Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Qwen2.5-7B-Instruct-bnb-4bit
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Qwen2.5-7B-Instruct-bnb-4bit",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "down_proj",
+    "q_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 sha256:0ac8ec847aa8edfaab72a95213038a3b2a5de7bf32c11363f3274caaab4c07ff
+size 323014168

added_tokens.json

@@ -0,0 +1,25 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|PAD_TOKEN|>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa3c011edc9c67e821fc549cd0f054287ed29306effe2dbefc7b714079a79665
+size 164464564

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ca3ca8c3c11c29e1764b7a24572028c7d3e1c34fd909d101b6466b69ddbdfa2
+size 1064

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|PAD_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fab42efe8d17406525a9154b728cf9e957629a8ed7ce997770efdd71128c6a1a
+size 11422086

tokenizer_config.json

@@ -0,0 +1,217 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|PAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,213 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9635036496350367,
+  "eval_steps": 500,
+  "global_step": 204,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.291970802919708,
+      "grad_norm": 1.0873714685440063,
+      "learning_rate": 0.0004761904761904762,
+      "log_odds_chosen": -0.5441410541534424,
+      "log_odds_ratio": -1.0390523672103882,
+      "logits/chosen": -0.621608316898346,
+      "logits/rejected": -0.6012401580810547,
+      "logps/chosen": -1.8206005096435547,
+      "logps/rejected": -1.3865854740142822,
+      "loss": 1.4562,
+      "nll_loss": 1.352305293083191,
+      "rewards/accuracies": 0.15000000596046448,
+      "rewards/chosen": -0.18206006288528442,
+      "rewards/margins": -0.04340151697397232,
+      "rewards/rejected": -0.1386585533618927,
+      "step": 20
+    },
+    {
+      "epoch": 0.583941605839416,
+      "grad_norm": 1.0895646810531616,
+      "learning_rate": 0.0004868186180746792,
+      "log_odds_chosen": -0.3829799294471741,
+      "log_odds_ratio": -0.9370166063308716,
+      "logits/chosen": -0.4700603485107422,
+      "logits/rejected": -0.44150036573410034,
+      "logps/chosen": -1.2983076572418213,
+      "logps/rejected": -1.0247515439987183,
+      "loss": 1.0145,
+      "nll_loss": 0.92084801197052,
+      "rewards/accuracies": 0.234375,
+      "rewards/chosen": -0.1298307627439499,
+      "rewards/margins": -0.027355605736374855,
+      "rewards/rejected": -0.10247516632080078,
+      "step": 40
+    },
+    {
+      "epoch": 0.8759124087591241,
+      "grad_norm": 1.0798814296722412,
+      "learning_rate": 0.00044602995164417765,
+      "log_odds_chosen": -0.20668645203113556,
+      "log_odds_ratio": -0.8541840314865112,
+      "logits/chosen": -0.46093836426734924,
+      "logits/rejected": -0.45649147033691406,
+      "logps/chosen": -1.2755881547927856,
+      "logps/rejected": -1.1037111282348633,
+      "loss": 0.9847,
+      "nll_loss": 0.8992462158203125,
+      "rewards/accuracies": 0.34062498807907104,
+      "rewards/chosen": -0.12755881249904633,
+      "rewards/margins": -0.01718769781291485,
+      "rewards/rejected": -0.11037111282348633,
+      "step": 60
+    },
+    {
+      "epoch": 1.1605839416058394,
+      "grad_norm": 1.3134093284606934,
+      "learning_rate": 0.0003823584728045463,
+      "log_odds_chosen": 0.21238426864147186,
+      "log_odds_ratio": -0.6697712540626526,
+      "logits/chosen": -0.6017207503318787,
+      "logits/rejected": -0.6049566268920898,
+      "logps/chosen": -1.103987455368042,
+      "logps/rejected": -1.2036486864089966,
+      "loss": 0.8466,
+      "nll_loss": 0.8013469576835632,
+      "rewards/accuracies": 0.5256410241127014,
+      "rewards/chosen": -0.11039875447750092,
+      "rewards/margins": 0.009966122917830944,
+      "rewards/rejected": -0.12036487460136414,
+      "step": 80
+    },
+    {
+      "epoch": 1.4525547445255476,
+      "grad_norm": 1.4332325458526611,
+      "learning_rate": 0.00030323662998460395,
+      "log_odds_chosen": 0.5833564400672913,
+      "log_odds_ratio": -0.5137361884117126,
+      "logits/chosen": -0.7008029818534851,
+      "logits/rejected": -0.6883307695388794,
+      "logps/chosen": -0.8778481483459473,
+      "logps/rejected": -1.199577808380127,
+      "loss": 0.7714,
+      "nll_loss": 0.7199974656105042,
+      "rewards/accuracies": 0.7718750238418579,
+      "rewards/chosen": -0.08778481185436249,
+      "rewards/margins": 0.03217295557260513,
+      "rewards/rejected": -0.11995778232812881,
+      "step": 100
+    },
+    {
+      "epoch": 1.7445255474452555,
+      "grad_norm": 1.5278706550598145,
+      "learning_rate": 0.00021790041121336223,
+      "log_odds_chosen": 0.4335743486881256,
+      "log_odds_ratio": -0.5648446083068848,
+      "logits/chosen": -0.6764112114906311,
+      "logits/rejected": -0.6685619950294495,
+      "logps/chosen": -0.9028280377388,
+      "logps/rejected": -1.147694706916809,
+      "loss": 0.7602,
+      "nll_loss": 0.7037514448165894,
+      "rewards/accuracies": 0.7093750238418579,
+      "rewards/chosen": -0.09028279781341553,
+      "rewards/margins": 0.02448667585849762,
+      "rewards/rejected": -0.11476948112249374,
+      "step": 120
+    },
+    {
+      "epoch": 2.0291970802919708,
+      "grad_norm": 1.2298489809036255,
+      "learning_rate": 0.00013631121611097364,
+      "log_odds_chosen": 0.8053007125854492,
+      "log_odds_ratio": -0.4435744285583496,
+      "logits/chosen": -0.6849303841590881,
+      "logits/rejected": -0.6694097518920898,
+      "logps/chosen": -0.7989615797996521,
+      "logps/rejected": -1.2587368488311768,
+      "loss": 0.7171,
+      "nll_loss": 0.6910890936851501,
+      "rewards/accuracies": 0.817307710647583,
+      "rewards/chosen": -0.07989615947008133,
+      "rewards/margins": 0.04597752168774605,
+      "rewards/rejected": -0.12587368488311768,
+      "step": 140
+    },
+    {
+      "epoch": 2.321167883211679,
+      "grad_norm": 1.4861160516738892,
+      "learning_rate": 6.799304971075382e-05,
+      "log_odds_chosen": 2.2542662620544434,
+      "log_odds_ratio": -0.14231202006340027,
+      "logits/chosen": -0.8755828738212585,
+      "logits/rejected": -0.8502569198608398,
+      "logps/chosen": -0.46075183153152466,
+      "logps/rejected": -1.7119022607803345,
+      "loss": 0.5128,
+      "nll_loss": 0.4985771179199219,
+      "rewards/accuracies": 0.9906250238418579,
+      "rewards/chosen": -0.046075187623500824,
+      "rewards/margins": 0.1251150369644165,
+      "rewards/rejected": -0.17119023203849792,
+      "step": 160
+    },
+    {
+      "epoch": 2.613138686131387,
+      "grad_norm": 1.5773358345031738,
+      "learning_rate": 2.092077387824884e-05,
+      "log_odds_chosen": 2.26225209236145,
+      "log_odds_ratio": -0.13692842423915863,
+      "logits/chosen": -0.9204779863357544,
+      "logits/rejected": -0.8904932141304016,
+      "logps/chosen": -0.4740973114967346,
+      "logps/rejected": -1.7312190532684326,
+      "loss": 0.5437,
+      "nll_loss": 0.5300474762916565,
+      "rewards/accuracies": 0.996874988079071,
+      "rewards/chosen": -0.04740973562002182,
+      "rewards/margins": 0.12571218609809875,
+      "rewards/rejected": -0.17312191426753998,
+      "step": 180
+    },
+    {
+      "epoch": 2.905109489051095,
+      "grad_norm": 1.3676555156707764,
+      "learning_rate": 5.891920784984184e-07,
+      "log_odds_chosen": 2.3821473121643066,
+      "log_odds_ratio": -0.13435281813144684,
+      "logits/chosen": -0.9195858240127563,
+      "logits/rejected": -0.8968290090560913,
+      "logps/chosen": -0.40853673219680786,
+      "logps/rejected": -1.648188829421997,
+      "loss": 0.5142,
+      "nll_loss": 0.5008108615875244,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": -0.040853675454854965,
+      "rewards/margins": 0.12396518886089325,
+      "rewards/rejected": -0.16481885313987732,
+      "step": 200
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 204,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cb25eef1d2e1445433372042224ef0f0db23def1f0c43edd6927f8601b6d471
+size 5624