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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "gate_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 sha256:9375e4299b66071d20a4b3c1af5964eb4ca451935b4545bd7dbe0c1d64dd8795
+size 671149168

checkpoint-180/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0e7ab7032ec0f26f1e8fbb743a793603f611fb31ee0c672bce05487e159905f
+size 1342555602

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": 0.008221210911870003,
+  "best_model_checkpoint": "./mistral/22-04-24-Weni-WeniGPT-Agents-Mistral-1.0.0-SFT-1.0.24-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": 18.102449417114258,
+      "learning_rate": 4.971264367816092e-06,
+      "logits/chosen": -1.8189502954483032,
+      "logits/rejected": -1.8384132385253906,
+      "logps/chosen": -183.32998657226562,
+      "logps/rejected": -217.82275390625,
+      "loss": 0.6772,
+      "rewards/accuracies": 0.3499999940395355,
+      "rewards/chosen": 0.028210829943418503,
+      "rewards/margins": 0.022311249747872353,
+      "rewards/rejected": 0.0058995820581912994,
+      "step": 10
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 20.25644302368164,
+      "learning_rate": 4.71264367816092e-06,
+      "logits/chosen": -1.8640209436416626,
+      "logits/rejected": -1.8766177892684937,
+      "logps/chosen": -152.9895477294922,
+      "logps/rejected": -246.1815948486328,
+      "loss": 0.4471,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 0.5268799662590027,
+      "rewards/margins": 0.6505464315414429,
+      "rewards/rejected": -0.12366630882024765,
+      "step": 20
+    },
+    {
+      "epoch": 0.967741935483871,
+      "grad_norm": 23.647602081298828,
+      "learning_rate": 4.42528735632184e-06,
+      "logits/chosen": -1.8179765939712524,
+      "logits/rejected": -1.8386437892913818,
+      "logps/chosen": -154.68057250976562,
+      "logps/rejected": -222.60986328125,
+      "loss": 0.2964,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 1.1595659255981445,
+      "rewards/margins": 1.5337896347045898,
+      "rewards/rejected": -0.3742235600948334,
+      "step": 30
+    },
+    {
+      "epoch": 0.967741935483871,
+      "eval_logits/chosen": -1.922228217124939,
+      "eval_logits/rejected": -1.9377918243408203,
+      "eval_logps/chosen": -190.84751892089844,
+      "eval_logps/rejected": -194.19583129882812,
+      "eval_loss": 0.25011441111564636,
+      "eval_rewards/accuracies": 0.8571428656578064,
+      "eval_rewards/chosen": 0.8715044856071472,
+      "eval_rewards/margins": 1.0091807842254639,
+      "eval_rewards/rejected": -0.13767634332180023,
+      "eval_runtime": 15.9917,
+      "eval_samples_per_second": 1.751,
+      "eval_steps_per_second": 0.438,
+      "step": 30
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 14.360973358154297,
+      "learning_rate": 4.137931034482759e-06,
+      "logits/chosen": -1.7312577962875366,
+      "logits/rejected": -1.720571517944336,
+      "logps/chosen": -133.35958862304688,
+      "logps/rejected": -174.8995361328125,
+      "loss": 0.1702,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 2.0476880073547363,
+      "rewards/margins": 2.6601643562316895,
+      "rewards/rejected": -0.6124762296676636,
+      "step": 40
+    },
+    {
+      "epoch": 1.6129032258064515,
+      "grad_norm": 7.5603814125061035,
+      "learning_rate": 3.850574712643678e-06,
+      "logits/chosen": -1.814079999923706,
+      "logits/rejected": -1.8412790298461914,
+      "logps/chosen": -135.43051147460938,
+      "logps/rejected": -218.2666473388672,
+      "loss": 0.1671,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.6564764976501465,
+      "rewards/margins": 3.553129196166992,
+      "rewards/rejected": -0.8966524004936218,
+      "step": 50
+    },
+    {
+      "epoch": 1.935483870967742,
+      "grad_norm": 1.6607310771942139,
+      "learning_rate": 3.563218390804598e-06,
+      "logits/chosen": -1.8398892879486084,
+      "logits/rejected": -1.8503402471542358,
+      "logps/chosen": -147.40121459960938,
+      "logps/rejected": -175.20462036132812,
+      "loss": 0.1148,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 2.9025120735168457,
+      "rewards/margins": 3.795964002609253,
+      "rewards/rejected": -0.8934518098831177,
+      "step": 60
+    },
+    {
+      "epoch": 1.935483870967742,
+      "eval_logits/chosen": -1.933964729309082,
+      "eval_logits/rejected": -1.9501203298568726,
+      "eval_logps/chosen": -186.97340393066406,
+      "eval_logps/rejected": -197.0532989501953,
+      "eval_loss": 0.11131088435649872,
+      "eval_rewards/accuracies": 0.8571428656578064,
+      "eval_rewards/chosen": 1.6463254690170288,
+      "eval_rewards/margins": 2.355492115020752,
+      "eval_rewards/rejected": -0.7091667056083679,
+      "eval_runtime": 15.9564,
+      "eval_samples_per_second": 1.755,
+      "eval_steps_per_second": 0.439,
+      "step": 60
+    },
+    {
+      "epoch": 2.258064516129032,
+      "grad_norm": 1.0933343172073364,
+      "learning_rate": 3.2758620689655175e-06,
+      "logits/chosen": -1.8214714527130127,
+      "logits/rejected": -1.8398475646972656,
+      "logps/chosen": -123.23341369628906,
+      "logps/rejected": -169.8323974609375,
+      "loss": 0.0958,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 3.013068914413452,
+      "rewards/margins": 3.9151065349578857,
+      "rewards/rejected": -0.9020377993583679,
+      "step": 70
+    },
+    {
+      "epoch": 2.5806451612903225,
+      "grad_norm": 1.6529628038406372,
+      "learning_rate": 2.988505747126437e-06,
+      "logits/chosen": -1.8991115093231201,
+      "logits/rejected": -1.9303562641143799,
+      "logps/chosen": -126.10279846191406,
+      "logps/rejected": -249.8067169189453,
+      "loss": 0.0542,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.2060089111328125,
+      "rewards/margins": 4.4772820472717285,
+      "rewards/rejected": -2.271273136138916,
+      "step": 80
+    },
+    {
+      "epoch": 2.903225806451613,
+      "grad_norm": 1.3197133541107178,
+      "learning_rate": 2.7011494252873567e-06,
+      "logits/chosen": -1.9221817255020142,
+      "logits/rejected": -1.926163911819458,
+      "logps/chosen": -130.5477752685547,
+      "logps/rejected": -212.64401245117188,
+      "loss": 0.0655,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.013507127761841,
+      "rewards/margins": 4.679448127746582,
+      "rewards/rejected": -1.665941596031189,
+      "step": 90
+    },
+    {
+      "epoch": 2.903225806451613,
+      "eval_logits/chosen": -1.9456537961959839,
+      "eval_logits/rejected": -1.9615535736083984,
+      "eval_logps/chosen": -184.64419555664062,
+      "eval_logps/rejected": -200.91307067871094,
+      "eval_loss": 0.04710844159126282,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 2.112164258956909,
+      "eval_rewards/margins": 3.5932810306549072,
+      "eval_rewards/rejected": -1.4811171293258667,
+      "eval_runtime": 15.9489,
+      "eval_samples_per_second": 1.756,
+      "eval_steps_per_second": 0.439,
+      "step": 90
+    },
+    {
+      "epoch": 3.225806451612903,
+      "grad_norm": 2.4013547897338867,
+      "learning_rate": 2.4137931034482762e-06,
+      "logits/chosen": -1.9110629558563232,
+      "logits/rejected": -1.9329030513763428,
+      "logps/chosen": -179.32308959960938,
+      "logps/rejected": -215.67276000976562,
+      "loss": 0.0299,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.2354037761688232,
+      "rewards/margins": 5.5415449142456055,
+      "rewards/rejected": -2.306140899658203,
+      "step": 100
+    },
+    {
+      "epoch": 3.5483870967741935,
+      "grad_norm": 0.48385706543922424,
+      "learning_rate": 2.1264367816091954e-06,
+      "logits/chosen": -1.823560357093811,
+      "logits/rejected": -1.8429410457611084,
+      "logps/chosen": -130.30816650390625,
+      "logps/rejected": -174.5900421142578,
+      "loss": 0.0258,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.3877785205841064,
+      "rewards/margins": 5.6454548835754395,
+      "rewards/rejected": -2.257676362991333,
+      "step": 110
+    },
+    {
+      "epoch": 3.870967741935484,
+      "grad_norm": 1.8376439809799194,
+      "learning_rate": 1.839080459770115e-06,
+      "logits/chosen": -1.8113921880722046,
+      "logits/rejected": -1.84001886844635,
+      "logps/chosen": -103.96414947509766,
+      "logps/rejected": -215.3662567138672,
+      "loss": 0.0279,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.767807722091675,
+      "rewards/margins": 6.228771686553955,
+      "rewards/rejected": -2.4609639644622803,
+      "step": 120
+    },
+    {
+      "epoch": 3.870967741935484,
+      "eval_logits/chosen": -1.9401109218597412,
+      "eval_logits/rejected": -1.9554412364959717,
+      "eval_logps/chosen": -182.276611328125,
+      "eval_logps/rejected": -205.226806640625,
+      "eval_loss": 0.021757256239652634,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 2.5856850147247314,
+      "eval_rewards/margins": 4.929553031921387,
+      "eval_rewards/rejected": -2.343867063522339,
+      "eval_runtime": 15.9568,
+      "eval_samples_per_second": 1.755,
+      "eval_steps_per_second": 0.439,
+      "step": 120
+    },
+    {
+      "epoch": 4.193548387096774,
+      "grad_norm": 1.051574945449829,
+      "learning_rate": 1.5517241379310346e-06,
+      "logits/chosen": -1.7715396881103516,
+      "logits/rejected": -1.800817847251892,
+      "logps/chosen": -138.27340698242188,
+      "logps/rejected": -260.06707763671875,
+      "loss": 0.0085,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.7098026275634766,
+      "rewards/margins": 6.347060203552246,
+      "rewards/rejected": -2.6372570991516113,
+      "step": 130
+    },
+    {
+      "epoch": 4.516129032258064,
+      "grad_norm": 0.16267022490501404,
+      "learning_rate": 1.2643678160919542e-06,
+      "logits/chosen": -1.9076522588729858,
+      "logits/rejected": -1.918107032775879,
+      "logps/chosen": -137.17124938964844,
+      "logps/rejected": -228.12289428710938,
+      "loss": 0.0115,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.818920135498047,
+      "rewards/margins": 6.401350498199463,
+      "rewards/rejected": -2.582429885864258,
+      "step": 140
+    },
+    {
+      "epoch": 4.838709677419355,
+      "grad_norm": 0.16799844801425934,
+      "learning_rate": 9.770114942528738e-07,
+      "logits/chosen": -1.8482967615127563,
+      "logits/rejected": -1.8852136135101318,
+      "logps/chosen": -141.45462036132812,
+      "logps/rejected": -242.177001953125,
+      "loss": 0.0103,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.5341572761535645,
+      "rewards/margins": 6.518949031829834,
+      "rewards/rejected": -3.9847919940948486,
+      "step": 150
+    },
+    {
+      "epoch": 4.838709677419355,
+      "eval_logits/chosen": -1.9384099245071411,
+      "eval_logits/rejected": -1.9533499479293823,
+      "eval_logps/chosen": -181.96482849121094,
+      "eval_logps/rejected": -207.08641052246094,
+      "eval_loss": 0.011733152903616428,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 2.648041009902954,
+      "eval_rewards/margins": 5.363831043243408,
+      "eval_rewards/rejected": -2.715789794921875,
+      "eval_runtime": 15.9585,
+      "eval_samples_per_second": 1.755,
+      "eval_steps_per_second": 0.439,
+      "step": 150
+    },
+    {
+      "epoch": 5.161290322580645,
+      "grad_norm": 1.120850682258606,
+      "learning_rate": 6.896551724137931e-07,
+      "logits/chosen": -1.8036308288574219,
+      "logits/rejected": -1.8216148614883423,
+      "logps/chosen": -128.22866821289062,
+      "logps/rejected": -178.14285278320312,
+      "loss": 0.0188,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 4.342329978942871,
+      "rewards/margins": 7.637845516204834,
+      "rewards/rejected": -3.2955150604248047,
+      "step": 160
+    },
+    {
+      "epoch": 5.483870967741936,
+      "grad_norm": 0.16266854107379913,
+      "learning_rate": 4.0229885057471266e-07,
+      "logits/chosen": -1.8207981586456299,
+      "logits/rejected": -1.833634376525879,
+      "logps/chosen": -129.1037139892578,
+      "logps/rejected": -241.2229766845703,
+      "loss": 0.0084,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.3222718238830566,
+      "rewards/margins": 6.783128261566162,
+      "rewards/rejected": -3.4608569145202637,
+      "step": 170
+    },
+    {
+      "epoch": 5.806451612903226,
+      "grad_norm": 0.10640519857406616,
+      "learning_rate": 1.1494252873563219e-07,
+      "logits/chosen": -1.8020225763320923,
+      "logits/rejected": -1.8122638463974,
+      "logps/chosen": -130.1725616455078,
+      "logps/rejected": -187.38192749023438,
+      "loss": 0.0052,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.5991992950439453,
+      "rewards/margins": 6.856170654296875,
+      "rewards/rejected": -3.2569713592529297,
+      "step": 180
+    },
+    {
+      "epoch": 5.806451612903226,
+      "eval_logits/chosen": -1.9320443868637085,
+      "eval_logits/rejected": -1.9468201398849487,
+      "eval_logps/chosen": -182.0274200439453,
+      "eval_logps/rejected": -208.50425720214844,
+      "eval_loss": 0.008221210911870003,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 2.6355252265930176,
+      "eval_rewards/margins": 5.634881496429443,
+      "eval_rewards/rejected": -2.999356508255005,
+      "eval_runtime": 15.9642,
+      "eval_samples_per_second": 1.754,
+      "eval_steps_per_second": 0.438,
+      "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:baec7ea2b41466caf7e604a031129dac45a16ab7fc0b825bc8ae51c489e5f800
+size 5432