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": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "o_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 sha256:75cb876f0ad4274e5d3679c7ff5dd13ccdc9b4c2e79095c7a76c883c76975465
+size 1342238560

checkpoint-180/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3612fff323d722c9a6b1521af18de0e28cd70e884adc36e84ad1d4e3335d81c
+size 2684732882

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": 0.004782966338098049,
+  "best_model_checkpoint": "./mistral/22-04-24-Weni-WeniGPT-Agents-Mistral-1.0.0-SFT-1.0.25-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": 24.6901912689209,
+      "learning_rate": 5e-06,
+      "logits/chosen": -1.8365566730499268,
+      "logits/rejected": -1.8444175720214844,
+      "logps/chosen": -195.56666564941406,
+      "logps/rejected": -191.41812133789062,
+      "loss": 0.653,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 0.09110366553068161,
+      "rewards/margins": 0.10920021682977676,
+      "rewards/rejected": -0.018096545711159706,
+      "step": 10
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 13.191404342651367,
+      "learning_rate": 4.71264367816092e-06,
+      "logits/chosen": -1.7314943075180054,
+      "logits/rejected": -1.766556978225708,
+      "logps/chosen": -137.64279174804688,
+      "logps/rejected": -220.5197296142578,
+      "loss": 0.3701,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 1.1793702840805054,
+      "rewards/margins": 1.4335505962371826,
+      "rewards/rejected": -0.2541801631450653,
+      "step": 20
+    },
+    {
+      "epoch": 0.967741935483871,
+      "grad_norm": 20.181856155395508,
+      "learning_rate": 4.42528735632184e-06,
+      "logits/chosen": -1.8526036739349365,
+      "logits/rejected": -1.86077880859375,
+      "logps/chosen": -121.78877258300781,
+      "logps/rejected": -151.2501678466797,
+      "loss": 0.225,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 1.4271174669265747,
+      "rewards/margins": 1.875509262084961,
+      "rewards/rejected": -0.4483918249607086,
+      "step": 30
+    },
+    {
+      "epoch": 0.967741935483871,
+      "eval_logits/chosen": -1.9326385259628296,
+      "eval_logits/rejected": -1.9565868377685547,
+      "eval_logps/chosen": -123.71134185791016,
+      "eval_logps/rejected": -215.0025634765625,
+      "eval_loss": 0.22270560264587402,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 2.6680667400360107,
+      "eval_rewards/margins": 3.676541566848755,
+      "eval_rewards/rejected": -1.008474588394165,
+      "eval_runtime": 15.7165,
+      "eval_samples_per_second": 1.782,
+      "eval_steps_per_second": 0.445,
+      "step": 30
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 1.0404773950576782,
+      "learning_rate": 4.137931034482759e-06,
+      "logits/chosen": -1.9101307392120361,
+      "logits/rejected": -1.9370834827423096,
+      "logps/chosen": -146.01133728027344,
+      "logps/rejected": -237.4972686767578,
+      "loss": 0.0848,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.0706539154052734,
+      "rewards/margins": 5.080114364624023,
+      "rewards/rejected": -2.009460926055908,
+      "step": 40
+    },
+    {
+      "epoch": 1.6129032258064515,
+      "grad_norm": 17.344457626342773,
+      "learning_rate": 3.850574712643678e-06,
+      "logits/chosen": -1.8972657918930054,
+      "logits/rejected": -1.9069604873657227,
+      "logps/chosen": -195.85150146484375,
+      "logps/rejected": -158.05677795410156,
+      "loss": 0.0755,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 3.0010573863983154,
+      "rewards/margins": 4.110104560852051,
+      "rewards/rejected": -1.1090469360351562,
+      "step": 50
+    },
+    {
+      "epoch": 1.935483870967742,
+      "grad_norm": 0.7190752029418945,
+      "learning_rate": 3.563218390804598e-06,
+      "logits/chosen": -1.8297414779663086,
+      "logits/rejected": -1.857456922531128,
+      "logps/chosen": -144.957275390625,
+      "logps/rejected": -232.25784301757812,
+      "loss": 0.0853,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 3.4944889545440674,
+      "rewards/margins": 5.610640525817871,
+      "rewards/rejected": -2.116152286529541,
+      "step": 60
+    },
+    {
+      "epoch": 1.935483870967742,
+      "eval_logits/chosen": -1.9170362949371338,
+      "eval_logits/rejected": -1.9400348663330078,
+      "eval_logps/chosen": -118.40864562988281,
+      "eval_logps/rejected": -221.06422424316406,
+      "eval_loss": 0.10952840745449066,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 3.7286033630371094,
+      "eval_rewards/margins": 5.949405193328857,
+      "eval_rewards/rejected": -2.220801830291748,
+      "eval_runtime": 15.4022,
+      "eval_samples_per_second": 1.818,
+      "eval_steps_per_second": 0.454,
+      "step": 60
+    },
+    {
+      "epoch": 2.258064516129032,
+      "grad_norm": 6.895229339599609,
+      "learning_rate": 3.2758620689655175e-06,
+      "logits/chosen": -1.7604904174804688,
+      "logits/rejected": -1.7763350009918213,
+      "logps/chosen": -94.25442504882812,
+      "logps/rejected": -200.06292724609375,
+      "loss": 0.0336,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.892274856567383,
+      "rewards/margins": 7.140706539154053,
+      "rewards/rejected": -3.248431444168091,
+      "step": 70
+    },
+    {
+      "epoch": 2.5806451612903225,
+      "grad_norm": 3.1107871532440186,
+      "learning_rate": 2.988505747126437e-06,
+      "logits/chosen": -1.773847222328186,
+      "logits/rejected": -1.7859563827514648,
+      "logps/chosen": -134.7067108154297,
+      "logps/rejected": -175.28102111816406,
+      "loss": 0.0191,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 3.6734061241149902,
+      "rewards/margins": 6.411807060241699,
+      "rewards/rejected": -2.738400936126709,
+      "step": 80
+    },
+    {
+      "epoch": 2.903225806451613,
+      "grad_norm": 0.4654656946659088,
+      "learning_rate": 2.7011494252873567e-06,
+      "logits/chosen": -1.8632606267929077,
+      "logits/rejected": -1.8870786428451538,
+      "logps/chosen": -152.00164794921875,
+      "logps/rejected": -194.2272186279297,
+      "loss": 0.0285,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 3.7533652782440186,
+      "rewards/margins": 6.942251682281494,
+      "rewards/rejected": -3.1888861656188965,
+      "step": 90
+    },
+    {
+      "epoch": 2.903225806451613,
+      "eval_logits/chosen": -1.9063053131103516,
+      "eval_logits/rejected": -1.930100679397583,
+      "eval_logps/chosen": -116.32177734375,
+      "eval_logps/rejected": -229.86549377441406,
+      "eval_loss": 0.05446601286530495,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 4.145977973937988,
+      "eval_rewards/margins": 8.12703800201416,
+      "eval_rewards/rejected": -3.9810593128204346,
+      "eval_runtime": 15.401,
+      "eval_samples_per_second": 1.818,
+      "eval_steps_per_second": 0.455,
+      "step": 90
+    },
+    {
+      "epoch": 3.225806451612903,
+      "grad_norm": 0.023089677095413208,
+      "learning_rate": 2.4137931034482762e-06,
+      "logits/chosen": -1.8187129497528076,
+      "logits/rejected": -1.8321533203125,
+      "logps/chosen": -118.27799987792969,
+      "logps/rejected": -238.4324493408203,
+      "loss": 0.0031,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.572004318237305,
+      "rewards/margins": 9.180875778198242,
+      "rewards/rejected": -4.608872413635254,
+      "step": 100
+    },
+    {
+      "epoch": 3.5483870967741935,
+      "grad_norm": 0.9019374251365662,
+      "learning_rate": 2.1264367816091954e-06,
+      "logits/chosen": -1.903515100479126,
+      "logits/rejected": -1.9107078313827515,
+      "logps/chosen": -154.8245849609375,
+      "logps/rejected": -195.23399353027344,
+      "loss": 0.0127,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.906761646270752,
+      "rewards/margins": 8.078901290893555,
+      "rewards/rejected": -5.172140121459961,
+      "step": 110
+    },
+    {
+      "epoch": 3.870967741935484,
+      "grad_norm": 0.11791550368070602,
+      "learning_rate": 1.839080459770115e-06,
+      "logits/chosen": -1.7719767093658447,
+      "logits/rejected": -1.7978557348251343,
+      "logps/chosen": -135.73764038085938,
+      "logps/rejected": -233.47396850585938,
+      "loss": 0.001,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.7881596088409424,
+      "rewards/margins": 10.058608055114746,
+      "rewards/rejected": -6.270449161529541,
+      "step": 120
+    },
+    {
+      "epoch": 3.870967741935484,
+      "eval_logits/chosen": -1.8902080059051514,
+      "eval_logits/rejected": -1.9141491651535034,
+      "eval_logps/chosen": -116.14888763427734,
+      "eval_logps/rejected": -235.0476531982422,
+      "eval_loss": 0.04676542058587074,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 4.18055534362793,
+      "eval_rewards/margins": 9.198049545288086,
+      "eval_rewards/rejected": -5.01749324798584,
+      "eval_runtime": 15.4024,
+      "eval_samples_per_second": 1.818,
+      "eval_steps_per_second": 0.454,
+      "step": 120
+    },
+    {
+      "epoch": 4.193548387096774,
+      "grad_norm": 0.062105003744363785,
+      "learning_rate": 1.5517241379310346e-06,
+      "logits/chosen": -1.7840442657470703,
+      "logits/rejected": -1.7999883890151978,
+      "logps/chosen": -116.44026184082031,
+      "logps/rejected": -252.85220336914062,
+      "loss": 0.0192,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.862762451171875,
+      "rewards/margins": 9.177450180053711,
+      "rewards/rejected": -6.314688205718994,
+      "step": 130
+    },
+    {
+      "epoch": 4.516129032258064,
+      "grad_norm": 0.3371919095516205,
+      "learning_rate": 1.2643678160919542e-06,
+      "logits/chosen": -1.7637265920639038,
+      "logits/rejected": -1.7790952920913696,
+      "logps/chosen": -149.11972045898438,
+      "logps/rejected": -200.7391357421875,
+      "loss": 0.0156,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 1.933764100074768,
+      "rewards/margins": 7.311190128326416,
+      "rewards/rejected": -5.377426624298096,
+      "step": 140
+    },
+    {
+      "epoch": 4.838709677419355,
+      "grad_norm": 0.4724487066268921,
+      "learning_rate": 9.770114942528738e-07,
+      "logits/chosen": -1.7254791259765625,
+      "logits/rejected": -1.754163384437561,
+      "logps/chosen": -142.09568786621094,
+      "logps/rejected": -264.6880798339844,
+      "loss": 0.0021,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.6306958198547363,
+      "rewards/margins": 9.091299057006836,
+      "rewards/rejected": -5.460603713989258,
+      "step": 150
+    },
+    {
+      "epoch": 4.838709677419355,
+      "eval_logits/chosen": -1.881463885307312,
+      "eval_logits/rejected": -1.9056099653244019,
+      "eval_logps/chosen": -117.07276916503906,
+      "eval_logps/rejected": -239.6072235107422,
+      "eval_loss": 0.00868917815387249,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 3.995779514312744,
+      "eval_rewards/margins": 9.925186157226562,
+      "eval_rewards/rejected": -5.929406642913818,
+      "eval_runtime": 15.4035,
+      "eval_samples_per_second": 1.818,
+      "eval_steps_per_second": 0.454,
+      "step": 150
+    },
+    {
+      "epoch": 5.161290322580645,
+      "grad_norm": 0.4406607449054718,
+      "learning_rate": 6.896551724137931e-07,
+      "logits/chosen": -1.8259941339492798,
+      "logits/rejected": -1.8320337533950806,
+      "logps/chosen": -178.92930603027344,
+      "logps/rejected": -274.9721984863281,
+      "loss": 0.0028,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.2369651794433594,
+      "rewards/margins": 9.267016410827637,
+      "rewards/rejected": -7.030051231384277,
+      "step": 160
+    },
+    {
+      "epoch": 5.483870967741936,
+      "grad_norm": 0.02007269859313965,
+      "learning_rate": 4.0229885057471266e-07,
+      "logits/chosen": -1.7874090671539307,
+      "logits/rejected": -1.8095813989639282,
+      "logps/chosen": -149.6767120361328,
+      "logps/rejected": -237.3863067626953,
+      "loss": 0.0006,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.129965782165527,
+      "rewards/margins": 11.051237106323242,
+      "rewards/rejected": -6.921273708343506,
+      "step": 170
+    },
+    {
+      "epoch": 5.806451612903226,
+      "grad_norm": 0.5593944787979126,
+      "learning_rate": 1.1494252873563219e-07,
+      "logits/chosen": -1.8051351308822632,
+      "logits/rejected": -1.8224855661392212,
+      "logps/chosen": -168.2032928466797,
+      "logps/rejected": -221.9829864501953,
+      "loss": 0.0014,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.834609270095825,
+      "rewards/margins": 9.291410446166992,
+      "rewards/rejected": -6.456801414489746,
+      "step": 180
+    },
+    {
+      "epoch": 5.806451612903226,
+      "eval_logits/chosen": -1.8786267042160034,
+      "eval_logits/rejected": -1.9027243852615356,
+      "eval_logps/chosen": -117.46734619140625,
+      "eval_logps/rejected": -240.9935760498047,
+      "eval_loss": 0.004782966338098049,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 3.9168648719787598,
+      "eval_rewards/margins": 10.123543739318848,
+      "eval_rewards/rejected": -6.206678867340088,
+      "eval_runtime": 15.4023,
+      "eval_samples_per_second": 1.818,
+      "eval_steps_per_second": 0.454,
+      "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:b64e66ea1f05cb0d2ed18c0eafe68e7039e2b9fa4f6c712b2f68b8fb7d83e353
+size 5432