Upload 16 files

README.md

@@ -1,3 +1,202 @@
----
-license: mit
----
+---
+library_name: peft
+base_model: Qwen2/Qwen2-7B-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 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/root/LLM_Data_Engineer/LLaMA-Factory/models/Qwen2-7B-Instruct-dpo-06212336",
+  "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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:160f730207986ebe0d3c7c5d2486cc8ba918e41b6a093734432783c97902ea25
+size 80792096

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.935251798561151,
+    "total_flos": 8.94448793688146e+16,
+    "train_loss": 0.4110284693100873,
+    "train_runtime": 896.119,
+    "train_samples_per_second": 3.713,
+    "train_steps_per_second": 0.114
+}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.935251798561151,
+    "total_flos": 8.94448793688146e+16,
+    "train_loss": 0.4110284693100873,
+    "train_runtime": 896.119,
+    "train_samples_per_second": 3.713,
+    "train_steps_per_second": 0.114
+}

trainer_log.jsonl

@@ -0,0 +1,52 @@
+{"current_steps": 2, "total_steps": 102, "loss": 0.6931, "accuracy": 0.0, "learning_rate": 9.090909090909091e-07, "epoch": 0.05755395683453238, "percentage": 1.96, "elapsed_time": "0:00:18", "remaining_time": "0:15:17", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 4, "total_steps": 102, "loss": 0.7202, "accuracy": 0.421875, "learning_rate": 1.8181818181818183e-06, "epoch": 0.11510791366906475, "percentage": 3.92, "elapsed_time": "0:00:36", "remaining_time": "0:15:04", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 6, "total_steps": 102, "loss": 0.6931, "accuracy": 0.578125, "learning_rate": 2.7272727272727272e-06, "epoch": 0.17266187050359713, "percentage": 5.88, "elapsed_time": "0:00:52", "remaining_time": "0:14:01", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 8, "total_steps": 102, "loss": 0.7227, "accuracy": 0.453125, "learning_rate": 3.6363636363636366e-06, "epoch": 0.2302158273381295, "percentage": 7.84, "elapsed_time": "0:01:08", "remaining_time": "0:13:21", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 10, "total_steps": 102, "loss": 0.7281, "accuracy": 0.46875, "learning_rate": 4.5454545454545455e-06, "epoch": 0.28776978417266186, "percentage": 9.8, "elapsed_time": "0:01:24", "remaining_time": "0:12:58", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 12, "total_steps": 102, "loss": 0.6629, "accuracy": 0.65625, "learning_rate": 4.998510351377676e-06, "epoch": 0.34532374100719426, "percentage": 11.76, "elapsed_time": "0:01:41", "remaining_time": "0:12:40", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 14, "total_steps": 102, "loss": 0.6747, "accuracy": 0.578125, "learning_rate": 4.986603811737982e-06, "epoch": 0.4028776978417266, "percentage": 13.73, "elapsed_time": "0:01:57", "remaining_time": "0:12:18", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 16, "total_steps": 102, "loss": 0.6627, "accuracy": 0.65625, "learning_rate": 4.9628474725421845e-06, "epoch": 0.460431654676259, "percentage": 15.69, "elapsed_time": "0:02:16", "remaining_time": "0:12:15", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 18, "total_steps": 102, "loss": 0.6371, "accuracy": 0.609375, "learning_rate": 4.927354543565131e-06, "epoch": 0.5179856115107914, "percentage": 17.65, "elapsed_time": "0:02:33", "remaining_time": "0:11:55", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 20, "total_steps": 102, "loss": 0.6767, "accuracy": 0.5, "learning_rate": 4.880294164776785e-06, "epoch": 0.5755395683453237, "percentage": 19.61, "elapsed_time": "0:02:48", "remaining_time": "0:11:31", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 22, "total_steps": 102, "loss": 0.6326, "accuracy": 0.59375, "learning_rate": 4.821890600313256e-06, "epoch": 0.6330935251798561, "percentage": 21.57, "elapsed_time": "0:03:05", "remaining_time": "0:11:16", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 24, "total_steps": 102, "loss": 0.6138, "accuracy": 0.6875, "learning_rate": 4.752422169756048e-06, "epoch": 0.6906474820143885, "percentage": 23.53, "elapsed_time": "0:03:26", "remaining_time": "0:11:09", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 26, "total_steps": 102, "loss": 0.6185, "accuracy": 0.65625, "learning_rate": 4.672219921812517e-06, "epoch": 0.7482014388489209, "percentage": 25.49, "elapsed_time": "0:03:43", "remaining_time": "0:10:52", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 28, "total_steps": 102, "loss": 0.6222, "accuracy": 0.640625, "learning_rate": 4.581666056718016e-06, "epoch": 0.8057553956834532, "percentage": 27.45, "elapsed_time": "0:04:02", "remaining_time": "0:10:40", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 30, "total_steps": 102, "loss": 0.4954, "accuracy": 0.875, "learning_rate": 4.481192104877727e-06, "epoch": 0.8633093525179856, "percentage": 29.41, "elapsed_time": "0:04:20", "remaining_time": "0:10:24", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 32, "total_steps": 102, "loss": 0.4999, "accuracy": 0.84375, "learning_rate": 4.3712768704277535e-06, "epoch": 0.920863309352518, "percentage": 31.37, "elapsed_time": "0:04:40", "remaining_time": "0:10:14", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 34, "total_steps": 102, "loss": 0.4695, "accuracy": 0.828125, "learning_rate": 4.252444149515374e-06, "epoch": 0.9784172661870504, "percentage": 33.33, "elapsed_time": "0:04:57", "remaining_time": "0:09:55", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 36, "total_steps": 102, "loss": 0.4663, "accuracy": 0.84375, "learning_rate": 4.125260234171861e-06, "epoch": 1.0359712230215827, "percentage": 35.29, "elapsed_time": "0:05:16", "remaining_time": "0:09:41", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 38, "total_steps": 102, "loss": 0.4458, "accuracy": 0.78125, "learning_rate": 3.990331213673064e-06, "epoch": 1.0935251798561152, "percentage": 37.25, "elapsed_time": "0:05:34", "remaining_time": "0:09:24", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 40, "total_steps": 102, "loss": 0.3395, "accuracy": 0.921875, "learning_rate": 3.848300086247998e-06, "epoch": 1.1510791366906474, "percentage": 39.22, "elapsed_time": "0:05:52", "remaining_time": "0:09:06", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 42, "total_steps": 102, "loss": 0.3934, "accuracy": 0.890625, "learning_rate": 3.6998436948994664e-06, "epoch": 1.20863309352518, "percentage": 41.18, "elapsed_time": "0:06:08", "remaining_time": "0:08:46", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 44, "total_steps": 102, "loss": 0.4418, "accuracy": 0.796875, "learning_rate": 3.545669501938913e-06, "epoch": 1.2661870503597124, "percentage": 43.14, "elapsed_time": "0:06:26", "remaining_time": "0:08:28", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 46, "total_steps": 102, "loss": 0.35, "accuracy": 0.859375, "learning_rate": 3.386512217606339e-06, "epoch": 1.3237410071942446, "percentage": 45.1, "elapsed_time": "0:06:41", "remaining_time": "0:08:08", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 48, "total_steps": 102, "loss": 0.3598, "accuracy": 0.875, "learning_rate": 3.2231302988414198e-06, "epoch": 1.381294964028777, "percentage": 47.06, "elapsed_time": "0:07:00", "remaining_time": "0:07:52", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 50, "total_steps": 102, "loss": 0.3145, "accuracy": 0.90625, "learning_rate": 3.056302334890786e-06, "epoch": 1.4388489208633093, "percentage": 49.02, "elapsed_time": "0:07:18", "remaining_time": "0:07:35", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 52, "total_steps": 102, "loss": 0.3824, "accuracy": 0.828125, "learning_rate": 2.886823336975703e-06, "epoch": 1.4964028776978417, "percentage": 50.98, "elapsed_time": "0:07:37", "remaining_time": "0:07:19", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 54, "total_steps": 102, "loss": 0.3495, "accuracy": 0.890625, "learning_rate": 2.7155009497015487e-06, "epoch": 1.5539568345323742, "percentage": 52.94, "elapsed_time": "0:07:53", "remaining_time": "0:07:00", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 56, "total_steps": 102, "loss": 0.3193, "accuracy": 0.84375, "learning_rate": 2.5431516022634718e-06, "epoch": 1.6115107913669064, "percentage": 54.9, "elapsed_time": "0:08:09", "remaining_time": "0:06:42", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 58, "total_steps": 102, "loss": 0.3311, "accuracy": 0.8125, "learning_rate": 2.3705966177894763e-06, "epoch": 1.6690647482014387, "percentage": 56.86, "elapsed_time": "0:08:28", "remaining_time": "0:06:26", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 60, "total_steps": 102, "loss": 0.2872, "accuracy": 0.90625, "learning_rate": 2.1986582993616926e-06, "epoch": 1.7266187050359711, "percentage": 58.82, "elapsed_time": "0:08:45", "remaining_time": "0:06:08", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 62, "total_steps": 102, "loss": 0.3258, "accuracy": 0.90625, "learning_rate": 2.0281560113677085e-06, "epoch": 1.7841726618705036, "percentage": 60.78, "elapsed_time": "0:09:05", "remaining_time": "0:05:52", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 64, "total_steps": 102, "loss": 0.2994, "accuracy": 0.921875, "learning_rate": 1.8599022748561324e-06, "epoch": 1.841726618705036, "percentage": 62.75, "elapsed_time": "0:09:22", "remaining_time": "0:05:33", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 66, "total_steps": 102, "loss": 0.2577, "accuracy": 0.921875, "learning_rate": 1.694698895503774e-06, "epoch": 1.8992805755395683, "percentage": 64.71, "elapsed_time": "0:09:39", "remaining_time": "0:05:16", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 68, "total_steps": 102, "loss": 0.2053, "accuracy": 0.96875, "learning_rate": 1.5333331426464532e-06, "epoch": 1.9568345323741008, "percentage": 66.67, "elapsed_time": "0:10:00", "remaining_time": "0:05:00", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 70, "total_steps": 102, "loss": 0.3402, "accuracy": 0.84375, "learning_rate": 1.3765739975820964e-06, "epoch": 2.014388489208633, "percentage": 68.63, "elapsed_time": "0:10:17", "remaining_time": "0:04:42", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 72, "total_steps": 102, "loss": 0.3119, "accuracy": 0.890625, "learning_rate": 1.225168489024661e-06, "epoch": 2.0719424460431655, "percentage": 70.59, "elapsed_time": "0:10:33", "remaining_time": "0:04:24", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 74, "total_steps": 102, "loss": 0.2232, "accuracy": 0.9375, "learning_rate": 1.079838133172111e-06, "epoch": 2.129496402877698, "percentage": 72.55, "elapsed_time": "0:10:51", "remaining_time": "0:04:06", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 76, "total_steps": 102, "loss": 0.2777, "accuracy": 0.875, "learning_rate": 9.412754953531664e-07, "epoch": 2.1870503597122304, "percentage": 74.51, "elapsed_time": "0:11:06", "remaining_time": "0:03:48", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 78, "total_steps": 102, "loss": 0.2124, "accuracy": 0.953125, "learning_rate": 8.101408896381141e-07, "epoch": 2.2446043165467624, "percentage": 76.47, "elapsed_time": "0:11:25", "remaining_time": "0:03:30", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 80, "total_steps": 102, "loss": 0.1949, "accuracy": 0.96875, "learning_rate": 6.870592321415595e-07, "epoch": 2.302158273381295, "percentage": 78.43, "elapsed_time": "0:11:44", "remaining_time": "0:03:13", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 82, "total_steps": 102, "loss": 0.2402, "accuracy": 0.90625, "learning_rate": 5.72617063012551e-07, "epoch": 2.3597122302158273, "percentage": 80.39, "elapsed_time": "0:12:01", "remaining_time": "0:02:56", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 84, "total_steps": 102, "loss": 0.2859, "accuracy": 0.875, "learning_rate": 4.673597513036684e-07, "epoch": 2.41726618705036, "percentage": 82.35, "elapsed_time": "0:12:23", "remaining_time": "0:02:39", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 86, "total_steps": 102, "loss": 0.2294, "accuracy": 0.953125, "learning_rate": 3.717888960391222e-07, "epoch": 2.4748201438848922, "percentage": 84.31, "elapsed_time": "0:12:41", "remaining_time": "0:02:21", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 88, "total_steps": 102, "loss": 0.2516, "accuracy": 0.84375, "learning_rate": 2.8635993586697555e-07, "epoch": 2.5323741007194247, "percentage": 86.27, "elapsed_time": "0:12:55", "remaining_time": "0:02:03", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 90, "total_steps": 102, "loss": 0.2254, "accuracy": 0.953125, "learning_rate": 2.1147997868658427e-07, "epoch": 2.5899280575539567, "percentage": 88.24, "elapsed_time": "0:13:09", "remaining_time": "0:01:45", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 92, "total_steps": 102, "loss": 0.3215, "accuracy": 0.84375, "learning_rate": 1.4750586159405917e-07, "epoch": 2.647482014388489, "percentage": 90.2, "elapsed_time": "0:13:26", "remaining_time": "0:01:27", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 94, "total_steps": 102, "loss": 0.2675, "accuracy": 0.890625, "learning_rate": 9.474245039099883e-08, "epoch": 2.7050359712230216, "percentage": 92.16, "elapsed_time": "0:13:47", "remaining_time": "0:01:10", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 96, "total_steps": 102, "loss": 0.2482, "accuracy": 0.875, "learning_rate": 5.344118676011173e-08, "epoch": 2.762589928057554, "percentage": 94.12, "elapsed_time": "0:14:06", "remaining_time": "0:00:52", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 98, "total_steps": 102, "loss": 0.2811, "accuracy": 0.890625, "learning_rate": 2.3798890031092037e-08, "epoch": 2.8201438848920866, "percentage": 96.08, "elapsed_time": "0:14:23", "remaining_time": "0:00:35", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 100, "total_steps": 102, "loss": 0.169, "accuracy": 0.96875, "learning_rate": 5.9568192468811844e-09, "epoch": 2.8776978417266186, "percentage": 98.04, "elapsed_time": "0:14:40", "remaining_time": "0:00:17", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 102, "total_steps": 102, "loss": 0.19, "accuracy": 0.953125, "learning_rate": 0.0, "epoch": 2.935251798561151, "percentage": 100.0, "elapsed_time": "0:14:56", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 102, "total_steps": 102, "epoch": 2.935251798561151, "percentage": 100.0, "elapsed_time": "0:14:56", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}

trainer_state.json

@@ -0,0 +1,807 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.935251798561151,
+  "eval_steps": 500,
+  "global_step": 102,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05755395683453238,
+      "grad_norm": 12.61336898803711,
+      "learning_rate": 9.090909090909091e-07,
+      "logits/chosen": -1.8628841638565063,
+      "logits/rejected": -2.055020332336426,
+      "logps/chosen": -171.465087890625,
+      "logps/rejected": -237.2239532470703,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 2
+    },
+    {
+      "epoch": 0.11510791366906475,
+      "grad_norm": 13.303223609924316,
+      "learning_rate": 1.8181818181818183e-06,
+      "logits/chosen": -1.77495539188385,
+      "logits/rejected": -2.0203144550323486,
+      "logps/chosen": -174.85792541503906,
+      "logps/rejected": -223.60960388183594,
+      "loss": 0.7202,
+      "rewards/accuracies": 0.421875,
+      "rewards/chosen": 0.027576472610235214,
+      "rewards/margins": -0.017962537705898285,
+      "rewards/rejected": 0.0455390103161335,
+      "step": 4
+    },
+    {
+      "epoch": 0.17266187050359713,
+      "grad_norm": 13.142106056213379,
+      "learning_rate": 2.7272727272727272e-06,
+      "logits/chosen": -1.6846373081207275,
+      "logits/rejected": -1.8930776119232178,
+      "logps/chosen": -148.6173553466797,
+      "logps/rejected": -215.2635498046875,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": 0.01209343783557415,
+      "rewards/margins": 0.026968184858560562,
+      "rewards/rejected": -0.014874744229018688,
+      "step": 6
+    },
+    {
+      "epoch": 0.2302158273381295,
+      "grad_norm": 14.098532676696777,
+      "learning_rate": 3.6363636363636366e-06,
+      "logits/chosen": -1.664399266242981,
+      "logits/rejected": -1.8190324306488037,
+      "logps/chosen": -162.35986328125,
+      "logps/rejected": -209.52432250976562,
+      "loss": 0.7227,
+      "rewards/accuracies": 0.453125,
+      "rewards/chosen": -0.0490722618997097,
+      "rewards/margins": -0.019629262387752533,
+      "rewards/rejected": -0.029443001374602318,
+      "step": 8
+    },
+    {
+      "epoch": 0.28776978417266186,
+      "grad_norm": 17.35445213317871,
+      "learning_rate": 4.5454545454545455e-06,
+      "logits/chosen": -1.794135332107544,
+      "logits/rejected": -2.1967906951904297,
+      "logps/chosen": -175.1381378173828,
+      "logps/rejected": -199.35000610351562,
+      "loss": 0.7281,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.0006946558132767677,
+      "rewards/margins": -0.02462945692241192,
+      "rewards/rejected": 0.023934796452522278,
+      "step": 10
+    },
+    {
+      "epoch": 0.34532374100719426,
+      "grad_norm": 15.025739669799805,
+      "learning_rate": 4.998510351377676e-06,
+      "logits/chosen": -1.6492798328399658,
+      "logits/rejected": -1.9510689973831177,
+      "logps/chosen": -168.0927276611328,
+      "logps/rejected": -215.88006591796875,
+      "loss": 0.6629,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": 0.04117076098918915,
+      "rewards/margins": 0.11135232448577881,
+      "rewards/rejected": -0.07018155604600906,
+      "step": 12
+    },
+    {
+      "epoch": 0.4028776978417266,
+      "grad_norm": 13.217601776123047,
+      "learning_rate": 4.986603811737982e-06,
+      "logits/chosen": -1.6234389543533325,
+      "logits/rejected": -1.7974214553833008,
+      "logps/chosen": -181.07872009277344,
+      "logps/rejected": -224.6402130126953,
+      "loss": 0.6747,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": 0.05587499216198921,
+      "rewards/margins": 0.07424326241016388,
+      "rewards/rejected": -0.018368273973464966,
+      "step": 14
+    },
+    {
+      "epoch": 0.460431654676259,
+      "grad_norm": 13.030729293823242,
+      "learning_rate": 4.9628474725421845e-06,
+      "logits/chosen": -1.7801084518432617,
+      "logits/rejected": -2.158487319946289,
+      "logps/chosen": -183.85427856445312,
+      "logps/rejected": -220.0618133544922,
+      "loss": 0.6627,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": -0.03484422340989113,
+      "rewards/margins": 0.11216042935848236,
+      "rewards/rejected": -0.14700466394424438,
+      "step": 16
+    },
+    {
+      "epoch": 0.5179856115107914,
+      "grad_norm": 10.820516586303711,
+      "learning_rate": 4.927354543565131e-06,
+      "logits/chosen": -1.6137356758117676,
+      "logits/rejected": -1.8953951597213745,
+      "logps/chosen": -162.70101928710938,
+      "logps/rejected": -197.60382080078125,
+      "loss": 0.6371,
+      "rewards/accuracies": 0.609375,
+      "rewards/chosen": 0.11542239040136337,
+      "rewards/margins": 0.1481863409280777,
+      "rewards/rejected": -0.03276393562555313,
+      "step": 18
+    },
+    {
+      "epoch": 0.5755395683453237,
+      "grad_norm": 13.496746063232422,
+      "learning_rate": 4.880294164776785e-06,
+      "logits/chosen": -1.5672615766525269,
+      "logits/rejected": -1.799597978591919,
+      "logps/chosen": -166.3477020263672,
+      "logps/rejected": -206.35385131835938,
+      "loss": 0.6767,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.03490065410733223,
+      "rewards/margins": 0.07657002657651901,
+      "rewards/rejected": -0.041669368743896484,
+      "step": 20
+    },
+    {
+      "epoch": 0.6330935251798561,
+      "grad_norm": 13.735678672790527,
+      "learning_rate": 4.821890600313256e-06,
+      "logits/chosen": -1.8001123666763306,
+      "logits/rejected": -2.105792284011841,
+      "logps/chosen": -183.22373962402344,
+      "logps/rejected": -225.92710876464844,
+      "loss": 0.6326,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": 0.05107605457305908,
+      "rewards/margins": 0.1594647318124771,
+      "rewards/rejected": -0.10838868468999863,
+      "step": 22
+    },
+    {
+      "epoch": 0.6906474820143885,
+      "grad_norm": 11.953166961669922,
+      "learning_rate": 4.752422169756048e-06,
+      "logits/chosen": -1.9147757291793823,
+      "logits/rejected": -2.2474513053894043,
+      "logps/chosen": -181.51597595214844,
+      "logps/rejected": -195.81033325195312,
+      "loss": 0.6138,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 0.13331472873687744,
+      "rewards/margins": 0.21828582882881165,
+      "rewards/rejected": -0.0849711000919342,
+      "step": 24
+    },
+    {
+      "epoch": 0.7482014388489209,
+      "grad_norm": 10.812925338745117,
+      "learning_rate": 4.672219921812517e-06,
+      "logits/chosen": -2.0098390579223633,
+      "logits/rejected": -2.057783365249634,
+      "logps/chosen": -166.85260009765625,
+      "logps/rejected": -219.13427734375,
+      "loss": 0.6185,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": 0.12382392585277557,
+      "rewards/margins": 0.23543882369995117,
+      "rewards/rejected": -0.11161486804485321,
+      "step": 26
+    },
+    {
+      "epoch": 0.8057553956834532,
+      "grad_norm": 11.20254135131836,
+      "learning_rate": 4.581666056718016e-06,
+      "logits/chosen": -1.809260606765747,
+      "logits/rejected": -1.9223175048828125,
+      "logps/chosen": -194.20700073242188,
+      "logps/rejected": -236.03829956054688,
+      "loss": 0.6222,
+      "rewards/accuracies": 0.640625,
+      "rewards/chosen": 0.13630633056163788,
+      "rewards/margins": 0.2403251975774765,
+      "rewards/rejected": -0.10401885211467743,
+      "step": 28
+    },
+    {
+      "epoch": 0.8633093525179856,
+      "grad_norm": 11.394420623779297,
+      "learning_rate": 4.481192104877727e-06,
+      "logits/chosen": -1.6475874185562134,
+      "logits/rejected": -2.0424444675445557,
+      "logps/chosen": -177.6649169921875,
+      "logps/rejected": -217.6787872314453,
+      "loss": 0.4954,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": 0.23437190055847168,
+      "rewards/margins": 0.5494118928909302,
+      "rewards/rejected": -0.3150399923324585,
+      "step": 30
+    },
+    {
+      "epoch": 0.920863309352518,
+      "grad_norm": 13.055252075195312,
+      "learning_rate": 4.3712768704277535e-06,
+      "logits/chosen": -1.9410960674285889,
+      "logits/rejected": -2.216390371322632,
+      "logps/chosen": -178.47877502441406,
+      "logps/rejected": -221.4510498046875,
+      "loss": 0.4999,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": 0.19329071044921875,
+      "rewards/margins": 0.5714992880821228,
+      "rewards/rejected": -0.37820857763290405,
+      "step": 32
+    },
+    {
+      "epoch": 0.9784172661870504,
+      "grad_norm": 8.89469051361084,
+      "learning_rate": 4.252444149515374e-06,
+      "logits/chosen": -1.7217860221862793,
+      "logits/rejected": -1.8292845487594604,
+      "logps/chosen": -166.56455993652344,
+      "logps/rejected": -224.22413635253906,
+      "loss": 0.4695,
+      "rewards/accuracies": 0.828125,
+      "rewards/chosen": 0.21696212887763977,
+      "rewards/margins": 0.6354631781578064,
+      "rewards/rejected": -0.41850101947784424,
+      "step": 34
+    },
+    {
+      "epoch": 1.0359712230215827,
+      "grad_norm": 9.03423023223877,
+      "learning_rate": 4.125260234171861e-06,
+      "logits/chosen": -1.7452164888381958,
+      "logits/rejected": -1.9169570207595825,
+      "logps/chosen": -176.8074951171875,
+      "logps/rejected": -240.5430145263672,
+      "loss": 0.4663,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": 0.1004013791680336,
+      "rewards/margins": 0.6946967840194702,
+      "rewards/rejected": -0.5942954421043396,
+      "step": 36
+    },
+    {
+      "epoch": 1.0935251798561152,
+      "grad_norm": 8.077057838439941,
+      "learning_rate": 3.990331213673064e-06,
+      "logits/chosen": -1.7885024547576904,
+      "logits/rejected": -2.0291481018066406,
+      "logps/chosen": -182.01747131347656,
+      "logps/rejected": -220.93408203125,
+      "loss": 0.4458,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": 0.14817766845226288,
+      "rewards/margins": 0.8059278726577759,
+      "rewards/rejected": -0.6577501893043518,
+      "step": 38
+    },
+    {
+      "epoch": 1.1510791366906474,
+      "grad_norm": 7.7763776779174805,
+      "learning_rate": 3.848300086247998e-06,
+      "logits/chosen": -1.771430492401123,
+      "logits/rejected": -1.8969953060150146,
+      "logps/chosen": -169.00811767578125,
+      "logps/rejected": -216.32608032226562,
+      "loss": 0.3395,
+      "rewards/accuracies": 0.921875,
+      "rewards/chosen": 0.42292630672454834,
+      "rewards/margins": 1.200685739517212,
+      "rewards/rejected": -0.7777595520019531,
+      "step": 40
+    },
+    {
+      "epoch": 1.20863309352518,
+      "grad_norm": 9.472132682800293,
+      "learning_rate": 3.6998436948994664e-06,
+      "logits/chosen": -1.7478959560394287,
+      "logits/rejected": -1.946545124053955,
+      "logps/chosen": -154.75123596191406,
+      "logps/rejected": -207.8878631591797,
+      "loss": 0.3934,
+      "rewards/accuracies": 0.890625,
+      "rewards/chosen": 0.17304691672325134,
+      "rewards/margins": 0.9744219779968262,
+      "rewards/rejected": -0.8013750314712524,
+      "step": 42
+    },
+    {
+      "epoch": 1.2661870503597124,
+      "grad_norm": 8.541696548461914,
+      "learning_rate": 3.545669501938913e-06,
+      "logits/chosen": -1.6284449100494385,
+      "logits/rejected": -1.819665551185608,
+      "logps/chosen": -177.72425842285156,
+      "logps/rejected": -221.01028442382812,
+      "loss": 0.4418,
+      "rewards/accuracies": 0.796875,
+      "rewards/chosen": 0.3692091405391693,
+      "rewards/margins": 0.9766747951507568,
+      "rewards/rejected": -0.6074656248092651,
+      "step": 44
+    },
+    {
+      "epoch": 1.3237410071942446,
+      "grad_norm": 6.5243048667907715,
+      "learning_rate": 3.386512217606339e-06,
+      "logits/chosen": -1.5771324634552002,
+      "logits/rejected": -1.7775179147720337,
+      "logps/chosen": -170.24432373046875,
+      "logps/rejected": -210.37942504882812,
+      "loss": 0.35,
+      "rewards/accuracies": 0.859375,
+      "rewards/chosen": 0.14126329123973846,
+      "rewards/margins": 1.228642225265503,
+      "rewards/rejected": -1.087378978729248,
+      "step": 46
+    },
+    {
+      "epoch": 1.381294964028777,
+      "grad_norm": 7.318809509277344,
+      "learning_rate": 3.2231302988414198e-06,
+      "logits/chosen": -1.797095775604248,
+      "logits/rejected": -2.164658784866333,
+      "logps/chosen": -172.25515747070312,
+      "logps/rejected": -195.97921752929688,
+      "loss": 0.3598,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": 0.2658257484436035,
+      "rewards/margins": 1.1805520057678223,
+      "rewards/rejected": -0.914726197719574,
+      "step": 48
+    },
+    {
+      "epoch": 1.4388489208633093,
+      "grad_norm": 7.181938171386719,
+      "learning_rate": 3.056302334890786e-06,
+      "logits/chosen": -1.7573457956314087,
+      "logits/rejected": -2.1520862579345703,
+      "logps/chosen": -170.33551025390625,
+      "logps/rejected": -202.55755615234375,
+      "loss": 0.3145,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": 0.3353237211704254,
+      "rewards/margins": 1.4618067741394043,
+      "rewards/rejected": -1.1264830827713013,
+      "step": 50
+    },
+    {
+      "epoch": 1.4964028776978417,
+      "grad_norm": 10.611798286437988,
+      "learning_rate": 2.886823336975703e-06,
+      "logits/chosen": -1.9649319648742676,
+      "logits/rejected": -2.0540201663970947,
+      "logps/chosen": -172.51666259765625,
+      "logps/rejected": -220.8997039794922,
+      "loss": 0.3824,
+      "rewards/accuracies": 0.828125,
+      "rewards/chosen": 0.0204707570374012,
+      "rewards/margins": 1.466935396194458,
+      "rewards/rejected": -1.4464645385742188,
+      "step": 52
+    },
+    {
+      "epoch": 1.5539568345323742,
+      "grad_norm": 7.461566925048828,
+      "learning_rate": 2.7155009497015487e-06,
+      "logits/chosen": -1.7212716341018677,
+      "logits/rejected": -1.9288042783737183,
+      "logps/chosen": -161.3657989501953,
+      "logps/rejected": -203.9424285888672,
+      "loss": 0.3495,
+      "rewards/accuracies": 0.890625,
+      "rewards/chosen": 0.2896910011768341,
+      "rewards/margins": 1.4831678867340088,
+      "rewards/rejected": -1.193476915359497,
+      "step": 54
+    },
+    {
+      "epoch": 1.6115107913669064,
+      "grad_norm": 6.363231658935547,
+      "learning_rate": 2.5431516022634718e-06,
+      "logits/chosen": -1.7244608402252197,
+      "logits/rejected": -1.8467546701431274,
+      "logps/chosen": -169.42726135253906,
+      "logps/rejected": -238.03623962402344,
+      "loss": 0.3193,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": 0.5018333792686462,
+      "rewards/margins": 1.5871676206588745,
+      "rewards/rejected": -1.085334300994873,
+      "step": 56
+    },
+    {
+      "epoch": 1.6690647482014387,
+      "grad_norm": 8.272695541381836,
+      "learning_rate": 2.3705966177894763e-06,
+      "logits/chosen": -1.8467073440551758,
+      "logits/rejected": -2.1156005859375,
+      "logps/chosen": -169.63739013671875,
+      "logps/rejected": -229.26177978515625,
+      "loss": 0.3311,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": 0.4218375086784363,
+      "rewards/margins": 1.7388478517532349,
+      "rewards/rejected": -1.3170104026794434,
+      "step": 58
+    },
+    {
+      "epoch": 1.7266187050359711,
+      "grad_norm": 6.028374195098877,
+      "learning_rate": 2.1986582993616926e-06,
+      "logits/chosen": -1.7396399974822998,
+      "logits/rejected": -2.01945424079895,
+      "logps/chosen": -169.17230224609375,
+      "logps/rejected": -220.03109741210938,
+      "loss": 0.2872,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": 0.15267056226730347,
+      "rewards/margins": 1.99850594997406,
+      "rewards/rejected": -1.8458354473114014,
+      "step": 60
+    },
+    {
+      "epoch": 1.7841726618705036,
+      "grad_norm": 8.13830280303955,
+      "learning_rate": 2.0281560113677085e-06,
+      "logits/chosen": -1.8339189291000366,
+      "logits/rejected": -2.0238192081451416,
+      "logps/chosen": -176.9852752685547,
+      "logps/rejected": -219.31089782714844,
+      "loss": 0.3258,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": 0.418798565864563,
+      "rewards/margins": 1.8581160306930542,
+      "rewards/rejected": -1.4393174648284912,
+      "step": 62
+    },
+    {
+      "epoch": 1.841726618705036,
+      "grad_norm": 6.037229537963867,
+      "learning_rate": 1.8599022748561324e-06,
+      "logits/chosen": -1.6754798889160156,
+      "logits/rejected": -1.8604053258895874,
+      "logps/chosen": -179.31600952148438,
+      "logps/rejected": -222.77664184570312,
+      "loss": 0.2994,
+      "rewards/accuracies": 0.921875,
+      "rewards/chosen": 0.05394846200942993,
+      "rewards/margins": 1.9718104600906372,
+      "rewards/rejected": -1.9178617000579834,
+      "step": 64
+    },
+    {
+      "epoch": 1.8992805755395683,
+      "grad_norm": 5.1347336769104,
+      "learning_rate": 1.694698895503774e-06,
+      "logits/chosen": -1.6910380125045776,
+      "logits/rejected": -1.9908016920089722,
+      "logps/chosen": -168.50946044921875,
+      "logps/rejected": -230.62281799316406,
+      "loss": 0.2577,
+      "rewards/accuracies": 0.921875,
+      "rewards/chosen": 0.30626192688941956,
+      "rewards/margins": 2.129185199737549,
+      "rewards/rejected": -1.822923183441162,
+      "step": 66
+    },
+    {
+      "epoch": 1.9568345323741008,
+      "grad_norm": 4.9467926025390625,
+      "learning_rate": 1.5333331426464532e-06,
+      "logits/chosen": -1.836257815361023,
+      "logits/rejected": -2.202897310256958,
+      "logps/chosen": -191.49977111816406,
+      "logps/rejected": -229.22738647460938,
+      "loss": 0.2053,
+      "rewards/accuracies": 0.96875,
+      "rewards/chosen": 0.3933337330818176,
+      "rewards/margins": 2.6139490604400635,
+      "rewards/rejected": -2.2206156253814697,
+      "step": 68
+    },
+    {
+      "epoch": 2.014388489208633,
+      "grad_norm": 8.162074089050293,
+      "learning_rate": 1.3765739975820964e-06,
+      "logits/chosen": -1.7075754404067993,
+      "logits/rejected": -1.7874010801315308,
+      "logps/chosen": -185.13323974609375,
+      "logps/rejected": -241.02822875976562,
+      "loss": 0.3402,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": 0.3749930262565613,
+      "rewards/margins": 1.841801404953003,
+      "rewards/rejected": -1.4668081998825073,
+      "step": 70
+    },
+    {
+      "epoch": 2.0719424460431655,
+      "grad_norm": 9.112337112426758,
+      "learning_rate": 1.225168489024661e-06,
+      "logits/chosen": -1.6381630897521973,
+      "logits/rejected": -1.8705121278762817,
+      "logps/chosen": -164.97901916503906,
+      "logps/rejected": -204.80026245117188,
+      "loss": 0.3119,
+      "rewards/accuracies": 0.890625,
+      "rewards/chosen": 0.2434196174144745,
+      "rewards/margins": 1.9632219076156616,
+      "rewards/rejected": -1.7198021411895752,
+      "step": 72
+    },
+    {
+      "epoch": 2.129496402877698,
+      "grad_norm": 6.385829448699951,
+      "learning_rate": 1.079838133172111e-06,
+      "logits/chosen": -1.7317883968353271,
+      "logits/rejected": -1.9150619506835938,
+      "logps/chosen": -176.2250518798828,
+      "logps/rejected": -224.98941040039062,
+      "loss": 0.2232,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 0.1401495635509491,
+      "rewards/margins": 2.5023159980773926,
+      "rewards/rejected": -2.3621668815612793,
+      "step": 74
+    },
+    {
+      "epoch": 2.1870503597122304,
+      "grad_norm": 5.108960151672363,
+      "learning_rate": 9.412754953531664e-07,
+      "logits/chosen": -1.7440515756607056,
+      "logits/rejected": -1.87562096118927,
+      "logps/chosen": -171.93978881835938,
+      "logps/rejected": -214.25946044921875,
+      "loss": 0.2777,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -0.15876302123069763,
+      "rewards/margins": 2.08390212059021,
+      "rewards/rejected": -2.2426650524139404,
+      "step": 76
+    },
+    {
+      "epoch": 2.2446043165467624,
+      "grad_norm": 4.441920280456543,
+      "learning_rate": 8.101408896381141e-07,
+      "logits/chosen": -1.8361996412277222,
+      "logits/rejected": -2.2859373092651367,
+      "logps/chosen": -178.8001251220703,
+      "logps/rejected": -210.408447265625,
+      "loss": 0.2124,
+      "rewards/accuracies": 0.953125,
+      "rewards/chosen": 0.34240958094596863,
+      "rewards/margins": 2.488708734512329,
+      "rewards/rejected": -2.146299362182617,
+      "step": 78
+    },
+    {
+      "epoch": 2.302158273381295,
+      "grad_norm": 5.0956807136535645,
+      "learning_rate": 6.870592321415595e-07,
+      "logits/chosen": -1.7229351997375488,
+      "logits/rejected": -1.9915900230407715,
+      "logps/chosen": -176.20111083984375,
+      "logps/rejected": -228.6021728515625,
+      "loss": 0.1949,
+      "rewards/accuracies": 0.96875,
+      "rewards/chosen": 0.3722834885120392,
+      "rewards/margins": 2.7083969116210938,
+      "rewards/rejected": -2.336113214492798,
+      "step": 80
+    },
+    {
+      "epoch": 2.3597122302158273,
+      "grad_norm": 4.845056056976318,
+      "learning_rate": 5.72617063012551e-07,
+      "logits/chosen": -1.7617988586425781,
+      "logits/rejected": -1.9842320680618286,
+      "logps/chosen": -169.4710235595703,
+      "logps/rejected": -221.92437744140625,
+      "loss": 0.2402,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": 0.4934796690940857,
+      "rewards/margins": 2.6191768646240234,
+      "rewards/rejected": -2.125697374343872,
+      "step": 82
+    },
+    {
+      "epoch": 2.41726618705036,
+      "grad_norm": 6.618442535400391,
+      "learning_rate": 4.673597513036684e-07,
+      "logits/chosen": -1.8196489810943604,
+      "logits/rejected": -2.119847536087036,
+      "logps/chosen": -194.7741241455078,
+      "logps/rejected": -226.7880401611328,
+      "loss": 0.2859,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": 0.15423324704170227,
+      "rewards/margins": 1.936818242073059,
+      "rewards/rejected": -1.7825851440429688,
+      "step": 84
+    },
+    {
+      "epoch": 2.4748201438848922,
+      "grad_norm": 5.660532474517822,
+      "learning_rate": 3.717888960391222e-07,
+      "logits/chosen": -1.6743967533111572,
+      "logits/rejected": -2.142153263092041,
+      "logps/chosen": -182.84117126464844,
+      "logps/rejected": -236.10464477539062,
+      "loss": 0.2294,
+      "rewards/accuracies": 0.953125,
+      "rewards/chosen": -0.0025496408343315125,
+      "rewards/margins": 2.134979486465454,
+      "rewards/rejected": -2.137529134750366,
+      "step": 86
+    },
+    {
+      "epoch": 2.5323741007194247,
+      "grad_norm": 4.540892124176025,
+      "learning_rate": 2.8635993586697555e-07,
+      "logits/chosen": -1.559401273727417,
+      "logits/rejected": -1.7534209489822388,
+      "logps/chosen": -168.13064575195312,
+      "logps/rejected": -207.1958770751953,
+      "loss": 0.2516,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": -0.20388221740722656,
+      "rewards/margins": 2.3258824348449707,
+      "rewards/rejected": -2.5297646522521973,
+      "step": 88
+    },
+    {
+      "epoch": 2.5899280575539567,
+      "grad_norm": 5.678586483001709,
+      "learning_rate": 2.1147997868658427e-07,
+      "logits/chosen": -1.5231993198394775,
+      "logits/rejected": -1.73148512840271,
+      "logps/chosen": -158.38270568847656,
+      "logps/rejected": -204.1846466064453,
+      "loss": 0.2254,
+      "rewards/accuracies": 0.953125,
+      "rewards/chosen": 0.09025146812200546,
+      "rewards/margins": 2.35001277923584,
+      "rewards/rejected": -2.2597615718841553,
+      "step": 90
+    },
+    {
+      "epoch": 2.647482014388489,
+      "grad_norm": 7.349920749664307,
+      "learning_rate": 1.4750586159405917e-07,
+      "logits/chosen": -1.716179370880127,
+      "logits/rejected": -1.8096524477005005,
+      "logps/chosen": -162.72821044921875,
+      "logps/rejected": -225.792236328125,
+      "loss": 0.3215,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": 0.1088458001613617,
+      "rewards/margins": 1.9956300258636475,
+      "rewards/rejected": -1.886784315109253,
+      "step": 92
+    },
+    {
+      "epoch": 2.7050359712230216,
+      "grad_norm": 5.460008144378662,
+      "learning_rate": 9.474245039099883e-08,
+      "logits/chosen": -1.9032938480377197,
+      "logits/rejected": -2.2183752059936523,
+      "logps/chosen": -185.80279541015625,
+      "logps/rejected": -227.5401611328125,
+      "loss": 0.2675,
+      "rewards/accuracies": 0.890625,
+      "rewards/chosen": 0.1709720939397812,
+      "rewards/margins": 2.227972984313965,
+      "rewards/rejected": -2.0570011138916016,
+      "step": 94
+    },
+    {
+      "epoch": 2.762589928057554,
+      "grad_norm": 7.240005016326904,
+      "learning_rate": 5.344118676011173e-08,
+      "logits/chosen": -1.8280268907546997,
+      "logits/rejected": -2.053773880004883,
+      "logps/chosen": -182.4041748046875,
+      "logps/rejected": -230.9427032470703,
+      "loss": 0.2482,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": 0.03328900411725044,
+      "rewards/margins": 2.2742063999176025,
+      "rewards/rejected": -2.240917205810547,
+      "step": 96
+    },
+    {
+      "epoch": 2.8201438848920866,
+      "grad_norm": 8.40621566772461,
+      "learning_rate": 2.3798890031092037e-08,
+      "logits/chosen": -1.7997097969055176,
+      "logits/rejected": -1.9944825172424316,
+      "logps/chosen": -169.30648803710938,
+      "logps/rejected": -205.72390747070312,
+      "loss": 0.2811,
+      "rewards/accuracies": 0.890625,
+      "rewards/chosen": 0.2229904681444168,
+      "rewards/margins": 2.305001735687256,
+      "rewards/rejected": -2.0820112228393555,
+      "step": 98
+    },
+    {
+      "epoch": 2.8776978417266186,
+      "grad_norm": 4.172658443450928,
+      "learning_rate": 5.9568192468811844e-09,
+      "logits/chosen": -1.6826629638671875,
+      "logits/rejected": -1.8101749420166016,
+      "logps/chosen": -172.32896423339844,
+      "logps/rejected": -232.7934112548828,
+      "loss": 0.169,
+      "rewards/accuracies": 0.96875,
+      "rewards/chosen": 0.24307750165462494,
+      "rewards/margins": 2.7273943424224854,
+      "rewards/rejected": -2.484316825866699,
+      "step": 100
+    },
+    {
+      "epoch": 2.935251798561151,
+      "grad_norm": 4.340843200683594,
+      "learning_rate": 0.0,
+      "logits/chosen": -1.5438573360443115,
+      "logits/rejected": -1.7152578830718994,
+      "logps/chosen": -160.0493927001953,
+      "logps/rejected": -215.81707763671875,
+      "loss": 0.19,
+      "rewards/accuracies": 0.953125,
+      "rewards/chosen": 0.4251682162284851,
+      "rewards/margins": 2.6738100051879883,
+      "rewards/rejected": -2.2486419677734375,
+      "step": 102
+    },
+    {
+      "epoch": 2.935251798561151,
+      "step": 102,
+      "total_flos": 8.94448793688146e+16,
+      "train_loss": 0.4110284693100873,
+      "train_runtime": 896.119,
+      "train_samples_per_second": 3.713,
+      "train_steps_per_second": 0.114
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 102,
+  "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": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.94448793688146e+16,
+  "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:d5967ae507c9b731ecbe92c5eb87bf1e7efd9ef712219001ec9947dca931c2d5
+size 5304