Upload folder using huggingface_hub

README.md

@@ -1,82 +1,91 @@
 ---
-library_name: peft
+license: mit
+library_name: "trl"
 tags:
-- trl
-- dpo
 - DPO
 - WeniGPT
-- generated_from_trainer
 base_model: Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged
 model-index:
-- name: WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.8-DPO
+- name: Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.8-DPO
   results: []
+language: ['pt']
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
+# Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.8-DPO
 
-# WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.8-DPO
+This model is a fine-tuned version of [Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged] on the dataset Weni/wenigpt-agent-dpo-1.0.0 with the DPO trainer. It is part of the WeniGPT project for [Weni](https://weni.ai/).
+Description: Experiment on DPO with other hyperparameters and best SFT model of WeniGPT
 
-This model is a fine-tuned version of [Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged](https://huggingface.co/Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2005
-- Rewards/chosen: 1.7621
-- Rewards/rejected: -0.7248
-- Rewards/accuracies: 1.0
-- Rewards/margins: 2.4869
-- Logps/rejected: -271.5133
-- Logps/chosen: -102.9727
-- Logits/rejected: -1.8958
-- Logits/chosen: -1.8013
+{'eval_loss': 0.20048503577709198, 'eval_runtime': 9.9205, 'eval_samples_per_second': 2.822, 'eval_steps_per_second': 0.706, 'eval_rewards/chosen': 1.7620631456375122, 'eval_rewards/rejected': -0.7248173952102661, 'eval_rewards/accuracies': 1.0, 'eval_rewards/margins': 2.4868807792663574, 'eval_logps/rejected': -271.5132751464844, 'eval_logps/chosen': -102.97270202636719, 'eval_logits/rejected': -1.8957865238189697, 'eval_logits/chosen': -1.8012962341308594, 'epoch': 5.81}
 
-## Model description
+## Intended uses & limitations
 
-More information needed
+This model has not been trained to avoid specific intructions. 
 
-## Intended uses & limitations
+## Training procedure
 
-More information needed
+Finetuning was done on the model Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged with the following prompt:
 
-## Training and evaluation data
+```
+---------------------
+System_prompt:
+Agora você se chama {name}, você é {occupation} e seu objetivo é {chatbot_goal}. O adjetivo que mais define a sua personalidade é {adjective} e você se comporta da seguinte forma:
+{instructions_formatted}
 
-More information needed
+{context_statement}
+
+Lista de requisitos:
+ - Responda de forma natural, mas nunca fale sobre um assunto fora do contexto.
+ - Nunca traga informações do seu próprio conhecimento.
+ - Repito é crucial que você responda usando apenas informações do contexto.
+ - Nunca mencione o contexto fornecido.
+ - Nunca mencione a pergunta fornecida.
+ - Gere a resposta mais útil possível para a pergunta usando informações do conexto acima.
+ - Nunca elabore sobre o porque e como você fez a tarefa, apenas responda.
 
-## Training procedure
+
+---------------------
+
+```
 
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-06
-- train_batch_size: 1
-- eval_batch_size: 1
-- seed: 42
-- distributed_type: multi-GPU
-- num_devices: 4
+- per_device_train_batch_size: 1
+- per_device_eval_batch_size: 1
 - gradient_accumulation_steps: 2
+- num_gpus: 4
 - total_train_batch_size: 8
-- total_eval_batch_size: 4
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_ratio: 0.03
-- training_steps: 180
-- mixed_precision_training: Native AMP
+- optimizer: AdamW
+- lr_scheduler_type: cosine
+- num_steps: 180
+- quantization_type: bitsandbytes
+- LoRA: ("\n  - bits: 4\n  - use_exllama: True\n  - device_map: auto\n  - use_cache: False\n  - lora_r: 8\n  - lora_alpha: 16\n  - lora_dropout: 0.05\n  - bias: none\n  - target_modules: ['v_proj', 'q_proj']\n  - task_type: CAUSAL_LM",)
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
-|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
-| 0.5477        | 0.97  | 30   | 0.4843          | 0.4718         | -0.1109          | 0.8571             | 0.5827          | -269.4668      | -107.2735    | -1.8863         | -1.7949       |
-| 0.3542        | 1.94  | 60   | 0.3440          | 0.9609         | -0.2516          | 1.0                | 1.2125          | -269.9360      | -105.6431    | -1.8903         | -1.7979       |
-| 0.2892        | 2.9   | 90   | 0.2756          | 1.3199         | -0.4182          | 1.0                | 1.7381          | -270.4914      | -104.4467    | -1.8928         | -1.7995       |
-| 0.1858        | 3.87  | 120  | 0.2327          | 1.6010         | -0.5696          | 1.0                | 2.1706          | -270.9958      | -103.5094    | -1.8947         | -1.8008       |
-| 0.1811        | 4.84  | 150  | 0.2076          | 1.7245         | -0.6925          | 1.0                | 2.4170          | -271.4054      | -103.0979    | -1.8954         | -1.8010       |
-| 0.2065        | 5.81  | 180  | 0.2005          | 1.7621         | -0.7248          | 1.0                | 2.4869          | -271.5133      | -102.9727    | -1.8958         | -1.8013       |
-
-
 ### Framework versions
 
-- PEFT 0.10.0
-- Transformers 4.38.2
-- Pytorch 2.1.0+cu118
-- Datasets 2.18.0
-- Tokenizers 0.15.2
+- transformers==4.38.2
+- datasets==2.18.0
+- peft==0.10.0
+- safetensors==0.4.2
+- evaluate==0.4.1
+- bitsandbytes==0.43
+- huggingface_hub==0.22.2
+- seqeval==1.2.2
+- optimum==1.18.1
+- auto-gptq==0.7.1
+- gpustat==1.1.1
+- deepspeed==0.14.0
+- wandb==0.16.6
+- trl==0.8.1
+- accelerate==0.29.2
+- coloredlogs==15.0.1
+- traitlets==5.14.2
+- autoawq@https://github.com/casper-hansen/AutoAWQ/releases/download/v0.2.4/autoawq-0.2.4+cu118-cp310-cp310-linux_x86_64.whl
+
+### Hardware
+- Cloud provided: runpod.io

checkpoint-180/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: Weni/WeniGPT-Agents-Mistral-1.0.6-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 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Weni/WeniGPT-Agents-Mistral-1.0.6-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": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "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:b8e04b6837c63d0518aab621c468ca20a97c1e37060cf8cdc4141c1bbef0825b
+size 13648432

checkpoint-180/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:951bedc053daaa58558d748fea1f931a54c2182686f0138e07b71ea7fd47fe80
+size 27370618

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 sha256:74f15868c98428b757deb41ceef3036d052c50d320ff1d3c76314d699ef0babc
+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": 0.20048503577709198,
+  "best_model_checkpoint": "./mistral/20-04-24-Weni-WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.8-DPO_Experiment on DPO with other hyperparameters and best SFT model of WeniGPT-2_max_steps-180_batch_8_2024-04-20_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": 0.32,
+      "grad_norm": 27.100269317626953,
+      "learning_rate": 5e-06,
+      "logits/chosen": -1.7583906650543213,
+      "logits/rejected": -1.8312015533447266,
+      "logps/chosen": -173.15086364746094,
+      "logps/rejected": -269.08062744140625,
+      "loss": 0.69,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 0.01006038673222065,
+      "rewards/margins": 0.011446094140410423,
+      "rewards/rejected": -0.0013857081066817045,
+      "step": 10
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": NaN,
+      "learning_rate": 4.741379310344828e-06,
+      "logits/chosen": -1.7850843667984009,
+      "logits/rejected": -1.81415593624115,
+      "logps/chosen": -196.91897583007812,
+      "logps/rejected": -205.7848663330078,
+      "loss": 0.6264,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": 0.17185011506080627,
+      "rewards/margins": 0.14982673525810242,
+      "rewards/rejected": 0.022023344412446022,
+      "step": 20
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 23.862794876098633,
+      "learning_rate": 4.454022988505747e-06,
+      "logits/chosen": -1.7745271921157837,
+      "logits/rejected": -1.8100026845932007,
+      "logps/chosen": -197.96493530273438,
+      "logps/rejected": -184.85069274902344,
+      "loss": 0.5477,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 0.3463248908519745,
+      "rewards/margins": 0.35388293862342834,
+      "rewards/rejected": -0.007558024022728205,
+      "step": 30
+    },
+    {
+      "epoch": 0.97,
+      "eval_logits/chosen": -1.7948826551437378,
+      "eval_logits/rejected": -1.8862664699554443,
+      "eval_logps/chosen": -107.27352142333984,
+      "eval_logps/rejected": -269.4668273925781,
+      "eval_loss": 0.48426297307014465,
+      "eval_rewards/accuracies": 0.8571428656578064,
+      "eval_rewards/chosen": 0.4718170166015625,
+      "eval_rewards/margins": 0.5826946496963501,
+      "eval_rewards/rejected": -0.1108776405453682,
+      "eval_runtime": 9.9214,
+      "eval_samples_per_second": 2.822,
+      "eval_steps_per_second": 0.706,
+      "step": 30
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 33.898590087890625,
+      "learning_rate": 4.166666666666667e-06,
+      "logits/chosen": -1.7890510559082031,
+      "logits/rejected": -1.8475368022918701,
+      "logps/chosen": -193.50033569335938,
+      "logps/rejected": -206.31741333007812,
+      "loss": 0.4661,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 0.4587056636810303,
+      "rewards/margins": 0.5034217238426208,
+      "rewards/rejected": -0.04471604526042938,
+      "step": 40
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 29.36012840270996,
+      "learning_rate": 3.8793103448275865e-06,
+      "logits/chosen": -1.804456353187561,
+      "logits/rejected": -1.8586517572402954,
+      "logps/chosen": -136.4575958251953,
+      "logps/rejected": -212.65231323242188,
+      "loss": 0.4418,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.8421177864074707,
+      "rewards/margins": 0.988998293876648,
+      "rewards/rejected": -0.146880641579628,
+      "step": 50
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 25.15074348449707,
+      "learning_rate": 3.5919540229885056e-06,
+      "logits/chosen": -1.8009055852890015,
+      "logits/rejected": -1.8550602197647095,
+      "logps/chosen": -145.14044189453125,
+      "logps/rejected": -265.5760192871094,
+      "loss": 0.3542,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.742743730545044,
+      "rewards/margins": 1.1478015184402466,
+      "rewards/rejected": -0.4050576686859131,
+      "step": 60
+    },
+    {
+      "epoch": 1.94,
+      "eval_logits/chosen": -1.7979233264923096,
+      "eval_logits/rejected": -1.8902829885482788,
+      "eval_logps/chosen": -105.64314270019531,
+      "eval_logps/rejected": -269.93597412109375,
+      "eval_loss": 0.344027042388916,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 0.96092689037323,
+      "eval_rewards/margins": 1.212537407875061,
+      "eval_rewards/rejected": -0.2516104578971863,
+      "eval_runtime": 9.9306,
+      "eval_samples_per_second": 2.82,
+      "eval_steps_per_second": 0.705,
+      "step": 60
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 16.264854431152344,
+      "learning_rate": 3.3045977011494256e-06,
+      "logits/chosen": -1.8283793926239014,
+      "logits/rejected": -1.8581088781356812,
+      "logps/chosen": -245.49520874023438,
+      "logps/rejected": -240.85055541992188,
+      "loss": 0.3242,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 0.9433773756027222,
+      "rewards/margins": 0.9048371315002441,
+      "rewards/rejected": 0.0385403148829937,
+      "step": 70
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 18.855249404907227,
+      "learning_rate": 3.017241379310345e-06,
+      "logits/chosen": -1.912719964981079,
+      "logits/rejected": -1.9267578125,
+      "logps/chosen": -184.6862030029297,
+      "logps/rejected": -150.09349060058594,
+      "loss": 0.3063,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 0.9958856701850891,
+      "rewards/margins": 1.2241456508636475,
+      "rewards/rejected": -0.2282601296901703,
+      "step": 80
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 18.644786834716797,
+      "learning_rate": 2.729885057471265e-06,
+      "logits/chosen": -1.8041893243789673,
+      "logits/rejected": -1.8382984399795532,
+      "logps/chosen": -122.60682678222656,
+      "logps/rejected": -190.001220703125,
+      "loss": 0.2892,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 1.1825361251831055,
+      "rewards/margins": 1.4003632068634033,
+      "rewards/rejected": -0.2178269922733307,
+      "step": 90
+    },
+    {
+      "epoch": 2.9,
+      "eval_logits/chosen": -1.799451470375061,
+      "eval_logits/rejected": -1.8927640914916992,
+      "eval_logps/chosen": -104.44667053222656,
+      "eval_logps/rejected": -270.4913635253906,
+      "eval_loss": 0.275594562292099,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 1.319871187210083,
+      "eval_rewards/margins": 1.7381019592285156,
+      "eval_rewards/rejected": -0.4182307720184326,
+      "eval_runtime": 9.9268,
+      "eval_samples_per_second": 2.821,
+      "eval_steps_per_second": 0.705,
+      "step": 90
+    },
+    {
+      "epoch": 3.23,
+      "grad_norm": 12.1031494140625,
+      "learning_rate": 2.4425287356321844e-06,
+      "logits/chosen": -1.775871992111206,
+      "logits/rejected": -1.8304792642593384,
+      "logps/chosen": -152.18081665039062,
+      "logps/rejected": -200.20614624023438,
+      "loss": 0.2436,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 1.6016706228256226,
+      "rewards/margins": 1.9426767826080322,
+      "rewards/rejected": -0.3410060703754425,
+      "step": 100
+    },
+    {
+      "epoch": 3.55,
+      "grad_norm": 15.167205810546875,
+      "learning_rate": 2.1551724137931035e-06,
+      "logits/chosen": -1.7159019708633423,
+      "logits/rejected": -1.8178460597991943,
+      "logps/chosen": -141.62574768066406,
+      "logps/rejected": -293.3615417480469,
+      "loss": 0.2007,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 1.7044894695281982,
+      "rewards/margins": 2.599806308746338,
+      "rewards/rejected": -0.8953168988227844,
+      "step": 110
+    },
+    {
+      "epoch": 3.87,
+      "grad_norm": 15.17064094543457,
+      "learning_rate": 1.8678160919540231e-06,
+      "logits/chosen": -1.8141412734985352,
+      "logits/rejected": -1.881119728088379,
+      "logps/chosen": -113.6499252319336,
+      "logps/rejected": -246.5932159423828,
+      "loss": 0.1858,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 1.5452262163162231,
+      "rewards/margins": 2.416726589202881,
+      "rewards/rejected": -0.8715003728866577,
+      "step": 120
+    },
+    {
+      "epoch": 3.87,
+      "eval_logits/chosen": -1.8007782697677612,
+      "eval_logits/rejected": -1.8947203159332275,
+      "eval_logps/chosen": -103.50943756103516,
+      "eval_logps/rejected": -270.995849609375,
+      "eval_loss": 0.232688769698143,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 1.60104238986969,
+      "eval_rewards/margins": 2.170628309249878,
+      "eval_rewards/rejected": -0.5695859789848328,
+      "eval_runtime": 9.9278,
+      "eval_samples_per_second": 2.82,
+      "eval_steps_per_second": 0.705,
+      "step": 120
+    },
+    {
+      "epoch": 4.19,
+      "grad_norm": 9.949838638305664,
+      "learning_rate": 1.5804597701149427e-06,
+      "logits/chosen": -1.7835006713867188,
+      "logits/rejected": -1.8571557998657227,
+      "logps/chosen": -184.62295532226562,
+      "logps/rejected": -249.9383544921875,
+      "loss": 0.2255,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 1.7701829671859741,
+      "rewards/margins": 2.433096408843994,
+      "rewards/rejected": -0.6629135012626648,
+      "step": 130
+    },
+    {
+      "epoch": 4.52,
+      "grad_norm": 10.975859642028809,
+      "learning_rate": 1.2931034482758623e-06,
+      "logits/chosen": -1.8018295764923096,
+      "logits/rejected": -1.861405372619629,
+      "logps/chosen": -129.60470581054688,
+      "logps/rejected": -241.1371612548828,
+      "loss": 0.1645,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 1.7705247402191162,
+      "rewards/margins": 2.5183393955230713,
+      "rewards/rejected": -0.7478145956993103,
+      "step": 140
+    },
+    {
+      "epoch": 4.84,
+      "grad_norm": 12.812362670898438,
+      "learning_rate": 1.0057471264367817e-06,
+      "logits/chosen": -1.82421875,
+      "logits/rejected": -1.8583450317382812,
+      "logps/chosen": -201.688232421875,
+      "logps/rejected": -229.2138671875,
+      "loss": 0.1811,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 1.555559515953064,
+      "rewards/margins": 2.371445417404175,
+      "rewards/rejected": -0.8158857226371765,
+      "step": 150
+    },
+    {
+      "epoch": 4.84,
+      "eval_logits/chosen": -1.8010179996490479,
+      "eval_logits/rejected": -1.8953866958618164,
+      "eval_logps/chosen": -103.09788513183594,
+      "eval_logps/rejected": -271.4054260253906,
+      "eval_loss": 0.2075897753238678,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 1.7245090007781982,
+      "eval_rewards/margins": 2.4169600009918213,
+      "eval_rewards/rejected": -0.6924509406089783,
+      "eval_runtime": 9.9225,
+      "eval_samples_per_second": 2.822,
+      "eval_steps_per_second": 0.705,
+      "step": 150
+    },
+    {
+      "epoch": 5.16,
+      "grad_norm": 23.902271270751953,
+      "learning_rate": 7.183908045977011e-07,
+      "logits/chosen": -1.779550313949585,
+      "logits/rejected": -1.8266932964324951,
+      "logps/chosen": -145.10794067382812,
+      "logps/rejected": -194.99497985839844,
+      "loss": 0.182,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 1.5958274602890015,
+      "rewards/margins": 2.0814337730407715,
+      "rewards/rejected": -0.48560643196105957,
+      "step": 160
+    },
+    {
+      "epoch": 5.48,
+      "grad_norm": 25.761934280395508,
+      "learning_rate": 4.3103448275862073e-07,
+      "logits/chosen": -1.8421766757965088,
+      "logits/rejected": -1.8947057723999023,
+      "logps/chosen": -162.1377716064453,
+      "logps/rejected": -238.0432586669922,
+      "loss": 0.1725,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 1.420178771018982,
+      "rewards/margins": 2.578826427459717,
+      "rewards/rejected": -1.1586474180221558,
+      "step": 170
+    },
+    {
+      "epoch": 5.81,
+      "grad_norm": 22.726856231689453,
+      "learning_rate": 1.4367816091954023e-07,
+      "logits/chosen": -1.8062843084335327,
+      "logits/rejected": -1.8762874603271484,
+      "logps/chosen": -147.4128875732422,
+      "logps/rejected": -218.22811889648438,
+      "loss": 0.2065,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 1.3966058492660522,
+      "rewards/margins": 2.1112942695617676,
+      "rewards/rejected": -0.7146884202957153,
+      "step": 180
+    },
+    {
+      "epoch": 5.81,
+      "eval_logits/chosen": -1.8012962341308594,
+      "eval_logits/rejected": -1.8957865238189697,
+      "eval_logps/chosen": -102.97270202636719,
+      "eval_logps/rejected": -271.5132751464844,
+      "eval_loss": 0.20048503577709198,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 1.7620631456375122,
+      "eval_rewards/margins": 2.4868807792663574,
+      "eval_rewards/rejected": -0.7248173952102661,
+      "eval_runtime": 9.9214,
+      "eval_samples_per_second": 2.822,
+      "eval_steps_per_second": 0.706,
+      "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:ddb616965f243d067df3d0989701364bac00b0a89b6fb3bed8e9fc7ddb137e5f
+size 5304

checkpoint-90/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: Weni/WeniGPT-Agents-Mistral-1.0.6-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-90/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Weni/WeniGPT-Agents-Mistral-1.0.6-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": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-90/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dedcf22ffa9bcd052c69a81ed2bfaed4a6dc22901a7c2fdace542f0cfb46744
+size 13648432

checkpoint-90/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0425b4a2d9194f6dec707e6b3e109d1a9291b736fce3a4e87cb806968dfe249c
+size 27370618

checkpoint-90/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:418a5f105ae834c3075024076916b2a9475918fe034c12d0dd5b6d91f1aba467
+size 15024

checkpoint-90/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e07ace389d24bc1307b74f42a1e7b8f0117b0db853e2df64ff3f15cb92916a2
+size 15024

checkpoint-90/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da6a990f346d7014dffb28fa2bc7d3b890bd3c53712503fce3656da48d3d6e50
+size 15024

checkpoint-90/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e95f356ca38179b05993f55daece0223e96fa10b9a1b9ea2102a739211333f63
+size 15024

checkpoint-90/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e83e76d56bab031e020dbb8db0e99d785019f52c86d705dd2275cde1e9302a8d
+size 1064

checkpoint-90/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-90/tokenizer.model

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

checkpoint-90/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-90/trainer_state.json

@@ -0,0 +1,204 @@
+{
+  "best_metric": 0.275594562292099,
+  "best_model_checkpoint": "./mistral/20-04-24-Weni-WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.8-DPO_Experiment on DPO with other hyperparameters and best SFT model of WeniGPT-2_max_steps-180_batch_8_2024-04-20_ppid_9/checkpoint-90",
+  "epoch": 2.903225806451613,
+  "eval_steps": 30,
+  "global_step": 90,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32,
+      "grad_norm": 27.100269317626953,
+      "learning_rate": 5e-06,
+      "logits/chosen": -1.7583906650543213,
+      "logits/rejected": -1.8312015533447266,
+      "logps/chosen": -173.15086364746094,
+      "logps/rejected": -269.08062744140625,
+      "loss": 0.69,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 0.01006038673222065,
+      "rewards/margins": 0.011446094140410423,
+      "rewards/rejected": -0.0013857081066817045,
+      "step": 10
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": NaN,
+      "learning_rate": 4.741379310344828e-06,
+      "logits/chosen": -1.7850843667984009,
+      "logits/rejected": -1.81415593624115,
+      "logps/chosen": -196.91897583007812,
+      "logps/rejected": -205.7848663330078,
+      "loss": 0.6264,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": 0.17185011506080627,
+      "rewards/margins": 0.14982673525810242,
+      "rewards/rejected": 0.022023344412446022,
+      "step": 20
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 23.862794876098633,
+      "learning_rate": 4.454022988505747e-06,
+      "logits/chosen": -1.7745271921157837,
+      "logits/rejected": -1.8100026845932007,
+      "logps/chosen": -197.96493530273438,
+      "logps/rejected": -184.85069274902344,
+      "loss": 0.5477,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 0.3463248908519745,
+      "rewards/margins": 0.35388293862342834,
+      "rewards/rejected": -0.007558024022728205,
+      "step": 30
+    },
+    {
+      "epoch": 0.97,
+      "eval_logits/chosen": -1.7948826551437378,
+      "eval_logits/rejected": -1.8862664699554443,
+      "eval_logps/chosen": -107.27352142333984,
+      "eval_logps/rejected": -269.4668273925781,
+      "eval_loss": 0.48426297307014465,
+      "eval_rewards/accuracies": 0.8571428656578064,
+      "eval_rewards/chosen": 0.4718170166015625,
+      "eval_rewards/margins": 0.5826946496963501,
+      "eval_rewards/rejected": -0.1108776405453682,
+      "eval_runtime": 9.9214,
+      "eval_samples_per_second": 2.822,
+      "eval_steps_per_second": 0.706,
+      "step": 30
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 33.898590087890625,
+      "learning_rate": 4.166666666666667e-06,
+      "logits/chosen": -1.7890510559082031,
+      "logits/rejected": -1.8475368022918701,
+      "logps/chosen": -193.50033569335938,
+      "logps/rejected": -206.31741333007812,
+      "loss": 0.4661,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 0.4587056636810303,
+      "rewards/margins": 0.5034217238426208,
+      "rewards/rejected": -0.04471604526042938,
+      "step": 40
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 29.36012840270996,
+      "learning_rate": 3.8793103448275865e-06,
+      "logits/chosen": -1.804456353187561,
+      "logits/rejected": -1.8586517572402954,
+      "logps/chosen": -136.4575958251953,
+      "logps/rejected": -212.65231323242188,
+      "loss": 0.4418,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.8421177864074707,
+      "rewards/margins": 0.988998293876648,
+      "rewards/rejected": -0.146880641579628,
+      "step": 50
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 25.15074348449707,
+      "learning_rate": 3.5919540229885056e-06,
+      "logits/chosen": -1.8009055852890015,
+      "logits/rejected": -1.8550602197647095,
+      "logps/chosen": -145.14044189453125,
+      "logps/rejected": -265.5760192871094,
+      "loss": 0.3542,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.742743730545044,
+      "rewards/margins": 1.1478015184402466,
+      "rewards/rejected": -0.4050576686859131,
+      "step": 60
+    },
+    {
+      "epoch": 1.94,
+      "eval_logits/chosen": -1.7979233264923096,
+      "eval_logits/rejected": -1.8902829885482788,
+      "eval_logps/chosen": -105.64314270019531,
+      "eval_logps/rejected": -269.93597412109375,
+      "eval_loss": 0.344027042388916,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 0.96092689037323,
+      "eval_rewards/margins": 1.212537407875061,
+      "eval_rewards/rejected": -0.2516104578971863,
+      "eval_runtime": 9.9306,
+      "eval_samples_per_second": 2.82,
+      "eval_steps_per_second": 0.705,
+      "step": 60
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 16.264854431152344,
+      "learning_rate": 3.3045977011494256e-06,
+      "logits/chosen": -1.8283793926239014,
+      "logits/rejected": -1.8581088781356812,
+      "logps/chosen": -245.49520874023438,
+      "logps/rejected": -240.85055541992188,
+      "loss": 0.3242,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 0.9433773756027222,
+      "rewards/margins": 0.9048371315002441,
+      "rewards/rejected": 0.0385403148829937,
+      "step": 70
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 18.855249404907227,
+      "learning_rate": 3.017241379310345e-06,
+      "logits/chosen": -1.912719964981079,
+      "logits/rejected": -1.9267578125,
+      "logps/chosen": -184.6862030029297,
+      "logps/rejected": -150.09349060058594,
+      "loss": 0.3063,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 0.9958856701850891,
+      "rewards/margins": 1.2241456508636475,
+      "rewards/rejected": -0.2282601296901703,
+      "step": 80
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 18.644786834716797,
+      "learning_rate": 2.729885057471265e-06,
+      "logits/chosen": -1.8041893243789673,
+      "logits/rejected": -1.8382984399795532,
+      "logps/chosen": -122.60682678222656,
+      "logps/rejected": -190.001220703125,
+      "loss": 0.2892,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 1.1825361251831055,
+      "rewards/margins": 1.4003632068634033,
+      "rewards/rejected": -0.2178269922733307,
+      "step": 90
+    },
+    {
+      "epoch": 2.9,
+      "eval_logits/chosen": -1.799451470375061,
+      "eval_logits/rejected": -1.8927640914916992,
+      "eval_logps/chosen": -104.44667053222656,
+      "eval_logps/rejected": -270.4913635253906,
+      "eval_loss": 0.275594562292099,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 1.319871187210083,
+      "eval_rewards/margins": 1.7381019592285156,
+      "eval_rewards/rejected": -0.4182307720184326,
+      "eval_runtime": 9.9268,
+      "eval_samples_per_second": 2.821,
+      "eval_steps_per_second": 0.705,
+      "step": 90
+    }
+  ],
+  "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-90/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddb616965f243d067df3d0989701364bac00b0a89b6fb3bed8e9fc7ddb137e5f
+size 5304