Upload folder using huggingface_hub

README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit
+---
+
+# 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": "unsloth/Phi-3-mini-4k-instruct-bnb-4bit",
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "target_modules": [
+    "up_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": true
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e708067c46630c3a931b983c096967337b4bf51d7735e93c5bd11653ebfb621
+size 119597408

added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.7529747673697963,
+    "train_runtime": 21716.0887,
+    "train_samples_per_second": 0.936,
+    "train_steps_per_second": 0.059
+}

checkpoint-100/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit
+---
+
+# 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-100/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Phi-3-mini-4k-instruct-bnb-4bit",
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "target_modules": [
+    "up_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": true
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb18a2d97082f39660e4ffc2e340e9e75756f2e15dc528f8d7fad4bd055bcb97
+size 239135488

checkpoint-100/added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50c53945e1228646b54b3776633f2416b6e55fffdcd9cb19b4c9dd91e9e1feac
+size 120296276

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f9f1f3defe7d022b6fe26129c6021d1cffdc5913e9ce09542ec72062cd96625
+size 14244

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e8199b100d3cf767d811948eda8f2b7bd79e245995fdf17f94b6ef7779f9b4a
+size 1064

checkpoint-100/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": "<|endoftext|>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-100/tokenizer.model

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

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,130 @@
+{
+  "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
+    }
+  },
+  "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": "<|endoftext|>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,349 @@
+{
+  "best_metric": 0.6840614080429077,
+  "best_model_checkpoint": "./output/checkpoints/2024-05-27_09-01-43/checkpoint-100",
+  "epoch": 0.07867820613690008,
+  "eval_steps": 100,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003933910306845004,
+      "grad_norm": 33.997314453125,
+      "learning_rate": 1.25e-06,
+      "logits/chosen": -0.2329253852367401,
+      "logits/rejected": -0.7133080363273621,
+      "logps/chosen": -206.9918670654297,
+      "logps/rejected": -177.71676635742188,
+      "loss": 0.6965,
+      "rewards/accuracies": 0.16249999403953552,
+      "rewards/chosen": -0.0024444584269076586,
+      "rewards/margins": -0.0065179443918168545,
+      "rewards/rejected": 0.004073486663401127,
+      "step": 5
+    },
+    {
+      "epoch": 0.007867820613690008,
+      "grad_norm": 33.46182632446289,
+      "learning_rate": 2.8125e-06,
+      "logits/chosen": -0.39770540595054626,
+      "logits/rejected": -0.7366135120391846,
+      "logps/chosen": -200.96145629882812,
+      "logps/rejected": -177.04241943359375,
+      "loss": 0.6857,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": 0.028690528124570847,
+      "rewards/margins": 0.01567094773054123,
+      "rewards/rejected": 0.013019581325352192,
+      "step": 10
+    },
+    {
+      "epoch": 0.011801730920535013,
+      "grad_norm": 36.08251953125,
+      "learning_rate": 4.3750000000000005e-06,
+      "logits/chosen": -0.35487601161003113,
+      "logits/rejected": -0.6588561534881592,
+      "logps/chosen": -217.158203125,
+      "logps/rejected": -193.87928771972656,
+      "loss": 0.6847,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.1420166790485382,
+      "rewards/margins": 0.021750029176473618,
+      "rewards/rejected": 0.12026665359735489,
+      "step": 15
+    },
+    {
+      "epoch": 0.015735641227380016,
+      "grad_norm": 31.359071731567383,
+      "learning_rate": 5.9375e-06,
+      "logits/chosen": -0.38902169466018677,
+      "logits/rejected": -0.7328646779060364,
+      "logps/chosen": -208.9059600830078,
+      "logps/rejected": -179.52752685546875,
+      "loss": 0.6636,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 0.23876996338367462,
+      "rewards/margins": 0.07814005762338638,
+      "rewards/rejected": 0.16062989830970764,
+      "step": 20
+    },
+    {
+      "epoch": 0.01966955153422502,
+      "grad_norm": 37.41947555541992,
+      "learning_rate": 7.500000000000001e-06,
+      "logits/chosen": -0.24571442604064941,
+      "logits/rejected": -0.7017894983291626,
+      "logps/chosen": -195.68539428710938,
+      "logps/rejected": -178.2770233154297,
+      "loss": 0.6703,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": 0.38804444670677185,
+      "rewards/margins": 0.09177973121404648,
+      "rewards/rejected": 0.2962647080421448,
+      "step": 25
+    },
+    {
+      "epoch": 0.023603461841070025,
+      "grad_norm": 36.168155670166016,
+      "learning_rate": 9.0625e-06,
+      "logits/chosen": -0.3279009461402893,
+      "logits/rejected": -0.62000572681427,
+      "logps/chosen": -207.6711883544922,
+      "logps/rejected": -183.57412719726562,
+      "loss": 0.6945,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.5336718559265137,
+      "rewards/margins": 0.08061937242746353,
+      "rewards/rejected": 0.45305246114730835,
+      "step": 30
+    },
+    {
+      "epoch": 0.02753737214791503,
+      "grad_norm": 33.33737564086914,
+      "learning_rate": 1.0625e-05,
+      "logits/chosen": -0.4809085428714752,
+      "logits/rejected": -0.758043646812439,
+      "logps/chosen": -220.7525634765625,
+      "logps/rejected": -198.58531188964844,
+      "loss": 0.6564,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 0.8875558972358704,
+      "rewards/margins": 0.20188398659229279,
+      "rewards/rejected": 0.6856719255447388,
+      "step": 35
+    },
+    {
+      "epoch": 0.03147128245476003,
+      "grad_norm": 32.628173828125,
+      "learning_rate": 1.2187500000000001e-05,
+      "logits/chosen": -0.34948527812957764,
+      "logits/rejected": -0.7154799699783325,
+      "logps/chosen": -195.3294677734375,
+      "logps/rejected": -178.76821899414062,
+      "loss": 0.6995,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": 0.8487609624862671,
+      "rewards/margins": 0.11841963231563568,
+      "rewards/rejected": 0.7303413152694702,
+      "step": 40
+    },
+    {
+      "epoch": 0.03540519276160504,
+      "grad_norm": 34.517208099365234,
+      "learning_rate": 1.3125e-05,
+      "logits/chosen": -0.6799963712692261,
+      "logits/rejected": -1.0354492664337158,
+      "logps/chosen": -196.0514373779297,
+      "logps/rejected": -165.4368438720703,
+      "loss": 0.6874,
+      "rewards/accuracies": 0.512499988079071,
+      "rewards/chosen": 0.6915052533149719,
+      "rewards/margins": 0.18386030197143555,
+      "rewards/rejected": 0.5076450109481812,
+      "step": 45
+    },
+    {
+      "epoch": 0.03933910306845004,
+      "grad_norm": 39.48639678955078,
+      "learning_rate": 1.4687500000000001e-05,
+      "logits/chosen": -0.22616450488567352,
+      "logits/rejected": -0.3378121256828308,
+      "logps/chosen": -210.38534545898438,
+      "logps/rejected": -205.64596557617188,
+      "loss": 0.6612,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 0.6935254335403442,
+      "rewards/margins": 0.17534935474395752,
+      "rewards/rejected": 0.5181760191917419,
+      "step": 50
+    },
+    {
+      "epoch": 0.043273013375295044,
+      "grad_norm": 54.90278244018555,
+      "learning_rate": 1.6250000000000002e-05,
+      "logits/chosen": -0.5758259892463684,
+      "logits/rejected": -0.7866605520248413,
+      "logps/chosen": -194.25332641601562,
+      "logps/rejected": -179.38743591308594,
+      "loss": 0.7132,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.7601491212844849,
+      "rewards/margins": 0.13087329268455505,
+      "rewards/rejected": 0.629275918006897,
+      "step": 55
+    },
+    {
+      "epoch": 0.04720692368214005,
+      "grad_norm": 31.500804901123047,
+      "learning_rate": 1.7500000000000002e-05,
+      "logits/chosen": -0.3127598762512207,
+      "logits/rejected": -0.7857316136360168,
+      "logps/chosen": -214.54507446289062,
+      "logps/rejected": -167.3846435546875,
+      "loss": 0.659,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": 0.8511220216751099,
+      "rewards/margins": 0.3019554316997528,
+      "rewards/rejected": 0.5491665601730347,
+      "step": 60
+    },
+    {
+      "epoch": 0.05114083398898505,
+      "grad_norm": 39.18369674682617,
+      "learning_rate": 1.9062500000000003e-05,
+      "logits/chosen": -0.4257170557975769,
+      "logits/rejected": -0.7206593751907349,
+      "logps/chosen": -212.1534881591797,
+      "logps/rejected": -198.5198516845703,
+      "loss": 0.6603,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": 1.0609362125396729,
+      "rewards/margins": 0.4154728055000305,
+      "rewards/rejected": 0.6454635858535767,
+      "step": 65
+    },
+    {
+      "epoch": 0.05507474429583006,
+      "grad_norm": 23.921350479125977,
+      "learning_rate": 2.0625000000000003e-05,
+      "logits/chosen": -0.4161883294582367,
+      "logits/rejected": -0.7778038382530212,
+      "logps/chosen": -211.8742218017578,
+      "logps/rejected": -173.7216033935547,
+      "loss": 0.6306,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 1.1546392440795898,
+      "rewards/margins": 0.4130212366580963,
+      "rewards/rejected": 0.7416179180145264,
+      "step": 70
+    },
+    {
+      "epoch": 0.059008654602675056,
+      "grad_norm": 33.804962158203125,
+      "learning_rate": 2.21875e-05,
+      "logits/chosen": -0.11207835376262665,
+      "logits/rejected": -0.5466287136077881,
+      "logps/chosen": -206.02218627929688,
+      "logps/rejected": -185.80941772460938,
+      "loss": 0.719,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": 1.1464534997940063,
+      "rewards/margins": 0.2297494113445282,
+      "rewards/rejected": 0.9167040586471558,
+      "step": 75
+    },
+    {
+      "epoch": 0.06294256490952006,
+      "grad_norm": 42.39493942260742,
+      "learning_rate": 2.375e-05,
+      "logits/chosen": -0.2344416081905365,
+      "logits/rejected": -0.49077630043029785,
+      "logps/chosen": -209.4600067138672,
+      "logps/rejected": -198.47911071777344,
+      "loss": 0.663,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": 0.7387064099311829,
+      "rewards/margins": 0.3134633004665375,
+      "rewards/rejected": 0.4252430498600006,
+      "step": 80
+    },
+    {
+      "epoch": 0.06687647521636507,
+      "grad_norm": 35.38875961303711,
+      "learning_rate": 2.5312500000000002e-05,
+      "logits/chosen": -0.26731210947036743,
+      "logits/rejected": -0.7659153342247009,
+      "logps/chosen": -206.7689666748047,
+      "logps/rejected": -178.71986389160156,
+      "loss": 0.7082,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": 0.22556963562965393,
+      "rewards/margins": 0.251675546169281,
+      "rewards/rejected": -0.026105916127562523,
+      "step": 85
+    },
+    {
+      "epoch": 0.07081038552321008,
+      "grad_norm": 30.606552124023438,
+      "learning_rate": 2.6875000000000003e-05,
+      "logits/chosen": -0.34513598680496216,
+      "logits/rejected": -0.5674473643302917,
+      "logps/chosen": -208.49002075195312,
+      "logps/rejected": -184.6549072265625,
+      "loss": 0.7702,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": 0.2557719945907593,
+      "rewards/margins": 0.22060665488243103,
+      "rewards/rejected": 0.03516533225774765,
+      "step": 90
+    },
+    {
+      "epoch": 0.07474429583005507,
+      "grad_norm": 25.326486587524414,
+      "learning_rate": 2.8437500000000003e-05,
+      "logits/chosen": -0.21977896988391876,
+      "logits/rejected": -0.6439090371131897,
+      "logps/chosen": -201.21401977539062,
+      "logps/rejected": -183.35049438476562,
+      "loss": 0.713,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": 0.6074048280715942,
+      "rewards/margins": 0.23941688239574432,
+      "rewards/rejected": 0.3679879307746887,
+      "step": 95
+    },
+    {
+      "epoch": 0.07867820613690008,
+      "grad_norm": 34.922325134277344,
+      "learning_rate": 3.0000000000000004e-05,
+      "logits/chosen": -0.4304371774196625,
+      "logits/rejected": -0.7793359756469727,
+      "logps/chosen": -207.411376953125,
+      "logps/rejected": -178.08729553222656,
+      "loss": 0.7514,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": 0.6943355798721313,
+      "rewards/margins": 0.1873859167098999,
+      "rewards/rejected": 0.5069497227668762,
+      "step": 100
+    },
+    {
+      "epoch": 0.07867820613690008,
+      "eval_logits/chosen": 1.2959624528884888,
+      "eval_logits/rejected": 1.0611025094985962,
+      "eval_logps/chosen": -205.19613647460938,
+      "eval_logps/rejected": -178.5214385986328,
+      "eval_loss": 0.6840614080429077,
+      "eval_rewards/accuracies": 0.628125011920929,
+      "eval_rewards/chosen": 1.1096659898757935,
+      "eval_rewards/margins": 0.36510738730430603,
+      "eval_rewards/rejected": 0.7445584535598755,
+      "eval_runtime": 248.7873,
+      "eval_samples_per_second": 2.572,
+      "eval_steps_per_second": 0.161,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1271,
+  "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": 0.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7b2d0ede2c334e98351634546def1b2aab77cc0804c3984b2bbca8c3cd81ec6
+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": "<|endoftext|>",
+  "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 +1,130 @@
+{
+  "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
+    }
+  },
+  "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": "<|endoftext|>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.7529747673697963,
+    "train_runtime": 21716.0887,
+    "train_samples_per_second": 0.936,
+    "train_steps_per_second": 0.059
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7b2d0ede2c334e98351634546def1b2aab77cc0804c3984b2bbca8c3cd81ec6
+size 5688