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 +1,31 @@
+{
+  "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": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "q_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 sha256:00353346343731c94975c0ca2803571ee6d598d27e99ae337450e2251a2031fd
+size 27297032

checkpoint-180/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f419867db0ea67e7b4f962f242f5eeadb546b3ab209dbe676d8648548fdc2bc6
+size 54740730

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 sha256:3db171fd1632e7fa1f2bf61bae0838c79d128613f85598160a41fd69ac877a77
+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": 0.17089667916297913,
+  "best_model_checkpoint": "./mistral/21-04-24-Weni-WeniGPT-Agents-Mistral-1.0.0-SFT-1.0.14-DPO_Experiment on DPO with other hyperparameters and best SFT model of WeniGPT-2_max_steps-180_batch_8_2024-04-21_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": NaN,
+      "learning_rate": 4.166666666666667e-06,
+      "logits/chosen": -1.8499033451080322,
+      "logits/rejected": -1.8593229055404663,
+      "logps/chosen": -137.12442016601562,
+      "logps/rejected": -178.81710815429688,
+      "loss": 0.6926,
+      "rewards/accuracies": 0.15000000596046448,
+      "rewards/chosen": 0.0018950270023196936,
+      "rewards/margins": -0.002861480927094817,
+      "rewards/rejected": 0.004756507929414511,
+      "step": 10
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 35.12880325317383,
+      "learning_rate": 4.770114942528735e-06,
+      "logits/chosen": -1.849482774734497,
+      "logits/rejected": -1.8675953149795532,
+      "logps/chosen": -161.28775024414062,
+      "logps/rejected": -200.60560607910156,
+      "loss": 0.6451,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": 0.10006960481405258,
+      "rewards/margins": 0.09196183830499649,
+      "rewards/rejected": 0.00810776837170124,
+      "step": 20
+    },
+    {
+      "epoch": 0.967741935483871,
+      "grad_norm": 24.340425491333008,
+      "learning_rate": 4.482758620689656e-06,
+      "logits/chosen": -1.8481957912445068,
+      "logits/rejected": -1.8752952814102173,
+      "logps/chosen": -177.55410766601562,
+      "logps/rejected": -182.57843017578125,
+      "loss": 0.5263,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 0.3369366228580475,
+      "rewards/margins": 0.40268000960350037,
+      "rewards/rejected": -0.06574340164661407,
+      "step": 30
+    },
+    {
+      "epoch": 0.967741935483871,
+      "eval_logits/chosen": -1.8220570087432861,
+      "eval_logits/rejected": -1.8403350114822388,
+      "eval_logps/chosen": -116.7420654296875,
+      "eval_logps/rejected": -159.6157989501953,
+      "eval_loss": 0.5183293223381042,
+      "eval_rewards/accuracies": 0.7142857313156128,
+      "eval_rewards/chosen": 0.3988271653652191,
+      "eval_rewards/margins": 0.41541212797164917,
+      "eval_rewards/rejected": -0.016584938392043114,
+      "eval_runtime": 12.3087,
+      "eval_samples_per_second": 2.275,
+      "eval_steps_per_second": 0.569,
+      "step": 30
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 31.281463623046875,
+      "learning_rate": 4.1954022988505746e-06,
+      "logits/chosen": -1.7448915243148804,
+      "logits/rejected": -1.7752825021743774,
+      "logps/chosen": -121.0214614868164,
+      "logps/rejected": -183.06617736816406,
+      "loss": 0.4491,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 0.6125963926315308,
+      "rewards/margins": 0.6647117137908936,
+      "rewards/rejected": -0.05211536958813667,
+      "step": 40
+    },
+    {
+      "epoch": 1.6129032258064515,
+      "grad_norm": 19.422542572021484,
+      "learning_rate": 3.908045977011495e-06,
+      "logits/chosen": -1.8254241943359375,
+      "logits/rejected": -1.8358204364776611,
+      "logps/chosen": -171.71742248535156,
+      "logps/rejected": -190.7814178466797,
+      "loss": 0.3671,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 1.1753848791122437,
+      "rewards/margins": 1.248801589012146,
+      "rewards/rejected": -0.07341676950454712,
+      "step": 50
+    },
+    {
+      "epoch": 1.935483870967742,
+      "grad_norm": 34.390132904052734,
+      "learning_rate": 3.620689655172414e-06,
+      "logits/chosen": -1.7818552255630493,
+      "logits/rejected": -1.8110145330429077,
+      "logps/chosen": -130.157958984375,
+      "logps/rejected": -213.92398071289062,
+      "loss": 0.2814,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 1.2184925079345703,
+      "rewards/margins": 1.4377745389938354,
+      "rewards/rejected": -0.21928200125694275,
+      "step": 60
+    },
+    {
+      "epoch": 1.935483870967742,
+      "eval_logits/chosen": -1.8258559703826904,
+      "eval_logits/rejected": -1.8442572355270386,
+      "eval_logps/chosen": -114.84210968017578,
+      "eval_logps/rejected": -159.62986755371094,
+      "eval_loss": 0.35161063075065613,
+      "eval_rewards/accuracies": 0.7142857313156128,
+      "eval_rewards/chosen": 0.96880704164505,
+      "eval_rewards/margins": 0.9896138906478882,
+      "eval_rewards/rejected": -0.020806819200515747,
+      "eval_runtime": 12.2941,
+      "eval_samples_per_second": 2.278,
+      "eval_steps_per_second": 0.569,
+      "step": 60
+    },
+    {
+      "epoch": 2.258064516129032,
+      "grad_norm": 8.615694046020508,
+      "learning_rate": 3.3333333333333333e-06,
+      "logits/chosen": -1.8212693929672241,
+      "logits/rejected": -1.8290560245513916,
+      "logps/chosen": -175.70535278320312,
+      "logps/rejected": -190.63951110839844,
+      "loss": 0.2814,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 1.0433236360549927,
+      "rewards/margins": 1.054437279701233,
+      "rewards/rejected": -0.011113762855529785,
+      "step": 70
+    },
+    {
+      "epoch": 2.5806451612903225,
+      "grad_norm": 11.356379508972168,
+      "learning_rate": 3.0459770114942533e-06,
+      "logits/chosen": -1.8097782135009766,
+      "logits/rejected": -1.8336036205291748,
+      "logps/chosen": -172.34161376953125,
+      "logps/rejected": -199.13595581054688,
+      "loss": 0.2312,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 1.5693215131759644,
+      "rewards/margins": 1.6860816478729248,
+      "rewards/rejected": -0.11676013469696045,
+      "step": 80
+    },
+    {
+      "epoch": 2.903225806451613,
+      "grad_norm": 11.608332633972168,
+      "learning_rate": 2.7586206896551725e-06,
+      "logits/chosen": -1.7416813373565674,
+      "logits/rejected": -1.7631210088729858,
+      "logps/chosen": -182.21278381347656,
+      "logps/rejected": -222.73110961914062,
+      "loss": 0.1778,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.103548049926758,
+      "rewards/margins": 2.4875168800354004,
+      "rewards/rejected": -0.3839687705039978,
+      "step": 90
+    },
+    {
+      "epoch": 2.903225806451613,
+      "eval_logits/chosen": -1.8285714387893677,
+      "eval_logits/rejected": -1.8470104932785034,
+      "eval_logps/chosen": -113.45030212402344,
+      "eval_logps/rejected": -159.89283752441406,
+      "eval_loss": 0.2654591202735901,
+      "eval_rewards/accuracies": 0.8571428656578064,
+      "eval_rewards/chosen": 1.3863531351089478,
+      "eval_rewards/margins": 1.4860562086105347,
+      "eval_rewards/rejected": -0.09970321506261826,
+      "eval_runtime": 12.2991,
+      "eval_samples_per_second": 2.277,
+      "eval_steps_per_second": 0.569,
+      "step": 90
+    },
+    {
+      "epoch": 3.225806451612903,
+      "grad_norm": 7.114650249481201,
+      "learning_rate": 2.471264367816092e-06,
+      "logits/chosen": -1.8133283853530884,
+      "logits/rejected": -1.8451220989227295,
+      "logps/chosen": -138.87548828125,
+      "logps/rejected": -198.13101196289062,
+      "loss": 0.1459,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.256392002105713,
+      "rewards/margins": 2.756880283355713,
+      "rewards/rejected": -0.5004884004592896,
+      "step": 100
+    },
+    {
+      "epoch": 3.5483870967741935,
+      "grad_norm": 12.849534034729004,
+      "learning_rate": 2.1839080459770117e-06,
+      "logits/chosen": -1.7662525177001953,
+      "logits/rejected": -1.7642558813095093,
+      "logps/chosen": -155.30789184570312,
+      "logps/rejected": -159.38949584960938,
+      "loss": 0.1789,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.2187705039978027,
+      "rewards/margins": 2.4316647052764893,
+      "rewards/rejected": -0.21289420127868652,
+      "step": 110
+    },
+    {
+      "epoch": 3.870967741935484,
+      "grad_norm": 7.466335296630859,
+      "learning_rate": 1.896551724137931e-06,
+      "logits/chosen": -1.8234498500823975,
+      "logits/rejected": -1.853283166885376,
+      "logps/chosen": -133.28704833984375,
+      "logps/rejected": -280.7538757324219,
+      "loss": 0.1388,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 1.9359486103057861,
+      "rewards/margins": 2.878314733505249,
+      "rewards/rejected": -0.9423659443855286,
+      "step": 120
+    },
+    {
+      "epoch": 3.870967741935484,
+      "eval_logits/chosen": -1.8311470746994019,
+      "eval_logits/rejected": -1.8493815660476685,
+      "eval_logps/chosen": -112.39806365966797,
+      "eval_logps/rejected": -160.39405822753906,
+      "eval_loss": 0.21281231939792633,
+      "eval_rewards/accuracies": 0.8571428656578064,
+      "eval_rewards/chosen": 1.7020235061645508,
+      "eval_rewards/margins": 1.9520938396453857,
+      "eval_rewards/rejected": -0.25007033348083496,
+      "eval_runtime": 12.2964,
+      "eval_samples_per_second": 2.277,
+      "eval_steps_per_second": 0.569,
+      "step": 120
+    },
+    {
+      "epoch": 4.193548387096774,
+      "grad_norm": 21.260452270507812,
+      "learning_rate": 1.6091954022988506e-06,
+      "logits/chosen": -1.7886619567871094,
+      "logits/rejected": -1.8132593631744385,
+      "logps/chosen": -152.92860412597656,
+      "logps/rejected": -252.961181640625,
+      "loss": 0.1086,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.3473799228668213,
+      "rewards/margins": 3.206756591796875,
+      "rewards/rejected": -0.8593767285346985,
+      "step": 130
+    },
+    {
+      "epoch": 4.516129032258064,
+      "grad_norm": 7.079931259155273,
+      "learning_rate": 1.3218390804597702e-06,
+      "logits/chosen": -1.8788702487945557,
+      "logits/rejected": -1.8994357585906982,
+      "logps/chosen": -124.8019790649414,
+      "logps/rejected": -295.32659912109375,
+      "loss": 0.1028,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.1898932456970215,
+      "rewards/margins": 3.444843292236328,
+      "rewards/rejected": -1.2549502849578857,
+      "step": 140
+    },
+    {
+      "epoch": 4.838709677419355,
+      "grad_norm": 12.231162071228027,
+      "learning_rate": 1.0344827586206898e-06,
+      "logits/chosen": -1.8672927618026733,
+      "logits/rejected": -1.8958708047866821,
+      "logps/chosen": -173.41452026367188,
+      "logps/rejected": -194.92208862304688,
+      "loss": 0.1349,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.1828112602233887,
+      "rewards/margins": 2.7352542877197266,
+      "rewards/rejected": -0.5524431467056274,
+      "step": 150
+    },
+    {
+      "epoch": 4.838709677419355,
+      "eval_logits/chosen": -1.8318535089492798,
+      "eval_logits/rejected": -1.8499395847320557,
+      "eval_logps/chosen": -111.63077545166016,
+      "eval_logps/rejected": -160.8158416748047,
+      "eval_loss": 0.18409298360347748,
+      "eval_rewards/accuracies": 0.8571428656578064,
+      "eval_rewards/chosen": 1.9322131872177124,
+      "eval_rewards/margins": 2.3088152408599854,
+      "eval_rewards/rejected": -0.3766022026538849,
+      "eval_runtime": 12.2951,
+      "eval_samples_per_second": 2.277,
+      "eval_steps_per_second": 0.569,
+      "step": 150
+    },
+    {
+      "epoch": 5.161290322580645,
+      "grad_norm": 9.910337448120117,
+      "learning_rate": 7.471264367816093e-07,
+      "logits/chosen": -1.8977758884429932,
+      "logits/rejected": -1.9045531749725342,
+      "logps/chosen": -156.08912658691406,
+      "logps/rejected": -190.29718017578125,
+      "loss": 0.1264,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 1.8854892253875732,
+      "rewards/margins": 2.6321709156036377,
+      "rewards/rejected": -0.7466816306114197,
+      "step": 160
+    },
+    {
+      "epoch": 5.483870967741936,
+      "grad_norm": 6.945619106292725,
+      "learning_rate": 4.5977011494252875e-07,
+      "logits/chosen": -1.8437045812606812,
+      "logits/rejected": -1.8835852146148682,
+      "logps/chosen": -158.87789916992188,
+      "logps/rejected": -304.09381103515625,
+      "loss": 0.0936,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.3152341842651367,
+      "rewards/margins": 3.6110222339630127,
+      "rewards/rejected": -1.295788049697876,
+      "step": 170
+    },
+    {
+      "epoch": 5.806451612903226,
+      "grad_norm": 12.827499389648438,
+      "learning_rate": 1.7241379310344828e-07,
+      "logits/chosen": -1.849789023399353,
+      "logits/rejected": -1.8577123880386353,
+      "logps/chosen": -192.8300018310547,
+      "logps/rejected": -179.1296844482422,
+      "loss": 0.1178,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.6929664611816406,
+      "rewards/margins": 2.7719972133636475,
+      "rewards/rejected": -0.07903085649013519,
+      "step": 180
+    },
+    {
+      "epoch": 5.806451612903226,
+      "eval_logits/chosen": -1.8318606615066528,
+      "eval_logits/rejected": -1.849859595298767,
+      "eval_logps/chosen": -111.4244613647461,
+      "eval_logps/rejected": -161.04356384277344,
+      "eval_loss": 0.17089667916297913,
+      "eval_rewards/accuracies": 0.8571428656578064,
+      "eval_rewards/chosen": 1.9941052198410034,
+      "eval_rewards/margins": 2.4390182495117188,
+      "eval_rewards/rejected": -0.4449131190776825,
+      "eval_runtime": 12.2948,
+      "eval_samples_per_second": 2.277,
+      "eval_steps_per_second": 0.569,
+      "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 sha256:6f66e0f121f8ca1d82a3291f2e3f2c92d150014d848f4ac69e4bfd03a319353b
+size 5432