Training in progress, step 500, checkpoint

checkpoint-500/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: HuggingFaceH4/zephyr-7b-beta
+---
+
+# 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 0.10.0

checkpoint-500/adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b5255da8f350d25a6a3be54b46ff4d41494a110f9c434118ba48a81c654a532
+size 54560368

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:367b66890bc31e6e5760395bebda2352a7522536f399cd118ec9e9cef619be3b
+size 109267450

checkpoint-500/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce210eb9b40cd3fb20f04853762d7801d40ffa6d286995c5796f1822212ae3f0
+size 14512

checkpoint-500/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e213b5d8efffdbfeff77e59867f4ec63355feef1d77d63f4f84443e245315fb9
+size 14512

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f9383bbb245a0112ed68ac9db24f4a14c7d6d232df19cd6a20aa297ecea7bf0
+size 1064

checkpoint-500/special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-500/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-500/tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "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": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "max_lenght": 8192,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "padding": true,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

checkpoint-500/trainer_state.json

@@ -0,0 +1,486 @@
+{
+  "best_metric": 0.014748962596058846,
+  "best_model_checkpoint": "./Zephyr/27-03-24-Weni-kto-test_WeniGPT Experiment using KTO trainer with no collator-2_max_steps-786_batch_16_2024-03-27_ppid_1885/checkpoint-300",
+  "epoch": 3.8095238095238093,
+  "eval_steps": 50,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15,
+      "grad_norm": 2.2224462032318115,
+      "kl": 0.054589949548244476,
+      "learning_rate": 0.0001666666666666667,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 704.2891,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 20
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.9781014919281006,
+      "kl": 0.014553820714354515,
+      "learning_rate": 0.00019580052493438322,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 371.0873,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 40
+    },
+    {
+      "epoch": 0.38,
+      "eval_kl": 0.014955863356590271,
+      "eval_logps/chosen": -139.6813507080078,
+      "eval_logps/rejected": -288.11480712890625,
+      "eval_loss": 0.0440419502556324,
+      "eval_rewards/chosen": 4.680752754211426,
+      "eval_rewards/margins": 14.199661254882812,
+      "eval_rewards/rejected": -9.518909454345703,
+      "eval_runtime": 437.1874,
+      "eval_samples_per_second": 1.07,
+      "eval_steps_per_second": 0.268,
+      "step": 50
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.7002557516098022,
+      "kl": 0.36391472816467285,
+      "learning_rate": 0.0001905511811023622,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 165.1605,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 60
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.5644651651382446,
+      "kl": 0.01063810009509325,
+      "learning_rate": 0.00018556430446194227,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 89.197,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 80
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.18941974639892578,
+      "kl": 0.0,
+      "learning_rate": 0.0001805774278215223,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 57.9834,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 100
+    },
+    {
+      "epoch": 0.76,
+      "eval_kl": 0.0,
+      "eval_logps/chosen": -135.0946807861328,
+      "eval_logps/rejected": -511.870361328125,
+      "eval_loss": 0.027495555579662323,
+      "eval_rewards/chosen": 5.139419078826904,
+      "eval_rewards/margins": 37.033878326416016,
+      "eval_rewards/rejected": -31.89446258544922,
+      "eval_runtime": 437.2677,
+      "eval_samples_per_second": 1.07,
+      "eval_steps_per_second": 0.268,
+      "step": 100
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.2737089395523071,
+      "kl": 0.0,
+      "learning_rate": 0.00017532808398950132,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 1101.4947,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 120
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 0.10652273148298264,
+      "kl": 0.0,
+      "learning_rate": 0.00017007874015748033,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 37.3685,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 140
+    },
+    {
+      "epoch": 1.14,
+      "eval_kl": 0.0,
+      "eval_logps/chosen": -133.9324951171875,
+      "eval_logps/rejected": -464.85992431640625,
+      "eval_loss": 0.019584182649850845,
+      "eval_rewards/chosen": 5.25563907623291,
+      "eval_rewards/margins": 32.449058532714844,
+      "eval_rewards/rejected": -27.19342041015625,
+      "eval_runtime": 437.0658,
+      "eval_samples_per_second": 1.071,
+      "eval_steps_per_second": 0.268,
+      "step": 150
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.060089632868766785,
+      "kl": 0.21830137073993683,
+      "learning_rate": 0.00016482939632545934,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 91.1641,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 160
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 0.08910108357667923,
+      "kl": 0.03056584671139717,
+      "learning_rate": 0.00015958005249343832,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 8.2078,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 180
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.025327660143375397,
+      "kl": 0.0,
+      "learning_rate": 0.00015433070866141733,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 3.6561,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 200
+    },
+    {
+      "epoch": 1.52,
+      "eval_kl": 0.0,
+      "eval_logps/chosen": -132.1833038330078,
+      "eval_logps/rejected": -419.2353820800781,
+      "eval_loss": 0.016207611188292503,
+      "eval_rewards/chosen": 5.430557727813721,
+      "eval_rewards/margins": 28.061521530151367,
+      "eval_rewards/rejected": -22.630962371826172,
+      "eval_runtime": 437.1734,
+      "eval_samples_per_second": 1.071,
+      "eval_steps_per_second": 0.268,
+      "step": 200
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 0.04120240360498428,
+      "kl": 0.04972388595342636,
+      "learning_rate": 0.00014908136482939634,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 21.787,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 220
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 0.043324064463377,
+      "kl": 0.09086960554122925,
+      "learning_rate": 0.00014383202099737535,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 59.5367,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 240
+    },
+    {
+      "epoch": 1.9,
+      "eval_kl": 0.0,
+      "eval_logps/chosen": -129.1339111328125,
+      "eval_logps/rejected": -504.5447998046875,
+      "eval_loss": 0.01432154793292284,
+      "eval_rewards/chosen": 5.7354960441589355,
+      "eval_rewards/margins": 36.89740753173828,
+      "eval_rewards/rejected": -31.161909103393555,
+      "eval_runtime": 437.5542,
+      "eval_samples_per_second": 1.07,
+      "eval_steps_per_second": 0.267,
+      "step": 250
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 0.028953969478607178,
+      "kl": 0.0,
+      "learning_rate": 0.00013858267716535433,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 5.7556,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 260
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 0.022753821685910225,
+      "kl": 0.18936340510845184,
+      "learning_rate": 0.00013333333333333334,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 4.7774,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 280
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 0.038736581802368164,
+      "kl": 0.0,
+      "learning_rate": 0.00012808398950131235,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 13.1891,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 300
+    },
+    {
+      "epoch": 2.29,
+      "eval_kl": 0.0,
+      "eval_logps/chosen": -130.3461151123047,
+      "eval_logps/rejected": -503.4655456542969,
+      "eval_loss": 0.014748962596058846,
+      "eval_rewards/chosen": 5.614275932312012,
+      "eval_rewards/margins": 36.66826248168945,
+      "eval_rewards/rejected": -31.05398178100586,
+      "eval_runtime": 437.6283,
+      "eval_samples_per_second": 1.069,
+      "eval_steps_per_second": 0.267,
+      "step": 300
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.015456304885447025,
+      "kl": 0.016447115689516068,
+      "learning_rate": 0.00012283464566929136,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 2.946,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 320
+    },
+    {
+      "epoch": 2.59,
+      "grad_norm": 0.03844680264592171,
+      "kl": 0.0,
+      "learning_rate": 0.00011758530183727034,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 3.8532,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 340
+    },
+    {
+      "epoch": 2.67,
+      "eval_kl": 0.0,
+      "eval_logps/chosen": -127.6288833618164,
+      "eval_logps/rejected": -457.08013916015625,
+      "eval_loss": 0.013063323684036732,
+      "eval_rewards/chosen": 5.886001110076904,
+      "eval_rewards/margins": 32.30144119262695,
+      "eval_rewards/rejected": -26.415441513061523,
+      "eval_runtime": 437.2,
+      "eval_samples_per_second": 1.07,
+      "eval_steps_per_second": 0.268,
+      "step": 350
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 0.013407759368419647,
+      "kl": 0.0,
+      "learning_rate": 0.00011233595800524934,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 14.6044,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 360
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.1375456601381302,
+      "kl": 0.042511165142059326,
+      "learning_rate": 0.00010708661417322836,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 20.8824,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 380
+    },
+    {
+      "epoch": 3.05,
+      "grad_norm": 0.012805495411157608,
+      "kl": 0.0,
+      "learning_rate": 0.00010183727034120735,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 3.7678,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 400
+    },
+    {
+      "epoch": 3.05,
+      "eval_kl": 0.0,
+      "eval_logps/chosen": -127.17108917236328,
+      "eval_logps/rejected": -460.4493408203125,
+      "eval_loss": 0.016150476410984993,
+      "eval_rewards/chosen": 5.931778430938721,
+      "eval_rewards/margins": 32.684139251708984,
+      "eval_rewards/rejected": -26.75235939025879,
+      "eval_runtime": 437.1823,
+      "eval_samples_per_second": 1.07,
+      "eval_steps_per_second": 0.268,
+      "step": 400
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.017726995050907135,
+      "kl": 0.2870129942893982,
+      "learning_rate": 9.658792650918635e-05,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 1.685,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 420
+    },
+    {
+      "epoch": 3.35,
+      "grad_norm": 0.007917443290352821,
+      "kl": 0.0,
+      "learning_rate": 9.133858267716536e-05,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 49.3456,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 440
+    },
+    {
+      "epoch": 3.43,
+      "eval_kl": 0.0,
+      "eval_logps/chosen": -127.23651123046875,
+      "eval_logps/rejected": -479.95904541015625,
+      "eval_loss": 0.016735197976231575,
+      "eval_rewards/chosen": 5.925236225128174,
+      "eval_rewards/margins": 34.628562927246094,
+      "eval_rewards/rejected": -28.703327178955078,
+      "eval_runtime": 437.235,
+      "eval_samples_per_second": 1.07,
+      "eval_steps_per_second": 0.268,
+      "step": 450
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.016776828095316887,
+      "kl": 0.0,
+      "learning_rate": 8.608923884514435e-05,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 6.9542,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 460
+    },
+    {
+      "epoch": 3.66,
+      "grad_norm": 0.009395829401910305,
+      "kl": 0.0,
+      "learning_rate": 8.083989501312336e-05,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 25.7168,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 480
+    },
+    {
+      "epoch": 3.81,
+      "grad_norm": 0.008246039040386677,
+      "kl": 0.028682123869657516,
+      "learning_rate": 7.559055118110236e-05,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 12.2886,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 500
+    },
+    {
+      "epoch": 3.81,
+      "eval_kl": 0.0,
+      "eval_logps/chosen": -126.48030090332031,
+      "eval_logps/rejected": -487.4185485839844,
+      "eval_loss": 0.01638978347182274,
+      "eval_rewards/chosen": 6.000857830047607,
+      "eval_rewards/margins": 35.45014190673828,
+      "eval_rewards/rejected": -29.44928550720215,
+      "eval_runtime": 437.6004,
+      "eval_samples_per_second": 1.069,
+      "eval_steps_per_second": 0.267,
+      "step": 500
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 786,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 100,
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c04380dac1b289b8afea7297ea9ea9e1ac98da4787c8cec5f2868e7236a8fefb
+size 5560