval_loss": 1.0484665632247925,
+      "eval_runtime": 10.6182,
+      "eval_samples_per_second": 11.019,
+      "eval_steps_per_second": 0.753,
+      "step": 33
+    },
+    {
+      "epoch": 0.7906976744186046,
+      "grad_norm": 0.04280296340584755,
+      "learning_rate": 9.473684210526316e-05,
+      "loss": 1.0339,
+      "step": 34
+    },
+    {
+      "epoch": 0.7906976744186046,
+      "eval_loss": 1.047668218612671,
+      "eval_runtime": 10.5375,
+      "eval_samples_per_second": 11.103,
+      "eval_steps_per_second": 0.759,
+      "step": 34
+    },
+    {
+      "epoch": 0.813953488372093,
+      "grad_norm": 0.048476554453372955,
+      "learning_rate": 8.421052631578948e-05,
+      "loss": 1.0452,
+      "step": 35
+    },
+    {
+      "epoch": 0.813953488372093,
+      "eval_loss": 1.0469459295272827,
+      "eval_runtime": 10.5569,
+      "eval_samples_per_second": 11.083,
+      "eval_steps_per_second": 0.758,
+      "step": 35
+    },
+    {
+      "epoch": 0.8372093023255814,
+      "grad_norm": 0.03983575850725174,
+      "learning_rate": 7.368421052631579e-05,
+      "loss": 1.0112,
+      "step": 36
+    },
+    {
+      "epoch": 0.8372093023255814,
+      "eval_loss": 1.0462400913238525,
+      "eval_runtime": 10.5644,
+      "eval_samples_per_second": 11.075,
+      "eval_steps_per_second": 0.757,
+      "step": 36
+    },
+    {
+      "epoch": 0.8604651162790697,
+      "grad_norm": 0.04240667447447777,
+      "learning_rate": 6.31578947368421e-05,
+      "loss": 1.032,
+      "step": 37
+    },
+    {
+      "epoch": 0.8604651162790697,
+      "eval_loss": 1.0456737279891968,
+      "eval_runtime": 10.5478,
+      "eval_samples_per_second": 11.092,
+      "eval_steps_per_second": 0.758,
+      "step": 37
+    },
+    {
+      "epoch": 0.8837209302325582,
+      "grad_norm": 0.04697669297456741,
+      "learning_rate": 5.2631578947368424e-05,
+      "loss": 1.0216,
+      "step": 38
+    },
+    {
+      "epoch": 0.8837209302325582,
+      "eval_loss": 1.0451328754425049,
+      "eval_runtime": 10.5909,
+      "eval_samples_per_second": 11.047,
+      "eval_steps_per_second": 0.755,
+      "step": 38
+    },
+    {
+      "epoch": 0.9069767441860465,
+      "grad_norm": 0.04411022737622261,
+      "learning_rate": 4.210526315789474e-05,
+      "loss": 1.0367,
+      "step": 39
+    },
+    {
+      "epoch": 0.9069767441860465,
+      "eval_loss": 1.0447440147399902,
+      "eval_runtime": 10.5309,
+      "eval_samples_per_second": 11.11,
+      "eval_steps_per_second": 0.76,
+      "step": 39
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": 0.051756396889686584,
+      "learning_rate": 3.157894736842105e-05,
+      "loss": 1.0144,
+      "step": 40
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "eval_loss": 1.0443669557571411,
+      "eval_runtime": 10.545,
+      "eval_samples_per_second": 11.095,
+      "eval_steps_per_second": 0.759,
+      "step": 40
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 43,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.483568811343872e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-40/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:417a57553f0c0ac7b33f24b375a6fbd3ea5498665711fbab7f1379b01809ad0b
+size 5688

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,139 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32011": {
+      "content": "eos_token",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.4361294785211252,
+    "train_runtime": 852.0177,
+    "train_samples_per_second": 1.592,
+    "train_steps_per_second": 0.05
+}

trainer_state.json

@@ -0,0 +1,687 @@
+{
+  "best_metric": 1.0443669557571411,
+  "best_model_checkpoint": "./output/checkpoints/2024-06-10_23-12-21/checkpoint-40",
+  "epoch": 1.0,
+  "eval_steps": 1,
+  "global_step": 43,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.023255813953488372,
+      "grad_norm": 3.1748037338256836,
+      "learning_rate": 8e-05,
+      "loss": 5.1513,
+      "step": 1
+    },
+    {
+      "epoch": 0.023255813953488372,
+      "eval_loss": 5.098567485809326,
+      "eval_runtime": 10.4736,
+      "eval_samples_per_second": 11.171,
+      "eval_steps_per_second": 0.764,
+      "step": 1
+    },
+    {
+      "epoch": 0.046511627906976744,
+      "grad_norm": 3.149711847305298,
+      "learning_rate": 0.00016,
+      "loss": 5.1556,
+      "step": 2
+    },
+    {
+      "epoch": 0.046511627906976744,
+      "eval_loss": 4.689513683319092,
+      "eval_runtime": 10.5409,
+      "eval_samples_per_second": 11.1,
+      "eval_steps_per_second": 0.759,
+      "step": 2
+    },
+    {
+      "epoch": 0.06976744186046512,
+      "grad_norm": 3.1611013412475586,
+      "learning_rate": 0.00024,
+      "loss": 4.6255,
+      "step": 3
+    },
+    {
+      "epoch": 0.06976744186046512,
+      "eval_loss": 3.2834692001342773,
+      "eval_runtime": 10.5481,
+      "eval_samples_per_second": 11.092,
+      "eval_steps_per_second": 0.758,
+      "step": 3
+    },
+    {
+      "epoch": 0.09302325581395349,
+      "grad_norm": 3.4506750106811523,
+      "learning_rate": 0.00032,
+      "loss": 3.268,
+      "step": 4
+    },
+    {
+      "epoch": 0.09302325581395349,
+      "eval_loss": 2.105466604232788,
+      "eval_runtime": 10.6124,
+      "eval_samples_per_second": 11.025,
+      "eval_steps_per_second": 0.754,
+      "step": 4
+    },
+    {
+      "epoch": 0.11627906976744186,
+      "grad_norm": 2.139575719833374,
+      "learning_rate": 0.0004,
+      "loss": 2.0627,
+      "step": 5
+    },
+    {
+      "epoch": 0.11627906976744186,
+      "eval_loss": 1.586738109588623,
+      "eval_runtime": 10.5613,
+      "eval_samples_per_second": 11.078,
+      "eval_steps_per_second": 0.757,
+      "step": 5
+    },
+    {
+      "epoch": 0.13953488372093023,
+      "grad_norm": 1.1181566715240479,
+      "learning_rate": 0.00038947368421052633,
+      "loss": 1.5525,
+      "step": 6
+    },
+    {
+      "epoch": 0.13953488372093023,
+      "eval_loss": 1.442232608795166,
+      "eval_runtime": 10.458,
+      "eval_samples_per_second": 11.188,
+      "eval_steps_per_second": 0.765,
+      "step": 6
+    },
+    {
+      "epoch": 0.16279069767441862,
+      "grad_norm": 1.6108548641204834,
+      "learning_rate": 0.00037894736842105265,
+      "loss": 1.4249,
+      "step": 7
+    },
+    {
+      "epoch": 0.16279069767441862,
+      "eval_loss": 1.2906938791275024,
+      "eval_runtime": 10.5694,
+      "eval_samples_per_second": 11.07,
+      "eval_steps_per_second": 0.757,
+      "step": 7
+    },
+    {
+      "epoch": 0.18604651162790697,
+      "grad_norm": 0.19699308276176453,
+      "learning_rate": 0.00036842105263157896,
+      "loss": 1.2713,
+      "step": 8
+    },
+    {
+      "epoch": 0.18604651162790697,
+      "eval_loss": 1.2516891956329346,
+      "eval_runtime": 10.4427,
+      "eval_samples_per_second": 11.204,
+      "eval_steps_per_second": 0.766,
+      "step": 8
+    },
+    {
+      "epoch": 0.20930232558139536,
+      "grad_norm": 0.12418746948242188,
+      "learning_rate": 0.0003578947368421053,
+      "loss": 1.2447,
+      "step": 9
+    },
+    {
+      "epoch": 0.20930232558139536,
+      "eval_loss": 1.2212988138198853,
+      "eval_runtime": 10.4966,
+      "eval_samples_per_second": 11.146,
+      "eval_steps_per_second": 0.762,
+      "step": 9
+    },
+    {
+      "epoch": 0.23255813953488372,
+      "grad_norm": 0.10525760799646378,
+      "learning_rate": 0.0003473684210526316,
+      "loss": 1.2071,
+      "step": 10
+    },
+    {
+      "epoch": 0.23255813953488372,
+      "eval_loss": 1.1963647603988647,
+      "eval_runtime": 10.5914,
+      "eval_samples_per_second": 11.047,
+      "eval_steps_per_second": 0.755,
+      "step": 10
+    },
+    {
+      "epoch": 0.2558139534883721,
+      "grad_norm": 0.1781289279460907,
+      "learning_rate": 0.0003368421052631579,
+      "loss": 1.1832,
+      "step": 11
+    },
+    {
+      "epoch": 0.2558139534883721,
+      "eval_loss": 1.1730906963348389,
+      "eval_runtime": 10.565,
+      "eval_samples_per_second": 11.074,
+      "eval_steps_per_second": 0.757,
+      "step": 11
+    },
+    {
+      "epoch": 0.27906976744186046,
+      "grad_norm": 0.16088849306106567,
+      "learning_rate": 0.0003263157894736842,
+      "loss": 1.1447,
+      "step": 12
+    },
+    {
+      "epoch": 0.27906976744186046,
+      "eval_loss": 1.1521227359771729,
+      "eval_runtime": 10.5741,
+      "eval_samples_per_second": 11.065,
+      "eval_steps_per_second": 0.757,
+      "step": 12
+    },
+    {
+      "epoch": 0.3023255813953488,
+      "grad_norm": 0.11435263603925705,
+      "learning_rate": 0.00031578947368421053,
+      "loss": 1.1098,
+      "step": 13
+    },
+    {
+      "epoch": 0.3023255813953488,
+      "eval_loss": 1.131661295890808,
+      "eval_runtime": 10.5531,
+      "eval_samples_per_second": 11.087,
+      "eval_steps_per_second": 0.758,
+      "step": 13
+    },
+    {
+      "epoch": 0.32558139534883723,
+      "grad_norm": 0.0963783711194992,
+      "learning_rate": 0.0003052631578947369,
+      "loss": 1.1298,
+      "step": 14
+    },
+    {
+      "epoch": 0.32558139534883723,
+      "eval_loss": 1.115828275680542,
+      "eval_runtime": 10.5575,
+      "eval_samples_per_second": 11.082,
+      "eval_steps_per_second": 0.758,
+      "step": 14
+    },
+    {
+      "epoch": 0.3488372093023256,
+      "grad_norm": 0.0737914890050888,
+      "learning_rate": 0.00029473684210526316,
+      "loss": 1.0838,
+      "step": 15
+    },
+    {
+      "epoch": 0.3488372093023256,
+      "eval_loss": 1.1041659116744995,
+      "eval_runtime": 10.4999,
+      "eval_samples_per_second": 11.143,
+      "eval_steps_per_second": 0.762,
+      "step": 15
+    },
+    {
+      "epoch": 0.37209302325581395,
+      "grad_norm": 0.06079930067062378,
+      "learning_rate": 0.00028421052631578947,
+      "loss": 1.0878,
+      "step": 16
+    },
+    {
+      "epoch": 0.37209302325581395,
+      "eval_loss": 1.0959372520446777,
+      "eval_runtime": 10.5731,
+      "eval_samples_per_second": 11.066,
+      "eval_steps_per_second": 0.757,
+      "step": 16
+    },
+    {
+      "epoch": 0.3953488372093023,
+      "grad_norm": 0.05798230320215225,
+      "learning_rate": 0.0002736842105263158,
+      "loss": 1.0726,
+      "step": 17
+    },
+    {
+      "epoch": 0.3953488372093023,
+      "eval_loss": 1.0892282724380493,
+      "eval_runtime": 10.5989,
+      "eval_samples_per_second": 11.039,
+      "eval_steps_per_second": 0.755,
+      "step": 17
+    },
+    {
+      "epoch": 0.4186046511627907,
+      "grad_norm": 0.05506344139575958,
+      "learning_rate": 0.00026315789473684215,
+      "loss": 1.0643,
+      "step": 18
+    },
+    {
+      "epoch": 0.4186046511627907,
+      "eval_loss": 1.0838031768798828,
+      "eval_runtime": 10.583,
+      "eval_samples_per_second": 11.055,
+      "eval_steps_per_second": 0.756,
+      "step": 18
+    },
+    {
+      "epoch": 0.4418604651162791,
+      "grad_norm": 0.05198650062084198,
+      "learning_rate": 0.0002526315789473684,
+      "loss": 1.0661,
+      "step": 19
+    },
+    {
+      "epoch": 0.4418604651162791,
+      "eval_loss": 1.0791563987731934,
+      "eval_runtime": 10.5263,
+      "eval_samples_per_second": 11.115,
+      "eval_steps_per_second": 0.76,
+      "step": 19
+    },
+    {
+      "epoch": 0.46511627906976744,
+      "grad_norm": 0.051451779901981354,
+      "learning_rate": 0.00024210526315789475,
+      "loss": 1.062,
+      "step": 20
+    },
+    {
+      "epoch": 0.46511627906976744,
+      "eval_loss": 1.0747723579406738,
+      "eval_runtime": 10.5633,
+      "eval_samples_per_second": 11.076,
+      "eval_steps_per_second": 0.757,
+      "step": 20
+    },
+    {
+      "epoch": 0.4883720930232558,
+      "grad_norm": 0.04886360839009285,
+      "learning_rate": 0.00023157894736842107,
+      "loss": 1.0482,
+      "step": 21
+    },
+    {
+      "epoch": 0.4883720930232558,
+      "eval_loss": 1.0707547664642334,
+      "eval_runtime": 10.5723,
+      "eval_samples_per_second": 11.067,
+      "eval_steps_per_second": 0.757,
+      "step": 21
+    },
+    {
+      "epoch": 0.5116279069767442,
+      "grad_norm": 0.04511698707938194,
+      "learning_rate": 0.0002210526315789474,
+      "loss": 1.0526,
+      "step": 22
+    },
+    {
+      "epoch": 0.5116279069767442,
+      "eval_loss": 1.0674015283584595,
+      "eval_runtime": 10.5187,
+      "eval_samples_per_second": 11.123,
+      "eval_steps_per_second": 0.761,
+      "step": 22
+    },
+    {
+      "epoch": 0.5348837209302325,
+      "grad_norm": 0.049303531646728516,
+      "learning_rate": 0.0002105263157894737,
+      "loss": 1.0154,
+      "step": 23
+    },
+    {
+      "epoch": 0.5348837209302325,
+      "eval_loss": 1.0645886659622192,
+      "eval_runtime": 10.5824,
+      "eval_samples_per_second": 11.056,
+      "eval_steps_per_second": 0.756,
+      "step": 23
+    },
+    {
+      "epoch": 0.5581395348837209,
+      "grad_norm": 0.13970467448234558,
+      "learning_rate": 0.0002,
+      "loss": 1.0336,
+      "step": 24
+    },
+    {
+      "epoch": 0.5581395348837209,
+      "eval_loss": 1.0622761249542236,
+      "eval_runtime": 10.5378,
+      "eval_samples_per_second": 11.103,
+      "eval_steps_per_second": 0.759,
+      "step": 24
+    },
+    {
+      "epoch": 0.5813953488372093,
+      "grad_norm": 0.04498777911067009,
+      "learning_rate": 0.00018947368421052632,
+      "loss": 1.0727,
+      "step": 25
+    },
+    {
+      "epoch": 0.5813953488372093,
+      "eval_loss": 1.0603291988372803,
+      "eval_runtime": 10.5222,
+      "eval_samples_per_second": 11.119,
+      "eval_steps_per_second": 0.76,
+      "step": 25
+    },
+    {
+      "epoch": 0.6046511627906976,
+      "grad_norm": 0.04431827366352081,
+      "learning_rate": 0.00017894736842105264,
+      "loss": 1.035,
+      "step": 26
+    },
+    {
+      "epoch": 0.6046511627906976,
+      "eval_loss": 1.0584354400634766,
+      "eval_runtime": 10.5855,
+      "eval_samples_per_second": 11.053,
+      "eval_steps_per_second": 0.756,
+      "step": 26
+    },
+    {
+      "epoch": 0.627906976744186,
+      "grad_norm": 0.0488644503057003,
+      "learning_rate": 0.00016842105263157895,
+      "loss": 1.057,
+      "step": 27
+    },
+    {
+      "epoch": 0.627906976744186,
+      "eval_loss": 1.0564749240875244,
+      "eval_runtime": 10.5114,
+      "eval_samples_per_second": 11.131,
+      "eval_steps_per_second": 0.761,
+      "step": 27
+    },
+    {
+      "epoch": 0.6511627906976745,
+      "grad_norm": 0.04599970951676369,
+      "learning_rate": 0.00015789473684210527,
+      "loss": 1.0386,
+      "step": 28
+    },
+    {
+      "epoch": 0.6511627906976745,
+      "eval_loss": 1.0546391010284424,
+      "eval_runtime": 10.536,
+      "eval_samples_per_second": 11.105,
+      "eval_steps_per_second": 0.759,
+      "step": 28
+    },
+    {
+      "epoch": 0.6744186046511628,
+      "grad_norm": 0.04661059379577637,
+      "learning_rate": 0.00014736842105263158,
+      "loss": 1.0552,
+      "step": 29
+    },
+    {
+      "epoch": 0.6744186046511628,
+      "eval_loss": 1.0529735088348389,
+      "eval_runtime": 10.5645,
+      "eval_samples_per_second": 11.075,
+      "eval_steps_per_second": 0.757,
+      "step": 29
+    },
+    {
+      "epoch": 0.6976744186046512,
+      "grad_norm": 0.04191095009446144,
+      "learning_rate": 0.0001368421052631579,
+      "loss": 1.0261,
+      "step": 30
+    },
+    {
+      "epoch": 0.6976744186046512,
+      "eval_loss": 1.0515702962875366,
+      "eval_runtime": 10.5459,
+      "eval_samples_per_second": 11.094,
+      "eval_steps_per_second": 0.759,
+      "step": 30
+    },
+    {
+      "epoch": 0.7209302325581395,
+      "grad_norm": 0.04263598471879959,
+      "learning_rate": 0.0001263157894736842,
+      "loss": 1.0265,
+      "step": 31
+    },
+    {
+      "epoch": 0.7209302325581395,
+      "eval_loss": 1.0504158735275269,
+      "eval_runtime": 10.5618,
+      "eval_samples_per_second": 11.078,
+      "eval_steps_per_second": 0.757,
+      "step": 31
+    },
+    {
+      "epoch": 0.7441860465116279,
+      "grad_norm": 0.043207377195358276,
+      "learning_rate": 0.00011578947368421053,
+      "loss": 1.038,
+      "step": 32
+    },
+    {
+      "epoch": 0.7441860465116279,
+      "eval_loss": 1.049385905265808,
+      "eval_runtime": 10.5765,
+      "eval_samples_per_second": 11.062,
+      "eval_steps_per_second": 0.756,
+      "step": 32
+    },
+    {
+      "epoch": 0.7674418604651163,
+      "grad_norm": 0.0437220074236393,
+      "learning_rate": 0.00010526315789473685,
+      "loss": 1.0456,
+      "step": 33
+    },
+    {
+      "epoch": 0.7674418604651163,
+      "eval_loss": 1.0484665632247925,
+      "eval_runtime": 10.6182,
+      "eval_samples_per_second": 11.019,
+      "eval_steps_per_second": 0.753,
+      "step": 33
+    },
+    {
+      "epoch": 0.7906976744186046,
+      "grad_norm": 0.04280296340584755,
+      "learning_rate": 9.473684210526316e-05,
+      "loss": 1.0339,
+      "step": 34
+    },
+    {
+      "epoch": 0.7906976744186046,
+      "eval_loss": 1.047668218612671,
+      "eval_runtime": 10.5375,
+      "eval_samples_per_second": 11.103,
+      "eval_steps_per_second": 0.759,
+      "step": 34
+    },
+    {
+      "epoch": 0.813953488372093,
+      "grad_norm": 0.048476554453372955,
+      "learning_rate": 8.421052631578948e-05,
+      "loss": 1.0452,
+      "step": 35
+    },
+    {
+      "epoch": 0.813953488372093,
+      "eval_loss": 1.0469459295272827,
+      "eval_runtime": 10.5569,
+      "eval_samples_per_second": 11.083,
+      "eval_steps_per_second": 0.758,
+      "step": 35
+    },
+    {
+      "epoch": 0.8372093023255814,
+      "grad_norm": 0.03983575850725174,
+      "learning_rate": 7.368421052631579e-05,
+      "loss": 1.0112,
+      "step": 36
+    },
+    {
+      "epoch": 0.8372093023255814,
+      "eval_loss": 1.0462400913238525,
+      "eval_runtime": 10.5644,
+      "eval_samples_per_second": 11.075,
+      "eval_steps_per_second": 0.757,
+      "step": 36
+    },
+    {
+      "epoch": 0.8604651162790697,
+      "grad_norm": 0.04240667447447777,
+      "learning_rate": 6.31578947368421e-05,
+      "loss": 1.032,
+      "step": 37
+    },
+    {
+      "epoch": 0.8604651162790697,
+      "eval_loss": 1.0456737279891968,
+      "eval_runtime": 10.5478,
+      "eval_samples_per_second": 11.092,
+      "eval_steps_per_second": 0.758,
+      "step": 37
+    },
+    {
+      "epoch": 0.8837209302325582,
+      "grad_norm": 0.04697669297456741,
+      "learning_rate": 5.2631578947368424e-05,
+      "loss": 1.0216,
+      "step": 38
+    },
+    {
+      "epoch": 0.8837209302325582,
+      "eval_loss": 1.0451328754425049,
+      "eval_runtime": 10.5909,
+      "eval_samples_per_second": 11.047,
+      "eval_steps_per_second": 0.755,
+      "step": 38
+    },
+    {
+      "epoch": 0.9069767441860465,
+      "grad_norm": 0.04411022737622261,
+      "learning_rate": 4.210526315789474e-05,
+      "loss": 1.0367,
+      "step": 39
+    },
+    {
+      "epoch": 0.9069767441860465,
+      "eval_loss": 1.0447440147399902,
+      "eval_runtime": 10.5309,
+      "eval_samples_per_second": 11.11,
+      "eval_steps_per_second": 0.76,
+      "step": 39
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": 0.051756396889686584,
+      "learning_rate": 3.157894736842105e-05,
+      "loss": 1.0144,
+      "step": 40
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "eval_loss": 1.0443669557571411,
+      "eval_runtime": 10.545,
+      "eval_samples_per_second": 11.095,
+      "eval_steps_per_second": 0.759,
+      "step": 40
+    },
+    {
+      "epoch": 0.9534883720930233,
+      "grad_norm": 0.05069413781166077,
+      "learning_rate": 2.105263157894737e-05,
+      "loss": 1.0339,
+      "step": 41
+    },
+    {
+      "epoch": 0.9534883720930233,
+      "eval_loss": 1.0441150665283203,
+      "eval_runtime": 10.5475,
+      "eval_samples_per_second": 11.093,
+      "eval_steps_per_second": 0.758,
+      "step": 41
+    },
+    {
+      "epoch": 0.9767441860465116,
+      "grad_norm": 0.03964732587337494,
+      "learning_rate": 1.0526315789473684e-05,
+      "loss": 1.0046,
+      "step": 42
+    },
+    {
+      "epoch": 0.9767441860465116,
+      "eval_loss": 1.043948769569397,
+      "eval_runtime": 10.5196,
+      "eval_samples_per_second": 11.122,
+      "eval_steps_per_second": 0.76,
+      "step": 42
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.06997141987085342,
+      "learning_rate": 0.0,
+      "loss": 1.0082,
+      "step": 43
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.0438673496246338,
+      "eval_runtime": 10.5692,
+      "eval_samples_per_second": 11.07,
+      "eval_steps_per_second": 0.757,
+      "step": 43
+    },
+    {
+      "epoch": 1.0,
+      "step": 43,
+      "total_flos": 1.5716557095174144e+16,
+      "train_loss": 1.4361294785211252,
+      "train_runtime": 852.0177,
+      "train_samples_per_second": 1.592,
+      "train_steps_per_second": 0.05
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 43,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5716557095174144e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:417a57553f0c0ac7b33f24b375a6fbd3ea5498665711fbab7f1379b01809ad0b
+size 5688