Upload folder using huggingface_hub

README.md

@@ -1,3 +1,202 @@
----
-license: apache-2.0
----
+---
+base_model: microsoft/Phi-3-mini-4k-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 0.11.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "up_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:c0b9e2849cf1fc4e50c9aa729d7208db96353d45013346dd6ba71075127889bc
+size 35668592

checkpoint-1000/README.md

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

checkpoint-1000/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d398d2a610aba121a624d1c201b788791745004cefa7f1ba5c9ec9a78826b5d
+size 35668592

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66bf97cd0324c12a45e5141fbe9d70a7cc64a2310e4674ec9095bbcfdaa18514
+size 71380026

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:297a3e765407fac712fb7ec6816b2b05f84a4fb146d1ef89fa207c0425b37699
+size 14244

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96334ef546952ffd8cce266c36168ef845c05c23f11db329b2e99b83cb389446
+size 1064

checkpoint-1000/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-1000/tokenizer_config.json

@@ -0,0 +1,131 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": true,
+  "add_prefix_space": null,
+  "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
+    }
+  },
+  "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": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,1533 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6597394029358403,
+  "eval_steps": 10,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006597394029358403,
+      "grad_norm": 1.2868798971176147,
+      "learning_rate": 3.2894736842105265e-06,
+      "loss": 4.6934,
+      "step": 10
+    },
+    {
+      "epoch": 0.006597394029358403,
+      "eval_loss": 4.687362194061279,
+      "eval_runtime": 282.9655,
+      "eval_samples_per_second": 18.045,
+      "eval_steps_per_second": 0.565,
+      "step": 10
+    },
+    {
+      "epoch": 0.013194788058716806,
+      "grad_norm": 1.302221417427063,
+      "learning_rate": 6.578947368421053e-06,
+      "loss": 4.6651,
+      "step": 20
+    },
+    {
+      "epoch": 0.013194788058716806,
+      "eval_loss": 4.648743152618408,
+      "eval_runtime": 282.9326,
+      "eval_samples_per_second": 18.047,
+      "eval_steps_per_second": 0.566,
+      "step": 20
+    },
+    {
+      "epoch": 0.01979218208807521,
+      "grad_norm": 1.4535945653915405,
+      "learning_rate": 9.868421052631579e-06,
+      "loss": 4.6063,
+      "step": 30
+    },
+    {
+      "epoch": 0.01979218208807521,
+      "eval_loss": 4.54951286315918,
+      "eval_runtime": 282.3584,
+      "eval_samples_per_second": 18.083,
+      "eval_steps_per_second": 0.567,
+      "step": 30
+    },
+    {
+      "epoch": 0.026389576117433613,
+      "grad_norm": 1.714498519897461,
+      "learning_rate": 1.3157894736842106e-05,
+      "loss": 4.4527,
+      "step": 40
+    },
+    {
+      "epoch": 0.026389576117433613,
+      "eval_loss": 4.304062366485596,
+      "eval_runtime": 282.5935,
+      "eval_samples_per_second": 18.068,
+      "eval_steps_per_second": 0.566,
+      "step": 40
+    },
+    {
+      "epoch": 0.03298697014679202,
+      "grad_norm": 1.832472324371338,
+      "learning_rate": 1.6447368421052635e-05,
+      "loss": 4.1216,
+      "step": 50
+    },
+    {
+      "epoch": 0.03298697014679202,
+      "eval_loss": 3.8426761627197266,
+      "eval_runtime": 281.3902,
+      "eval_samples_per_second": 18.146,
+      "eval_steps_per_second": 0.569,
+      "step": 50
+    },
+    {
+      "epoch": 0.03958436417615042,
+      "grad_norm": 1.1160222291946411,
+      "learning_rate": 1.9736842105263158e-05,
+      "loss": 3.6561,
+      "step": 60
+    },
+    {
+      "epoch": 0.03958436417615042,
+      "eval_loss": 3.4654476642608643,
+      "eval_runtime": 282.2746,
+      "eval_samples_per_second": 18.089,
+      "eval_steps_per_second": 0.567,
+      "step": 60
+    },
+    {
+      "epoch": 0.04618175820550882,
+      "grad_norm": 1.1160507202148438,
+      "learning_rate": 2.3026315789473685e-05,
+      "loss": 3.2993,
+      "step": 70
+    },
+    {
+      "epoch": 0.04618175820550882,
+      "eval_loss": 3.0560474395751953,
+      "eval_runtime": 282.4864,
+      "eval_samples_per_second": 18.075,
+      "eval_steps_per_second": 0.566,
+      "step": 70
+    },
+    {
+      "epoch": 0.052779152234867226,
+      "grad_norm": 0.7468234896659851,
+      "learning_rate": 2.6315789473684212e-05,
+      "loss": 2.8777,
+      "step": 80
+    },
+    {
+      "epoch": 0.052779152234867226,
+      "eval_loss": 2.7082414627075195,
+      "eval_runtime": 282.279,
+      "eval_samples_per_second": 18.088,
+      "eval_steps_per_second": 0.567,
+      "step": 80
+    },
+    {
+      "epoch": 0.05937654626422563,
+      "grad_norm": 0.7456527948379517,
+      "learning_rate": 2.9605263157894735e-05,
+      "loss": 2.5844,
+      "step": 90
+    },
+    {
+      "epoch": 0.05937654626422563,
+      "eval_loss": 2.400399923324585,
+      "eval_runtime": 282.4234,
+      "eval_samples_per_second": 18.079,
+      "eval_steps_per_second": 0.567,
+      "step": 90
+    },
+    {
+      "epoch": 0.06597394029358404,
+      "grad_norm": 0.7843755483627319,
+      "learning_rate": 3.289473684210527e-05,
+      "loss": 2.2405,
+      "step": 100
+    },
+    {
+      "epoch": 0.06597394029358404,
+      "eval_loss": 2.043464422225952,
+      "eval_runtime": 282.4971,
+      "eval_samples_per_second": 18.075,
+      "eval_steps_per_second": 0.566,
+      "step": 100
+    },
+    {
+      "epoch": 0.07257133432294244,
+      "grad_norm": 0.7848460078239441,
+      "learning_rate": 3.618421052631579e-05,
+      "loss": 1.8797,
+      "step": 110
+    },
+    {
+      "epoch": 0.07257133432294244,
+      "eval_loss": 1.6749211549758911,
+      "eval_runtime": 282.4596,
+      "eval_samples_per_second": 18.077,
+      "eval_steps_per_second": 0.566,
+      "step": 110
+    },
+    {
+      "epoch": 0.07916872835230084,
+      "grad_norm": 0.8517773151397705,
+      "learning_rate": 3.9473684210526316e-05,
+      "loss": 1.5041,
+      "step": 120
+    },
+    {
+      "epoch": 0.07916872835230084,
+      "eval_loss": 1.322484016418457,
+      "eval_runtime": 282.425,
+      "eval_samples_per_second": 18.079,
+      "eval_steps_per_second": 0.567,
+      "step": 120
+    },
+    {
+      "epoch": 0.08576612238165925,
+      "grad_norm": 0.924010694026947,
+      "learning_rate": 4.2763157894736847e-05,
+      "loss": 1.1712,
+      "step": 130
+    },
+    {
+      "epoch": 0.08576612238165925,
+      "eval_loss": 1.0092010498046875,
+      "eval_runtime": 282.4135,
+      "eval_samples_per_second": 18.08,
+      "eval_steps_per_second": 0.567,
+      "step": 130
+    },
+    {
+      "epoch": 0.09236351641101764,
+      "grad_norm": 0.599291205406189,
+      "learning_rate": 4.605263157894737e-05,
+      "loss": 0.9068,
+      "step": 140
+    },
+    {
+      "epoch": 0.09236351641101764,
+      "eval_loss": 0.8262147307395935,
+      "eval_runtime": 282.3089,
+      "eval_samples_per_second": 18.087,
+      "eval_steps_per_second": 0.567,
+      "step": 140
+    },
+    {
+      "epoch": 0.09896091044037605,
+      "grad_norm": 0.4690685570240021,
+      "learning_rate": 4.9342105263157894e-05,
+      "loss": 0.7821,
+      "step": 150
+    },
+    {
+      "epoch": 0.09896091044037605,
+      "eval_loss": 0.7165087461471558,
+      "eval_runtime": 282.1805,
+      "eval_samples_per_second": 18.095,
+      "eval_steps_per_second": 0.567,
+      "step": 150
+    },
+    {
+      "epoch": 0.10555830446973445,
+      "grad_norm": 0.5129504203796387,
+      "learning_rate": 4.9706529713866475e-05,
+      "loss": 0.6867,
+      "step": 160
+    },
+    {
+      "epoch": 0.10555830446973445,
+      "eval_loss": 0.6483914256095886,
+      "eval_runtime": 282.207,
+      "eval_samples_per_second": 18.093,
+      "eval_steps_per_second": 0.567,
+      "step": 160
+    },
+    {
+      "epoch": 0.11215569849909286,
+      "grad_norm": 0.4116060435771942,
+      "learning_rate": 4.933969185619956e-05,
+      "loss": 0.6315,
+      "step": 170
+    },
+    {
+      "epoch": 0.11215569849909286,
+      "eval_loss": 0.6029236912727356,
+      "eval_runtime": 282.3594,
+      "eval_samples_per_second": 18.083,
+      "eval_steps_per_second": 0.567,
+      "step": 170
+    },
+    {
+      "epoch": 0.11875309252845126,
+      "grad_norm": 0.4301941990852356,
+      "learning_rate": 4.8972853998532655e-05,
+      "loss": 0.5833,
+      "step": 180
+    },
+    {
+      "epoch": 0.11875309252845126,
+      "eval_loss": 0.5720704197883606,
+      "eval_runtime": 282.0439,
+      "eval_samples_per_second": 18.104,
+      "eval_steps_per_second": 0.567,
+      "step": 180
+    },
+    {
+      "epoch": 0.12535048655780967,
+      "grad_norm": 0.5514675378799438,
+      "learning_rate": 4.860601614086574e-05,
+      "loss": 0.5667,
+      "step": 190
+    },
+    {
+      "epoch": 0.12535048655780967,
+      "eval_loss": 0.5490744709968567,
+      "eval_runtime": 282.3239,
+      "eval_samples_per_second": 18.086,
+      "eval_steps_per_second": 0.567,
+      "step": 190
+    },
+    {
+      "epoch": 0.13194788058716808,
+      "grad_norm": 0.4441012144088745,
+      "learning_rate": 4.823917828319883e-05,
+      "loss": 0.5303,
+      "step": 200
+    },
+    {
+      "epoch": 0.13194788058716808,
+      "eval_loss": 0.5291892886161804,
+      "eval_runtime": 282.4233,
+      "eval_samples_per_second": 18.079,
+      "eval_steps_per_second": 0.567,
+      "step": 200
+    },
+    {
+      "epoch": 0.13854527461652646,
+      "grad_norm": 0.4900895059108734,
+      "learning_rate": 4.787234042553192e-05,
+      "loss": 0.5109,
+      "step": 210
+    },
+    {
+      "epoch": 0.13854527461652646,
+      "eval_loss": 0.5132142901420593,
+      "eval_runtime": 282.4262,
+      "eval_samples_per_second": 18.079,
+      "eval_steps_per_second": 0.567,
+      "step": 210
+    },
+    {
+      "epoch": 0.14514266864588488,
+      "grad_norm": 0.4287125766277313,
+      "learning_rate": 4.750550256786501e-05,
+      "loss": 0.5109,
+      "step": 220
+    },
+    {
+      "epoch": 0.14514266864588488,
+      "eval_loss": 0.4994109869003296,
+      "eval_runtime": 282.5477,
+      "eval_samples_per_second": 18.071,
+      "eval_steps_per_second": 0.566,
+      "step": 220
+    },
+    {
+      "epoch": 0.1517400626752433,
+      "grad_norm": 0.4390946626663208,
+      "learning_rate": 4.713866471019809e-05,
+      "loss": 0.4952,
+      "step": 230
+    },
+    {
+      "epoch": 0.1517400626752433,
+      "eval_loss": 0.4881007969379425,
+      "eval_runtime": 282.5158,
+      "eval_samples_per_second": 18.073,
+      "eval_steps_per_second": 0.566,
+      "step": 230
+    },
+    {
+      "epoch": 0.15833745670460167,
+      "grad_norm": 0.5645927786827087,
+      "learning_rate": 4.677182685253118e-05,
+      "loss": 0.488,
+      "step": 240
+    },
+    {
+      "epoch": 0.15833745670460167,
+      "eval_loss": 0.4788074791431427,
+      "eval_runtime": 282.6337,
+      "eval_samples_per_second": 18.066,
+      "eval_steps_per_second": 0.566,
+      "step": 240
+    },
+    {
+      "epoch": 0.16493485073396008,
+      "grad_norm": 0.5930696129798889,
+      "learning_rate": 4.6404988994864274e-05,
+      "loss": 0.4833,
+      "step": 250
+    },
+    {
+      "epoch": 0.16493485073396008,
+      "eval_loss": 0.4700024425983429,
+      "eval_runtime": 282.5674,
+      "eval_samples_per_second": 18.07,
+      "eval_steps_per_second": 0.566,
+      "step": 250
+    },
+    {
+      "epoch": 0.1715322447633185,
+      "grad_norm": 0.408792644739151,
+      "learning_rate": 4.6038151137197364e-05,
+      "loss": 0.4696,
+      "step": 260
+    },
+    {
+      "epoch": 0.1715322447633185,
+      "eval_loss": 0.46224626898765564,
+      "eval_runtime": 282.2108,
+      "eval_samples_per_second": 18.093,
+      "eval_steps_per_second": 0.567,
+      "step": 260
+    },
+    {
+      "epoch": 0.1781296387926769,
+      "grad_norm": 0.5276111960411072,
+      "learning_rate": 4.567131327953045e-05,
+      "loss": 0.4579,
+      "step": 270
+    },
+    {
+      "epoch": 0.1781296387926769,
+      "eval_loss": 0.455151230096817,
+      "eval_runtime": 282.6419,
+      "eval_samples_per_second": 18.065,
+      "eval_steps_per_second": 0.566,
+      "step": 270
+    },
+    {
+      "epoch": 0.1847270328220353,
+      "grad_norm": 0.5726278424263,
+      "learning_rate": 4.530447542186354e-05,
+      "loss": 0.4547,
+      "step": 280
+    },
+    {
+      "epoch": 0.1847270328220353,
+      "eval_loss": 0.44886669516563416,
+      "eval_runtime": 282.6094,
+      "eval_samples_per_second": 18.067,
+      "eval_steps_per_second": 0.566,
+      "step": 280
+    },
+    {
+      "epoch": 0.1913244268513937,
+      "grad_norm": 0.4161057770252228,
+      "learning_rate": 4.493763756419663e-05,
+      "loss": 0.4513,
+      "step": 290
+    },
+    {
+      "epoch": 0.1913244268513937,
+      "eval_loss": 0.44479382038116455,
+      "eval_runtime": 282.5015,
+      "eval_samples_per_second": 18.074,
+      "eval_steps_per_second": 0.566,
+      "step": 290
+    },
+    {
+      "epoch": 0.1979218208807521,
+      "grad_norm": 0.4173205494880676,
+      "learning_rate": 4.457079970652971e-05,
+      "loss": 0.4364,
+      "step": 300
+    },
+    {
+      "epoch": 0.1979218208807521,
+      "eval_loss": 0.4391051232814789,
+      "eval_runtime": 282.6206,
+      "eval_samples_per_second": 18.067,
+      "eval_steps_per_second": 0.566,
+      "step": 300
+    },
+    {
+      "epoch": 0.20451921491011052,
+      "grad_norm": 0.4726370871067047,
+      "learning_rate": 4.420396184886281e-05,
+      "loss": 0.4413,
+      "step": 310
+    },
+    {
+      "epoch": 0.20451921491011052,
+      "eval_loss": 0.43503668904304504,
+      "eval_runtime": 282.4681,
+      "eval_samples_per_second": 18.076,
+      "eval_steps_per_second": 0.566,
+      "step": 310
+    },
+    {
+      "epoch": 0.2111166089394689,
+      "grad_norm": 0.528791069984436,
+      "learning_rate": 4.383712399119589e-05,
+      "loss": 0.4347,
+      "step": 320
+    },
+    {
+      "epoch": 0.2111166089394689,
+      "eval_loss": 0.4299105107784271,
+      "eval_runtime": 282.3837,
+      "eval_samples_per_second": 18.082,
+      "eval_steps_per_second": 0.567,
+      "step": 320
+    },
+    {
+      "epoch": 0.2177140029688273,
+      "grad_norm": 0.4637807607650757,
+      "learning_rate": 4.347028613352898e-05,
+      "loss": 0.4263,
+      "step": 330
+    },
+    {
+      "epoch": 0.2177140029688273,
+      "eval_loss": 0.42648786306381226,
+      "eval_runtime": 282.4045,
+      "eval_samples_per_second": 18.08,
+      "eval_steps_per_second": 0.567,
+      "step": 330
+    },
+    {
+      "epoch": 0.22431139699818572,
+      "grad_norm": 0.5652016401290894,
+      "learning_rate": 4.3103448275862066e-05,
+      "loss": 0.424,
+      "step": 340
+    },
+    {
+      "epoch": 0.22431139699818572,
+      "eval_loss": 0.42295747995376587,
+      "eval_runtime": 282.132,
+      "eval_samples_per_second": 18.098,
+      "eval_steps_per_second": 0.567,
+      "step": 340
+    },
+    {
+      "epoch": 0.2309087910275441,
+      "grad_norm": 0.5480278134346008,
+      "learning_rate": 4.273661041819516e-05,
+      "loss": 0.4246,
+      "step": 350
+    },
+    {
+      "epoch": 0.2309087910275441,
+      "eval_loss": 0.4191484749317169,
+      "eval_runtime": 282.8434,
+      "eval_samples_per_second": 18.052,
+      "eval_steps_per_second": 0.566,
+      "step": 350
+    },
+    {
+      "epoch": 0.23750618505690252,
+      "grad_norm": 0.5954585671424866,
+      "learning_rate": 4.2369772560528246e-05,
+      "loss": 0.4194,
+      "step": 360
+    },
+    {
+      "epoch": 0.23750618505690252,
+      "eval_loss": 0.4160284399986267,
+      "eval_runtime": 282.0609,
+      "eval_samples_per_second": 18.102,
+      "eval_steps_per_second": 0.567,
+      "step": 360
+    },
+    {
+      "epoch": 0.24410357908626093,
+      "grad_norm": 0.6444059610366821,
+      "learning_rate": 4.2002934702861336e-05,
+      "loss": 0.4151,
+      "step": 370
+    },
+    {
+      "epoch": 0.24410357908626093,
+      "eval_loss": 0.4145909547805786,
+      "eval_runtime": 282.2951,
+      "eval_samples_per_second": 18.087,
+      "eval_steps_per_second": 0.567,
+      "step": 370
+    },
+    {
+      "epoch": 0.25070097311561934,
+      "grad_norm": 0.5506740212440491,
+      "learning_rate": 4.163609684519443e-05,
+      "loss": 0.4143,
+      "step": 380
+    },
+    {
+      "epoch": 0.25070097311561934,
+      "eval_loss": 0.41122376918792725,
+      "eval_runtime": 282.3323,
+      "eval_samples_per_second": 18.085,
+      "eval_steps_per_second": 0.567,
+      "step": 380
+    },
+    {
+      "epoch": 0.2572983671449777,
+      "grad_norm": 0.5273014307022095,
+      "learning_rate": 4.126925898752752e-05,
+      "loss": 0.4059,
+      "step": 390
+    },
+    {
+      "epoch": 0.2572983671449777,
+      "eval_loss": 0.41092923283576965,
+      "eval_runtime": 282.2453,
+      "eval_samples_per_second": 18.091,
+      "eval_steps_per_second": 0.567,
+      "step": 390
+    },
+    {
+      "epoch": 0.26389576117433616,
+      "grad_norm": 0.5662177205085754,
+      "learning_rate": 4.09024211298606e-05,
+      "loss": 0.411,
+      "step": 400
+    },
+    {
+      "epoch": 0.26389576117433616,
+      "eval_loss": 0.40584176778793335,
+      "eval_runtime": 282.2166,
+      "eval_samples_per_second": 18.092,
+      "eval_steps_per_second": 0.567,
+      "step": 400
+    },
+    {
+      "epoch": 0.27049315520369455,
+      "grad_norm": 0.6541048884391785,
+      "learning_rate": 4.05355832721937e-05,
+      "loss": 0.4017,
+      "step": 410
+    },
+    {
+      "epoch": 0.27049315520369455,
+      "eval_loss": 0.4048697054386139,
+      "eval_runtime": 282.3287,
+      "eval_samples_per_second": 18.085,
+      "eval_steps_per_second": 0.567,
+      "step": 410
+    },
+    {
+      "epoch": 0.27709054923305293,
+      "grad_norm": 0.490032821893692,
+      "learning_rate": 4.016874541452678e-05,
+      "loss": 0.3986,
+      "step": 420
+    },
+    {
+      "epoch": 0.27709054923305293,
+      "eval_loss": 0.4038483202457428,
+      "eval_runtime": 282.2547,
+      "eval_samples_per_second": 18.09,
+      "eval_steps_per_second": 0.567,
+      "step": 420
+    },
+    {
+      "epoch": 0.28368794326241137,
+      "grad_norm": 0.4884147644042969,
+      "learning_rate": 3.980190755685987e-05,
+      "loss": 0.4003,
+      "step": 430
+    },
+    {
+      "epoch": 0.28368794326241137,
+      "eval_loss": 0.40054452419281006,
+      "eval_runtime": 282.2046,
+      "eval_samples_per_second": 18.093,
+      "eval_steps_per_second": 0.567,
+      "step": 430
+    },
+    {
+      "epoch": 0.29028533729176975,
+      "grad_norm": 0.5234985947608948,
+      "learning_rate": 3.943506969919296e-05,
+      "loss": 0.4005,
+      "step": 440
+    },
+    {
+      "epoch": 0.29028533729176975,
+      "eval_loss": 0.39862698316574097,
+      "eval_runtime": 282.1876,
+      "eval_samples_per_second": 18.094,
+      "eval_steps_per_second": 0.567,
+      "step": 440
+    },
+    {
+      "epoch": 0.29688273132112813,
+      "grad_norm": 0.512843668460846,
+      "learning_rate": 3.9068231841526045e-05,
+      "loss": 0.3952,
+      "step": 450
+    },
+    {
+      "epoch": 0.29688273132112813,
+      "eval_loss": 0.3970402181148529,
+      "eval_runtime": 282.2615,
+      "eval_samples_per_second": 18.09,
+      "eval_steps_per_second": 0.567,
+      "step": 450
+    },
+    {
+      "epoch": 0.3034801253504866,
+      "grad_norm": 0.46752044558525085,
+      "learning_rate": 3.8701393983859135e-05,
+      "loss": 0.3967,
+      "step": 460
+    },
+    {
+      "epoch": 0.3034801253504866,
+      "eval_loss": 0.39410126209259033,
+      "eval_runtime": 282.2669,
+      "eval_samples_per_second": 18.089,
+      "eval_steps_per_second": 0.567,
+      "step": 460
+    },
+    {
+      "epoch": 0.31007751937984496,
+      "grad_norm": 0.49608954787254333,
+      "learning_rate": 3.8334556126192226e-05,
+      "loss": 0.3893,
+      "step": 470
+    },
+    {
+      "epoch": 0.31007751937984496,
+      "eval_loss": 0.3944699168205261,
+      "eval_runtime": 282.3461,
+      "eval_samples_per_second": 18.084,
+      "eval_steps_per_second": 0.567,
+      "step": 470
+    },
+    {
+      "epoch": 0.31667491340920334,
+      "grad_norm": 0.4948144853115082,
+      "learning_rate": 3.7967718268525316e-05,
+      "loss": 0.3883,
+      "step": 480
+    },
+    {
+      "epoch": 0.31667491340920334,
+      "eval_loss": 0.3926471471786499,
+      "eval_runtime": 282.4921,
+      "eval_samples_per_second": 18.075,
+      "eval_steps_per_second": 0.566,
+      "step": 480
+    },
+    {
+      "epoch": 0.3232723074385618,
+      "grad_norm": 0.5696155428886414,
+      "learning_rate": 3.76008804108584e-05,
+      "loss": 0.3921,
+      "step": 490
+    },
+    {
+      "epoch": 0.3232723074385618,
+      "eval_loss": 0.39166340231895447,
+      "eval_runtime": 282.2989,
+      "eval_samples_per_second": 18.087,
+      "eval_steps_per_second": 0.567,
+      "step": 490
+    },
+    {
+      "epoch": 0.32986970146792016,
+      "grad_norm": 0.5400599241256714,
+      "learning_rate": 3.723404255319149e-05,
+      "loss": 0.3927,
+      "step": 500
+    },
+    {
+      "epoch": 0.32986970146792016,
+      "eval_loss": 0.3899206817150116,
+      "eval_runtime": 282.6164,
+      "eval_samples_per_second": 18.067,
+      "eval_steps_per_second": 0.566,
+      "step": 500
+    },
+    {
+      "epoch": 0.3364670954972786,
+      "grad_norm": 0.5328640937805176,
+      "learning_rate": 3.686720469552458e-05,
+      "loss": 0.3893,
+      "step": 510
+    },
+    {
+      "epoch": 0.3364670954972786,
+      "eval_loss": 0.388072669506073,
+      "eval_runtime": 282.6361,
+      "eval_samples_per_second": 18.066,
+      "eval_steps_per_second": 0.566,
+      "step": 510
+    },
+    {
+      "epoch": 0.343064489526637,
+      "grad_norm": 0.6197268962860107,
+      "learning_rate": 3.650036683785767e-05,
+      "loss": 0.3896,
+      "step": 520
+    },
+    {
+      "epoch": 0.343064489526637,
+      "eval_loss": 0.38577401638031006,
+      "eval_runtime": 282.5926,
+      "eval_samples_per_second": 18.068,
+      "eval_steps_per_second": 0.566,
+      "step": 520
+    },
+    {
+      "epoch": 0.34966188355599537,
+      "grad_norm": 0.5348854064941406,
+      "learning_rate": 3.6133528980190754e-05,
+      "loss": 0.3824,
+      "step": 530
+    },
+    {
+      "epoch": 0.34966188355599537,
+      "eval_loss": 0.38608622550964355,
+      "eval_runtime": 282.758,
+      "eval_samples_per_second": 18.058,
+      "eval_steps_per_second": 0.566,
+      "step": 530
+    },
+    {
+      "epoch": 0.3562592775853538,
+      "grad_norm": 0.46607691049575806,
+      "learning_rate": 3.576669112252385e-05,
+      "loss": 0.39,
+      "step": 540
+    },
+    {
+      "epoch": 0.3562592775853538,
+      "eval_loss": 0.3843710720539093,
+      "eval_runtime": 282.6255,
+      "eval_samples_per_second": 18.066,
+      "eval_steps_per_second": 0.566,
+      "step": 540
+    },
+    {
+      "epoch": 0.3628566716147122,
+      "grad_norm": 0.5211663246154785,
+      "learning_rate": 3.5399853264856934e-05,
+      "loss": 0.3831,
+      "step": 550
+    },
+    {
+      "epoch": 0.3628566716147122,
+      "eval_loss": 0.38406872749328613,
+      "eval_runtime": 282.6083,
+      "eval_samples_per_second": 18.067,
+      "eval_steps_per_second": 0.566,
+      "step": 550
+    },
+    {
+      "epoch": 0.3694540656440706,
+      "grad_norm": 0.4613727927207947,
+      "learning_rate": 3.5033015407190025e-05,
+      "loss": 0.3848,
+      "step": 560
+    },
+    {
+      "epoch": 0.3694540656440706,
+      "eval_loss": 0.38266727328300476,
+      "eval_runtime": 282.5681,
+      "eval_samples_per_second": 18.07,
+      "eval_steps_per_second": 0.566,
+      "step": 560
+    },
+    {
+      "epoch": 0.376051459673429,
+      "grad_norm": 0.4561725854873657,
+      "learning_rate": 3.466617754952311e-05,
+      "loss": 0.3771,
+      "step": 570
+    },
+    {
+      "epoch": 0.376051459673429,
+      "eval_loss": 0.38093405961990356,
+      "eval_runtime": 282.579,
+      "eval_samples_per_second": 18.069,
+      "eval_steps_per_second": 0.566,
+      "step": 570
+    },
+    {
+      "epoch": 0.3826488537027874,
+      "grad_norm": 0.5360392928123474,
+      "learning_rate": 3.4299339691856205e-05,
+      "loss": 0.3819,
+      "step": 580
+    },
+    {
+      "epoch": 0.3826488537027874,
+      "eval_loss": 0.380355566740036,
+      "eval_runtime": 282.5981,
+      "eval_samples_per_second": 18.068,
+      "eval_steps_per_second": 0.566,
+      "step": 580
+    },
+    {
+      "epoch": 0.3892462477321458,
+      "grad_norm": 0.6373459696769714,
+      "learning_rate": 3.393250183418929e-05,
+      "loss": 0.3773,
+      "step": 590
+    },
+    {
+      "epoch": 0.3892462477321458,
+      "eval_loss": 0.37904950976371765,
+      "eval_runtime": 282.4657,
+      "eval_samples_per_second": 18.077,
+      "eval_steps_per_second": 0.566,
+      "step": 590
+    },
+    {
+      "epoch": 0.3958436417615042,
+      "grad_norm": 0.4231775403022766,
+      "learning_rate": 3.356566397652238e-05,
+      "loss": 0.3736,
+      "step": 600
+    },
+    {
+      "epoch": 0.3958436417615042,
+      "eval_loss": 0.37867945432662964,
+      "eval_runtime": 282.479,
+      "eval_samples_per_second": 18.076,
+      "eval_steps_per_second": 0.566,
+      "step": 600
+    },
+    {
+      "epoch": 0.4024410357908626,
+      "grad_norm": 0.5430477261543274,
+      "learning_rate": 3.319882611885547e-05,
+      "loss": 0.3778,
+      "step": 610
+    },
+    {
+      "epoch": 0.4024410357908626,
+      "eval_loss": 0.3770335912704468,
+      "eval_runtime": 282.4938,
+      "eval_samples_per_second": 18.075,
+      "eval_steps_per_second": 0.566,
+      "step": 610
+    },
+    {
+      "epoch": 0.40903842982022104,
+      "grad_norm": 0.5898250341415405,
+      "learning_rate": 3.283198826118856e-05,
+      "loss": 0.3783,
+      "step": 620
+    },
+    {
+      "epoch": 0.40903842982022104,
+      "eval_loss": 0.37556448578834534,
+      "eval_runtime": 282.4757,
+      "eval_samples_per_second": 18.076,
+      "eval_steps_per_second": 0.566,
+      "step": 620
+    },
+    {
+      "epoch": 0.4156358238495794,
+      "grad_norm": 0.5367993116378784,
+      "learning_rate": 3.246515040352164e-05,
+      "loss": 0.3726,
+      "step": 630
+    },
+    {
+      "epoch": 0.4156358238495794,
+      "eval_loss": 0.37541213631629944,
+      "eval_runtime": 282.4621,
+      "eval_samples_per_second": 18.077,
+      "eval_steps_per_second": 0.566,
+      "step": 630
+    },
+    {
+      "epoch": 0.4222332178789378,
+      "grad_norm": 0.5479997992515564,
+      "learning_rate": 3.209831254585473e-05,
+      "loss": 0.3747,
+      "step": 640
+    },
+    {
+      "epoch": 0.4222332178789378,
+      "eval_loss": 0.37338846921920776,
+      "eval_runtime": 281.8183,
+      "eval_samples_per_second": 18.118,
+      "eval_steps_per_second": 0.568,
+      "step": 640
+    },
+    {
+      "epoch": 0.42883061190829624,
+      "grad_norm": 0.5168615579605103,
+      "learning_rate": 3.1731474688187823e-05,
+      "loss": 0.3748,
+      "step": 650
+    },
+    {
+      "epoch": 0.42883061190829624,
+      "eval_loss": 0.373104453086853,
+      "eval_runtime": 282.3532,
+      "eval_samples_per_second": 18.084,
+      "eval_steps_per_second": 0.567,
+      "step": 650
+    },
+    {
+      "epoch": 0.4354280059376546,
+      "grad_norm": 0.4789239764213562,
+      "learning_rate": 3.1364636830520914e-05,
+      "loss": 0.3725,
+      "step": 660
+    },
+    {
+      "epoch": 0.4354280059376546,
+      "eval_loss": 0.37169981002807617,
+      "eval_runtime": 282.5035,
+      "eval_samples_per_second": 18.074,
+      "eval_steps_per_second": 0.566,
+      "step": 660
+    },
+    {
+      "epoch": 0.442025399967013,
+      "grad_norm": 0.5288018584251404,
+      "learning_rate": 3.0997798972854e-05,
+      "loss": 0.3715,
+      "step": 670
+    },
+    {
+      "epoch": 0.442025399967013,
+      "eval_loss": 0.3723226487636566,
+      "eval_runtime": 282.4315,
+      "eval_samples_per_second": 18.079,
+      "eval_steps_per_second": 0.567,
+      "step": 670
+    },
+    {
+      "epoch": 0.44862279399637145,
+      "grad_norm": 0.5399067997932434,
+      "learning_rate": 3.063096111518709e-05,
+      "loss": 0.3672,
+      "step": 680
+    },
+    {
+      "epoch": 0.44862279399637145,
+      "eval_loss": 0.3709748387336731,
+      "eval_runtime": 282.3214,
+      "eval_samples_per_second": 18.086,
+      "eval_steps_per_second": 0.567,
+      "step": 680
+    },
+    {
+      "epoch": 0.45522018802572983,
+      "grad_norm": 0.5560658574104309,
+      "learning_rate": 3.0264123257520178e-05,
+      "loss": 0.3703,
+      "step": 690
+    },
+    {
+      "epoch": 0.45522018802572983,
+      "eval_loss": 0.3694921135902405,
+      "eval_runtime": 282.225,
+      "eval_samples_per_second": 18.092,
+      "eval_steps_per_second": 0.567,
+      "step": 690
+    },
+    {
+      "epoch": 0.4618175820550882,
+      "grad_norm": 0.46738743782043457,
+      "learning_rate": 2.9897285399853265e-05,
+      "loss": 0.3691,
+      "step": 700
+    },
+    {
+      "epoch": 0.4618175820550882,
+      "eval_loss": 0.36861899495124817,
+      "eval_runtime": 281.4833,
+      "eval_samples_per_second": 18.14,
+      "eval_steps_per_second": 0.568,
+      "step": 700
+    },
+    {
+      "epoch": 0.46841497608444665,
+      "grad_norm": 0.5636041760444641,
+      "learning_rate": 2.953044754218636e-05,
+      "loss": 0.3674,
+      "step": 710
+    },
+    {
+      "epoch": 0.46841497608444665,
+      "eval_loss": 0.3687904477119446,
+      "eval_runtime": 281.7696,
+      "eval_samples_per_second": 18.121,
+      "eval_steps_per_second": 0.568,
+      "step": 710
+    },
+    {
+      "epoch": 0.47501237011380504,
+      "grad_norm": 0.6417700052261353,
+      "learning_rate": 2.9163609684519445e-05,
+      "loss": 0.3676,
+      "step": 720
+    },
+    {
+      "epoch": 0.47501237011380504,
+      "eval_loss": 0.36721163988113403,
+      "eval_runtime": 281.7105,
+      "eval_samples_per_second": 18.125,
+      "eval_steps_per_second": 0.568,
+      "step": 720
+    },
+    {
+      "epoch": 0.4816097641431635,
+      "grad_norm": 0.5903835892677307,
+      "learning_rate": 2.8796771826852532e-05,
+      "loss": 0.3687,
+      "step": 730
+    },
+    {
+      "epoch": 0.4816097641431635,
+      "eval_loss": 0.36735713481903076,
+      "eval_runtime": 280.4935,
+      "eval_samples_per_second": 18.204,
+      "eval_steps_per_second": 0.57,
+      "step": 730
+    },
+    {
+      "epoch": 0.48820715817252186,
+      "grad_norm": 0.6300948858261108,
+      "learning_rate": 2.8429933969185622e-05,
+      "loss": 0.3649,
+      "step": 740
+    },
+    {
+      "epoch": 0.48820715817252186,
+      "eval_loss": 0.3654569089412689,
+      "eval_runtime": 282.5933,
+      "eval_samples_per_second": 18.068,
+      "eval_steps_per_second": 0.566,
+      "step": 740
+    },
+    {
+      "epoch": 0.49480455220188024,
+      "grad_norm": 0.5772879123687744,
+      "learning_rate": 2.806309611151871e-05,
+      "loss": 0.3636,
+      "step": 750
+    },
+    {
+      "epoch": 0.49480455220188024,
+      "eval_loss": 0.3652118444442749,
+      "eval_runtime": 281.9717,
+      "eval_samples_per_second": 18.108,
+      "eval_steps_per_second": 0.567,
+      "step": 750
+    },
+    {
+      "epoch": 0.5014019462312387,
+      "grad_norm": 0.46134456992149353,
+      "learning_rate": 2.7696258253851796e-05,
+      "loss": 0.3626,
+      "step": 760
+    },
+    {
+      "epoch": 0.5014019462312387,
+      "eval_loss": 0.364380419254303,
+      "eval_runtime": 281.1459,
+      "eval_samples_per_second": 18.161,
+      "eval_steps_per_second": 0.569,
+      "step": 760
+    },
+    {
+      "epoch": 0.507999340260597,
+      "grad_norm": 0.5804652571678162,
+      "learning_rate": 2.7329420396184886e-05,
+      "loss": 0.3611,
+      "step": 770
+    },
+    {
+      "epoch": 0.507999340260597,
+      "eval_loss": 0.3632882237434387,
+      "eval_runtime": 281.5379,
+      "eval_samples_per_second": 18.136,
+      "eval_steps_per_second": 0.568,
+      "step": 770
+    },
+    {
+      "epoch": 0.5145967342899554,
+      "grad_norm": 0.45915406942367554,
+      "learning_rate": 2.6962582538517977e-05,
+      "loss": 0.3599,
+      "step": 780
+    },
+    {
+      "epoch": 0.5145967342899554,
+      "eval_loss": 0.3634037375450134,
+      "eval_runtime": 281.4618,
+      "eval_samples_per_second": 18.141,
+      "eval_steps_per_second": 0.568,
+      "step": 780
+    },
+    {
+      "epoch": 0.5211941283193139,
+      "grad_norm": 0.4998124837875366,
+      "learning_rate": 2.6595744680851064e-05,
+      "loss": 0.3619,
+      "step": 790
+    },
+    {
+      "epoch": 0.5211941283193139,
+      "eval_loss": 0.3615591526031494,
+      "eval_runtime": 282.3789,
+      "eval_samples_per_second": 18.082,
+      "eval_steps_per_second": 0.567,
+      "step": 790
+    },
+    {
+      "epoch": 0.5277915223486723,
+      "grad_norm": 0.5479339361190796,
+      "learning_rate": 2.622890682318415e-05,
+      "loss": 0.3577,
+      "step": 800
+    },
+    {
+      "epoch": 0.5277915223486723,
+      "eval_loss": 0.3610810339450836,
+      "eval_runtime": 282.2307,
+      "eval_samples_per_second": 18.092,
+      "eval_steps_per_second": 0.567,
+      "step": 800
+    },
+    {
+      "epoch": 0.5343889163780307,
+      "grad_norm": 0.5121034383773804,
+      "learning_rate": 2.5862068965517244e-05,
+      "loss": 0.3621,
+      "step": 810
+    },
+    {
+      "epoch": 0.5343889163780307,
+      "eval_loss": 0.3605840802192688,
+      "eval_runtime": 281.2796,
+      "eval_samples_per_second": 18.153,
+      "eval_steps_per_second": 0.569,
+      "step": 810
+    },
+    {
+      "epoch": 0.5409863104073891,
+      "grad_norm": 0.5326396822929382,
+      "learning_rate": 2.549523110785033e-05,
+      "loss": 0.3575,
+      "step": 820
+    },
+    {
+      "epoch": 0.5409863104073891,
+      "eval_loss": 0.359646201133728,
+      "eval_runtime": 281.2148,
+      "eval_samples_per_second": 18.157,
+      "eval_steps_per_second": 0.569,
+      "step": 820
+    },
+    {
+      "epoch": 0.5475837044367475,
+      "grad_norm": 0.5050413608551025,
+      "learning_rate": 2.5128393250183418e-05,
+      "loss": 0.3545,
+      "step": 830
+    },
+    {
+      "epoch": 0.5475837044367475,
+      "eval_loss": 0.3594898581504822,
+      "eval_runtime": 281.2594,
+      "eval_samples_per_second": 18.154,
+      "eval_steps_per_second": 0.569,
+      "step": 830
+    },
+    {
+      "epoch": 0.5541810984661059,
+      "grad_norm": 0.45093920826911926,
+      "learning_rate": 2.4761555392516508e-05,
+      "loss": 0.3585,
+      "step": 840
+    },
+    {
+      "epoch": 0.5541810984661059,
+      "eval_loss": 0.35947272181510925,
+      "eval_runtime": 280.5764,
+      "eval_samples_per_second": 18.198,
+      "eval_steps_per_second": 0.57,
+      "step": 840
+    },
+    {
+      "epoch": 0.5607784924954643,
+      "grad_norm": 0.44670212268829346,
+      "learning_rate": 2.43947175348496e-05,
+      "loss": 0.3569,
+      "step": 850
+    },
+    {
+      "epoch": 0.5607784924954643,
+      "eval_loss": 0.3579043745994568,
+      "eval_runtime": 281.4427,
+      "eval_samples_per_second": 18.142,
+      "eval_steps_per_second": 0.568,
+      "step": 850
+    },
+    {
+      "epoch": 0.5673758865248227,
+      "grad_norm": 0.5422260761260986,
+      "learning_rate": 2.4027879677182685e-05,
+      "loss": 0.3525,
+      "step": 860
+    },
+    {
+      "epoch": 0.5673758865248227,
+      "eval_loss": 0.35847437381744385,
+      "eval_runtime": 280.6628,
+      "eval_samples_per_second": 18.193,
+      "eval_steps_per_second": 0.57,
+      "step": 860
+    },
+    {
+      "epoch": 0.5739732805541811,
+      "grad_norm": 0.49470987915992737,
+      "learning_rate": 2.3661041819515776e-05,
+      "loss": 0.3528,
+      "step": 870
+    },
+    {
+      "epoch": 0.5739732805541811,
+      "eval_loss": 0.35762321949005127,
+      "eval_runtime": 281.4774,
+      "eval_samples_per_second": 18.14,
+      "eval_steps_per_second": 0.568,
+      "step": 870
+    },
+    {
+      "epoch": 0.5805706745835395,
+      "grad_norm": 0.5388288497924805,
+      "learning_rate": 2.3294203961848866e-05,
+      "loss": 0.3533,
+      "step": 880
+    },
+    {
+      "epoch": 0.5805706745835395,
+      "eval_loss": 0.3578256666660309,
+      "eval_runtime": 280.4896,
+      "eval_samples_per_second": 18.204,
+      "eval_steps_per_second": 0.57,
+      "step": 880
+    },
+    {
+      "epoch": 0.5871680686128979,
+      "grad_norm": 0.4280325174331665,
+      "learning_rate": 2.2927366104181953e-05,
+      "loss": 0.3574,
+      "step": 890
+    },
+    {
+      "epoch": 0.5871680686128979,
+      "eval_loss": 0.35690200328826904,
+      "eval_runtime": 280.7823,
+      "eval_samples_per_second": 18.185,
+      "eval_steps_per_second": 0.57,
+      "step": 890
+    },
+    {
+      "epoch": 0.5937654626422563,
+      "grad_norm": 0.6243644952774048,
+      "learning_rate": 2.2560528246515043e-05,
+      "loss": 0.356,
+      "step": 900
+    },
+    {
+      "epoch": 0.5937654626422563,
+      "eval_loss": 0.3565099537372589,
+      "eval_runtime": 280.4402,
+      "eval_samples_per_second": 18.207,
+      "eval_steps_per_second": 0.571,
+      "step": 900
+    },
+    {
+      "epoch": 0.6003628566716147,
+      "grad_norm": 0.5401405096054077,
+      "learning_rate": 2.219369038884813e-05,
+      "loss": 0.3594,
+      "step": 910
+    },
+    {
+      "epoch": 0.6003628566716147,
+      "eval_loss": 0.3559376895427704,
+      "eval_runtime": 281.1004,
+      "eval_samples_per_second": 18.164,
+      "eval_steps_per_second": 0.569,
+      "step": 910
+    },
+    {
+      "epoch": 0.6069602507009731,
+      "grad_norm": 0.578926682472229,
+      "learning_rate": 2.182685253118122e-05,
+      "loss": 0.3542,
+      "step": 920
+    },
+    {
+      "epoch": 0.6069602507009731,
+      "eval_loss": 0.35559171438217163,
+      "eval_runtime": 281.4745,
+      "eval_samples_per_second": 18.14,
+      "eval_steps_per_second": 0.568,
+      "step": 920
+    },
+    {
+      "epoch": 0.6135576447303315,
+      "grad_norm": 0.460857629776001,
+      "learning_rate": 2.1460014673514307e-05,
+      "loss": 0.3587,
+      "step": 930
+    },
+    {
+      "epoch": 0.6135576447303315,
+      "eval_loss": 0.35534095764160156,
+      "eval_runtime": 280.8406,
+      "eval_samples_per_second": 18.181,
+      "eval_steps_per_second": 0.57,
+      "step": 930
+    },
+    {
+      "epoch": 0.6201550387596899,
+      "grad_norm": 0.5364406704902649,
+      "learning_rate": 2.1093176815847397e-05,
+      "loss": 0.353,
+      "step": 940
+    },
+    {
+      "epoch": 0.6201550387596899,
+      "eval_loss": 0.3539869785308838,
+      "eval_runtime": 280.7515,
+      "eval_samples_per_second": 18.187,
+      "eval_steps_per_second": 0.57,
+      "step": 940
+    },
+    {
+      "epoch": 0.6267524327890484,
+      "grad_norm": 0.50699782371521,
+      "learning_rate": 2.0726338958180484e-05,
+      "loss": 0.3525,
+      "step": 950
+    },
+    {
+      "epoch": 0.6267524327890484,
+      "eval_loss": 0.35391008853912354,
+      "eval_runtime": 281.3705,
+      "eval_samples_per_second": 18.147,
+      "eval_steps_per_second": 0.569,
+      "step": 950
+    },
+    {
+      "epoch": 0.6333498268184067,
+      "grad_norm": 0.6315603852272034,
+      "learning_rate": 2.035950110051357e-05,
+      "loss": 0.3546,
+      "step": 960
+    },
+    {
+      "epoch": 0.6333498268184067,
+      "eval_loss": 0.35362812876701355,
+      "eval_runtime": 281.4224,
+      "eval_samples_per_second": 18.144,
+      "eval_steps_per_second": 0.569,
+      "step": 960
+    },
+    {
+      "epoch": 0.6399472208477651,
+      "grad_norm": 0.5252578258514404,
+      "learning_rate": 1.999266324284666e-05,
+      "loss": 0.3521,
+      "step": 970
+    },
+    {
+      "epoch": 0.6399472208477651,
+      "eval_loss": 0.3530423045158386,
+      "eval_runtime": 280.5129,
+      "eval_samples_per_second": 18.202,
+      "eval_steps_per_second": 0.57,
+      "step": 970
+    },
+    {
+      "epoch": 0.6465446148771236,
+      "grad_norm": 0.5415360331535339,
+      "learning_rate": 1.962582538517975e-05,
+      "loss": 0.3543,
+      "step": 980
+    },
+    {
+      "epoch": 0.6465446148771236,
+      "eval_loss": 0.3528820276260376,
+      "eval_runtime": 280.8145,
+      "eval_samples_per_second": 18.183,
+      "eval_steps_per_second": 0.57,
+      "step": 980
+    },
+    {
+      "epoch": 0.6531420089064819,
+      "grad_norm": 0.5389861464500427,
+      "learning_rate": 1.925898752751284e-05,
+      "loss": 0.3528,
+      "step": 990
+    },
+    {
+      "epoch": 0.6531420089064819,
+      "eval_loss": 0.3525787889957428,
+      "eval_runtime": 280.6494,
+      "eval_samples_per_second": 18.194,
+      "eval_steps_per_second": 0.57,
+      "step": 990
+    },
+    {
+      "epoch": 0.6597394029358403,
+      "grad_norm": 0.47096070647239685,
+      "learning_rate": 1.889214966984593e-05,
+      "loss": 0.3514,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6597394029358403,
+      "eval_loss": 0.352372944355011,
+      "eval_runtime": 280.6707,
+      "eval_samples_per_second": 18.192,
+      "eval_steps_per_second": 0.57,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1515,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.3527241133195264e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20202947030b88d9f740e0704ab3de3052a0dd5ba3e216dcb5a8b4e2060d9f2c
+size 5368

checkpoint-500/README.md

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

checkpoint-500/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e722404e61c21dc3d110aab825fd82af32ddecd8cf256d41e869256c6b828be2
+size 35668592

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36a236d51f67c56db96fa81cd011cd94866551b643f656153c3a054e70571e80
+size 71380026

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3132d963f34a74461e24bb42f9713cd0ff7738c9fecc105a782c519817c0183e
+size 14244

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5202b531860b6267980bb7fd2f99eb07b95b7c967157881494f4209ff57feb09
+size 1064

checkpoint-500/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-500/tokenizer_config.json

@@ -0,0 +1,131 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": true,
+  "add_prefix_space": null,
+  "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
+    }
+  },
+  "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": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-500/trainer_state.json

@@ -0,0 +1,783 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.32986970146792016,
+  "eval_steps": 10,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006597394029358403,
+      "grad_norm": 1.2868798971176147,
+      "learning_rate": 3.2894736842105265e-06,
+      "loss": 4.6934,
+      "step": 10
+    },
+    {
+      "epoch": 0.006597394029358403,
+      "eval_loss": 4.687362194061279,
+      "eval_runtime": 282.9655,
+      "eval_samples_per_second": 18.045,
+      "eval_steps_per_second": 0.565,
+      "step": 10
+    },
+    {
+      "epoch": 0.013194788058716806,
+      "grad_norm": 1.302221417427063,
+      "learning_rate": 6.578947368421053e-06,
+      "loss": 4.6651,
+      "step": 20
+    },
+    {
+      "epoch": 0.013194788058716806,
+      "eval_loss": 4.648743152618408,
+      "eval_runtime": 282.9326,
+      "eval_samples_per_second": 18.047,
+      "eval_steps_per_second": 0.566,
+      "step": 20
+    },
+    {
+      "epoch": 0.01979218208807521,
+      "grad_norm": 1.4535945653915405,
+      "learning_rate": 9.868421052631579e-06,
+      "loss": 4.6063,
+      "step": 30
+    },
+    {
+      "epoch": 0.01979218208807521,
+      "eval_loss": 4.54951286315918,
+      "eval_runtime": 282.3584,
+      "eval_samples_per_second": 18.083,
+      "eval_steps_per_second": 0.567,
+      "step": 30
+    },
+    {
+      "epoch": 0.026389576117433613,
+      "grad_norm": 1.714498519897461,
+      "learning_rate": 1.3157894736842106e-05,
+      "loss": 4.4527,
+      "step": 40
+    },
+    {
+      "epoch": 0.026389576117433613,
+      "eval_loss": 4.304062366485596,
+      "eval_runtime": 282.5935,
+      "eval_samples_per_second": 18.068,
+      "eval_steps_per_second": 0.566,
+      "step": 40
+    },
+    {
+      "epoch": 0.03298697014679202,
+      "grad_norm": 1.832472324371338,
+      "learning_rate": 1.6447368421052635e-05,
+      "loss": 4.1216,
+      "step": 50
+    },
+    {
+      "epoch": 0.03298697014679202,
+      "eval_loss": 3.8426761627197266,
+      "eval_runtime": 281.3902,
+      "eval_samples_per_second": 18.146,
+      "eval_steps_per_second": 0.569,
+      "step": 50
+    },
+    {
+      "epoch": 0.03958436417615042,
+      "grad_norm": 1.1160222291946411,
+      "learning_rate": 1.9736842105263158e-05,
+      "loss": 3.6561,
+      "step": 60
+    },
+    {
+      "epoch": 0.03958436417615042,
+      "eval_loss": 3.4654476642608643,
+      "eval_runtime": 282.2746,
+      "eval_samples_per_second": 18.089,
+      "eval_steps_per_second": 0.567,
+      "step": 60
+    },
+    {
+      "epoch": 0.04618175820550882,
+      "grad_norm": 1.1160507202148438,
+      "learning_rate": 2.3026315789473685e-05,
+      "loss": 3.2993,
+      "step": 70
+    },
+    {
+      "epoch": 0.04618175820550882,
+      "eval_loss": 3.0560474395751953,
+      "eval_runtime": 282.4864,
+      "eval_samples_per_second": 18.075,
+      "eval_steps_per_second": 0.566,
+      "step": 70
+    },
+    {
+      "epoch": 0.052779152234867226,
+      "grad_norm": 0.7468234896659851,
+      "learning_rate": 2.6315789473684212e-05,
+      "loss": 2.8777,
+      "step": 80
+    },
+    {
+      "epoch": 0.052779152234867226,
+      "eval_loss": 2.7082414627075195,
+      "eval_runtime": 282.279,
+      "eval_samples_per_second": 18.088,
+      "eval_steps_per_second": 0.567,
+      "step": 80
+    },
+    {
+      "epoch": 0.05937654626422563,
+      "grad_norm": 0.7456527948379517,
+      "learning_rate": 2.9605263157894735e-05,
+      "loss": 2.5844,
+      "step": 90
+    },
+    {
+      "epoch": 0.05937654626422563,
+      "eval_loss": 2.400399923324585,
+      "eval_runtime": 282.4234,
+      "eval_samples_per_second": 18.079,
+      "eval_steps_per_second": 0.567,
+      "step": 90
+    },
+    {
+      "epoch": 0.06597394029358404,
+      "grad_norm": 0.7843755483627319,
+      "learning_rate": 3.289473684210527e-05,
+      "loss": 2.2405,
+      "step": 100
+    },
+    {
+      "epoch": 0.06597394029358404,
+      "eval_loss": 2.043464422225952,
+      "eval_runtime": 282.4971,
+      "eval_samples_per_second": 18.075,
+      "eval_steps_per_second": 0.566,
+      "step": 100
+    },
+    {
+      "epoch": 0.07257133432294244,
+      "grad_norm": 0.7848460078239441,
+      "learning_rate": 3.618421052631579e-05,
+      "loss": 1.8797,
+      "step": 110
+    },
+    {
+      "epoch": 0.07257133432294244,
+      "eval_loss": 1.6749211549758911,
+      "eval_runtime": 282.4596,
+      "eval_samples_per_second": 18.077,
+      "eval_steps_per_second": 0.566,
+      "step": 110
+    },
+    {
+      "epoch": 0.07916872835230084,
+      "grad_norm": 0.8517773151397705,
+      "learning_rate": 3.9473684210526316e-05,
+      "loss": 1.5041,
+      "step": 120
+    },
+    {
+      "epoch": 0.07916872835230084,
+      "eval_loss": 1.322484016418457,
+      "eval_runtime": 282.425,
+      "eval_samples_per_second": 18.079,
+      "eval_steps_per_second": 0.567,
+      "step": 120
+    },
+    {
+      "epoch": 0.08576612238165925,
+      "grad_norm": 0.924010694026947,
+      "learning_rate": 4.2763157894736847e-05,
+      "loss": 1.1712,
+      "step": 130
+    },
+    {
+      "epoch": 0.08576612238165925,
+      "eval_loss": 1.0092010498046875,
+      "eval_runtime": 282.4135,
+      "eval_samples_per_second": 18.08,
+      "eval_steps_per_second": 0.567,
+      "step": 130
+    },
+    {
+      "epoch": 0.09236351641101764,
+      "grad_norm": 0.599291205406189,
+      "learning_rate": 4.605263157894737e-05,
+      "loss": 0.9068,
+      "step": 140
+    },
+    {
+      "epoch": 0.09236351641101764,
+      "eval_loss": 0.8262147307395935,
+      "eval_runtime": 282.3089,
+      "eval_samples_per_second": 18.087,
+      "eval_steps_per_second": 0.567,
+      "step": 140
+    },
+    {
+      "epoch": 0.09896091044037605,
+      "grad_norm": 0.4690685570240021,
+      "learning_rate": 4.9342105263157894e-05,
+      "loss": 0.7821,
+      "step": 150
+    },
+    {
+      "epoch": 0.09896091044037605,
+      "eval_loss": 0.7165087461471558,
+      "eval_runtime": 282.1805,
+      "eval_samples_per_second": 18.095,
+      "eval_steps_per_second": 0.567,
+      "step": 150
+    },
+    {
+      "epoch": 0.10555830446973445,
+      "grad_norm": 0.5129504203796387,
+      "learning_rate": 4.9706529713866475e-05,
+      "loss": 0.6867,
+      "step": 160
+    },
+    {
+      "epoch": 0.10555830446973445,
+      "eval_loss": 0.6483914256095886,
+      "eval_runtime": 282.207,
+      "eval_samples_per_second": 18.093,
+      "eval_steps_per_second": 0.567,
+      "step": 160
+    },
+    {
+      "epoch": 0.11215569849909286,
+      "grad_norm": 0.4116060435771942,
+      "learning_rate": 4.933969185619956e-05,
+      "loss": 0.6315,
+      "step": 170
+    },
+    {
+      "epoch": 0.11215569849909286,
+      "eval_loss": 0.6029236912727356,
+      "eval_runtime": 282.3594,
+      "eval_samples_per_second": 18.083,
+      "eval_steps_per_second": 0.567,
+      "step": 170
+    },
+    {
+      "epoch": 0.11875309252845126,
+      "grad_norm": 0.4301941990852356,
+      "learning_rate": 4.8972853998532655e-05,
+      "loss": 0.5833,
+      "step": 180
+    },
+    {
+      "epoch": 0.11875309252845126,
+      "eval_loss": 0.5720704197883606,
+      "eval_runtime": 282.0439,
+      "eval_samples_per_second": 18.104,
+      "eval_steps_per_second": 0.567,
+      "step": 180
+    },
+    {
+      "epoch": 0.12535048655780967,
+      "grad_norm": 0.5514675378799438,
+      "learning_rate": 4.860601614086574e-05,
+      "loss": 0.5667,
+      "step": 190
+    },
+    {
+      "epoch": 0.12535048655780967,
+      "eval_loss": 0.5490744709968567,
+      "eval_runtime": 282.3239,
+      "eval_samples_per_second": 18.086,
+      "eval_steps_per_second": 0.567,
+      "step": 190
+    },
+    {
+      "epoch": 0.13194788058716808,
+      "grad_norm": 0.4441012144088745,
+      "learning_rate": 4.823917828319883e-05,
+      "loss": 0.5303,
+      "step": 200
+    },
+    {
+      "epoch": 0.13194788058716808,
+      "eval_loss": 0.5291892886161804,
+      "eval_runtime": 282.4233,
+      "eval_samples_per_second": 18.079,
+      "eval_steps_per_second": 0.567,
+      "step": 200
+    },
+    {
+      "epoch": 0.13854527461652646,
+      "grad_norm": 0.4900895059108734,
+      "learning_rate": 4.787234042553192e-05,
+      "loss": 0.5109,
+      "step": 210
+    },
+    {
+      "epoch": 0.13854527461652646,
+      "eval_loss": 0.5132142901420593,
+      "eval_runtime": 282.4262,
+      "eval_samples_per_second": 18.079,
+      "eval_steps_per_second": 0.567,
+      "step": 210
+    },
+    {
+      "epoch": 0.14514266864588488,
+      "grad_norm": 0.4287125766277313,
+      "learning_rate": 4.750550256786501e-05,
+      "loss": 0.5109,
+      "step": 220
+    },
+    {
+      "epoch": 0.14514266864588488,
+      "eval_loss": 0.4994109869003296,
+      "eval_runtime": 282.5477,
+      "eval_samples_per_second": 18.071,
+      "eval_steps_per_second": 0.566,
+      "step": 220
+    },
+    {
+      "epoch": 0.1517400626752433,
+      "grad_norm": 0.4390946626663208,
+      "learning_rate": 4.713866471019809e-05,
+      "loss": 0.4952,
+      "step": 230
+    },
+    {
+      "epoch": 0.1517400626752433,
+      "eval_loss": 0.4881007969379425,
+      "eval_runtime": 282.5158,
+      "eval_samples_per_second": 18.073,
+      "eval_steps_per_second": 0.566,
+      "step": 230
+    },
+    {
+      "epoch": 0.15833745670460167,
+      "grad_norm": 0.5645927786827087,
+      "learning_rate": 4.677182685253118e-05,
+      "loss": 0.488,
+      "step": 240
+    },
+    {
+      "epoch": 0.15833745670460167,
+      "eval_loss": 0.4788074791431427,
+      "eval_runtime": 282.6337,
+      "eval_samples_per_second": 18.066,
+      "eval_steps_per_second": 0.566,
+      "step": 240
+    },
+    {
+      "epoch": 0.16493485073396008,
+      "grad_norm": 0.5930696129798889,
+      "learning_rate": 4.6404988994864274e-05,
+      "loss": 0.4833,
+      "step": 250
+    },
+    {
+      "epoch": 0.16493485073396008,
+      "eval_loss": 0.4700024425983429,
+      "eval_runtime": 282.5674,
+      "eval_samples_per_second": 18.07,
+      "eval_steps_per_second": 0.566,
+      "step": 250
+    },
+    {
+      "epoch": 0.1715322447633185,
+      "grad_norm": 0.408792644739151,
+      "learning_rate": 4.6038151137197364e-05,
+      "loss": 0.4696,
+      "step": 260
+    },
+    {
+      "epoch": 0.1715322447633185,
+      "eval_loss": 0.46224626898765564,
+      "eval_runtime": 282.2108,
+      "eval_samples_per_second": 18.093,
+      "eval_steps_per_second": 0.567,
+      "step": 260
+    },
+    {
+      "epoch": 0.1781296387926769,
+      "grad_norm": 0.5276111960411072,
+      "learning_rate": 4.567131327953045e-05,
+      "loss": 0.4579,
+      "step": 270
+    },
+    {
+      "epoch": 0.1781296387926769,
+      "eval_loss": 0.455151230096817,
+      "eval_runtime": 282.6419,
+      "eval_samples_per_second": 18.065,
+      "eval_steps_per_second": 0.566,
+      "step": 270
+    },
+    {
+      "epoch": 0.1847270328220353,
+      "grad_norm": 0.5726278424263,
+      "learning_rate": 4.530447542186354e-05,
+      "loss": 0.4547,
+      "step": 280
+    },
+    {
+      "epoch": 0.1847270328220353,
+      "eval_loss": 0.44886669516563416,
+      "eval_runtime": 282.6094,
+      "eval_samples_per_second": 18.067,
+      "eval_steps_per_second": 0.566,
+      "step": 280
+    },
+    {
+      "epoch": 0.1913244268513937,
+      "grad_norm": 0.4161057770252228,
+      "learning_rate": 4.493763756419663e-05,
+      "loss": 0.4513,
+      "step": 290
+    },
+    {
+      "epoch": 0.1913244268513937,
+      "eval_loss": 0.44479382038116455,
+      "eval_runtime": 282.5015,
+      "eval_samples_per_second": 18.074,
+      "eval_steps_per_second": 0.566,
+      "step": 290
+    },
+    {
+      "epoch": 0.1979218208807521,
+      "grad_norm": 0.4173205494880676,
+      "learning_rate": 4.457079970652971e-05,
+      "loss": 0.4364,
+      "step": 300
+    },
+    {
+      "epoch": 0.1979218208807521,
+      "eval_loss": 0.4391051232814789,
+      "eval_runtime": 282.6206,
+      "eval_samples_per_second": 18.067,
+      "eval_steps_per_second": 0.566,
+      "step": 300
+    },
+    {
+      "epoch": 0.20451921491011052,
+      "grad_norm": 0.4726370871067047,
+      "learning_rate": 4.420396184886281e-05,
+      "loss": 0.4413,
+      "step": 310
+    },
+    {
+      "epoch": 0.20451921491011052,
+      "eval_loss": 0.43503668904304504,
+      "eval_runtime": 282.4681,
+      "eval_samples_per_second": 18.076,
+      "eval_steps_per_second": 0.566,
+      "step": 310
+    },
+    {
+      "epoch": 0.2111166089394689,
+      "grad_norm": 0.528791069984436,
+      "learning_rate": 4.383712399119589e-05,
+      "loss": 0.4347,
+      "step": 320
+    },
+    {
+      "epoch": 0.2111166089394689,
+      "eval_loss": 0.4299105107784271,
+      "eval_runtime": 282.3837,
+      "eval_samples_per_second": 18.082,
+      "eval_steps_per_second": 0.567,
+      "step": 320
+    },
+    {
+      "epoch": 0.2177140029688273,
+      "grad_norm": 0.4637807607650757,
+      "learning_rate": 4.347028613352898e-05,
+      "loss": 0.4263,
+      "step": 330
+    },
+    {
+      "epoch": 0.2177140029688273,
+      "eval_loss": 0.42648786306381226,
+      "eval_runtime": 282.4045,
+      "eval_samples_per_second": 18.08,
+      "eval_steps_per_second": 0.567,
+      "step": 330
+    },
+    {
+      "epoch": 0.22431139699818572,
+      "grad_norm": 0.5652016401290894,
+      "learning_rate": 4.3103448275862066e-05,
+      "loss": 0.424,
+      "step": 340
+    },
+    {
+      "epoch": 0.22431139699818572,
+      "eval_loss": 0.42295747995376587,
+      "eval_runtime": 282.132,
+      "eval_samples_per_second": 18.098,
+      "eval_steps_per_second": 0.567,
+      "step": 340
+    },
+    {
+      "epoch": 0.2309087910275441,
+      "grad_norm": 0.5480278134346008,
+      "learning_rate": 4.273661041819516e-05,
+      "loss": 0.4246,
+      "step": 350
+    },
+    {
+      "epoch": 0.2309087910275441,
+      "eval_loss": 0.4191484749317169,
+      "eval_runtime": 282.8434,
+      "eval_samples_per_second": 18.052,
+      "eval_steps_per_second": 0.566,
+      "step": 350
+    },
+    {
+      "epoch": 0.23750618505690252,
+      "grad_norm": 0.5954585671424866,
+      "learning_rate": 4.2369772560528246e-05,
+      "loss": 0.4194,
+      "step": 360
+    },
+    {
+      "epoch": 0.23750618505690252,
+      "eval_loss": 0.4160284399986267,
+      "eval_runtime": 282.0609,
+      "eval_samples_per_second": 18.102,
+      "eval_steps_per_second": 0.567,
+      "step": 360
+    },
+    {
+      "epoch": 0.24410357908626093,
+      "grad_norm": 0.6444059610366821,
+      "learning_rate": 4.2002934702861336e-05,
+      "loss": 0.4151,
+      "step": 370
+    },
+    {
+      "epoch": 0.24410357908626093,
+      "eval_loss": 0.4145909547805786,
+      "eval_runtime": 282.2951,
+      "eval_samples_per_second": 18.087,
+      "eval_steps_per_second": 0.567,
+      "step": 370
+    },
+    {
+      "epoch": 0.25070097311561934,
+      "grad_norm": 0.5506740212440491,
+      "learning_rate": 4.163609684519443e-05,
+      "loss": 0.4143,
+      "step": 380
+    },
+    {
+      "epoch": 0.25070097311561934,
+      "eval_loss": 0.41122376918792725,
+      "eval_runtime": 282.3323,
+      "eval_samples_per_second": 18.085,
+      "eval_steps_per_second": 0.567,
+      "step": 380
+    },
+    {
+      "epoch": 0.2572983671449777,
+      "grad_norm": 0.5273014307022095,
+      "learning_rate": 4.126925898752752e-05,
+      "loss": 0.4059,
+      "step": 390
+    },
+    {
+      "epoch": 0.2572983671449777,
+      "eval_loss": 0.41092923283576965,
+      "eval_runtime": 282.2453,
+      "eval_samples_per_second": 18.091,
+      "eval_steps_per_second": 0.567,
+      "step": 390
+    },
+    {
+      "epoch": 0.26389576117433616,
+      "grad_norm": 0.5662177205085754,
+      "learning_rate": 4.09024211298606e-05,
+      "loss": 0.411,
+      "step": 400
+    },
+    {
+      "epoch": 0.26389576117433616,
+      "eval_loss": 0.40584176778793335,
+      "eval_runtime": 282.2166,
+      "eval_samples_per_second": 18.092,
+      "eval_steps_per_second": 0.567,
+      "step": 400
+    },
+    {
+      "epoch": 0.27049315520369455,
+      "grad_norm": 0.6541048884391785,
+      "learning_rate": 4.05355832721937e-05,
+      "loss": 0.4017,
+      "step": 410
+    },
+    {
+      "epoch": 0.27049315520369455,
+      "eval_loss": 0.4048697054386139,
+      "eval_runtime": 282.3287,
+      "eval_samples_per_second": 18.085,
+      "eval_steps_per_second": 0.567,
+      "step": 410
+    },
+    {
+      "epoch": 0.27709054923305293,
+      "grad_norm": 0.490032821893692,
+      "learning_rate": 4.016874541452678e-05,
+      "loss": 0.3986,
+      "step": 420
+    },
+    {
+      "epoch": 0.27709054923305293,
+      "eval_loss": 0.4038483202457428,
+      "eval_runtime": 282.2547,
+      "eval_samples_per_second": 18.09,
+      "eval_steps_per_second": 0.567,
+      "step": 420
+    },
+    {
+      "epoch": 0.28368794326241137,
+      "grad_norm": 0.4884147644042969,
+      "learning_rate": 3.980190755685987e-05,
+      "loss": 0.4003,
+      "step": 430
+    },
+    {
+      "epoch": 0.28368794326241137,
+      "eval_loss": 0.40054452419281006,
+      "eval_runtime": 282.2046,
+      "eval_samples_per_second": 18.093,
+      "eval_steps_per_second": 0.567,
+      "step": 430
+    },
+    {
+      "epoch": 0.29028533729176975,
+      "grad_norm": 0.5234985947608948,
+      "learning_rate": 3.943506969919296e-05,
+      "loss": 0.4005,
+      "step": 440
+    },
+    {
+      "epoch": 0.29028533729176975,
+      "eval_loss": 0.39862698316574097,
+      "eval_runtime": 282.1876,
+      "eval_samples_per_second": 18.094,
+      "eval_steps_per_second": 0.567,
+      "step": 440
+    },
+    {
+      "epoch": 0.29688273132112813,
+      "grad_norm": 0.512843668460846,
+      "learning_rate": 3.9068231841526045e-05,
+      "loss": 0.3952,
+      "step": 450
+    },
+    {
+      "epoch": 0.29688273132112813,
+      "eval_loss": 0.3970402181148529,
+      "eval_runtime": 282.2615,
+      "eval_samples_per_second": 18.09,
+      "eval_steps_per_second": 0.567,
+      "step": 450
+    },
+    {
+      "epoch": 0.3034801253504866,
+      "grad_norm": 0.46752044558525085,
+      "learning_rate": 3.8701393983859135e-05,
+      "loss": 0.3967,
+      "step": 460
+    },
+    {
+      "epoch": 0.3034801253504866,
+      "eval_loss": 0.39410126209259033,
+      "eval_runtime": 282.2669,
+      "eval_samples_per_second": 18.089,
+      "eval_steps_per_second": 0.567,
+      "step": 460
+    },
+    {
+      "epoch": 0.31007751937984496,
+      "grad_norm": 0.49608954787254333,
+      "learning_rate": 3.8334556126192226e-05,
+      "loss": 0.3893,
+      "step": 470
+    },
+    {
+      "epoch": 0.31007751937984496,
+      "eval_loss": 0.3944699168205261,
+      "eval_runtime": 282.3461,
+      "eval_samples_per_second": 18.084,
+      "eval_steps_per_second": 0.567,
+      "step": 470
+    },
+    {
+      "epoch": 0.31667491340920334,
+      "grad_norm": 0.4948144853115082,
+      "learning_rate": 3.7967718268525316e-05,
+      "loss": 0.3883,
+      "step": 480
+    },
+    {
+      "epoch": 0.31667491340920334,
+      "eval_loss": 0.3926471471786499,
+      "eval_runtime": 282.4921,
+      "eval_samples_per_second": 18.075,
+      "eval_steps_per_second": 0.566,
+      "step": 480
+    },
+    {
+      "epoch": 0.3232723074385618,
+      "grad_norm": 0.5696155428886414,
+      "learning_rate": 3.76008804108584e-05,
+      "loss": 0.3921,
+      "step": 490
+    },
+    {
+      "epoch": 0.3232723074385618,
+      "eval_loss": 0.39166340231895447,
+      "eval_runtime": 282.2989,
+      "eval_samples_per_second": 18.087,
+      "eval_steps_per_second": 0.567,
+      "step": 490
+    },
+    {
+      "epoch": 0.32986970146792016,
+      "grad_norm": 0.5400599241256714,
+      "learning_rate": 3.723404255319149e-05,
+      "loss": 0.3927,
+      "step": 500
+    },
+    {
+      "epoch": 0.32986970146792016,
+      "eval_loss": 0.3899206817150116,
+      "eval_runtime": 282.6164,
+      "eval_samples_per_second": 18.067,
+      "eval_steps_per_second": 0.566,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1515,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1763083231772672e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20202947030b88d9f740e0704ab3de3052a0dd5ba3e216dcb5a8b4e2060d9f2c
+size 5368

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_config.json

@@ -0,0 +1,131 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": true,
+  "add_prefix_space": null,
+  "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
+    }
+  },
+  "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": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20202947030b88d9f740e0704ab3de3052a0dd5ba3e216dcb5a8b4e2060d9f2c
+size 5368