Upload folder using huggingface_hub

README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: microsoft/Phi-3-mini-4k-instruct
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "qkv_proj",
+    "gate_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 sha256:27960ea85c5e90128c40979df6ebd3efcdd74246545d80e16ce4fbef244e9a60
+size 201361312

added_tokens.json

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

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.5526673584371,
+    "train_runtime": 758.4004,
+    "train_samples_per_second": 1.552,
+    "train_steps_per_second": 0.049
+}

checkpoint-30/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: microsoft/Phi-3-mini-4k-instruct
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

checkpoint-30/adapter_config.json

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

checkpoint-30/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b9b4bfd5a8abb85e5184513e75547c6bcfc885e2b1e86b8f601eda4dc317984
+size 201361312

checkpoint-30/added_tokens.json

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

checkpoint-30/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:216b12dc5b9a6ceb61dd6218a185077907c9e85f9da126f27314b2627cabebdb
+size 402807738

checkpoint-30/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eac44814ffb9482f32f7d108b872e0833cd2a3012223ddc96b39b2e8d64c66a1
+size 14180

checkpoint-30/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67cc9e39e8feea09990024036c87a4ead2c2c013e11c9bfefa2b47eab30caf86
+size 1064

checkpoint-30/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-30/tokenizer.model

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

checkpoint-30/tokenizer_config.json

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

checkpoint-30/trainer_state.json

@@ -0,0 +1,483 @@
+{
+  "best_metric": 1.6244161128997803,
+  "best_model_checkpoint": "./output/checkpoints/2024-06-11_10-58-33/checkpoint-30",
+  "epoch": 0.8108108108108109,
+  "eval_steps": 1,
+  "global_step": 30,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02702702702702703,
+      "grad_norm": 3.2274646759033203,
+      "learning_rate": 0.0001,
+      "loss": 5.7374,
+      "step": 1
+    },
+    {
+      "epoch": 0.02702702702702703,
+      "eval_loss": 5.6431050300598145,
+      "eval_runtime": 10.9746,
+      "eval_samples_per_second": 11.299,
+      "eval_steps_per_second": 0.729,
+      "step": 1
+    },
+    {
+      "epoch": 0.05405405405405406,
+      "grad_norm": 3.1417839527130127,
+      "learning_rate": 0.0002,
+      "loss": 5.6423,
+      "step": 2
+    },
+    {
+      "epoch": 0.05405405405405406,
+      "eval_loss": 5.1099138259887695,
+      "eval_runtime": 11.0219,
+      "eval_samples_per_second": 11.25,
+      "eval_steps_per_second": 0.726,
+      "step": 2
+    },
+    {
+      "epoch": 0.08108108108108109,
+      "grad_norm": 3.1990153789520264,
+      "learning_rate": 0.00030000000000000003,
+      "loss": 5.0948,
+      "step": 3
+    },
+    {
+      "epoch": 0.08108108108108109,
+      "eval_loss": 3.559605836868286,
+      "eval_runtime": 11.0991,
+      "eval_samples_per_second": 11.172,
+      "eval_steps_per_second": 0.721,
+      "step": 3
+    },
+    {
+      "epoch": 0.10810810810810811,
+      "grad_norm": 3.2903366088867188,
+      "learning_rate": 0.0004,
+      "loss": 3.4375,
+      "step": 4
+    },
+    {
+      "epoch": 0.10810810810810811,
+      "eval_loss": 2.3610196113586426,
+      "eval_runtime": 11.0573,
+      "eval_samples_per_second": 11.214,
+      "eval_steps_per_second": 0.724,
+      "step": 4
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 1.878879189491272,
+      "learning_rate": 0.0003878787878787879,
+      "loss": 2.2693,
+      "step": 5
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "eval_loss": 1.8543975353240967,
+      "eval_runtime": 11.1541,
+      "eval_samples_per_second": 11.117,
+      "eval_steps_per_second": 0.717,
+      "step": 5
+    },
+    {
+      "epoch": 0.16216216216216217,
+      "grad_norm": 1.2040495872497559,
+      "learning_rate": 0.0003757575757575758,
+      "loss": 1.7546,
+      "step": 6
+    },
+    {
+      "epoch": 0.16216216216216217,
+      "eval_loss": 1.7222554683685303,
+      "eval_runtime": 11.0742,
+      "eval_samples_per_second": 11.197,
+      "eval_steps_per_second": 0.722,
+      "step": 6
+    },
+    {
+      "epoch": 0.1891891891891892,
+      "grad_norm": 1.080614447593689,
+      "learning_rate": 0.00036363636363636367,
+      "loss": 1.6633,
+      "step": 7
+    },
+    {
+      "epoch": 0.1891891891891892,
+      "eval_loss": 1.610931158065796,
+      "eval_runtime": 11.0872,
+      "eval_samples_per_second": 11.184,
+      "eval_steps_per_second": 0.722,
+      "step": 7
+    },
+    {
+      "epoch": 0.21621621621621623,
+      "grad_norm": 0.28874385356903076,
+      "learning_rate": 0.00035151515151515155,
+      "loss": 1.5122,
+      "step": 8
+    },
+    {
+      "epoch": 0.21621621621621623,
+      "eval_loss": 1.5804481506347656,
+      "eval_runtime": 11.053,
+      "eval_samples_per_second": 11.219,
+      "eval_steps_per_second": 0.724,
+      "step": 8
+    },
+    {
+      "epoch": 0.24324324324324326,
+      "grad_norm": 0.32991790771484375,
+      "learning_rate": 0.00033939393939393943,
+      "loss": 1.4316,
+      "step": 9
+    },
+    {
+      "epoch": 0.24324324324324326,
+      "eval_loss": 1.5746935606002808,
+      "eval_runtime": 11.152,
+      "eval_samples_per_second": 11.119,
+      "eval_steps_per_second": 0.717,
+      "step": 9
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "grad_norm": 0.5137693285942078,
+      "learning_rate": 0.0003272727272727273,
+      "loss": 1.3161,
+      "step": 10
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "eval_loss": 1.651396632194519,
+      "eval_runtime": 11.1562,
+      "eval_samples_per_second": 11.115,
+      "eval_steps_per_second": 0.717,
+      "step": 10
+    },
+    {
+      "epoch": 0.2972972972972973,
+      "grad_norm": 0.25246673822402954,
+      "learning_rate": 0.00031515151515151515,
+      "loss": 1.207,
+      "step": 11
+    },
+    {
+      "epoch": 0.2972972972972973,
+      "eval_loss": 1.7246230840682983,
+      "eval_runtime": 11.1298,
+      "eval_samples_per_second": 11.141,
+      "eval_steps_per_second": 0.719,
+      "step": 11
+    },
+    {
+      "epoch": 0.32432432432432434,
+      "grad_norm": 0.2032381296157837,
+      "learning_rate": 0.00030303030303030303,
+      "loss": 1.158,
+      "step": 12
+    },
+    {
+      "epoch": 0.32432432432432434,
+      "eval_loss": 1.7255425453186035,
+      "eval_runtime": 11.0733,
+      "eval_samples_per_second": 11.198,
+      "eval_steps_per_second": 0.722,
+      "step": 12
+    },
+    {
+      "epoch": 0.35135135135135137,
+      "grad_norm": 0.2133413404226303,
+      "learning_rate": 0.0002909090909090909,
+      "loss": 1.1137,
+      "step": 13
+    },
+    {
+      "epoch": 0.35135135135135137,
+      "eval_loss": 1.6880252361297607,
+      "eval_runtime": 11.2007,
+      "eval_samples_per_second": 11.071,
+      "eval_steps_per_second": 0.714,
+      "step": 13
+    },
+    {
+      "epoch": 0.3783783783783784,
+      "grad_norm": 0.20175401866436005,
+      "learning_rate": 0.0002787878787878788,
+      "loss": 1.1059,
+      "step": 14
+    },
+    {
+      "epoch": 0.3783783783783784,
+      "eval_loss": 1.6500831842422485,
+      "eval_runtime": 11.1367,
+      "eval_samples_per_second": 11.134,
+      "eval_steps_per_second": 0.718,
+      "step": 14
+    },
+    {
+      "epoch": 0.40540540540540543,
+      "grad_norm": 0.22595511376857758,
+      "learning_rate": 0.0002666666666666667,
+      "loss": 1.0483,
+      "step": 15
+    },
+    {
+      "epoch": 0.40540540540540543,
+      "eval_loss": 1.6288588047027588,
+      "eval_runtime": 11.1914,
+      "eval_samples_per_second": 11.08,
+      "eval_steps_per_second": 0.715,
+      "step": 15
+    },
+    {
+      "epoch": 0.43243243243243246,
+      "grad_norm": 0.17468485236167908,
+      "learning_rate": 0.00025454545454545456,
+      "loss": 1.0584,
+      "step": 16
+    },
+    {
+      "epoch": 0.43243243243243246,
+      "eval_loss": 1.6247642040252686,
+      "eval_runtime": 11.1035,
+      "eval_samples_per_second": 11.168,
+      "eval_steps_per_second": 0.72,
+      "step": 16
+    },
+    {
+      "epoch": 0.4594594594594595,
+      "grad_norm": 0.1654416024684906,
+      "learning_rate": 0.00024242424242424245,
+      "loss": 1.0402,
+      "step": 17
+    },
+    {
+      "epoch": 0.4594594594594595,
+      "eval_loss": 1.6316722631454468,
+      "eval_runtime": 11.2065,
+      "eval_samples_per_second": 11.065,
+      "eval_steps_per_second": 0.714,
+      "step": 17
+    },
+    {
+      "epoch": 0.4864864864864865,
+      "grad_norm": 0.10361829400062561,
+      "learning_rate": 0.00023030303030303033,
+      "loss": 1.0301,
+      "step": 18
+    },
+    {
+      "epoch": 0.4864864864864865,
+      "eval_loss": 1.6415338516235352,
+      "eval_runtime": 11.18,
+      "eval_samples_per_second": 11.091,
+      "eval_steps_per_second": 0.716,
+      "step": 18
+    },
+    {
+      "epoch": 0.5135135135135135,
+      "grad_norm": 0.09156349301338196,
+      "learning_rate": 0.00021818181818181818,
+      "loss": 1.0183,
+      "step": 19
+    },
+    {
+      "epoch": 0.5135135135135135,
+      "eval_loss": 1.6544169187545776,
+      "eval_runtime": 11.1626,
+      "eval_samples_per_second": 11.109,
+      "eval_steps_per_second": 0.717,
+      "step": 19
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 0.087005615234375,
+      "learning_rate": 0.00020606060606060607,
+      "loss": 1.028,
+      "step": 20
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "eval_loss": 1.6620415449142456,
+      "eval_runtime": 11.2393,
+      "eval_samples_per_second": 11.033,
+      "eval_steps_per_second": 0.712,
+      "step": 20
+    },
+    {
+      "epoch": 0.5675675675675675,
+      "grad_norm": 0.09235216677188873,
+      "learning_rate": 0.00019393939393939395,
+      "loss": 0.9825,
+      "step": 21
+    },
+    {
+      "epoch": 0.5675675675675675,
+      "eval_loss": 1.6642476320266724,
+      "eval_runtime": 11.2278,
+      "eval_samples_per_second": 11.044,
+      "eval_steps_per_second": 0.713,
+      "step": 21
+    },
+    {
+      "epoch": 0.5945945945945946,
+      "grad_norm": 0.0915454775094986,
+      "learning_rate": 0.00018181818181818183,
+      "loss": 0.9991,
+      "step": 22
+    },
+    {
+      "epoch": 0.5945945945945946,
+      "eval_loss": 1.6625572443008423,
+      "eval_runtime": 11.1424,
+      "eval_samples_per_second": 11.129,
+      "eval_steps_per_second": 0.718,
+      "step": 22
+    },
+    {
+      "epoch": 0.6216216216216216,
+      "grad_norm": 0.09213992953300476,
+      "learning_rate": 0.00016969696969696972,
+      "loss": 1.0211,
+      "step": 23
+    },
+    {
+      "epoch": 0.6216216216216216,
+      "eval_loss": 1.6593235731124878,
+      "eval_runtime": 11.1978,
+      "eval_samples_per_second": 11.074,
+      "eval_steps_per_second": 0.714,
+      "step": 23
+    },
+    {
+      "epoch": 0.6486486486486487,
+      "grad_norm": 0.0854020044207573,
+      "learning_rate": 0.00015757575757575757,
+      "loss": 1.0291,
+      "step": 24
+    },
+    {
+      "epoch": 0.6486486486486487,
+      "eval_loss": 1.6526458263397217,
+      "eval_runtime": 11.2323,
+      "eval_samples_per_second": 11.04,
+      "eval_steps_per_second": 0.712,
+      "step": 24
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "grad_norm": 0.08045388758182526,
+      "learning_rate": 0.00014545454545454546,
+      "loss": 0.9887,
+      "step": 25
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "eval_loss": 1.6451815366744995,
+      "eval_runtime": 11.1905,
+      "eval_samples_per_second": 11.081,
+      "eval_steps_per_second": 0.715,
+      "step": 25
+    },
+    {
+      "epoch": 0.7027027027027027,
+      "grad_norm": 0.07576093822717667,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 1.0044,
+      "step": 26
+    },
+    {
+      "epoch": 0.7027027027027027,
+      "eval_loss": 1.6377238035202026,
+      "eval_runtime": 11.1714,
+      "eval_samples_per_second": 11.1,
+      "eval_steps_per_second": 0.716,
+      "step": 26
+    },
+    {
+      "epoch": 0.7297297297297297,
+      "grad_norm": 0.07311829924583435,
+      "learning_rate": 0.00012121212121212122,
+      "loss": 0.9772,
+      "step": 27
+    },
+    {
+      "epoch": 0.7297297297297297,
+      "eval_loss": 1.6314424276351929,
+      "eval_runtime": 11.1489,
+      "eval_samples_per_second": 11.122,
+      "eval_steps_per_second": 0.718,
+      "step": 27
+    },
+    {
+      "epoch": 0.7567567567567568,
+      "grad_norm": 0.07776332646608353,
+      "learning_rate": 0.00010909090909090909,
+      "loss": 0.9902,
+      "step": 28
+    },
+    {
+      "epoch": 0.7567567567567568,
+      "eval_loss": 1.625641942024231,
+      "eval_runtime": 11.1261,
+      "eval_samples_per_second": 11.145,
+      "eval_steps_per_second": 0.719,
+      "step": 28
+    },
+    {
+      "epoch": 0.7837837837837838,
+      "grad_norm": 0.07536856085062027,
+      "learning_rate": 9.696969696969698e-05,
+      "loss": 0.9902,
+      "step": 29
+    },
+    {
+      "epoch": 0.7837837837837838,
+      "eval_loss": 1.6233930587768555,
+      "eval_runtime": 11.1754,
+      "eval_samples_per_second": 11.096,
+      "eval_steps_per_second": 0.716,
+      "step": 29
+    },
+    {
+      "epoch": 0.8108108108108109,
+      "grad_norm": 0.07941398024559021,
+      "learning_rate": 8.484848484848486e-05,
+      "loss": 0.9784,
+      "step": 30
+    },
+    {
+      "epoch": 0.8108108108108109,
+      "eval_loss": 1.6244161128997803,
+      "eval_runtime": 11.2511,
+      "eval_samples_per_second": 11.021,
+      "eval_steps_per_second": 0.711,
+      "step": 30
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 37,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.112676608507904e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-30/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb3142b18989e7c2d16024033b2170dd8aada190fd9a38b7a18b5251cf944dde
+size 5688

special_tokens_map.json

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

tokenizer.model

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

tokenizer_config.json

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

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.5526673584371,
+    "train_runtime": 758.4004,
+    "train_samples_per_second": 1.552,
+    "train_steps_per_second": 0.049
+}

trainer_state.json

@@ -0,0 +1,597 @@
+{
+  "best_metric": 1.6244161128997803,
+  "best_model_checkpoint": "./output/checkpoints/2024-06-11_10-58-33/checkpoint-30",
+  "epoch": 1.0,
+  "eval_steps": 1,
+  "global_step": 37,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02702702702702703,
+      "grad_norm": 3.2274646759033203,
+      "learning_rate": 0.0001,
+      "loss": 5.7374,
+      "step": 1
+    },
+    {
+      "epoch": 0.02702702702702703,
+      "eval_loss": 5.6431050300598145,
+      "eval_runtime": 10.9746,
+      "eval_samples_per_second": 11.299,
+      "eval_steps_per_second": 0.729,
+      "step": 1
+    },
+    {
+      "epoch": 0.05405405405405406,
+      "grad_norm": 3.1417839527130127,
+      "learning_rate": 0.0002,
+      "loss": 5.6423,
+      "step": 2
+    },
+    {
+      "epoch": 0.05405405405405406,
+      "eval_loss": 5.1099138259887695,
+      "eval_runtime": 11.0219,
+      "eval_samples_per_second": 11.25,
+      "eval_steps_per_second": 0.726,
+      "step": 2
+    },
+    {
+      "epoch": 0.08108108108108109,
+      "grad_norm": 3.1990153789520264,
+      "learning_rate": 0.00030000000000000003,
+      "loss": 5.0948,
+      "step": 3
+    },
+    {
+      "epoch": 0.08108108108108109,
+      "eval_loss": 3.559605836868286,
+      "eval_runtime": 11.0991,
+      "eval_samples_per_second": 11.172,
+      "eval_steps_per_second": 0.721,
+      "step": 3
+    },
+    {
+      "epoch": 0.10810810810810811,
+      "grad_norm": 3.2903366088867188,
+      "learning_rate": 0.0004,
+      "loss": 3.4375,
+      "step": 4
+    },
+    {
+      "epoch": 0.10810810810810811,
+      "eval_loss": 2.3610196113586426,
+      "eval_runtime": 11.0573,
+      "eval_samples_per_second": 11.214,
+      "eval_steps_per_second": 0.724,
+      "step": 4
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 1.878879189491272,
+      "learning_rate": 0.0003878787878787879,
+      "loss": 2.2693,
+      "step": 5
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "eval_loss": 1.8543975353240967,
+      "eval_runtime": 11.1541,
+      "eval_samples_per_second": 11.117,
+      "eval_steps_per_second": 0.717,
+      "step": 5
+    },
+    {
+      "epoch": 0.16216216216216217,
+      "grad_norm": 1.2040495872497559,
+      "learning_rate": 0.0003757575757575758,
+      "loss": 1.7546,
+      "step": 6
+    },
+    {
+      "epoch": 0.16216216216216217,
+      "eval_loss": 1.7222554683685303,
+      "eval_runtime": 11.0742,
+      "eval_samples_per_second": 11.197,
+      "eval_steps_per_second": 0.722,
+      "step": 6
+    },
+    {
+      "epoch": 0.1891891891891892,
+      "grad_norm": 1.080614447593689,
+      "learning_rate": 0.00036363636363636367,
+      "loss": 1.6633,
+      "step": 7
+    },
+    {
+      "epoch": 0.1891891891891892,
+      "eval_loss": 1.610931158065796,
+      "eval_runtime": 11.0872,
+      "eval_samples_per_second": 11.184,
+      "eval_steps_per_second": 0.722,
+      "step": 7
+    },
+    {
+      "epoch": 0.21621621621621623,
+      "grad_norm": 0.28874385356903076,
+      "learning_rate": 0.00035151515151515155,
+      "loss": 1.5122,
+      "step": 8
+    },
+    {
+      "epoch": 0.21621621621621623,
+      "eval_loss": 1.5804481506347656,
+      "eval_runtime": 11.053,
+      "eval_samples_per_second": 11.219,
+      "eval_steps_per_second": 0.724,
+      "step": 8
+    },
+    {
+      "epoch": 0.24324324324324326,
+      "grad_norm": 0.32991790771484375,
+      "learning_rate": 0.00033939393939393943,
+      "loss": 1.4316,
+      "step": 9
+    },
+    {
+      "epoch": 0.24324324324324326,
+      "eval_loss": 1.5746935606002808,
+      "eval_runtime": 11.152,
+      "eval_samples_per_second": 11.119,
+      "eval_steps_per_second": 0.717,
+      "step": 9
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "grad_norm": 0.5137693285942078,
+      "learning_rate": 0.0003272727272727273,
+      "loss": 1.3161,
+      "step": 10
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "eval_loss": 1.651396632194519,
+      "eval_runtime": 11.1562,
+      "eval_samples_per_second": 11.115,
+      "eval_steps_per_second": 0.717,
+      "step": 10
+    },
+    {
+      "epoch": 0.2972972972972973,
+      "grad_norm": 0.25246673822402954,
+      "learning_rate": 0.00031515151515151515,
+      "loss": 1.207,
+      "step": 11
+    },
+    {
+      "epoch": 0.2972972972972973,
+      "eval_loss": 1.7246230840682983,
+      "eval_runtime": 11.1298,
+      "eval_samples_per_second": 11.141,
+      "eval_steps_per_second": 0.719,
+      "step": 11
+    },
+    {
+      "epoch": 0.32432432432432434,
+      "grad_norm": 0.2032381296157837,
+      "learning_rate": 0.00030303030303030303,
+      "loss": 1.158,
+      "step": 12
+    },
+    {
+      "epoch": 0.32432432432432434,
+      "eval_loss": 1.7255425453186035,
+      "eval_runtime": 11.0733,
+      "eval_samples_per_second": 11.198,
+      "eval_steps_per_second": 0.722,
+      "step": 12
+    },
+    {
+      "epoch": 0.35135135135135137,
+      "grad_norm": 0.2133413404226303,
+      "learning_rate": 0.0002909090909090909,
+      "loss": 1.1137,
+      "step": 13
+    },
+    {
+      "epoch": 0.35135135135135137,
+      "eval_loss": 1.6880252361297607,
+      "eval_runtime": 11.2007,
+      "eval_samples_per_second": 11.071,
+      "eval_steps_per_second": 0.714,
+      "step": 13
+    },
+    {
+      "epoch": 0.3783783783783784,
+      "grad_norm": 0.20175401866436005,
+      "learning_rate": 0.0002787878787878788,
+      "loss": 1.1059,
+      "step": 14
+    },
+    {
+      "epoch": 0.3783783783783784,
+      "eval_loss": 1.6500831842422485,
+      "eval_runtime": 11.1367,
+      "eval_samples_per_second": 11.134,
+      "eval_steps_per_second": 0.718,
+      "step": 14
+    },
+    {
+      "epoch": 0.40540540540540543,
+      "grad_norm": 0.22595511376857758,
+      "learning_rate": 0.0002666666666666667,
+      "loss": 1.0483,
+      "step": 15
+    },
+    {
+      "epoch": 0.40540540540540543,
+      "eval_loss": 1.6288588047027588,
+      "eval_runtime": 11.1914,
+      "eval_samples_per_second": 11.08,
+      "eval_steps_per_second": 0.715,
+      "step": 15
+    },
+    {
+      "epoch": 0.43243243243243246,
+      "grad_norm": 0.17468485236167908,
+      "learning_rate": 0.00025454545454545456,
+      "loss": 1.0584,
+      "step": 16
+    },
+    {
+      "epoch": 0.43243243243243246,
+      "eval_loss": 1.6247642040252686,
+      "eval_runtime": 11.1035,
+      "eval_samples_per_second": 11.168,
+      "eval_steps_per_second": 0.72,
+      "step": 16
+    },
+    {
+      "epoch": 0.4594594594594595,
+      "grad_norm": 0.1654416024684906,
+      "learning_rate": 0.00024242424242424245,
+      "loss": 1.0402,
+      "step": 17
+    },
+    {
+      "epoch": 0.4594594594594595,
+      "eval_loss": 1.6316722631454468,
+      "eval_runtime": 11.2065,
+      "eval_samples_per_second": 11.065,
+      "eval_steps_per_second": 0.714,
+      "step": 17
+    },
+    {
+      "epoch": 0.4864864864864865,
+      "grad_norm": 0.10361829400062561,
+      "learning_rate": 0.00023030303030303033,
+      "loss": 1.0301,
+      "step": 18
+    },
+    {
+      "epoch": 0.4864864864864865,
+      "eval_loss": 1.6415338516235352,
+      "eval_runtime": 11.18,
+      "eval_samples_per_second": 11.091,
+      "eval_steps_per_second": 0.716,
+      "step": 18
+    },
+    {
+      "epoch": 0.5135135135135135,
+      "grad_norm": 0.09156349301338196,
+      "learning_rate": 0.00021818181818181818,
+      "loss": 1.0183,
+      "step": 19
+    },
+    {
+      "epoch": 0.5135135135135135,
+      "eval_loss": 1.6544169187545776,
+      "eval_runtime": 11.1626,
+      "eval_samples_per_second": 11.109,
+      "eval_steps_per_second": 0.717,
+      "step": 19
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 0.087005615234375,
+      "learning_rate": 0.00020606060606060607,
+      "loss": 1.028,
+      "step": 20
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "eval_loss": 1.6620415449142456,
+      "eval_runtime": 11.2393,
+      "eval_samples_per_second": 11.033,
+      "eval_steps_per_second": 0.712,
+      "step": 20
+    },
+    {
+      "epoch": 0.5675675675675675,
+      "grad_norm": 0.09235216677188873,
+      "learning_rate": 0.00019393939393939395,
+      "loss": 0.9825,
+      "step": 21
+    },
+    {
+      "epoch": 0.5675675675675675,
+      "eval_loss": 1.6642476320266724,
+      "eval_runtime": 11.2278,
+      "eval_samples_per_second": 11.044,
+      "eval_steps_per_second": 0.713,
+      "step": 21
+    },
+    {
+      "epoch": 0.5945945945945946,
+      "grad_norm": 0.0915454775094986,
+      "learning_rate": 0.00018181818181818183,
+      "loss": 0.9991,
+      "step": 22
+    },
+    {
+      "epoch": 0.5945945945945946,
+      "eval_loss": 1.6625572443008423,
+      "eval_runtime": 11.1424,
+      "eval_samples_per_second": 11.129,
+      "eval_steps_per_second": 0.718,
+      "step": 22
+    },
+    {
+      "epoch": 0.6216216216216216,
+      "grad_norm": 0.09213992953300476,
+      "learning_rate": 0.00016969696969696972,
+      "loss": 1.0211,
+      "step": 23
+    },
+    {
+      "epoch": 0.6216216216216216,
+      "eval_loss": 1.6593235731124878,
+      "eval_runtime": 11.1978,
+      "eval_samples_per_second": 11.074,
+      "eval_steps_per_second": 0.714,
+      "step": 23
+    },
+    {
+      "epoch": 0.6486486486486487,
+      "grad_norm": 0.0854020044207573,
+      "learning_rate": 0.00015757575757575757,
+      "loss": 1.0291,
+      "step": 24
+    },
+    {
+      "epoch": 0.6486486486486487,
+      "eval_loss": 1.6526458263397217,
+      "eval_runtime": 11.2323,
+      "eval_samples_per_second": 11.04,
+      "eval_steps_per_second": 0.712,
+      "step": 24
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "grad_norm": 0.08045388758182526,
+      "learning_rate": 0.00014545454545454546,
+      "loss": 0.9887,
+      "step": 25
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "eval_loss": 1.6451815366744995,
+      "eval_runtime": 11.1905,
+      "eval_samples_per_second": 11.081,
+      "eval_steps_per_second": 0.715,
+      "step": 25
+    },
+    {
+      "epoch": 0.7027027027027027,
+      "grad_norm": 0.07576093822717667,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 1.0044,
+      "step": 26
+    },
+    {
+      "epoch": 0.7027027027027027,
+      "eval_loss": 1.6377238035202026,
+      "eval_runtime": 11.1714,
+      "eval_samples_per_second": 11.1,
+      "eval_steps_per_second": 0.716,
+      "step": 26
+    },
+    {
+      "epoch": 0.7297297297297297,
+      "grad_norm": 0.07311829924583435,
+      "learning_rate": 0.00012121212121212122,
+      "loss": 0.9772,
+      "step": 27
+    },
+    {
+      "epoch": 0.7297297297297297,
+      "eval_loss": 1.6314424276351929,
+      "eval_runtime": 11.1489,
+      "eval_samples_per_second": 11.122,
+      "eval_steps_per_second": 0.718,
+      "step": 27
+    },
+    {
+      "epoch": 0.7567567567567568,
+      "grad_norm": 0.07776332646608353,
+      "learning_rate": 0.00010909090909090909,
+      "loss": 0.9902,
+      "step": 28
+    },
+    {
+      "epoch": 0.7567567567567568,
+      "eval_loss": 1.625641942024231,
+      "eval_runtime": 11.1261,
+      "eval_samples_per_second": 11.145,
+      "eval_steps_per_second": 0.719,
+      "step": 28
+    },
+    {
+      "epoch": 0.7837837837837838,
+      "grad_norm": 0.07536856085062027,
+      "learning_rate": 9.696969696969698e-05,
+      "loss": 0.9902,
+      "step": 29
+    },
+    {
+      "epoch": 0.7837837837837838,
+      "eval_loss": 1.6233930587768555,
+      "eval_runtime": 11.1754,
+      "eval_samples_per_second": 11.096,
+      "eval_steps_per_second": 0.716,
+      "step": 29
+    },
+    {
+      "epoch": 0.8108108108108109,
+      "grad_norm": 0.07941398024559021,
+      "learning_rate": 8.484848484848486e-05,
+      "loss": 0.9784,
+      "step": 30
+    },
+    {
+      "epoch": 0.8108108108108109,
+      "eval_loss": 1.6244161128997803,
+      "eval_runtime": 11.2511,
+      "eval_samples_per_second": 11.021,
+      "eval_steps_per_second": 0.711,
+      "step": 30
+    },
+    {
+      "epoch": 0.8378378378378378,
+      "grad_norm": 0.07617861032485962,
+      "learning_rate": 7.272727272727273e-05,
+      "loss": 1.0064,
+      "step": 31
+    },
+    {
+      "epoch": 0.8378378378378378,
+      "eval_loss": 1.62636399269104,
+      "eval_runtime": 11.1098,
+      "eval_samples_per_second": 11.161,
+      "eval_steps_per_second": 0.72,
+      "step": 31
+    },
+    {
+      "epoch": 0.8648648648648649,
+      "grad_norm": 0.06959453225135803,
+      "learning_rate": 6.060606060606061e-05,
+      "loss": 0.9764,
+      "step": 32
+    },
+    {
+      "epoch": 0.8648648648648649,
+      "eval_loss": 1.6286530494689941,
+      "eval_runtime": 11.2497,
+      "eval_samples_per_second": 11.023,
+      "eval_steps_per_second": 0.711,
+      "step": 32
+    },
+    {
+      "epoch": 0.8918918918918919,
+      "grad_norm": 0.07171300053596497,
+      "learning_rate": 4.848484848484849e-05,
+      "loss": 0.9921,
+      "step": 33
+    },
+    {
+      "epoch": 0.8918918918918919,
+      "eval_loss": 1.630918264389038,
+      "eval_runtime": 11.1794,
+      "eval_samples_per_second": 11.092,
+      "eval_steps_per_second": 0.716,
+      "step": 33
+    },
+    {
+      "epoch": 0.918918918918919,
+      "grad_norm": 0.07644116133451462,
+      "learning_rate": 3.6363636363636364e-05,
+      "loss": 0.9716,
+      "step": 34
+    },
+    {
+      "epoch": 0.918918918918919,
+      "eval_loss": 1.63330078125,
+      "eval_runtime": 11.1352,
+      "eval_samples_per_second": 11.136,
+      "eval_steps_per_second": 0.718,
+      "step": 34
+    },
+    {
+      "epoch": 0.9459459459459459,
+      "grad_norm": 0.07242273539304733,
+      "learning_rate": 2.4242424242424244e-05,
+      "loss": 0.9781,
+      "step": 35
+    },
+    {
+      "epoch": 0.9459459459459459,
+      "eval_loss": 1.634429931640625,
+      "eval_runtime": 11.203,
+      "eval_samples_per_second": 11.069,
+      "eval_steps_per_second": 0.714,
+      "step": 35
+    },
+    {
+      "epoch": 0.972972972972973,
+      "grad_norm": 0.069486603140831,
+      "learning_rate": 1.2121212121212122e-05,
+      "loss": 0.9592,
+      "step": 36
+    },
+    {
+      "epoch": 0.972972972972973,
+      "eval_loss": 1.6349563598632812,
+      "eval_runtime": 11.1077,
+      "eval_samples_per_second": 11.163,
+      "eval_steps_per_second": 0.72,
+      "step": 36
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.07558272778987885,
+      "learning_rate": 0.0,
+      "loss": 0.9368,
+      "step": 37
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.6352812051773071,
+      "eval_runtime": 11.1164,
+      "eval_samples_per_second": 11.155,
+      "eval_steps_per_second": 0.72,
+      "step": 37
+    },
+    {
+      "epoch": 1.0,
+      "step": 37,
+      "total_flos": 1.3641878835560448e+16,
+      "train_loss": 1.5526673584371,
+      "train_runtime": 758.4004,
+      "train_samples_per_second": 1.552,
+      "train_steps_per_second": 0.049
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 37,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3641878835560448e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb3142b18989e7c2d16024033b2170dd8aada190fd9a38b7a18b5251cf944dde
+size 5688