Upload folder using huggingface_hub

README.md

@@ -1,95 +1,91 @@
 ---
-library_name: peft
+license: mit
+library_name: "trl"
 tags:
-- trl
-- dpo
-- generated_from_trainer
+- DPO
+- WeniGPT
 base_model: Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged
 model-index:
-- name: WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.4-DPO
+- name: Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.4-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-1.0.4-DPO
 
-# WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.4-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: 0.4296
-- Rewards/chosen: 2.1700
-- Rewards/rejected: -0.6894
-- Rewards/accuracies: 0.4286
-- Rewards/margins: 2.8595
-- Logps/rejected: -98.0954
-- Logps/chosen: -47.9682
-- Logits/rejected: -1.8433
-- Logits/chosen: -1.8191
+{'eval_loss': 0.42961153388023376, 'eval_runtime': 8.5144, 'eval_samples_per_second': 3.289, 'eval_steps_per_second': 1.644, 'eval_rewards/chosen': 2.170013666152954, 'eval_rewards/rejected': -0.6894403696060181, 'eval_rewards/accuracies': 0.4285714328289032, 'eval_rewards/margins': 2.8594539165496826, 'eval_logps/rejected': -98.09535217285156, 'eval_logps/chosen': -47.96824264526367, 'eval_logits/rejected': -1.8433464765548706, 'eval_logits/chosen': -1.8190696239471436, 'epoch': 11.9}
 
-## 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: 2
-- eval_batch_size: 2
-- seed: 42
+- per_device_train_batch_size: 2
+- per_device_eval_batch_size: 2
 - gradient_accumulation_steps: 2
+- num_gpus: 1
 - total_train_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: 732
-- mixed_precision_training: Native AMP
+- optimizer: AdamW
+- lr_scheduler_type: cosine
+- num_steps: 732
+- 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 |
-|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
-| 0.665         | 0.49  | 30   | 0.6322          | 0.1457         | 0.0118           | 0.4286             | 0.1339          | -95.7578       | -54.7160     | -1.7981         | -1.7801       |
-| 0.5445        | 0.98  | 60   | 0.5272          | 0.4942         | 0.0186           | 0.4286             | 0.4756          | -95.7351       | -53.5543     | -1.8031         | -1.7844       |
-| 0.4616        | 1.46  | 90   | 0.4622          | 0.9572         | -0.0104          | 0.4286             | 0.9676          | -95.8320       | -52.0111     | -1.8099         | -1.7902       |
-| 0.5327        | 1.95  | 120  | 0.4424          | 1.3376         | -0.0803          | 0.4286             | 1.4179          | -96.0649       | -50.7429     | -1.8171         | -1.7963       |
-| 0.5459        | 2.44  | 150  | 0.4335          | 1.6435         | -0.1846          | 0.4286             | 1.8281          | -96.4125       | -49.7233     | -1.8243         | -1.8025       |
-| 0.4055        | 2.93  | 180  | 0.4326          | 1.8624         | -0.3390          | 0.4286             | 2.2014          | -96.9273       | -48.9936     | -1.8301         | -1.8074       |
-| 0.4694        | 3.41  | 210  | 0.4311          | 1.9971         | -0.4435          | 0.4286             | 2.4406          | -97.2756       | -48.5445     | -1.8368         | -1.8136       |
-| 0.5431        | 3.9   | 240  | 0.4247          | 2.0881         | -0.5490          | 0.4286             | 2.6371          | -97.6273       | -48.2414     | -1.8401         | -1.8164       |
-| 0.4547        | 4.39  | 270  | 0.4296          | 2.1700         | -0.6894          | 0.4286             | 2.8595          | -98.0954       | -47.9682     | -1.8433         | -1.8191       |
-| 0.3606        | 4.88  | 300  | 0.4290          | 2.2236         | -0.7919          | 0.4286             | 3.0155          | -98.4369       | -47.7897     | -1.8460         | -1.8213       |
-| 0.4021        | 5.37  | 330  | 0.4302          | 2.2553         | -0.9243          | 0.4286             | 3.1797          | -98.8783       | -47.6839     | -1.8471         | -1.8219       |
-| 0.419         | 5.85  | 360  | 0.4336          | 2.2579         | -1.0063          | 0.4286             | 3.2642          | -99.1514       | -47.6751     | -1.8470         | -1.8214       |
-| 0.3984        | 6.34  | 390  | 0.4291          | 2.2716         | -1.0712          | 0.4286             | 3.3428          | -99.3678       | -47.6296     | -1.8499         | -1.8243       |
-| 0.435         | 6.83  | 420  | 0.4285          | 2.2724         | -1.1240          | 0.4286             | 3.3965          | -99.5441       | -47.6268     | -1.8495         | -1.8236       |
-| 0.5148        | 7.32  | 450  | 0.4309          | 2.2693         | -1.2113          | 0.4286             | 3.4806          | -99.8349       | -47.6373     | -1.8482         | -1.8220       |
-| 0.412         | 7.8   | 480  | 0.4308          | 2.2647         | -1.2626          | 0.4286             | 3.5273          | -100.0060      | -47.6527     | -1.8481         | -1.8217       |
-| 0.4911        | 8.29  | 510  | 0.4331          | 2.2554         | -1.3097          | 0.4286             | 3.5651          | -100.1629      | -47.6835     | -1.8466         | -1.8200       |
-| 0.4433        | 8.78  | 540  | 0.4317          | 2.2453         | -1.3403          | 0.4286             | 3.5855          | -100.2648      | -47.7174     | -1.8468         | -1.8201       |
-| 0.3813        | 9.27  | 570  | 0.4338          | 2.2396         | -1.3854          | 0.4286             | 3.6250          | -100.4154      | -47.7365     | -1.8473         | -1.8205       |
-| 0.5026        | 9.76  | 600  | 0.4333          | 2.2386         | -1.4022          | 0.4286             | 3.6408          | -100.4712      | -47.7397     | -1.8472         | -1.8203       |
-| 0.3121        | 10.24 | 630  | 0.4324          | 2.2339         | -1.4158          | 0.4286             | 3.6497          | -100.5166      | -47.7553     | -1.8462         | -1.8193       |
-| 0.4165        | 10.73 | 660  | 0.4319          | 2.2307         | -1.4318          | 0.4286             | 3.6625          | -100.5699      | -47.7659     | -1.8462         | -1.8193       |
-| 0.5328        | 11.22 | 690  | 0.4329          | 2.2254         | -1.4478          | 0.4286             | 3.6732          | -100.6233      | -47.7837     | -1.8457         | -1.8186       |
-| 0.4046        | 11.71 | 720  | 0.4335          | 2.2229         | -1.4565          | 0.4286             | 3.6793          | -100.6521      | -47.7921     | -1.8454         | -1.8183       |
-
-
 ### 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 sha256:120464c7595b7b37a2471602c526093f16cf2a72fa223503e881163b1513d136
+size 13648432

checkpoint-180/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9e33c0047a47e6df9ee18f7c49734c2f0be35e8e27c13acec249ec95550c022
+size 27370618

checkpoint-180/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48ee9b73399c28d7e668360bf1d5a4d11095c4738bf96c13f7bb6fbff59f8ccb
+size 14244

checkpoint-180/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f0d33dc5847fd79dd9a2a4e7fb4f19e095e7b02f8f0ed2e65c94f5a363f81df
+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": 0.4326101839542389,
+  "best_model_checkpoint": "./mistral/19-04-24-Weni-WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.4-DPO_Experiment on DPO with other hyperparameters and best SFT model of WeniGPT-2_max_steps-732_batch_4_2024-04-19_ppid_9/checkpoint-180",
+  "epoch": 2.926829268292683,
+  "eval_steps": 30,
+  "global_step": 180,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "grad_norm": 38.021175384521484,
+      "learning_rate": 1.590909090909091e-06,
+      "logits/chosen": -1.7808929681777954,
+      "logits/rejected": -1.8136215209960938,
+      "logps/chosen": -52.2663688659668,
+      "logps/rejected": -88.76155853271484,
+      "loss": 0.6927,
+      "rewards/accuracies": 0.20000000298023224,
+      "rewards/chosen": 0.0008833981119096279,
+      "rewards/margins": 0.0009520913590677083,
+      "rewards/rejected": -6.869318895041943e-05,
+      "step": 10
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 19.505126953125,
+      "learning_rate": 3.863636363636364e-06,
+      "logits/chosen": -1.865220308303833,
+      "logits/rejected": -1.880090355873108,
+      "logps/chosen": -34.3599967956543,
+      "logps/rejected": -53.656646728515625,
+      "loss": 0.6846,
+      "rewards/accuracies": 0.22499999403953552,
+      "rewards/chosen": 0.019346294924616814,
+      "rewards/margins": 0.017682768404483795,
+      "rewards/rejected": 0.0016635276842862368,
+      "step": 20
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 16.67194938659668,
+      "learning_rate": 4.964788732394366e-06,
+      "logits/chosen": -1.7692855596542358,
+      "logits/rejected": -1.7932851314544678,
+      "logps/chosen": -38.679237365722656,
+      "logps/rejected": -79.23713684082031,
+      "loss": 0.665,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": 0.07158979028463364,
+      "rewards/margins": 0.061105482280254364,
+      "rewards/rejected": 0.010484304279088974,
+      "step": 30
+    },
+    {
+      "epoch": 0.49,
+      "eval_logits/chosen": -1.7801028490066528,
+      "eval_logits/rejected": -1.7981160879135132,
+      "eval_logps/chosen": -54.71597671508789,
+      "eval_logps/rejected": -95.75775909423828,
+      "eval_loss": 0.6322354674339294,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 0.14569346606731415,
+      "eval_rewards/margins": 0.13385750353336334,
+      "eval_rewards/rejected": 0.011835969984531403,
+      "eval_runtime": 8.5124,
+      "eval_samples_per_second": 3.289,
+      "eval_steps_per_second": 1.645,
+      "step": 30
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 22.69721031188965,
+      "learning_rate": 4.894366197183099e-06,
+      "logits/chosen": -1.8458446264266968,
+      "logits/rejected": -1.8594070672988892,
+      "logps/chosen": -39.180992126464844,
+      "logps/rejected": -57.04741287231445,
+      "loss": 0.6164,
+      "rewards/accuracies": 0.3499999940395355,
+      "rewards/chosen": 0.19042351841926575,
+      "rewards/margins": 0.18086455762386322,
+      "rewards/rejected": 0.009558964520692825,
+      "step": 40
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.0,
+      "learning_rate": 4.823943661971832e-06,
+      "logits/chosen": -1.8411815166473389,
+      "logits/rejected": -1.8659855127334595,
+      "logps/chosen": -31.194744110107422,
+      "logps/rejected": -58.17326736450195,
+      "loss": 0.6138,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.19823171198368073,
+      "rewards/margins": 0.19669394195079803,
+      "rewards/rejected": 0.0015377718955278397,
+      "step": 50
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 10.77029800415039,
+      "learning_rate": 4.753521126760564e-06,
+      "logits/chosen": -1.816936731338501,
+      "logits/rejected": -1.8421777486801147,
+      "logps/chosen": -50.517478942871094,
+      "logps/rejected": -80.6562728881836,
+      "loss": 0.5445,
+      "rewards/accuracies": 0.42500001192092896,
+      "rewards/chosen": 0.4567543864250183,
+      "rewards/margins": 0.42180705070495605,
+      "rewards/rejected": 0.03494739532470703,
+      "step": 60
+    },
+    {
+      "epoch": 0.98,
+      "eval_logits/chosen": -1.784444808959961,
+      "eval_logits/rejected": -1.8030898571014404,
+      "eval_logps/chosen": -53.55432891845703,
+      "eval_logps/rejected": -95.73511505126953,
+      "eval_loss": 0.527186930179596,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 0.4941868484020233,
+      "eval_rewards/margins": 0.47555941343307495,
+      "eval_rewards/rejected": 0.018627464771270752,
+      "eval_runtime": 8.5149,
+      "eval_samples_per_second": 3.288,
+      "eval_steps_per_second": 1.644,
+      "step": 60
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 8.583382606506348,
+      "learning_rate": 4.683098591549296e-06,
+      "logits/chosen": -1.7579460144042969,
+      "logits/rejected": -1.776581048965454,
+      "logps/chosen": -54.420066833496094,
+      "logps/rejected": -79.0608901977539,
+      "loss": 0.451,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": 0.8353117108345032,
+      "rewards/margins": 0.8680375814437866,
+      "rewards/rejected": -0.032725896686315536,
+      "step": 70
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 2.3610572814941406,
+      "learning_rate": 4.612676056338028e-06,
+      "logits/chosen": -1.8833833932876587,
+      "logits/rejected": -1.9092212915420532,
+      "logps/chosen": -25.5800724029541,
+      "logps/rejected": -64.96099853515625,
+      "loss": 0.5302,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.5431563258171082,
+      "rewards/margins": 0.6763826012611389,
+      "rewards/rejected": -0.13322624564170837,
+      "step": 80
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 3.739367723464966,
+      "learning_rate": 4.542253521126761e-06,
+      "logits/chosen": -1.8194096088409424,
+      "logits/rejected": -1.8343127965927124,
+      "logps/chosen": -41.80801773071289,
+      "logps/rejected": -63.005592346191406,
+      "loss": 0.4616,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": 0.830731213092804,
+      "rewards/margins": 0.9403120875358582,
+      "rewards/rejected": -0.109580859541893,
+      "step": 90
+    },
+    {
+      "epoch": 1.46,
+      "eval_logits/chosen": -1.7902206182479858,
+      "eval_logits/rejected": -1.8099161386489868,
+      "eval_logps/chosen": -52.01105880737305,
+      "eval_logps/rejected": -95.83198547363281,
+      "eval_loss": 0.46216800808906555,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 0.957168459892273,
+      "eval_rewards/margins": 0.9676021337509155,
+      "eval_rewards/rejected": -0.010433738119900227,
+      "eval_runtime": 8.5144,
+      "eval_samples_per_second": 3.289,
+      "eval_steps_per_second": 1.644,
+      "step": 90
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.5382364988327026,
+      "learning_rate": 4.471830985915494e-06,
+      "logits/chosen": -1.845868468284607,
+      "logits/rejected": -1.8715919256210327,
+      "logps/chosen": -40.285335540771484,
+      "logps/rejected": -73.16102600097656,
+      "loss": 0.4611,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 1.0631928443908691,
+      "rewards/margins": 1.3067411184310913,
+      "rewards/rejected": -0.24354824423789978,
+      "step": 100
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 12.538246154785156,
+      "learning_rate": 4.401408450704226e-06,
+      "logits/chosen": -1.8342373371124268,
+      "logits/rejected": -1.862433671951294,
+      "logps/chosen": -29.438589096069336,
+      "logps/rejected": -62.31974411010742,
+      "loss": 0.5266,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.7012811899185181,
+      "rewards/margins": 0.8140069246292114,
+      "rewards/rejected": -0.11272567510604858,
+      "step": 110
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 2.3604652881622314,
+      "learning_rate": 4.3309859154929575e-06,
+      "logits/chosen": -1.8481504917144775,
+      "logits/rejected": -1.8528194427490234,
+      "logps/chosen": -35.794334411621094,
+      "logps/rejected": -56.22735595703125,
+      "loss": 0.5327,
+      "rewards/accuracies": 0.32499998807907104,
+      "rewards/chosen": 1.078013300895691,
+      "rewards/margins": 0.9431617856025696,
+      "rewards/rejected": 0.1348516196012497,
+      "step": 120
+    },
+    {
+      "epoch": 1.95,
+      "eval_logits/chosen": -1.7962983846664429,
+      "eval_logits/rejected": -1.8171442747116089,
+      "eval_logps/chosen": -50.74287796020508,
+      "eval_logps/rejected": -96.0649185180664,
+      "eval_loss": 0.4424423575401306,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 1.337624192237854,
+      "eval_rewards/margins": 1.4179356098175049,
+      "eval_rewards/rejected": -0.08031141757965088,
+      "eval_runtime": 8.5188,
+      "eval_samples_per_second": 3.287,
+      "eval_steps_per_second": 1.643,
+      "step": 120
+    },
+    {
+      "epoch": 2.11,
+      "grad_norm": 5.3829216957092285,
+      "learning_rate": 4.26056338028169e-06,
+      "logits/chosen": -1.8153988122940063,
+      "logits/rejected": -1.853118658065796,
+      "logps/chosen": -44.251441955566406,
+      "logps/rejected": -85.38258361816406,
+      "loss": 0.4011,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": 1.5001299381256104,
+      "rewards/margins": 1.9703232049942017,
+      "rewards/rejected": -0.4701933264732361,
+      "step": 130
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 0.6282079815864563,
+      "learning_rate": 4.190140845070423e-06,
+      "logits/chosen": -1.8527545928955078,
+      "logits/rejected": -1.8757705688476562,
+      "logps/chosen": -35.6223258972168,
+      "logps/rejected": -80.99830627441406,
+      "loss": 0.4423,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": 1.484961748123169,
+      "rewards/margins": 1.8964126110076904,
+      "rewards/rejected": -0.41145071387290955,
+      "step": 140
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.0,
+      "learning_rate": 4.119718309859156e-06,
+      "logits/chosen": -1.9129869937896729,
+      "logits/rejected": -1.927869439125061,
+      "logps/chosen": -24.400936126708984,
+      "logps/rejected": -50.861839294433594,
+      "loss": 0.5459,
+      "rewards/accuracies": 0.25,
+      "rewards/chosen": 0.8408910036087036,
+      "rewards/margins": 1.1376488208770752,
+      "rewards/rejected": -0.2967577874660492,
+      "step": 150
+    },
+    {
+      "epoch": 2.44,
+      "eval_logits/chosen": -1.8025389909744263,
+      "eval_logits/rejected": -1.824258804321289,
+      "eval_logps/chosen": -49.72334671020508,
+      "eval_logps/rejected": -96.41252899169922,
+      "eval_loss": 0.4335039258003235,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 1.6434847116470337,
+      "eval_rewards/margins": 1.828076720237732,
+      "eval_rewards/rejected": -0.1845920830965042,
+      "eval_runtime": 8.5149,
+      "eval_samples_per_second": 3.288,
+      "eval_steps_per_second": 1.644,
+      "step": 150
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.7459288239479065,
+      "learning_rate": 4.0492957746478875e-06,
+      "logits/chosen": -1.786231279373169,
+      "logits/rejected": -1.8223682641983032,
+      "logps/chosen": -40.68749237060547,
+      "logps/rejected": -78.1619873046875,
+      "loss": 0.4348,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": 1.9040056467056274,
+      "rewards/margins": 2.482433795928955,
+      "rewards/rejected": -0.5784280896186829,
+      "step": 160
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 1.4669339656829834,
+      "learning_rate": 3.97887323943662e-06,
+      "logits/chosen": -1.8449195623397827,
+      "logits/rejected": -1.871626615524292,
+      "logps/chosen": -46.335182189941406,
+      "logps/rejected": -86.10281372070312,
+      "loss": 0.4232,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 1.8989893198013306,
+      "rewards/margins": 2.384274482727051,
+      "rewards/rejected": -0.4852851927280426,
+      "step": 170
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 0.0301869735121727,
+      "learning_rate": 3.908450704225352e-06,
+      "logits/chosen": -1.8375946283340454,
+      "logits/rejected": -1.8527040481567383,
+      "logps/chosen": -39.01136016845703,
+      "logps/rejected": -65.78593444824219,
+      "loss": 0.4055,
+      "rewards/accuracies": 0.42500001192092896,
+      "rewards/chosen": 1.9841420650482178,
+      "rewards/margins": 2.3045599460601807,
+      "rewards/rejected": -0.32041770219802856,
+      "step": 180
+    },
+    {
+      "epoch": 2.93,
+      "eval_logits/chosen": -1.8074016571044922,
+      "eval_logits/rejected": -1.830051064491272,
+      "eval_logps/chosen": -48.993629455566406,
+      "eval_logps/rejected": -96.92731475830078,
+      "eval_loss": 0.4326101839542389,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 1.8623981475830078,
+      "eval_rewards/margins": 2.201425075531006,
+      "eval_rewards/rejected": -0.3390272557735443,
+      "eval_runtime": 8.5144,
+      "eval_samples_per_second": 3.289,
+      "eval_steps_per_second": 1.644,
+      "step": 180
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 732,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "save_steps": 90,
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-180/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a9e56dbe2b48a488c5411e841b81929760b46d9a622b353a65d00ada1e6a94f
+size 5304

checkpoint-270/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-270/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-270/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fc4205bc93d6795cf17821f662a891c4d28c9b793aea2722bad767836694c35
+size 13648432

checkpoint-270/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4f8ddec4ea9af434e83b5a25dc091fc601be40052c74984f0ef065e4452ee71
+size 27370618

checkpoint-270/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d3b7102895eb0637b0cab516bd672f216b2bf79078a83eb301011a90444f44c
+size 14244

checkpoint-270/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6d94f322c4589ac5c8ea8cc5fb2273467078032f4b0038251c171dd6df2c9d4
+size 1064

checkpoint-270/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-270/tokenizer.model

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

checkpoint-270/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-270/trainer_state.json

@@ -0,0 +1,570 @@
+{
+  "best_metric": 0.42961153388023376,
+  "best_model_checkpoint": "./mistral/19-04-24-Weni-WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.4-DPO_Experiment on DPO with other hyperparameters and best SFT model of WeniGPT-2_max_steps-732_batch_4_2024-04-19_ppid_9/checkpoint-270",
+  "epoch": 4.390243902439025,
+  "eval_steps": 30,
+  "global_step": 270,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "grad_norm": 38.021175384521484,
+      "learning_rate": 1.590909090909091e-06,
+      "logits/chosen": -1.7808929681777954,
+      "logits/rejected": -1.8136215209960938,
+      "logps/chosen": -52.2663688659668,
+      "logps/rejected": -88.76155853271484,
+      "loss": 0.6927,
+      "rewards/accuracies": 0.20000000298023224,
+      "rewards/chosen": 0.0008833981119096279,
+      "rewards/margins": 0.0009520913590677083,
+      "rewards/rejected": -6.869318895041943e-05,
+      "step": 10
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 19.505126953125,
+      "learning_rate": 3.863636363636364e-06,
+      "logits/chosen": -1.865220308303833,
+      "logits/rejected": -1.880090355873108,
+      "logps/chosen": -34.3599967956543,
+      "logps/rejected": -53.656646728515625,
+      "loss": 0.6846,
+      "rewards/accuracies": 0.22499999403953552,
+      "rewards/chosen": 0.019346294924616814,
+      "rewards/margins": 0.017682768404483795,
+      "rewards/rejected": 0.0016635276842862368,
+      "step": 20
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 16.67194938659668,
+      "learning_rate": 4.964788732394366e-06,
+      "logits/chosen": -1.7692855596542358,
+      "logits/rejected": -1.7932851314544678,
+      "logps/chosen": -38.679237365722656,
+      "logps/rejected": -79.23713684082031,
+      "loss": 0.665,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": 0.07158979028463364,
+      "rewards/margins": 0.061105482280254364,
+      "rewards/rejected": 0.010484304279088974,
+      "step": 30
+    },
+    {
+      "epoch": 0.49,
+      "eval_logits/chosen": -1.7801028490066528,
+      "eval_logits/rejected": -1.7981160879135132,
+      "eval_logps/chosen": -54.71597671508789,
+      "eval_logps/rejected": -95.75775909423828,
+      "eval_loss": 0.6322354674339294,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 0.14569346606731415,
+      "eval_rewards/margins": 0.13385750353336334,
+      "eval_rewards/rejected": 0.011835969984531403,
+      "eval_runtime": 8.5124,
+      "eval_samples_per_second": 3.289,
+      "eval_steps_per_second": 1.645,
+      "step": 30
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 22.69721031188965,
+      "learning_rate": 4.894366197183099e-06,
+      "logits/chosen": -1.8458446264266968,
+      "logits/rejected": -1.8594070672988892,
+      "logps/chosen": -39.180992126464844,
+      "logps/rejected": -57.04741287231445,
+      "loss": 0.6164,
+      "rewards/accuracies": 0.3499999940395355,
+      "rewards/chosen": 0.19042351841926575,
+      "rewards/margins": 0.18086455762386322,
+      "rewards/rejected": 0.009558964520692825,
+      "step": 40
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.0,
+      "learning_rate": 4.823943661971832e-06,
+      "logits/chosen": -1.8411815166473389,
+      "logits/rejected": -1.8659855127334595,
+      "logps/chosen": -31.194744110107422,
+      "logps/rejected": -58.17326736450195,
+      "loss": 0.6138,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.19823171198368073,
+      "rewards/margins": 0.19669394195079803,
+      "rewards/rejected": 0.0015377718955278397,
+      "step": 50
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 10.77029800415039,
+      "learning_rate": 4.753521126760564e-06,
+      "logits/chosen": -1.816936731338501,
+      "logits/rejected": -1.8421777486801147,
+      "logps/chosen": -50.517478942871094,
+      "logps/rejected": -80.6562728881836,
+      "loss": 0.5445,
+      "rewards/accuracies": 0.42500001192092896,
+      "rewards/chosen": 0.4567543864250183,
+      "rewards/margins": 0.42180705070495605,
+      "rewards/rejected": 0.03494739532470703,
+      "step": 60
+    },
+    {
+      "epoch": 0.98,
+      "eval_logits/chosen": -1.784444808959961,
+      "eval_logits/rejected": -1.8030898571014404,
+      "eval_logps/chosen": -53.55432891845703,
+      "eval_logps/rejected": -95.73511505126953,
+      "eval_loss": 0.527186930179596,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 0.4941868484020233,
+      "eval_rewards/margins": 0.47555941343307495,
+      "eval_rewards/rejected": 0.018627464771270752,
+      "eval_runtime": 8.5149,
+      "eval_samples_per_second": 3.288,
+      "eval_steps_per_second": 1.644,
+      "step": 60
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 8.583382606506348,
+      "learning_rate": 4.683098591549296e-06,
+      "logits/chosen": -1.7579460144042969,
+      "logits/rejected": -1.776581048965454,
+      "logps/chosen": -54.420066833496094,
+      "logps/rejected": -79.0608901977539,
+      "loss": 0.451,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": 0.8353117108345032,
+      "rewards/margins": 0.8680375814437866,
+      "rewards/rejected": -0.032725896686315536,
+      "step": 70
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 2.3610572814941406,
+      "learning_rate": 4.612676056338028e-06,
+      "logits/chosen": -1.8833833932876587,
+      "logits/rejected": -1.9092212915420532,
+      "logps/chosen": -25.5800724029541,
+      "logps/rejected": -64.96099853515625,
+      "loss": 0.5302,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.5431563258171082,
+      "rewards/margins": 0.6763826012611389,
+      "rewards/rejected": -0.13322624564170837,
+      "step": 80
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 3.739367723464966,
+      "learning_rate": 4.542253521126761e-06,
+      "logits/chosen": -1.8194096088409424,
+      "logits/rejected": -1.8343127965927124,
+      "logps/chosen": -41.80801773071289,
+      "logps/rejected": -63.005592346191406,
+      "loss": 0.4616,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": 0.830731213092804,
+      "rewards/margins": 0.9403120875358582,
+      "rewards/rejected": -0.109580859541893,
+      "step": 90
+    },
+    {
+      "epoch": 1.46,
+      "eval_logits/chosen": -1.7902206182479858,
+      "eval_logits/rejected": -1.8099161386489868,
+      "eval_logps/chosen": -52.01105880737305,
+      "eval_logps/rejected": -95.83198547363281,
+      "eval_loss": 0.46216800808906555,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 0.957168459892273,
+      "eval_rewards/margins": 0.9676021337509155,
+      "eval_rewards/rejected": -0.010433738119900227,
+      "eval_runtime": 8.5144,
+      "eval_samples_per_second": 3.289,
+      "eval_steps_per_second": 1.644,
+      "step": 90
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.5382364988327026,
+      "learning_rate": 4.471830985915494e-06,
+      "logits/chosen": -1.845868468284607,
+      "logits/rejected": -1.8715919256210327,
+      "logps/chosen": -40.285335540771484,
+      "logps/rejected": -73.16102600097656,
+      "loss": 0.4611,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 1.0631928443908691,
+      "rewards/margins": 1.3067411184310913,
+      "rewards/rejected": -0.24354824423789978,
+      "step": 100
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 12.538246154785156,
+      "learning_rate": 4.401408450704226e-06,
+      "logits/chosen": -1.8342373371124268,
+      "logits/rejected": -1.862433671951294,
+      "logps/chosen": -29.438589096069336,
+      "logps/rejected": -62.31974411010742,
+      "loss": 0.5266,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.7012811899185181,
+      "rewards/margins": 0.8140069246292114,
+      "rewards/rejected": -0.11272567510604858,
+      "step": 110
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 2.3604652881622314,
+      "learning_rate": 4.3309859154929575e-06,
+      "logits/chosen": -1.8481504917144775,
+      "logits/rejected": -1.8528194427490234,
+      "logps/chosen": -35.794334411621094,
+      "logps/rejected": -56.22735595703125,
+      "loss": 0.5327,
+      "rewards/accuracies": 0.32499998807907104,
+      "rewards/chosen": 1.078013300895691,
+      "rewards/margins": 0.9431617856025696,
+      "rewards/rejected": 0.1348516196012497,
+      "step": 120
+    },
+    {
+      "epoch": 1.95,
+      "eval_logits/chosen": -1.7962983846664429,
+      "eval_logits/rejected": -1.8171442747116089,
+      "eval_logps/chosen": -50.74287796020508,
+      "eval_logps/rejected": -96.0649185180664,
+      "eval_loss": 0.4424423575401306,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 1.337624192237854,
+      "eval_rewards/margins": 1.4179356098175049,
+      "eval_rewards/rejected": -0.08031141757965088,
+      "eval_runtime": 8.5188,
+      "eval_samples_per_second": 3.287,
+      "eval_steps_per_second": 1.643,
+      "step": 120
+    },
+    {
+      "epoch": 2.11,
+      "grad_norm": 5.3829216957092285,
+      "learning_rate": 4.26056338028169e-06,
+      "logits/chosen": -1.8153988122940063,
+      "logits/rejected": -1.853118658065796,
+      "logps/chosen": -44.251441955566406,
+      "logps/rejected": -85.38258361816406,
+      "loss": 0.4011,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": 1.5001299381256104,
+      "rewards/margins": 1.9703232049942017,
+      "rewards/rejected": -0.4701933264732361,
+      "step": 130
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 0.6282079815864563,
+      "learning_rate": 4.190140845070423e-06,
+      "logits/chosen": -1.8527545928955078,
+      "logits/rejected": -1.8757705688476562,
+      "logps/chosen": -35.6223258972168,
+      "logps/rejected": -80.99830627441406,
+      "loss": 0.4423,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": 1.484961748123169,
+      "rewards/margins": 1.8964126110076904,
+      "rewards/rejected": -0.41145071387290955,
+      "step": 140
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.0,
+      "learning_rate": 4.119718309859156e-06,
+      "logits/chosen": -1.9129869937896729,
+      "logits/rejected": -1.927869439125061,
+      "logps/chosen": -24.400936126708984,
+      "logps/rejected": -50.861839294433594,
+      "loss": 0.5459,
+      "rewards/accuracies": 0.25,
+      "rewards/chosen": 0.8408910036087036,
+      "rewards/margins": 1.1376488208770752,
+      "rewards/rejected": -0.2967577874660492,
+      "step": 150
+    },
+    {
+      "epoch": 2.44,
+      "eval_logits/chosen": -1.8025389909744263,
+      "eval_logits/rejected": -1.824258804321289,
+      "eval_logps/chosen": -49.72334671020508,
+      "eval_logps/rejected": -96.41252899169922,
+      "eval_loss": 0.4335039258003235,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 1.6434847116470337,
+      "eval_rewards/margins": 1.828076720237732,
+      "eval_rewards/rejected": -0.1845920830965042,
+      "eval_runtime": 8.5149,
+      "eval_samples_per_second": 3.288,
+      "eval_steps_per_second": 1.644,
+      "step": 150
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.7459288239479065,
+      "learning_rate": 4.0492957746478875e-06,
+      "logits/chosen": -1.786231279373169,
+      "logits/rejected": -1.8223682641983032,
+      "logps/chosen": -40.68749237060547,
+      "logps/rejected": -78.1619873046875,
+      "loss": 0.4348,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": 1.9040056467056274,
+      "rewards/margins": 2.482433795928955,
+      "rewards/rejected": -0.5784280896186829,
+      "step": 160
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 1.4669339656829834,
+      "learning_rate": 3.97887323943662e-06,
+      "logits/chosen": -1.8449195623397827,
+      "logits/rejected": -1.871626615524292,
+      "logps/chosen": -46.335182189941406,
+      "logps/rejected": -86.10281372070312,
+      "loss": 0.4232,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 1.8989893198013306,
+      "rewards/margins": 2.384274482727051,
+      "rewards/rejected": -0.4852851927280426,
+      "step": 170
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 0.0301869735121727,
+      "learning_rate": 3.908450704225352e-06,
+      "logits/chosen": -1.8375946283340454,
+      "logits/rejected": -1.8527040481567383,
+      "logps/chosen": -39.01136016845703,
+      "logps/rejected": -65.78593444824219,
+      "loss": 0.4055,
+      "rewards/accuracies": 0.42500001192092896,
+      "rewards/chosen": 1.9841420650482178,
+      "rewards/margins": 2.3045599460601807,
+      "rewards/rejected": -0.32041770219802856,
+      "step": 180
+    },
+    {
+      "epoch": 2.93,
+      "eval_logits/chosen": -1.8074016571044922,
+      "eval_logits/rejected": -1.830051064491272,
+      "eval_logps/chosen": -48.993629455566406,
+      "eval_logps/rejected": -96.92731475830078,
+      "eval_loss": 0.4326101839542389,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 1.8623981475830078,
+      "eval_rewards/margins": 2.201425075531006,
+      "eval_rewards/rejected": -0.3390272557735443,
+      "eval_runtime": 8.5144,
+      "eval_samples_per_second": 3.289,
+      "eval_steps_per_second": 1.644,
+      "step": 180
+    },
+    {
+      "epoch": 3.09,
+      "grad_norm": 2.224493980407715,
+      "learning_rate": 3.838028169014085e-06,
+      "logits/chosen": -1.8459789752960205,
+      "logits/rejected": -1.8675992488861084,
+      "logps/chosen": -32.56737518310547,
+      "logps/rejected": -61.4633674621582,
+      "loss": 0.4576,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": 1.5155870914459229,
+      "rewards/margins": 1.9375633001327515,
+      "rewards/rejected": -0.42197614908218384,
+      "step": 190
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 16.606130599975586,
+      "learning_rate": 3.767605633802817e-06,
+      "logits/chosen": -1.8678531646728516,
+      "logits/rejected": -1.8987194299697876,
+      "logps/chosen": -36.32281494140625,
+      "logps/rejected": -82.02101135253906,
+      "loss": 0.4697,
+      "rewards/accuracies": 0.3499999940395355,
+      "rewards/chosen": 1.7492707967758179,
+      "rewards/margins": 2.534116268157959,
+      "rewards/rejected": -0.7848455309867859,
+      "step": 200
+    },
+    {
+      "epoch": 3.41,
+      "grad_norm": 2.050732135772705,
+      "learning_rate": 3.69718309859155e-06,
+      "logits/chosen": -1.8438726663589478,
+      "logits/rejected": -1.8704954385757446,
+      "logps/chosen": -31.156131744384766,
+      "logps/rejected": -71.87327575683594,
+      "loss": 0.4694,
+      "rewards/accuracies": 0.32499998807907104,
+      "rewards/chosen": 1.7663137912750244,
+      "rewards/margins": 2.468672513961792,
+      "rewards/rejected": -0.702358603477478,
+      "step": 210
+    },
+    {
+      "epoch": 3.41,
+      "eval_logits/chosen": -1.8135889768600464,
+      "eval_logits/rejected": -1.836788535118103,
+      "eval_logps/chosen": -48.54452133178711,
+      "eval_logps/rejected": -97.27555084228516,
+      "eval_loss": 0.43106651306152344,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 1.99713134765625,
+      "eval_rewards/margins": 2.4406321048736572,
+      "eval_rewards/rejected": -0.4435007870197296,
+      "eval_runtime": 8.5161,
+      "eval_samples_per_second": 3.288,
+      "eval_steps_per_second": 1.644,
+      "step": 210
+    },
+    {
+      "epoch": 3.58,
+      "grad_norm": 1.3447190523147583,
+      "learning_rate": 3.626760563380282e-06,
+      "logits/chosen": -1.9027411937713623,
+      "logits/rejected": -1.9270541667938232,
+      "logps/chosen": -31.44101333618164,
+      "logps/rejected": -62.2841911315918,
+      "loss": 0.4686,
+      "rewards/accuracies": 0.32499998807907104,
+      "rewards/chosen": 1.8702812194824219,
+      "rewards/margins": 2.6481127738952637,
+      "rewards/rejected": -0.7778315544128418,
+      "step": 220
+    },
+    {
+      "epoch": 3.74,
+      "grad_norm": 0.8471798300743103,
+      "learning_rate": 3.5563380281690144e-06,
+      "logits/chosen": -1.7770761251449585,
+      "logits/rejected": -1.8111178874969482,
+      "logps/chosen": -48.4028434753418,
+      "logps/rejected": -93.4535903930664,
+      "loss": 0.3062,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": 2.7809433937072754,
+      "rewards/margins": 3.951282501220703,
+      "rewards/rejected": -1.1703392267227173,
+      "step": 230
+    },
+    {
+      "epoch": 3.9,
+      "grad_norm": 0.017692934721708298,
+      "learning_rate": 3.4859154929577467e-06,
+      "logits/chosen": -1.8823143243789673,
+      "logits/rejected": -1.908074975013733,
+      "logps/chosen": -24.35366439819336,
+      "logps/rejected": -55.66550827026367,
+      "loss": 0.5431,
+      "rewards/accuracies": 0.2750000059604645,
+      "rewards/chosen": 1.2430522441864014,
+      "rewards/margins": 1.8208128213882446,
+      "rewards/rejected": -0.577760636806488,
+      "step": 240
+    },
+    {
+      "epoch": 3.9,
+      "eval_logits/chosen": -1.8164188861846924,
+      "eval_logits/rejected": -1.840105652809143,
+      "eval_logps/chosen": -48.241355895996094,
+      "eval_logps/rejected": -97.6273422241211,
+      "eval_loss": 0.4247165322303772,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 2.0880820751190186,
+      "eval_rewards/margins": 2.6371231079101562,
+      "eval_rewards/rejected": -0.5490409731864929,
+      "eval_runtime": 8.5143,
+      "eval_samples_per_second": 3.289,
+      "eval_steps_per_second": 1.644,
+      "step": 240
+    },
+    {
+      "epoch": 4.07,
+      "grad_norm": 0.06990335881710052,
+      "learning_rate": 3.415492957746479e-06,
+      "logits/chosen": -1.855215311050415,
+      "logits/rejected": -1.8647253513336182,
+      "logps/chosen": -41.163124084472656,
+      "logps/rejected": -63.0202751159668,
+      "loss": 0.3954,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": 2.336212635040283,
+      "rewards/margins": 2.88411283493042,
+      "rewards/rejected": -0.5479003190994263,
+      "step": 250
+    },
+    {
+      "epoch": 4.23,
+      "grad_norm": 0.5815927386283875,
+      "learning_rate": 3.3450704225352113e-06,
+      "logits/chosen": -1.9256658554077148,
+      "logits/rejected": -1.930415153503418,
+      "logps/chosen": -24.930946350097656,
+      "logps/rejected": -40.15483474731445,
+      "loss": 0.5089,
+      "rewards/accuracies": 0.2750000059604645,
+      "rewards/chosen": 1.2408175468444824,
+      "rewards/margins": 1.7317492961883545,
+      "rewards/rejected": -0.49093180894851685,
+      "step": 260
+    },
+    {
+      "epoch": 4.39,
+      "grad_norm": 0.38188156485557556,
+      "learning_rate": 3.274647887323944e-06,
+      "logits/chosen": -1.8994340896606445,
+      "logits/rejected": -1.9313939809799194,
+      "logps/chosen": -27.106714248657227,
+      "logps/rejected": -67.90898132324219,
+      "loss": 0.4547,
+      "rewards/accuracies": 0.3499999940395355,
+      "rewards/chosen": 1.7479994297027588,
+      "rewards/margins": 2.5788474082946777,
+      "rewards/rejected": -0.830848217010498,
+      "step": 270
+    },
+    {
+      "epoch": 4.39,
+      "eval_logits/chosen": -1.8190696239471436,
+      "eval_logits/rejected": -1.8433464765548706,
+      "eval_logps/chosen": -47.96824264526367,
+      "eval_logps/rejected": -98.09535217285156,
+      "eval_loss": 0.42961153388023376,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 2.170013666152954,
+      "eval_rewards/margins": 2.8594539165496826,
+      "eval_rewards/rejected": -0.6894403696060181,
+      "eval_runtime": 8.5148,
+      "eval_samples_per_second": 3.288,
+      "eval_steps_per_second": 1.644,
+      "step": 270
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 732,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "save_steps": 90,
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-270/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a9e56dbe2b48a488c5411e841b81929760b46d9a622b353a65d00ada1e6a94f
+size 5304

checkpoint-360/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-360/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-360/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87e32a7372be5f5217ef933596b86850b08090f49388115b209f858bb3900ecd
+size 13648432

checkpoint-360/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d016982ba34f201b341482672164185c914d43d996fef6484cee99f030193543
+size 27370618

checkpoint-360/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adbac4581908b419c3039e502a4aacf8ebe77d7c5097a659c9e661f2ab321b78
+size 14244

checkpoint-360/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26cb7dded4a9f8139a282964142640781770711e462a0c8bd5464e290e8b4d27
+size 1064

checkpoint-360/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-360/tokenizer.model

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

checkpoint-360/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-360/trainer_state.json

@@ -0,0 +1,753 @@
+{
+  "best_metric": 0.42961153388023376,
+  "best_model_checkpoint": "./mistral/19-04-24-Weni-WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.4-DPO_Experiment on DPO with other hyperparameters and best SFT model of WeniGPT-2_max_steps-732_batch_4_2024-04-19_ppid_9/checkpoint-270",
+  "epoch": 5.853658536585366,
+  "eval_steps": 30,
+  "global_step": 360,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "grad_norm": 38.021175384521484,
+      "learning_rate": 1.590909090909091e-06,
+      "logits/chosen": -1.7808929681777954,
+      "logits/rejected": -1.8136215209960938,
+      "logps/chosen": -52.2663688659668,
+      "logps/rejected": -88.76155853271484,
+      "loss": 0.6927,
+      "rewards/accuracies": 0.20000000298023224,
+      "rewards/chosen": 0.0008833981119096279,
+      "rewards/margins": 0.0009520913590677083,
+      "rewards/rejected": -6.869318895041943e-05,
+      "step": 10
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 19.505126953125,
+      "learning_rate": 3.863636363636364e-06,
+      "logits/chosen": -1.865220308303833,
+      "logits/rejected": -1.880090355873108,
+      "logps/chosen": -34.3599967956543,
+      "logps/rejected": -53.656646728515625,
+      "loss": 0.6846,
+      "rewards/accuracies": 0.22499999403953552,
+      "rewards/chosen": 0.019346294924616814,
+      "rewards/margins": 0.017682768404483795,
+      "rewards/rejected": 0.0016635276842862368,
+      "step": 20
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 16.67194938659668,
+      "learning_rate": 4.964788732394366e-06,
+      "logits/chosen": -1.7692855596542358,
+      "logits/rejected": -1.7932851314544678,
+      "logps/chosen": -38.679237365722656,
+      "logps/rejected": -79.23713684082031,
+      "loss": 0.665,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": 0.07158979028463364,
+      "rewards/margins": 0.061105482280254364,
+      "rewards/rejected": 0.010484304279088974,
+      "step": 30
+    },
+    {
+      "epoch": 0.49,
+      "eval_logits/chosen": -1.7801028490066528,
+      "eval_logits/rejected": -1.7981160879135132,
+      "eval_logps/chosen": -54.71597671508789,
+      "eval_logps/rejected": -95.75775909423828,
+      "eval_loss": 0.6322354674339294,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 0.14569346606731415,
+      "eval_rewards/margins": 0.13385750353336334,
+      "eval_rewards/rejected": 0.011835969984531403,
+      "eval_runtime": 8.5124,
+      "eval_samples_per_second": 3.289,
+      "eval_steps_per_second": 1.645,
+      "step": 30
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 22.69721031188965,
+      "learning_rate": 4.894366197183099e-06,
+      "logits/chosen": -1.8458446264266968,
+      "logits/rejected": -1.8594070672988892,
+      "logps/chosen": -39.180992126464844,
+      "logps/rejected": -57.04741287231445,
+      "loss": 0.6164,
+      "rewards/accuracies": 0.3499999940395355,
+      "rewards/chosen": 0.19042351841926575,
+      "rewards/margins": 0.18086455762386322,
+      "rewards/rejected": 0.009558964520692825,
+      "step": 40
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.0,
+      "learning_rate": 4.823943661971832e-06,
+      "logits/chosen": -1.8411815166473389,
+      "logits/rejected": -1.8659855127334595,
+      "logps/chosen": -31.194744110107422,
+      "logps/rejected": -58.17326736450195,
+      "loss": 0.6138,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.19823171198368073,
+      "rewards/margins": 0.19669394195079803,
+      "rewards/rejected": 0.0015377718955278397,
+      "step": 50
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 10.77029800415039,
+      "learning_rate": 4.753521126760564e-06,
+      "logits/chosen": -1.816936731338501,
+      "logits/rejected": -1.8421777486801147,
+      "logps/chosen": -50.517478942871094,
+      "logps/rejected": -80.6562728881836,
+      "loss": 0.5445,
+      "rewards/accuracies": 0.42500001192092896,
+      "rewards/chosen": 0.4567543864250183,
+      "rewards/margins": 0.42180705070495605,
+      "rewards/rejected": 0.03494739532470703,
+      "step": 60
+    },
+    {
+      "epoch": 0.98,
+      "eval_logits/chosen": -1.784444808959961,
+      "eval_logits/rejected": -1.8030898571014404,
+      "eval_logps/chosen": -53.55432891845703,
+      "eval_logps/rejected": -95.73511505126953,
+      "eval_loss": 0.527186930179596,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 0.4941868484020233,
+      "eval_rewards/margins": 0.47555941343307495,
+      "eval_rewards/rejected": 0.018627464771270752,
+      "eval_runtime": 8.5149,
+      "eval_samples_per_second": 3.288,
+      "eval_steps_per_second": 1.644,
+      "step": 60
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 8.583382606506348,
+      "learning_rate": 4.683098591549296e-06,
+      "logits/chosen": -1.7579460144042969,
+      "logits/rejected": -1.776581048965454,
+      "logps/chosen": -54.420066833496094,
+      "logps/rejected": -79.0608901977539,
+      "loss": 0.451,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": 0.8353117108345032,
+      "rewards/margins": 0.8680375814437866,
+      "rewards/rejected": -0.032725896686315536,
+      "step": 70
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 2.3610572814941406,
+      "learning_rate": 4.612676056338028e-06,
+      "logits/chosen": -1.8833833932876587,
+      "logits/rejected": -1.9092212915420532,
+      "logps/chosen": -25.5800724029541,
+      "logps/rejected": -64.96099853515625,
+      "loss": 0.5302,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.5431563258171082,
+      "rewards/margins": 0.6763826012611389,
+      "rewards/rejected": -0.13322624564170837,
+      "step": 80
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 3.739367723464966,
+      "learning_rate": 4.542253521126761e-06,
+      "logits/chosen": -1.8194096088409424,
+      "logits/rejected": -1.8343127965927124,
+      "logps/chosen": -41.80801773071289,
+      "logps/rejected": -63.005592346191406,
+      "loss": 0.4616,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": 0.830731213092804,
+      "rewards/margins": 0.9403120875358582,
+      "rewards/rejected": -0.109580859541893,
+      "step": 90
+    },
+    {
+      "epoch": 1.46,
+      "eval_logits/chosen": -1.7902206182479858,
+      "eval_logits/rejected": -1.8099161386489868,
+      "eval_logps/chosen": -52.01105880737305,
+      "eval_logps/rejected": -95.83198547363281,
+      "eval_loss": 0.46216800808906555,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 0.957168459892273,
+      "eval_rewards/margins": 0.9676021337509155,
+      "eval_rewards/rejected": -0.010433738119900227,
+      "eval_runtime": 8.5144,
+      "eval_samples_per_second": 3.289,
+      "eval_steps_per_second": 1.644,
+      "step": 90
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.5382364988327026,
+      "learning_rate": 4.471830985915494e-06,
+      "logits/chosen": -1.845868468284607,
+      "logits/rejected": -1.8715919256210327,
+      "logps/chosen": -40.285335540771484,
+      "logps/rejected": -73.16102600097656,
+      "loss": 0.4611,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 1.0631928443908691,
+      "rewards/margins": 1.3067411184310913,
+      "rewards/rejected": -0.24354824423789978,
+      "step": 100
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 12.538246154785156,
+      "learning_rate": 4.401408450704226e-06,
+      "logits/chosen": -1.8342373371124268,
+      "logits/rejected": -1.862433671951294,
+      "logps/chosen": -29.438589096069336,
+      "logps/rejected": -62.31974411010742,
+      "loss": 0.5266,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.7012811899185181,
+      "rewards/margins": 0.8140069246292114,
+      "rewards/rejected": -0.11272567510604858,
+      "step": 110
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 2.3604652881622314,
+      "learning_rate": 4.3309859154929575e-06,
+      "logits/chosen": -1.8481504917144775,
+      "logits/rejected": -1.8528194427490234,
+      "logps/chosen": -35.794334411621094,
+      "logps/rejected": -56.22735595703125,
+      "loss": 0.5327,
+      "rewards/accuracies": 0.32499998807907104,
+      "rewards/chosen": 1.078013300895691,
+      "rewards/margins": 0.9431617856025696,
+      "rewards/rejected": 0.1348516196012497,
+      "step": 120
+    },
+    {
+      "epoch": 1.95,
+      "eval_logits/chosen": -1.7962983846664429,
+      "eval_logits/rejected": -1.8171442747116089,
+      "eval_logps/chosen": -50.74287796020508,
+      "eval_logps/rejected": -96.0649185180664,
+      "eval_loss": 0.4424423575401306,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 1.337624192237854,
+      "eval_rewards/margins": 1.4179356098175049,
+      "eval_rewards/rejected": -0.08031141757965088,
+      "eval_runtime": 8.5188,
+      "eval_samples_per_second": 3.287,
+      "eval_steps_per_second": 1.643,
+      "step": 120
+    },
+    {
+      "epoch": 2.11,
+      "grad_norm": 5.3829216957092285,
+      "learning_rate": 4.26056338028169e-06,
+      "logits/chosen": -1.8153988122940063,
+      "logits/rejected": -1.853118658065796,
+      "logps/chosen": -44.251441955566406,
+      "logps/rejected": -85.38258361816406,
+      "loss": 0.4011,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": 1.5001299381256104,
+      "rewards/margins": 1.9703232049942017,
+      "rewards/rejected": -0.4701933264732361,
+      "step": 130
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 0.6282079815864563,
+      "learning_rate": 4.190140845070423e-06,
+      "logits/chosen": -1.8527545928955078,
+      "logits/rejected": -1.8757705688476562,
+      "logps/chosen": -35.6223258972168,
+      "logps/rejected": -80.99830627441406,
+      "loss": 0.4423,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": 1.484961748123169,
+      "rewards/margins": 1.8964126110076904,
+      "rewards/rejected": -0.41145071387290955,
+      "step": 140
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.0,
+      "learning_rate": 4.119718309859156e-06,
+      "logits/chosen": -1.9129869937896729,
+      "logits/rejected": -1.927869439125061,
+      "logps/chosen": -24.400936126708984,
+      "logps/rejected": -50.861839294433594,
+      "loss": 0.5459,
+      "rewards/accuracies": 0.25,
+      "rewards/chosen": 0.8408910036087036,
+      "rewards/margins": 1.1376488208770752,
+      "rewards/rejected": -0.2967577874660492,
+      "step": 150
+    },
+    {
+      "epoch": 2.44,
+      "eval_logits/chosen": -1.8025389909744263,
+      "eval_logits/rejected": -1.824258804321289,
+      "eval_logps/chosen": -49.72334671020508,
+      "eval_logps/rejected": -96.41252899169922,
+      "eval_loss": 0.4335039258003235,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 1.6434847116470337,
+      "eval_rewards/margins": 1.828076720237732,
+      "eval_rewards/rejected": -0.1845920830965042,
+      "eval_runtime": 8.5149,
+      "eval_samples_per_second": 3.288,
+      "eval_steps_per_second": 1.644,
+      "step": 150
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.7459288239479065,
+      "learning_rate": 4.0492957746478875e-06,
+      "logits/chosen": -1.786231279373169,
+      "logits/rejected": -1.8223682641983032,
+      "logps/chosen": -40.68749237060547,
+      "logps/rejected": -78.1619873046875,
+      "loss": 0.4348,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": 1.9040056467056274,
+      "rewards/margins": 2.482433795928955,
+      "rewards/rejected": -0.5784280896186829,
+      "step": 160
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 1.4669339656829834,
+      "learning_rate": 3.97887323943662e-06,
+      "logits/chosen": -1.8449195623397827,
+      "logits/rejected": -1.871626615524292,
+      "logps/chosen": -46.335182189941406,
+      "logps/rejected": -86.10281372070312,
+      "loss": 0.4232,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 1.8989893198013306,
+      "rewards/margins": 2.384274482727051,
+      "rewards/rejected": -0.4852851927280426,
+      "step": 170
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 0.0301869735121727,
+      "learning_rate": 3.908450704225352e-06,
+      "logits/chosen": -1.8375946283340454,
+      "logits/rejected": -1.8527040481567383,
+      "logps/chosen": -39.01136016845703,
+      "logps/rejected": -65.78593444824219,
+      "loss": 0.4055,
+      "rewards/accuracies": 0.42500001192092896,
+      "rewards/chosen": 1.9841420650482178,
+      "rewards/margins": 2.3045599460601807,
+      "rewards/rejected": -0.32041770219802856,
+      "step": 180
+    },
+    {
+      "epoch": 2.93,
+      "eval_logits/chosen": -1.8074016571044922,
+      "eval_logits/rejected": -1.830051064491272,
+      "eval_logps/chosen": -48.993629455566406,
+      "eval_logps/rejected": -96.92731475830078,
+      "eval_loss": 0.4326101839542389,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 1.8623981475830078,
+      "eval_rewards/margins": 2.201425075531006,
+      "eval_rewards/rejected": -0.3390272557735443,
+      "eval_runtime": 8.5144,
+      "eval_samples_per_second": 3.289,
+      "eval_steps_per_second": 1.644,
+      "step": 180
+    },
+    {
+      "epoch": 3.09,
+      "grad_norm": 2.224493980407715,
+      "learning_rate": 3.838028169014085e-06,
+      "logits/chosen": -1.8459789752960205,
+      "logits/rejected": -1.8675992488861084,
+      "logps/chosen": -32.56737518310547,
+      "logps/rejected": -61.4633674621582,
+      "loss": 0.4576,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": 1.5155870914459229,
+      "rewards/margins": 1.9375633001327515,
+      "rewards/rejected": -0.42197614908218384,
+      "step": 190
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 16.606130599975586,
+      "learning_rate": 3.767605633802817e-06,
+      "logits/chosen": -1.8678531646728516,
+      "logits/rejected": -1.8987194299697876,
+      "logps/chosen": -36.32281494140625,
+      "logps/rejected": -82.02101135253906,
+      "loss": 0.4697,
+      "rewards/accuracies": 0.3499999940395355,
+      "rewards/chosen": 1.7492707967758179,
+      "rewards/margins": 2.534116268157959,
+      "rewards/rejected": -0.7848455309867859,
+      "step": 200
+    },
+    {
+      "epoch": 3.41,
+      "grad_norm": 2.050732135772705,
+      "learning_rate": 3.69718309859155e-06,
+      "logits/chosen": -1.8438726663589478,
+      "logits/rejected": -1.8704954385757446,
+      "logps/chosen": -31.156131744384766,
+      "logps/rejected": -71.87327575683594,
+      "loss": 0.4694,
+      "rewards/accuracies": 0.32499998807907104,
+      "rewards/chosen": 1.7663137912750244,
+      "rewards/margins": 2.468672513961792,
+      "rewards/rejected": -0.702358603477478,
+      "step": 210
+    },
+    {
+      "epoch": 3.41,
+      "eval_logits/chosen": -1.8135889768600464,
+      "eval_logits/rejected": -1.836788535118103,
+      "eval_logps/chosen": -48.54452133178711,
+      "eval_logps/rejected": -97.27555084228516,
+      "eval_loss": 0.43106651306152344,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 1.99713134765625,
+      "eval_rewards/margins": 2.4406321048736572,
+      "eval_rewards/rejected": -0.4435007870197296,
+      "eval_runtime": 8.5161,
+      "eval_samples_per_second": 3.288,
+      "eval_steps_per_second": 1.644,
+      "step": 210
+    },
+    {
+      "epoch": 3.58,
+      "grad_norm": 1.3447190523147583,
+      "learning_rate": 3.626760563380282e-06,
+      "logits/chosen": -1.9027411937713623,
+      "logits/rejected": -1.9270541667938232,
+      "logps/chosen": -31.44101333618164,
+      "logps/rejected": -62.2841911315918,
+      "loss": 0.4686,
+      "rewards/accuracies": 0.32499998807907104,
+      "rewards/chosen": 1.8702812194824219,
+      "rewards/margins": 2.6481127738952637,
+      "rewards/rejected": -0.7778315544128418,
+      "step": 220
+    },
+    {
+      "epoch": 3.74,
+      "grad_norm": 0.8471798300743103,
+      "learning_rate": 3.5563380281690144e-06,
+      "logits/chosen": -1.7770761251449585,
+      "logits/rejected": -1.8111178874969482,
+      "logps/chosen": -48.4028434753418,
+      "logps/rejected": -93.4535903930664,
+      "loss": 0.3062,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": 2.7809433937072754,
+      "rewards/margins": 3.951282501220703,
+      "rewards/rejected": -1.1703392267227173,
+      "step": 230
+    },
+    {
+      "epoch": 3.9,
+      "grad_norm": 0.017692934721708298,
+      "learning_rate": 3.4859154929577467e-06,
+      "logits/chosen": -1.8823143243789673,
+      "logits/rejected": -1.908074975013733,
+      "logps/chosen": -24.35366439819336,
+      "logps/rejected": -55.66550827026367,
+      "loss": 0.5431,
+      "rewards/accuracies": 0.2750000059604645,
+      "rewards/chosen": 1.2430522441864014,
+      "rewards/margins": 1.8208128213882446,
+      "rewards/rejected": -0.577760636806488,
+      "step": 240
+    },
+    {
+      "epoch": 3.9,
+      "eval_logits/chosen": -1.8164188861846924,
+      "eval_logits/rejected": -1.840105652809143,
+      "eval_logps/chosen": -48.241355895996094,
+      "eval_logps/rejected": -97.6273422241211,
+      "eval_loss": 0.4247165322303772,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 2.0880820751190186,
+      "eval_rewards/margins": 2.6371231079101562,
+      "eval_rewards/rejected": -0.5490409731864929,
+      "eval_runtime": 8.5143,
+      "eval_samples_per_second": 3.289,
+      "eval_steps_per_second": 1.644,
+      "step": 240
+    },
+    {
+      "epoch": 4.07,
+      "grad_norm": 0.06990335881710052,
+      "learning_rate": 3.415492957746479e-06,
+      "logits/chosen": -1.855215311050415,
+      "logits/rejected": -1.8647253513336182,
+      "logps/chosen": -41.163124084472656,
+      "logps/rejected": -63.0202751159668,
+      "loss": 0.3954,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": 2.336212635040283,
+      "rewards/margins": 2.88411283493042,
+      "rewards/rejected": -0.5479003190994263,
+      "step": 250
+    },
+    {
+      "epoch": 4.23,
+      "grad_norm": 0.5815927386283875,
+      "learning_rate": 3.3450704225352113e-06,
+      "logits/chosen": -1.9256658554077148,
+      "logits/rejected": -1.930415153503418,
+      "logps/chosen": -24.930946350097656,
+      "logps/rejected": -40.15483474731445,
+      "loss": 0.5089,
+      "rewards/accuracies": 0.2750000059604645,
+      "rewards/chosen": 1.2408175468444824,
+      "rewards/margins": 1.7317492961883545,
+      "rewards/rejected": -0.49093180894851685,
+      "step": 260
+    },
+    {
+      "epoch": 4.39,
+      "grad_norm": 0.38188156485557556,
+      "learning_rate": 3.274647887323944e-06,
+      "logits/chosen": -1.8994340896606445,
+      "logits/rejected": -1.9313939809799194,
+      "logps/chosen": -27.106714248657227,
+      "logps/rejected": -67.90898132324219,
+      "loss": 0.4547,
+      "rewards/accuracies": 0.3499999940395355,
+      "rewards/chosen": 1.7479994297027588,
+      "rewards/margins": 2.5788474082946777,
+      "rewards/rejected": -0.830848217010498,
+      "step": 270
+    },
+    {
+      "epoch": 4.39,
+      "eval_logits/chosen": -1.8190696239471436,
+      "eval_logits/rejected": -1.8433464765548706,
+      "eval_logps/chosen": -47.96824264526367,
+      "eval_logps/rejected": -98.09535217285156,
+      "eval_loss": 0.42961153388023376,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 2.170013666152954,
+      "eval_rewards/margins": 2.8594539165496826,
+      "eval_rewards/rejected": -0.6894403696060181,
+      "eval_runtime": 8.5148,
+      "eval_samples_per_second": 3.288,
+      "eval_steps_per_second": 1.644,
+      "step": 270
+    },
+    {
+      "epoch": 4.55,
+      "grad_norm": 0.3809558153152466,
+      "learning_rate": 3.2042253521126764e-06,
+      "logits/chosen": -1.861537218093872,
+      "logits/rejected": -1.880858063697815,
+      "logps/chosen": -33.568603515625,
+      "logps/rejected": -57.01904296875,
+      "loss": 0.4508,
+      "rewards/accuracies": 0.3499999940395355,
+      "rewards/chosen": 2.471442699432373,
+      "rewards/margins": 3.4677319526672363,
+      "rewards/rejected": -0.996289074420929,
+      "step": 280
+    },
+    {
+      "epoch": 4.72,
+      "grad_norm": 0.03738081455230713,
+      "learning_rate": 3.133802816901409e-06,
+      "logits/chosen": -1.8528019189834595,
+      "logits/rejected": -1.8946154117584229,
+      "logps/chosen": -35.256317138671875,
+      "logps/rejected": -99.2815933227539,
+      "loss": 0.442,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": 1.5687124729156494,
+      "rewards/margins": 3.0280191898345947,
+      "rewards/rejected": -1.4593069553375244,
+      "step": 290
+    },
+    {
+      "epoch": 4.88,
+      "grad_norm": 0.007441267836838961,
+      "learning_rate": 3.063380281690141e-06,
+      "logits/chosen": -1.7671687602996826,
+      "logits/rejected": -1.7900078296661377,
+      "logps/chosen": -58.0703239440918,
+      "logps/rejected": -107.0584487915039,
+      "loss": 0.3606,
+      "rewards/accuracies": 0.550000011920929,
+      "rewards/chosen": 3.007930278778076,
+      "rewards/margins": 4.793817043304443,
+      "rewards/rejected": -1.7858864068984985,
+      "step": 300
+    },
+    {
+      "epoch": 4.88,
+      "eval_logits/chosen": -1.8213108777999878,
+      "eval_logits/rejected": -1.8460028171539307,
+      "eval_logps/chosen": -47.7896842956543,
+      "eval_logps/rejected": -98.4369125366211,
+      "eval_loss": 0.4289851188659668,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 2.223581314086914,
+      "eval_rewards/margins": 3.015495777130127,
+      "eval_rewards/rejected": -0.7919142842292786,
+      "eval_runtime": 8.5154,
+      "eval_samples_per_second": 3.288,
+      "eval_steps_per_second": 1.644,
+      "step": 300
+    },
+    {
+      "epoch": 5.04,
+      "grad_norm": 0.037768810987472534,
+      "learning_rate": 2.9929577464788733e-06,
+      "logits/chosen": -1.8851121664047241,
+      "logits/rejected": -1.9122593402862549,
+      "logps/chosen": -21.110910415649414,
+      "logps/rejected": -48.944602966308594,
+      "loss": 0.4731,
+      "rewards/accuracies": 0.32499998807907104,
+      "rewards/chosen": 1.653512954711914,
+      "rewards/margins": 2.38820219039917,
+      "rewards/rejected": -0.7346888780593872,
+      "step": 310
+    },
+    {
+      "epoch": 5.2,
+      "grad_norm": 0.0,
+      "learning_rate": 2.922535211267606e-06,
+      "logits/chosen": -1.8363854885101318,
+      "logits/rejected": -1.869361162185669,
+      "logps/chosen": -36.65054702758789,
+      "logps/rejected": -84.7163314819336,
+      "loss": 0.3992,
+      "rewards/accuracies": 0.42500001192092896,
+      "rewards/chosen": 2.3141231536865234,
+      "rewards/margins": 3.9065093994140625,
+      "rewards/rejected": -1.5923866033554077,
+      "step": 320
+    },
+    {
+      "epoch": 5.37,
+      "grad_norm": 0.08495225757360458,
+      "learning_rate": 2.8521126760563383e-06,
+      "logits/chosen": -1.854119062423706,
+      "logits/rejected": -1.8729274272918701,
+      "logps/chosen": -40.588775634765625,
+      "logps/rejected": -68.68611145019531,
+      "loss": 0.4021,
+      "rewards/accuracies": 0.42500001192092896,
+      "rewards/chosen": 2.146328926086426,
+      "rewards/margins": 3.4630661010742188,
+      "rewards/rejected": -1.3167372941970825,
+      "step": 330
+    },
+    {
+      "epoch": 5.37,
+      "eval_logits/chosen": -1.8219343423843384,
+      "eval_logits/rejected": -1.8470803499221802,
+      "eval_logps/chosen": -47.683902740478516,
+      "eval_logps/rejected": -98.87833404541016,
+      "eval_loss": 0.4302048683166504,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 2.255316734313965,
+      "eval_rewards/margins": 3.179651975631714,
+      "eval_rewards/rejected": -0.9243355989456177,
+      "eval_runtime": 8.5149,
+      "eval_samples_per_second": 3.288,
+      "eval_steps_per_second": 1.644,
+      "step": 330
+    },
+    {
+      "epoch": 5.53,
+      "grad_norm": 0.00047089156578294933,
+      "learning_rate": 2.781690140845071e-06,
+      "logits/chosen": -1.9298601150512695,
+      "logits/rejected": -1.9418340921401978,
+      "logps/chosen": -28.818872451782227,
+      "logps/rejected": -59.13349151611328,
+      "loss": 0.5413,
+      "rewards/accuracies": 0.2750000059604645,
+      "rewards/chosen": 1.8383833169937134,
+      "rewards/margins": 2.883132219314575,
+      "rewards/rejected": -1.0447486639022827,
+      "step": 340
+    },
+    {
+      "epoch": 5.69,
+      "grad_norm": 2.729531764984131,
+      "learning_rate": 2.7112676056338033e-06,
+      "logits/chosen": -1.8659921884536743,
+      "logits/rejected": -1.905010461807251,
+      "logps/chosen": -27.63974380493164,
+      "logps/rejected": -73.26609802246094,
+      "loss": 0.4368,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": 2.2738237380981445,
+      "rewards/margins": 3.4326729774475098,
+      "rewards/rejected": -1.1588493585586548,
+      "step": 350
+    },
+    {
+      "epoch": 5.85,
+      "grad_norm": 0.01013993564993143,
+      "learning_rate": 2.640845070422535e-06,
+      "logits/chosen": -1.8495924472808838,
+      "logits/rejected": -1.8761341571807861,
+      "logps/chosen": -33.9546012878418,
+      "logps/rejected": -70.13398742675781,
+      "loss": 0.419,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 2.0099234580993652,
+      "rewards/margins": 3.498170852661133,
+      "rewards/rejected": -1.488247275352478,
+      "step": 360
+    },
+    {
+      "epoch": 5.85,
+      "eval_logits/chosen": -1.8214120864868164,
+      "eval_logits/rejected": -1.8469568490982056,
+      "eval_logps/chosen": -47.67514419555664,
+      "eval_logps/rejected": -99.1513900756836,
+      "eval_loss": 0.43358945846557617,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 2.257944107055664,
+      "eval_rewards/margins": 3.264200210571289,
+      "eval_rewards/rejected": -1.0062559843063354,
+      "eval_runtime": 8.5148,
+      "eval_samples_per_second": 3.288,
+      "eval_steps_per_second": 1.644,
+      "step": 360
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 732,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "save_steps": 90,
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-360/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a9e56dbe2b48a488c5411e841b81929760b46d9a622b353a65d00ada1e6a94f
+size 5304

checkpoint-450/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-450/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-450/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27d48ea2bf443ece7a72d5b3bf45f5ce7ca671022c02bd7248f1870fd1094097
+size 13648432

checkpoint-450/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caa00dde6fb238c90b99ba545681ee9fe3580559c7e15bfdb8bcf50f02ddba78
+size 27370618

checkpoint-450/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d04e53e20ff2f98d1790a767178a0a2c6628c3c02f82f462c756ee89c4a2140
+size 14244

checkpoint-450/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9e5df58b309e8dbe4c69c46c6d0eae21a283223ca4c98c136b173192d0eb0ff
+size 1064

checkpoint-450/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-450/tokenizer.model

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

checkpoint-450/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-450/trainer_state.json

@@ -0,0 +1,936 @@
+{
+  "best_metric": 0.42961153388023376,
+  "best_model_checkpoint": "./mistral/19-04-24-Weni-WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.4-DPO_Experiment on DPO with other hyperparameters and best SFT model of WeniGPT-2_max_steps-732_batch_4_2024-04-19_ppid_9/checkpoint-270",
+  "epoch": 7.317073170731708,
+  "eval_steps": 30,
+  "global_step": 450,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "grad_norm": 38.021175384521484,
+      "learning_rate": 1.590909090909091e-06,
+      "logits/chosen": -1.7808929681777954,
+      "logits/rejected": -1.8136215209960938,
+      "logps/chosen": -52.2663688659668,
+      "logps/rejected": -88.76155853271484,
+      "loss": 0.6927,
+      "rewards/accuracies": 0.20000000298023224,
+      "rewards/chosen": 0.0008833981119096279,
+      "rewards/margins": 0.0009520913590677083,
+      "rewards/rejected": -6.869318895041943e-05,
+      "step": 10
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 19.505126953125,
+      "learning_rate": 3.863636363636364e-06,
+      "logits/chosen": -1.865220308303833,
+      "logits/rejected": -1.880090355873108,
+      "logps/chosen": -34.3599967956543,
+      "logps/rejected": -53.656646728515625,
+      "loss": 0.6846,
+      "rewards/accuracies": 0.22499999403953552,
+      "rewards/chosen": 0.019346294924616814,
+      "rewards/margins": 0.017682768404483795,
+      "rewards/rejected": 0.0016635276842862368,
+      "step": 20
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 16.67194938659668,
+      "learning_rate": 4.964788732394366e-06,
+      "logits/chosen": -1.7692855596542358,
+      "logits/rejected": -1.7932851314544678,
+      "logps/chosen": -38.679237365722656,
+      "logps/rejected": -79.23713684082031,
+      "loss": 0.665,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": 0.07158979028463364,
+      "rewards/margins": 0.061105482280254364,
+      "rewards/rejected": 0.010484304279088974,
+      "step": 30
+    },
+    {
+      "epoch": 0.49,
+      "eval_logits/chosen": -1.7801028490066528,
+      "eval_logits/rejected": -1.7981160879135132,
+      "eval_logps/chosen": -54.71597671508789,
+      "eval_logps/rejected": -95.75775909423828,
+      "eval_loss": 0.6322354674339294,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 0.14569346606731415,
+      "eval_rewards/margins": 0.13385750353336334,
+      "eval_rewards/rejected": 0.011835969984531403,
+      "eval_runtime": 8.5124,
+      "eval_samples_per_second": 3.289,
+      "eval_steps_per_second": 1.645,
+      "step": 30
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 22.69721031188965,
+      "learning_rate": 4.894366197183099e-06,
+      "logits/chosen": -1.8458446264266968,
+      "logits/rejected": -1.8594070672988892,
+      "logps/chosen": -39.180992126464844,
+      "logps/rejected": -57.04741287231445,
+      "loss": 0.6164,
+      "rewards/accuracies": 0.3499999940395355,
+      "rewards/chosen": 0.19042351841926575,
+      "rewards/margins": 0.18086455762386322,
+      "rewards/rejected": 0.009558964520692825,
+      "step": 40
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.0,
+      "learning_rate": 4.823943661971832e-06,
+      "logits/chosen": -1.8411815166473389,
+      "logits/rejected": -1.8659855127334595,
+      "logps/chosen": -31.194744110107422,
+      "logps/rejected": -58.17326736450195,
+      "loss": 0.6138,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.19823171198368073,
+      "rewards/margins": 0.19669394195079803,
+      "rewards/rejected": 0.0015377718955278397,
+      "step": 50
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 10.77029800415039,
+      "learning_rate": 4.753521126760564e-06,
+      "logits/chosen": -1.816936731338501,
+      "logits/rejected": -1.8421777486801147,
+      "logps/chosen": -50.517478942871094,
+      "logps/rejected": -80.6562728881836,
+      "loss": 0.5445,
+      "rewards/accuracies": 0.42500001192092896,
+      "rewards/chosen": 0.4567543864250183,
+      "rewards/margins": 0.42180705070495605,
+      "rewards/rejected": 0.03494739532470703,
+      "step": 60
+    },
+    {
+      "epoch": 0.98,
+      "eval_logits/chosen": -1.784444808959961,
+      "eval_logits/rejected": -1.8030898571014404,
+      "eval_logps/chosen": -53.55432891845703,
+      "eval_logps/rejected": -95.73511505126953,
+      "eval_loss": 0.527186930179596,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 0.4941868484020233,
+      "eval_rewards/margins": 0.47555941343307495,
+      "eval_rewards/rejected": 0.018627464771270752,
+      "eval_runtime": 8.5149,
+      "eval_samples_per_second": 3.288,
+      "eval_steps_per_second": 1.644,
+      "step": 60
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 8.583382606506348,
+      "learning_rate": 4.683098591549296e-06,
+      "logits/chosen": -1.7579460144042969,
+      "logits/rejected": -1.776581048965454,
+      "logps/chosen": -54.420066833496094,
+      "logps/rejected": -79.0608901977539,
+      "loss": 0.451,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": 0.8353117108345032,
+      "rewards/margins": 0.8680375814437866,
+      "rewards/rejected": -0.032725896686315536,
+      "step": 70
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 2.3610572814941406,
+      "learning_rate": 4.612676056338028e-06,
+      "logits/chosen": -1.8833833932876587,
+      "logits/rejected": -1.9092212915420532,
+      "logps/chosen": -25.5800724029541,
+      "logps/rejected": -64.96099853515625,
+      "loss": 0.5302,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.5431563258171082,
+      "rewards/margins": 0.6763826012611389,
+      "rewards/rejected": -0.13322624564170837,
+      "step": 80
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 3.739367723464966,
+      "learning_rate": 4.542253521126761e-06,
+      "logits/chosen": -1.8194096088409424,
+      "logits/rejected": -1.8343127965927124,
+      "logps/chosen": -41.80801773071289,
+      "logps/rejected": -63.005592346191406,
+      "loss": 0.4616,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": 0.830731213092804,
+      "rewards/margins": 0.9403120875358582,
+      "rewards/rejected": -0.109580859541893,
+      "step": 90
+    },
+    {
+      "epoch": 1.46,
+      "eval_logits/chosen": -1.7902206182479858,
+      "eval_logits/rejected": -1.8099161386489868,
+      "eval_logps/chosen": -52.01105880737305,
+      "eval_logps/rejected": -95.83198547363281,
+      "eval_loss": 0.46216800808906555,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 0.957168459892273,
+      "eval_rewards/margins": 0.9676021337509155,
+      "eval_rewards/rejected": -0.010433738119900227,
+      "eval_runtime": 8.5144,
+      "eval_samples_per_second": 3.289,
+      "eval_steps_per_second": 1.644,
+      "step": 90
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.5382364988327026,
+      "learning_rate": 4.471830985915494e-06,
+      "logits/chosen": -1.845868468284607,
+      "logits/rejected": -1.8715919256210327,
+      "logps/chosen": -40.285335540771484,
+      "logps/rejected": -73.16102600097656,
+      "loss": 0.4611,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 1.0631928443908691,
+      "rewards/margins": 1.3067411184310913,
+      "rewards/rejected": -0.24354824423789978,
+      "step": 100
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 12.538246154785156,
+      "learning_rate": 4.401408450704226e-06,
+      "logits/chosen": -1.8342373371124268,
+      "logits/rejected": -1.862433671951294,
+      "logps/chosen": -29.438589096069336,
+      "logps/rejected": -62.31974411010742,
+      "loss": 0.5266,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.7012811899185181,
+      "rewards/margins": 0.8140069246292114,
+      "rewards/rejected": -0.11272567510604858,
+      "step": 110
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 2.3604652881622314,
+      "learning_rate": 4.3309859154929575e-06,
+      "logits/chosen": -1.8481504917144775,
+      "logits/rejected": -1.8528194427490234,
+      "logps/chosen": -35.794334411621094,
+      "logps/rejected": -56.22735595703125,
+      "loss": 0.5327,
+      "rewards/accuracies": 0.32499998807907104,
+      "rewards/chosen": 1.078013300895691,
+      "rewards/margins": 0.9431617856025696,
+      "rewards/rejected": 0.1348516196012497,
+      "step": 120
+    },
+    {
+      "epoch": 1.95,
+      "eval_logits/chosen": -1.7962983846664429,
+      "eval_logits/rejected": -1.8171442747116089,
+      "eval_logps/chosen": -50.74287796020508,
+      "eval_logps/rejected": -96.0649185180664,
+      "eval_loss": 0.4424423575401306,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 1.337624192237854,
+      "eval_rewards/margins": 1.4179356098175049,
+      "eval_rewards/rejected": -0.08031141757965088,
+      "eval_runtime": 8.5188,
+      "eval_samples_per_second": 3.287,
+      "eval_steps_per_second": 1.643,
+      "step": 120
+    },
+    {
+      "epoch": 2.11,
+      "grad_norm": 5.3829216957092285,
+      "learning_rate": 4.26056338028169e-06,
+      "logits/chosen": -1.8153988122940063,
+      "logits/rejected": -1.853118658065796,
+      "logps/chosen": -44.251441955566406,
+      "logps/rejected": -85.38258361816406,
+      "loss": 0.4011,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": 1.5001299381256104,
+      "rewards/margins": 1.9703232049942017,
+      "rewards/rejected": -0.4701933264732361,
+      "step": 130
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 0.6282079815864563,
+      "learning_rate": 4.190140845070423e-06,
+      "logits/chosen": -1.8527545928955078,
+      "logits/rejected": -1.8757705688476562,
+      "logps/chosen": -35.6223258972168,
+      "logps/rejected": -80.99830627441406,
+      "loss": 0.4423,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": 1.484961748123169,
+      "rewards/margins": 1.8964126110076904,
+      "rewards/rejected": -0.41145071387290955,
+      "step": 140
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.0,
+      "learning_rate": 4.119718309859156e-06,
+      "logits/chosen": -1.9129869937896729,
+      "logits/rejected": -1.927869439125061,
+      "logps/chosen": -24.400936126708984,
+      "logps/rejected": -50.861839294433594,
+      "loss": 0.5459,
+      "rewards/accuracies": 0.25,
+      "rewards/chosen": 0.8408910036087036,
+      "rewards/margins": 1.1376488208770752,
+      "rewards/rejected": -0.2967577874660492,
+      "step": 150
+    },
+    {
+      "epoch": 2.44,
+      "eval_logits/chosen": -1.8025389909744263,
+      "eval_logits/rejected": -1.824258804321289,
+      "eval_logps/chosen": -49.72334671020508,
+      "eval_logps/rejected": -96.41252899169922,
+      "eval_loss": 0.4335039258003235,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 1.6434847116470337,
+      "eval_rewards/margins": 1.828076720237732,
+      "eval_rewards/rejected": -0.1845920830965042,
+      "eval_runtime": 8.5149,
+      "eval_samples_per_second": 3.288,
+      "eval_steps_per_second": 1.644,
+      "step": 150
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.7459288239479065,
+      "learning_rate": 4.0492957746478875e-06,
+      "logits/chosen": -1.786231279373169,
+      "logits/rejected": -1.8223682641983032,
+      "logps/chosen": -40.68749237060547,
+      "logps/rejected": -78.1619873046875,
+      "loss": 0.4348,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": 1.9040056467056274,
+      "rewards/margins": 2.482433795928955,
+      "rewards/rejected": -0.5784280896186829,
+      "step": 160
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 1.4669339656829834,
+      "learning_rate": 3.97887323943662e-06,
+      "logits/chosen": -1.8449195623397827,
+      "logits/rejected": -1.871626615524292,
+      "logps/chosen": -46.335182189941406,
+      "logps/rejected": -86.10281372070312,
+      "loss": 0.4232,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 1.8989893198013306,
+      "rewards/margins": 2.384274482727051,
+      "rewards/rejected": -0.4852851927280426,
+      "step": 170
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 0.0301869735121727,
+      "learning_rate": 3.908450704225352e-06,
+      "logits/chosen": -1.8375946283340454,
+      "logits/rejected": -1.8527040481567383,
+      "logps/chosen": -39.01136016845703,
+      "logps/rejected": -65.78593444824219,
+      "loss": 0.4055,
+      "rewards/accuracies": 0.42500001192092896,
+      "rewards/chosen": 1.9841420650482178,
+      "rewards/margins": 2.3045599460601807,
+      "rewards/rejected": -0.32041770219802856,
+      "step": 180
+    },
+    {
+      "epoch": 2.93,
+      "eval_logits/chosen": -1.8074016571044922,
+      "eval_logits/rejected": -1.830051064491272,
+      "eval_logps/chosen": -48.993629455566406,
+      "eval_logps/rejected": -96.92731475830078,
+      "eval_loss": 0.4326101839542389,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 1.8623981475830078,
+      "eval_rewards/margins": 2.201425075531006,
+      "eval_rewards/rejected": -0.3390272557735443,
+      "eval_runtime": 8.5144,
+      "eval_samples_per_second": 3.289,
+      "eval_steps_per_second": 1.644,
+      "step": 180
+    },
+    {
+      "epoch": 3.09,
+      "grad_norm": 2.224493980407715,
+      "learning_rate": 3.838028169014085e-06,
+      "logits/chosen": -1.8459789752960205,
+      "logits/rejected": -1.8675992488861084,
+      "logps/chosen": -32.56737518310547,
+      "logps/rejected": -61.4633674621582,
+      "loss": 0.4576,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": 1.5155870914459229,
+      "rewards/margins": 1.9375633001327515,
+      "rewards/rejected": -0.42197614908218384,
+      "step": 190
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 16.606130599975586,
+      "learning_rate": 3.767605633802817e-06,
+      "logits/chosen": -1.8678531646728516,
+      "logits/rejected": -1.8987194299697876,
+      "logps/chosen": -36.32281494140625,
+      "logps/rejected": -82.02101135253906,
+      "loss": 0.4697,
+      "rewards/accuracies": 0.3499999940395355,
+      "rewards/chosen": 1.7492707967758179,
+      "rewards/margins": 2.534116268157959,
+      "rewards/rejected": -0.7848455309867859,
+      "step": 200
+    },
+    {
+      "epoch": 3.41,
+      "grad_norm": 2.050732135772705,
+      "learning_rate": 3.69718309859155e-06,
+      "logits/chosen": -1.8438726663589478,
+      "logits/rejected": -1.8704954385757446,
+      "logps/chosen": -31.156131744384766,
+      "logps/rejected": -71.87327575683594,
+      "loss": 0.4694,
+      "rewards/accuracies": 0.32499998807907104,
+      "rewards/chosen": 1.7663137912750244,
+      "rewards/margins": 2.468672513961792,
+      "rewards/rejected": -0.702358603477478,
+      "step": 210
+    },
+    {
+      "epoch": 3.41,
+      "eval_logits/chosen": -1.8135889768600464,
+      "eval_logits/rejected": -1.836788535118103,
+      "eval_logps/chosen": -48.54452133178711,
+      "eval_logps/rejected": -97.27555084228516,
+      "eval_loss": 0.43106651306152344,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 1.99713134765625,
+      "eval_rewards/margins": 2.4406321048736572,
+      "eval_rewards/rejected": -0.4435007870197296,
+      "eval_runtime": 8.5161,
+      "eval_samples_per_second": 3.288,
+      "eval_steps_per_second": 1.644,
+      "step": 210
+    },
+    {
+      "epoch": 3.58,
+      "grad_norm": 1.3447190523147583,
+      "learning_rate": 3.626760563380282e-06,
+      "logits/chosen": -1.9027411937713623,
+      "logits/rejected": -1.9270541667938232,
+      "logps/chosen": -31.44101333618164,
+      "logps/rejected": -62.2841911315918,
+      "loss": 0.4686,
+      "rewards/accuracies": 0.32499998807907104,
+      "rewards/chosen": 1.8702812194824219,
+      "rewards/margins": 2.6481127738952637,
+      "rewards/rejected": -0.7778315544128418,
+      "step": 220
+    },
+    {
+      "epoch": 3.74,
+      "grad_norm": 0.8471798300743103,
+      "learning_rate": 3.5563380281690144e-06,
+      "logits/chosen": -1.7770761251449585,
+      "logits/rejected": -1.8111178874969482,
+      "logps/chosen": -48.4028434753418,
+      "logps/rejected": -93.4535903930664,
+      "loss": 0.3062,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": 2.7809433937072754,
+      "rewards/margins": 3.951282501220703,
+      "rewards/rejected": -1.1703392267227173,
+      "step": 230
+    },
+    {
+      "epoch": 3.9,
+      "grad_norm": 0.017692934721708298,
+      "learning_rate": 3.4859154929577467e-06,
+      "logits/chosen": -1.8823143243789673,
+      "logits/rejected": -1.908074975013733,
+      "logps/chosen": -24.35366439819336,
+      "logps/rejected": -55.66550827026367,
+      "loss": 0.5431,
+      "rewards/accuracies": 0.2750000059604645,
+      "rewards/chosen": 1.2430522441864014,
+      "rewards/margins": 1.8208128213882446,
+      "rewards/rejected": -0.577760636806488,
+      "step": 240
+    },
+    {
+      "epoch": 3.9,
+      "eval_logits/chosen": -1.8164188861846924,
+      "eval_logits/rejected": -1.840105652809143,
+      "eval_logps/chosen": -48.241355895996094,
+      "eval_logps/rejected": -97.6273422241211,
+      "eval_loss": 0.4247165322303772,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 2.0880820751190186,
+      "eval_rewards/margins": 2.6371231079101562,
+      "eval_rewards/rejected": -0.5490409731864929,
+      "eval_runtime": 8.5143,
+      "eval_samples_per_second": 3.289,
+      "eval_steps_per_second": 1.644,
+      "step": 240
+    },
+    {
+      "epoch": 4.07,
+      "grad_norm": 0.06990335881710052,
+      "learning_rate": 3.415492957746479e-06,
+      "logits/chosen": -1.855215311050415,
+      "logits/rejected": -1.8647253513336182,
+      "logps/chosen": -41.163124084472656,
+      "logps/rejected": -63.0202751159668,
+      "loss": 0.3954,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": 2.336212635040283,
+      "rewards/margins": 2.88411283493042,
+      "rewards/rejected": -0.5479003190994263,
+      "step": 250
+    },
+    {
+      "epoch": 4.23,
+      "grad_norm": 0.5815927386283875,
+      "learning_rate": 3.3450704225352113e-06,
+      "logits/chosen": -1.9256658554077148,
+      "logits/rejected": -1.930415153503418,
+      "logps/chosen": -24.930946350097656,
+      "logps/rejected": -40.15483474731445,
+      "loss": 0.5089,
+      "rewards/accuracies": 0.2750000059604645,
+      "rewards/chosen": 1.2408175468444824,
+      "rewards/margins": 1.7317492961883545,
+      "rewards/rejected": -0.49093180894851685,
+      "step": 260
+    },
+    {
+      "epoch": 4.39,
+      "grad_norm": 0.38188156485557556,
+      "learning_rate": 3.274647887323944e-06,
+      "logits/chosen": -1.8994340896606445,
+      "logits/rejected": -1.9313939809799194,
+      "logps/chosen": -27.106714248657227,
+      "logps/rejected": -67.90898132324219,
+      "loss": 0.4547,
+      "rewards/accuracies": 0.3499999940395355,
+      "rewards/chosen": 1.7479994297027588,
+      "rewards/margins": 2.5788474082946777,
+      "rewards/rejected": -0.830848217010498,
+      "step": 270
+    },
+    {
+      "epoch": 4.39,
+      "eval_logits/chosen": -1.8190696239471436,
+      "eval_logits/rejected": -1.8433464765548706,
+      "eval_logps/chosen": -47.96824264526367,
+      "eval_logps/rejected": -98.09535217285156,
+      "eval_loss": 0.42961153388023376,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 2.170013666152954,
+      "eval_rewards/margins": 2.8594539165496826,
+      "eval_rewards/rejected": -0.6894403696060181,
+      "eval_runtime": 8.5148,
+      "eval_samples_per_second": 3.288,
+      "eval_steps_per_second": 1.644,
+      "step": 270
+    },
+    {
+      "epoch": 4.55,
+      "grad_norm": 0.3809558153152466,
+      "learning_rate": 3.2042253521126764e-06,
+      "logits/chosen": -1.861537218093872,
+      "logits/rejected": -1.880858063697815,
+      "logps/chosen": -33.568603515625,
+      "logps/rejected": -57.01904296875,
+      "loss": 0.4508,
+      "rewards/accuracies": 0.3499999940395355,
+      "rewards/chosen": 2.471442699432373,
+      "rewards/margins": 3.4677319526672363,
+      "rewards/rejected": -0.996289074420929,
+      "step": 280
+    },
+    {
+      "epoch": 4.72,
+      "grad_norm": 0.03738081455230713,
+      "learning_rate": 3.133802816901409e-06,
+      "logits/chosen": -1.8528019189834595,
+      "logits/rejected": -1.8946154117584229,
+      "logps/chosen": -35.256317138671875,
+      "logps/rejected": -99.2815933227539,
+      "loss": 0.442,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": 1.5687124729156494,
+      "rewards/margins": 3.0280191898345947,
+      "rewards/rejected": -1.4593069553375244,
+      "step": 290
+    },
+    {
+      "epoch": 4.88,
+      "grad_norm": 0.007441267836838961,
+      "learning_rate": 3.063380281690141e-06,
+      "logits/chosen": -1.7671687602996826,
+      "logits/rejected": -1.7900078296661377,
+      "logps/chosen": -58.0703239440918,
+      "logps/rejected": -107.0584487915039,
+      "loss": 0.3606,
+      "rewards/accuracies": 0.550000011920929,
+      "rewards/chosen": 3.007930278778076,
+      "rewards/margins": 4.793817043304443,
+      "rewards/rejected": -1.7858864068984985,
+      "step": 300
+    },
+    {
+      "epoch": 4.88,
+      "eval_logits/chosen": -1.8213108777999878,
+      "eval_logits/rejected": -1.8460028171539307,
+      "eval_logps/chosen": -47.7896842956543,
+      "eval_logps/rejected": -98.4369125366211,
+      "eval_loss": 0.4289851188659668,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 2.223581314086914,
+      "eval_rewards/margins": 3.015495777130127,
+      "eval_rewards/rejected": -0.7919142842292786,
+      "eval_runtime": 8.5154,
+      "eval_samples_per_second": 3.288,
+      "eval_steps_per_second": 1.644,
+      "step": 300
+    },
+    {
+      "epoch": 5.04,
+      "grad_norm": 0.037768810987472534,
+      "learning_rate": 2.9929577464788733e-06,
+      "logits/chosen": -1.8851121664047241,
+      "logits/rejected": -1.9122593402862549,
+      "logps/chosen": -21.110910415649414,
+      "logps/rejected": -48.944602966308594,
+      "loss": 0.4731,
+      "rewards/accuracies": 0.32499998807907104,
+      "rewards/chosen": 1.653512954711914,
+      "rewards/margins": 2.38820219039917,
+      "rewards/rejected": -0.7346888780593872,
+      "step": 310
+    },
+    {
+      "epoch": 5.2,
+      "grad_norm": 0.0,
+      "learning_rate": 2.922535211267606e-06,
+      "logits/chosen": -1.8363854885101318,
+      "logits/rejected": -1.869361162185669,
+      "logps/chosen": -36.65054702758789,
+      "logps/rejected": -84.7163314819336,
+      "loss": 0.3992,
+      "rewards/accuracies": 0.42500001192092896,
+      "rewards/chosen": 2.3141231536865234,
+      "rewards/margins": 3.9065093994140625,
+      "rewards/rejected": -1.5923866033554077,
+      "step": 320
+    },
+    {
+      "epoch": 5.37,
+      "grad_norm": 0.08495225757360458,
+      "learning_rate": 2.8521126760563383e-06,
+      "logits/chosen": -1.854119062423706,
+      "logits/rejected": -1.8729274272918701,
+      "logps/chosen": -40.588775634765625,
+      "logps/rejected": -68.68611145019531,
+      "loss": 0.4021,
+      "rewards/accuracies": 0.42500001192092896,
+      "rewards/chosen": 2.146328926086426,
+      "rewards/margins": 3.4630661010742188,
+      "rewards/rejected": -1.3167372941970825,
+      "step": 330
+    },
+    {
+      "epoch": 5.37,
+      "eval_logits/chosen": -1.8219343423843384,
+      "eval_logits/rejected": -1.8470803499221802,
+      "eval_logps/chosen": -47.683902740478516,
+      "eval_logps/rejected": -98.87833404541016,
+      "eval_loss": 0.4302048683166504,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 2.255316734313965,
+      "eval_rewards/margins": 3.179651975631714,
+      "eval_rewards/rejected": -0.9243355989456177,
+      "eval_runtime": 8.5149,
+      "eval_samples_per_second": 3.288,
+      "eval_steps_per_second": 1.644,
+      "step": 330
+    },
+    {
+      "epoch": 5.53,
+      "grad_norm": 0.00047089156578294933,
+      "learning_rate": 2.781690140845071e-06,
+      "logits/chosen": -1.9298601150512695,
+      "logits/rejected": -1.9418340921401978,
+      "logps/chosen": -28.818872451782227,
+      "logps/rejected": -59.13349151611328,
+      "loss": 0.5413,
+      "rewards/accuracies": 0.2750000059604645,
+      "rewards/chosen": 1.8383833169937134,
+      "rewards/margins": 2.883132219314575,
+      "rewards/rejected": -1.0447486639022827,
+      "step": 340
+    },
+    {
+      "epoch": 5.69,
+      "grad_norm": 2.729531764984131,
+      "learning_rate": 2.7112676056338033e-06,
+      "logits/chosen": -1.8659921884536743,
+      "logits/rejected": -1.905010461807251,
+      "logps/chosen": -27.63974380493164,
+      "logps/rejected": -73.26609802246094,
+      "loss": 0.4368,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": 2.2738237380981445,
+      "rewards/margins": 3.4326729774475098,
+      "rewards/rejected": -1.1588493585586548,
+      "step": 350
+    },
+    {
+      "epoch": 5.85,
+      "grad_norm": 0.01013993564993143,
+      "learning_rate": 2.640845070422535e-06,
+      "logits/chosen": -1.8495924472808838,
+      "logits/rejected": -1.8761341571807861,
+      "logps/chosen": -33.9546012878418,
+      "logps/rejected": -70.13398742675781,
+      "loss": 0.419,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 2.0099234580993652,
+      "rewards/margins": 3.498170852661133,
+      "rewards/rejected": -1.488247275352478,
+      "step": 360
+    },
+    {
+      "epoch": 5.85,
+      "eval_logits/chosen": -1.8214120864868164,
+      "eval_logits/rejected": -1.8469568490982056,
+      "eval_logps/chosen": -47.67514419555664,
+      "eval_logps/rejected": -99.1513900756836,
+      "eval_loss": 0.43358945846557617,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 2.257944107055664,
+      "eval_rewards/margins": 3.264200210571289,
+      "eval_rewards/rejected": -1.0062559843063354,
+      "eval_runtime": 8.5148,
+      "eval_samples_per_second": 3.288,
+      "eval_steps_per_second": 1.644,
+      "step": 360
+    },
+    {
+      "epoch": 6.02,
+      "grad_norm": 0.10058386623859406,
+      "learning_rate": 2.570422535211268e-06,
+      "logits/chosen": -1.8099803924560547,
+      "logits/rejected": -1.8450464010238647,
+      "logps/chosen": -40.64691925048828,
+      "logps/rejected": -88.50006103515625,
+      "loss": 0.4072,
+      "rewards/accuracies": 0.42500001192092896,
+      "rewards/chosen": 2.367983341217041,
+      "rewards/margins": 3.652095079421997,
+      "rewards/rejected": -1.2841118574142456,
+      "step": 370
+    },
+    {
+      "epoch": 6.18,
+      "grad_norm": 0.0,
+      "learning_rate": 2.5e-06,
+      "logits/chosen": -1.8781477212905884,
+      "logits/rejected": -1.9100782871246338,
+      "logps/chosen": -33.296836853027344,
+      "logps/rejected": -83.65415954589844,
+      "loss": 0.4006,
+      "rewards/accuracies": 0.42500001192092896,
+      "rewards/chosen": 2.6570353507995605,
+      "rewards/margins": 4.220401763916016,
+      "rewards/rejected": -1.5633666515350342,
+      "step": 380
+    },
+    {
+      "epoch": 6.34,
+      "grad_norm": 0.6534411907196045,
+      "learning_rate": 2.4295774647887325e-06,
+      "logits/chosen": -1.8289324045181274,
+      "logits/rejected": -1.8389921188354492,
+      "logps/chosen": -46.14112091064453,
+      "logps/rejected": -61.8495979309082,
+      "loss": 0.3984,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": 2.3760623931884766,
+      "rewards/margins": 3.9815852642059326,
+      "rewards/rejected": -1.605522871017456,
+      "step": 390
+    },
+    {
+      "epoch": 6.34,
+      "eval_logits/chosen": -1.824257493019104,
+      "eval_logits/rejected": -1.8499394655227661,
+      "eval_logps/chosen": -47.629581451416016,
+      "eval_logps/rejected": -99.36784362792969,
+      "eval_loss": 0.42913129925727844,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 2.2716121673583984,
+      "eval_rewards/margins": 3.3427982330322266,
+      "eval_rewards/rejected": -1.0711863040924072,
+      "eval_runtime": 8.5204,
+      "eval_samples_per_second": 3.286,
+      "eval_steps_per_second": 1.643,
+      "step": 390
+    },
+    {
+      "epoch": 6.5,
+      "grad_norm": 0.10979699343442917,
+      "learning_rate": 2.359154929577465e-06,
+      "logits/chosen": -1.8595476150512695,
+      "logits/rejected": -1.8786380290985107,
+      "logps/chosen": -36.14017105102539,
+      "logps/rejected": -69.46199798583984,
+      "loss": 0.4672,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": 2.0604913234710693,
+      "rewards/margins": 3.718773365020752,
+      "rewards/rejected": -1.658281683921814,
+      "step": 400
+    },
+    {
+      "epoch": 6.67,
+      "grad_norm": 0.00019151422020513564,
+      "learning_rate": 2.2887323943661975e-06,
+      "logits/chosen": -1.8760582208633423,
+      "logits/rejected": -1.903466820716858,
+      "logps/chosen": -28.268178939819336,
+      "logps/rejected": -71.25038146972656,
+      "loss": 0.468,
+      "rewards/accuracies": 0.32499998807907104,
+      "rewards/chosen": 2.309755802154541,
+      "rewards/margins": 3.500605344772339,
+      "rewards/rejected": -1.190850019454956,
+      "step": 410
+    },
+    {
+      "epoch": 6.83,
+      "grad_norm": 0.015070440247654915,
+      "learning_rate": 2.21830985915493e-06,
+      "logits/chosen": -1.877672553062439,
+      "logits/rejected": -1.8992106914520264,
+      "logps/chosen": -34.51100158691406,
+      "logps/rejected": -69.979248046875,
+      "loss": 0.435,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": 2.112297534942627,
+      "rewards/margins": 3.443708896636963,
+      "rewards/rejected": -1.3314111232757568,
+      "step": 420
+    },
+    {
+      "epoch": 6.83,
+      "eval_logits/chosen": -1.8236370086669922,
+      "eval_logits/rejected": -1.8495099544525146,
+      "eval_logps/chosen": -47.62683868408203,
+      "eval_logps/rejected": -99.54405212402344,
+      "eval_loss": 0.4284569323062897,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 2.272435426712036,
+      "eval_rewards/margins": 3.396484613418579,
+      "eval_rewards/rejected": -1.1240490674972534,
+      "eval_runtime": 8.5146,
+      "eval_samples_per_second": 3.288,
+      "eval_steps_per_second": 1.644,
+      "step": 420
+    },
+    {
+      "epoch": 6.99,
+      "grad_norm": 0.027868641540408134,
+      "learning_rate": 2.147887323943662e-06,
+      "logits/chosen": -1.8732540607452393,
+      "logits/rejected": -1.9188286066055298,
+      "logps/chosen": -28.66534996032715,
+      "logps/rejected": -87.85456085205078,
+      "loss": 0.4359,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": 1.747658133506775,
+      "rewards/margins": 3.2419276237487793,
+      "rewards/rejected": -1.494269847869873,
+      "step": 430
+    },
+    {
+      "epoch": 7.15,
+      "grad_norm": 1.6011111736297607,
+      "learning_rate": 2.0774647887323944e-06,
+      "logits/chosen": -1.8680269718170166,
+      "logits/rejected": -1.883652925491333,
+      "logps/chosen": -22.022457122802734,
+      "logps/rejected": -51.710731506347656,
+      "loss": 0.4878,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 1.6784204244613647,
+      "rewards/margins": 2.697260856628418,
+      "rewards/rejected": -1.0188405513763428,
+      "step": 440
+    },
+    {
+      "epoch": 7.32,
+      "grad_norm": 0.005799587815999985,
+      "learning_rate": 2.007042253521127e-06,
+      "logits/chosen": -1.9159187078475952,
+      "logits/rejected": -1.942246675491333,
+      "logps/chosen": -26.426944732666016,
+      "logps/rejected": -63.260643005371094,
+      "loss": 0.5148,
+      "rewards/accuracies": 0.2750000059604645,
+      "rewards/chosen": 1.5094796419143677,
+      "rewards/margins": 2.8935487270355225,
+      "rewards/rejected": -1.3840690851211548,
+      "step": 450
+    },
+    {
+      "epoch": 7.32,
+      "eval_logits/chosen": -1.8220092058181763,
+      "eval_logits/rejected": -1.8481791019439697,
+      "eval_logps/chosen": -47.637298583984375,
+      "eval_logps/rejected": -99.83494567871094,
+      "eval_loss": 0.43089213967323303,
+      "eval_rewards/accuracies": 0.4285714328289032,
+      "eval_rewards/chosen": 2.2692975997924805,
+      "eval_rewards/margins": 3.480616331100464,
+      "eval_rewards/rejected": -1.211318850517273,
+      "eval_runtime": 8.5151,
+      "eval_samples_per_second": 3.288,
+      "eval_steps_per_second": 1.644,
+      "step": 450
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 732,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "save_steps": 90,
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-450/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a9e56dbe2b48a488c5411e841b81929760b46d9a622b353a65d00ada1e6a94f
+size 5304

checkpoint-540/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