Training in progress, step 180, checkpoint

checkpoint-180/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: Weni/WeniGPT-Agents-Mistral-1.0.0-SFT-merged
+---
+
+# 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-180/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Weni/WeniGPT-Agents-Mistral-1.0.0-SFT-merged",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-180/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34ee64adb3566f99c2c3fb611951165682902c6d4a486eac296af4ba33fa5e06
+size 335604696

checkpoint-180/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d744b66a0d8c639e6a962ba303b040d42e6af6cd10877c0dc1e3edf7d6d8ab86
+size 671466706

checkpoint-180/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae78313eb528c8d3695eebaf4de3539bd0a0bc6ee18c66af1ee183442f1758a0
+size 15024

checkpoint-180/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b38031f60d9e88601d369ef46bcdcf2b5b03f2cb4ba93853bcb2328df7ebb7c
+size 15024

checkpoint-180/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f58092375c93d237cd0e3149aecfbf83e2acdae46279e07a32920d01cb507e64
+size 15024

checkpoint-180/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83cd4bbff9962da7ec6787fcea8d65df7096917f9a5902e249ba7aee8887fe5f
+size 15024

checkpoint-180/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b47d7566b2e3ec8e96007d3ecf18c3cfe003d3d58d6c01ae710dc49dfbfb649
+size 1064

checkpoint-180/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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-180/tokenizer.model

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

checkpoint-180/tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "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": [],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'system' %}{{ '<<SYS>>\\n' + message['content'] + '\\n<</SYS>>\\n\\n' }}{% elif message['role'] == 'assistant' %}{{ ' '  + message['content'] + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "max_lenght": 8192,
+  "max_length": 8192,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "padding": true,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-180/trainer_state.json

@@ -0,0 +1,387 @@
+{
+  "best_metric": 0.052017249166965485,
+  "best_model_checkpoint": "./mistral/22-04-24-Weni-WeniGPT-Agents-Mistral-1.0.0-SFT-1.0.21-DPO_Experiment on DPO with other hyperparameters and best SFT model of WeniGPT-2_max_steps-180_batch_8_2024-04-22_ppid_9/checkpoint-180",
+  "epoch": 5.806451612903226,
+  "eval_steps": 30,
+  "global_step": 180,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3225806451612903,
+      "grad_norm": 13.277989387512207,
+      "learning_rate": 4.971264367816092e-06,
+      "logits/chosen": -1.7891426086425781,
+      "logits/rejected": -1.814126968383789,
+      "logps/chosen": -200.95481872558594,
+      "logps/rejected": -223.9504852294922,
+      "loss": 0.6771,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 0.02733452059328556,
+      "rewards/margins": 0.028555069118738174,
+      "rewards/rejected": -0.0012205507373437285,
+      "step": 10
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 11.217987060546875,
+      "learning_rate": 4.683908045977012e-06,
+      "logits/chosen": -1.8347755670547485,
+      "logits/rejected": -1.8467401266098022,
+      "logps/chosen": -144.74403381347656,
+      "logps/rejected": -191.45069885253906,
+      "loss": 0.5478,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 0.37081974744796753,
+      "rewards/margins": 0.4048076272010803,
+      "rewards/rejected": -0.03398784250020981,
+      "step": 20
+    },
+    {
+      "epoch": 0.967741935483871,
+      "grad_norm": 11.224645614624023,
+      "learning_rate": 4.396551724137931e-06,
+      "logits/chosen": -1.785586953163147,
+      "logits/rejected": -1.8152267932891846,
+      "logps/chosen": -190.48626708984375,
+      "logps/rejected": -248.2376251220703,
+      "loss": 0.3976,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.7104076147079468,
+      "rewards/margins": 0.848293662071228,
+      "rewards/rejected": -0.13788609206676483,
+      "step": 30
+    },
+    {
+      "epoch": 0.967741935483871,
+      "eval_logits/chosen": -1.7412782907485962,
+      "eval_logits/rejected": -1.7560926675796509,
+      "eval_logps/chosen": -115.03002166748047,
+      "eval_logps/rejected": -160.6632080078125,
+      "eval_loss": 0.3185553252696991,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 0.8372641801834106,
+      "eval_rewards/margins": 0.8753501176834106,
+      "eval_rewards/rejected": -0.038085997104644775,
+      "eval_runtime": 10.5823,
+      "eval_samples_per_second": 2.646,
+      "eval_steps_per_second": 0.661,
+      "step": 30
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 5.652975082397461,
+      "learning_rate": 4.1091954022988515e-06,
+      "logits/chosen": -1.7882213592529297,
+      "logits/rejected": -1.7954260110855103,
+      "logps/chosen": -159.75631713867188,
+      "logps/rejected": -182.1666717529297,
+      "loss": 0.2432,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 1.2001782655715942,
+      "rewards/margins": 1.2467749118804932,
+      "rewards/rejected": -0.04659665375947952,
+      "step": 40
+    },
+    {
+      "epoch": 1.6129032258064515,
+      "grad_norm": 3.635425090789795,
+      "learning_rate": 3.82183908045977e-06,
+      "logits/chosen": -1.8176883459091187,
+      "logits/rejected": -1.8400278091430664,
+      "logps/chosen": -114.22891998291016,
+      "logps/rejected": -197.11019897460938,
+      "loss": 0.242,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 1.5082905292510986,
+      "rewards/margins": 2.3228204250335693,
+      "rewards/rejected": -0.8145298957824707,
+      "step": 50
+    },
+    {
+      "epoch": 1.935483870967742,
+      "grad_norm": 5.051187038421631,
+      "learning_rate": 3.5344827586206898e-06,
+      "logits/chosen": -1.769321084022522,
+      "logits/rejected": -1.7883247137069702,
+      "logps/chosen": -149.78382873535156,
+      "logps/rejected": -172.86285400390625,
+      "loss": 0.1934,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 1.4219303131103516,
+      "rewards/margins": 1.7929319143295288,
+      "rewards/rejected": -0.3710017502307892,
+      "step": 60
+    },
+    {
+      "epoch": 1.935483870967742,
+      "eval_logits/chosen": -1.745606541633606,
+      "eval_logits/rejected": -1.7603371143341064,
+      "eval_logps/chosen": -110.98043060302734,
+      "eval_logps/rejected": -163.220703125,
+      "eval_loss": 0.17523464560508728,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 1.6471832990646362,
+      "eval_rewards/margins": 2.1967694759368896,
+      "eval_rewards/rejected": -0.5495859384536743,
+      "eval_runtime": 10.5122,
+      "eval_samples_per_second": 2.664,
+      "eval_steps_per_second": 0.666,
+      "step": 60
+    },
+    {
+      "epoch": 2.258064516129032,
+      "grad_norm": 5.4414238929748535,
+      "learning_rate": 3.24712643678161e-06,
+      "logits/chosen": -1.761417031288147,
+      "logits/rejected": -1.7780914306640625,
+      "logps/chosen": -153.3155059814453,
+      "logps/rejected": -175.71119689941406,
+      "loss": 0.1552,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 1.9575698375701904,
+      "rewards/margins": 2.617478847503662,
+      "rewards/rejected": -0.6599088907241821,
+      "step": 70
+    },
+    {
+      "epoch": 2.5806451612903225,
+      "grad_norm": 3.4745564460754395,
+      "learning_rate": 2.988505747126437e-06,
+      "logits/chosen": -1.8878180980682373,
+      "logits/rejected": -1.895895004272461,
+      "logps/chosen": -148.46951293945312,
+      "logps/rejected": -211.92874145507812,
+      "loss": 0.157,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 1.930851697921753,
+      "rewards/margins": 2.822469711303711,
+      "rewards/rejected": -0.8916179537773132,
+      "step": 80
+    },
+    {
+      "epoch": 2.903225806451613,
+      "grad_norm": 4.5158843994140625,
+      "learning_rate": 2.7011494252873567e-06,
+      "logits/chosen": -1.8586393594741821,
+      "logits/rejected": -1.8672926425933838,
+      "logps/chosen": -166.34080505371094,
+      "logps/rejected": -204.51248168945312,
+      "loss": 0.1058,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.207078695297241,
+      "rewards/margins": 3.182745933532715,
+      "rewards/rejected": -0.9756671190261841,
+      "step": 90
+    },
+    {
+      "epoch": 2.903225806451613,
+      "eval_logits/chosen": -1.7490978240966797,
+      "eval_logits/rejected": -1.7636711597442627,
+      "eval_logps/chosen": -109.27593231201172,
+      "eval_logps/rejected": -164.40065002441406,
+      "eval_loss": 0.1095743179321289,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 1.9880834817886353,
+      "eval_rewards/margins": 2.77366042137146,
+      "eval_rewards/rejected": -0.7855769991874695,
+      "eval_runtime": 10.5091,
+      "eval_samples_per_second": 2.664,
+      "eval_steps_per_second": 0.666,
+      "step": 90
+    },
+    {
+      "epoch": 3.225806451612903,
+      "grad_norm": 7.920010089874268,
+      "learning_rate": 2.4137931034482762e-06,
+      "logits/chosen": -1.8129634857177734,
+      "logits/rejected": -1.8248703479766846,
+      "logps/chosen": -188.29046630859375,
+      "logps/rejected": -166.93959045410156,
+      "loss": 0.0846,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.0221571922302246,
+      "rewards/margins": 2.638063669204712,
+      "rewards/rejected": -0.6159064769744873,
+      "step": 100
+    },
+    {
+      "epoch": 3.5483870967741935,
+      "grad_norm": 2.062326192855835,
+      "learning_rate": 2.1264367816091954e-06,
+      "logits/chosen": -1.780647873878479,
+      "logits/rejected": -1.8003911972045898,
+      "logps/chosen": -181.70352172851562,
+      "logps/rejected": -211.6031036376953,
+      "loss": 0.0915,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.376112937927246,
+      "rewards/margins": 3.2865447998046875,
+      "rewards/rejected": -0.9104318618774414,
+      "step": 110
+    },
+    {
+      "epoch": 3.870967741935484,
+      "grad_norm": 2.184727668762207,
+      "learning_rate": 1.839080459770115e-06,
+      "logits/chosen": -1.84122633934021,
+      "logits/rejected": -1.8630201816558838,
+      "logps/chosen": -110.26792907714844,
+      "logps/rejected": -188.52102661132812,
+      "loss": 0.0527,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.7806448936462402,
+      "rewards/margins": 4.270835876464844,
+      "rewards/rejected": -1.4901912212371826,
+      "step": 120
+    },
+    {
+      "epoch": 3.870967741935484,
+      "eval_logits/chosen": -1.7532367706298828,
+      "eval_logits/rejected": -1.767619013786316,
+      "eval_logps/chosen": -108.33710479736328,
+      "eval_logps/rejected": -165.59573364257812,
+      "eval_loss": 0.07865254580974579,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 2.175847291946411,
+      "eval_rewards/margins": 3.2004382610321045,
+      "eval_rewards/rejected": -1.0245908498764038,
+      "eval_runtime": 10.5128,
+      "eval_samples_per_second": 2.663,
+      "eval_steps_per_second": 0.666,
+      "step": 120
+    },
+    {
+      "epoch": 4.193548387096774,
+      "grad_norm": 3.8901867866516113,
+      "learning_rate": 1.5517241379310346e-06,
+      "logits/chosen": -1.80022394657135,
+      "logits/rejected": -1.8180515766143799,
+      "logps/chosen": -133.0179901123047,
+      "logps/rejected": -267.961181640625,
+      "loss": 0.0702,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 1.7386133670806885,
+      "rewards/margins": 3.7656383514404297,
+      "rewards/rejected": -2.0270252227783203,
+      "step": 130
+    },
+    {
+      "epoch": 4.516129032258064,
+      "grad_norm": 0.9774993062019348,
+      "learning_rate": 1.2643678160919542e-06,
+      "logits/chosen": -1.770490050315857,
+      "logits/rejected": -1.7988364696502686,
+      "logps/chosen": -134.59291076660156,
+      "logps/rejected": -227.28573608398438,
+      "loss": 0.0389,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.5844013690948486,
+      "rewards/margins": 4.34262752532959,
+      "rewards/rejected": -1.7582266330718994,
+      "step": 140
+    },
+    {
+      "epoch": 4.838709677419355,
+      "grad_norm": 2.1318492889404297,
+      "learning_rate": 9.770114942528738e-07,
+      "logits/chosen": -1.846001386642456,
+      "logits/rejected": -1.853493332862854,
+      "logps/chosen": -118.50834655761719,
+      "logps/rejected": -196.01217651367188,
+      "loss": 0.0526,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.303821086883545,
+      "rewards/margins": 3.837214231491089,
+      "rewards/rejected": -1.5333930253982544,
+      "step": 150
+    },
+    {
+      "epoch": 4.838709677419355,
+      "eval_logits/chosen": -1.7548978328704834,
+      "eval_logits/rejected": -1.7693225145339966,
+      "eval_logps/chosen": -107.8351058959961,
+      "eval_logps/rejected": -167.27781677246094,
+      "eval_loss": 0.05771544948220253,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 2.2762484550476074,
+      "eval_rewards/margins": 3.6372554302215576,
+      "eval_rewards/rejected": -1.3610070943832397,
+      "eval_runtime": 10.508,
+      "eval_samples_per_second": 2.665,
+      "eval_steps_per_second": 0.666,
+      "step": 150
+    },
+    {
+      "epoch": 5.161290322580645,
+      "grad_norm": 1.8219561576843262,
+      "learning_rate": 6.896551724137931e-07,
+      "logits/chosen": -1.8211644887924194,
+      "logits/rejected": -1.8465015888214111,
+      "logps/chosen": -104.08028411865234,
+      "logps/rejected": -210.0991973876953,
+      "loss": 0.0613,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.1849822998046875,
+      "rewards/margins": 4.971571922302246,
+      "rewards/rejected": -1.7865898609161377,
+      "step": 160
+    },
+    {
+      "epoch": 5.483870967741936,
+      "grad_norm": 1.121188998222351,
+      "learning_rate": 4.0229885057471266e-07,
+      "logits/chosen": -1.8207435607910156,
+      "logits/rejected": -1.8367401361465454,
+      "logps/chosen": -167.99905395507812,
+      "logps/rejected": -210.1734161376953,
+      "loss": 0.0339,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.480262517929077,
+      "rewards/margins": 4.021227836608887,
+      "rewards/rejected": -1.5409656763076782,
+      "step": 170
+    },
+    {
+      "epoch": 5.806451612903226,
+      "grad_norm": 1.1327688694000244,
+      "learning_rate": 1.1494252873563219e-07,
+      "logits/chosen": -1.875394582748413,
+      "logits/rejected": -1.887101411819458,
+      "logps/chosen": -181.40708923339844,
+      "logps/rejected": -255.3656463623047,
+      "loss": 0.0529,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.5407514572143555,
+      "rewards/margins": 5.552119731903076,
+      "rewards/rejected": -3.0113682746887207,
+      "step": 180
+    },
+    {
+      "epoch": 5.806451612903226,
+      "eval_logits/chosen": -1.7573397159576416,
+      "eval_logits/rejected": -1.7717255353927612,
+      "eval_logps/chosen": -107.60765075683594,
+      "eval_logps/rejected": -167.99813842773438,
+      "eval_loss": 0.052017249166965485,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 2.3217406272888184,
+      "eval_rewards/margins": 3.8268144130706787,
+      "eval_rewards/rejected": -1.5050735473632812,
+      "eval_runtime": 10.5205,
+      "eval_samples_per_second": 2.661,
+      "eval_steps_per_second": 0.665,
+      "step": 180
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 180,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 90,
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-180/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9886a680a1a96de313efe45aaff68cf35d0dbb41e31f6c248b2fb523f6f39aaf
+size 5432