Upload folder using huggingface_hub

README.md

@@ -0,0 +1,81 @@
+---
+license: mit
+library_name: "trl"
+tags:
+- DPO
+- WeniGPT
+base_model: Weni/WeniGPT-2.2.3-Zephyr-7B-merged-LLM_Base_2.0.3_SFT
+model-index:
+- name: Weni/WeniGPT-2.10.1-Zephyr-7B-DPO-prompt-binarized-GPTQ
+  results: []
+language: ['en']
+---
+
+# Weni/WeniGPT-2.10.1-Zephyr-7B-DPO-prompt-binarized-GPTQ
+
+This model is a fine-tuned version of [Weni/WeniGPT-2.2.3-Zephyr-7B-merged-LLM_Base_2.0.3_SFT] on the dataset HuggingFaceH4/ultrafeedback_binarized with the DPO trainer. It is part of the WeniGPT project for [Weni](https://weni.ai/).
+
+It achieves the following results on the evaluation set:
+{'eval_loss': 1.9277071952819824, 'eval_runtime': 94.1066, 'eval_samples_per_second': 2.125, 'eval_steps_per_second': 0.531, 'eval_rewards/chosen': 18.78862190246582, 'eval_rewards/rejected': 13.151841163635254, 'eval_rewards/accuracies': 0.5350000262260437, 'eval_rewards/margins': 5.63677978515625, 'eval_logps/rejected': -329.4024658203125, 'eval_logps/chosen': -334.51287841796875, 'eval_logits/rejected': -2.746166467666626, 'eval_logits/chosen': -2.7368459701538086, 'epoch': 7.96}
+
+## Intended uses & limitations
+
+This model has not been trained to avoid specific intructions. 
+
+## Training procedure
+
+Finetuning was done on the model Weni/WeniGPT-2.2.3-Zephyr-7B-merged-LLM_Base_2.0.3_SFT with the following prompt:
+
+```
+Prompt:
+<|user|>{prompt}</s>
+
+
+Chosen:
+<|assistant|>{chosen}</s>
+
+
+Rejected:
+<|assistant|>{rejected}</s>
+```
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- per_device_train_batch_size: 4
+- per_device_eval_batch_size: 4
+- gradient_accumulation_steps: 4
+- num_gpus: 1
+- total_train_batch_size: 16
+- optimizer: AdamW
+- lr_scheduler_type: cosine
+- num_steps: 896
+- quantization_type: gptq
+- LoRA: ("\n  - bits: 4\n  - use_exllama: True\n  - device_map: auto\n  - use_cache: False\n  - lora_r: 16\n  - lora_alpha: 16\n  - lora_dropout: 0.05\n  - bias: none\n  - target_modules: ['q_proj', 'k_proj', 'v_proj', 'o_proj']\n  - task_type: CAUSAL_LM",)
+
+### Training results
+
+### Framework versions
+
+- transformers==4.38.2
+- datasets==2.17.1
+- peft==0.8.2
+- safetensors==0.4.2
+- evaluate==0.4.1
+- bitsandbytes==0.42
+- huggingface_hub==0.20.3
+- seqeval==1.2.2
+- optimum==1.17.1
+- auto-gptq==0.7.0
+- gpustat==1.1.1
+- deepspeed==0.13.2
+- wandb==0.16.3
+- trl==0.7.11
+- accelerate==0.27.2
+- coloredlogs==15.0.1
+- traitlets==5.14.1
+- autoawq@https://github.com/casper-hansen/AutoAWQ/releases/download/v0.2.0/autoawq-0.2.0+cu118-cp310-cp310-linux_x86_64.whl
+
+### Hardware
+- Cloud provided: runpod.io

checkpoint-100/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: Weni/WeniGPT-2.2.3-Zephyr-7B-merged-LLM_Base_2.0.3_SFT
+---
+
+# 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 0.8.2

checkpoint-100/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Weni/WeniGPT-2.2.3-Zephyr-7B-merged-LLM_Base_2.0.3_SFT",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88433522cb21b0ecb7788c520895e34dc5661b6c1933a5484f8b39bec1e24375
+size 54560368

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a0f2cda1db186d6fc85b387d24af1c604746f6e18eb34e88f5a6264f234eebf
+size 109267450

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
+size 14244

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b477035e30bed4c4a6bb69d7df73b19925bc0eb0c504817df41db5cf3395b904
+size 1064

checkpoint-100/special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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-100/tokenizer.model

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

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "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": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "max_lenght": 2048,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "padding": true,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,112 @@
+{
+  "best_metric": 1.9277071952819824,
+  "best_model_checkpoint": "./Zephyr/08-03-24-Weni-WeniGPT-2.10.1-Zephyr-7B-DPO-prompt-binarized-GPTQ_DPO tests with binarized dataset GPTQ-2_max_steps-896_batch_16_2024-03-08_ppid_7990/checkpoint-100",
+  "epoch": 0.8888888888888888,
+  "eval_steps": 100,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18,
+      "grad_norm": 119.0400161743164,
+      "learning_rate": 3.111111111111111e-05,
+      "logits/chosen": -2.6437883377075195,
+      "logits/rejected": -2.640676498413086,
+      "logps/chosen": -346.0354309082031,
+      "logps/rejected": -315.1640319824219,
+      "loss": 0.6706,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.2039356678724289,
+      "rewards/margins": 0.1839628666639328,
+      "rewards/rejected": 0.019972801208496094,
+      "step": 20
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 55.844058990478516,
+      "learning_rate": 7.555555555555556e-05,
+      "logits/chosen": -2.7053043842315674,
+      "logits/rejected": -2.706561326980591,
+      "logps/chosen": -348.75,
+      "logps/rejected": -336.07830810546875,
+      "loss": 0.7255,
+      "rewards/accuracies": 0.5062500238418579,
+      "rewards/chosen": -0.3999950885772705,
+      "rewards/margins": 0.9534912109375,
+      "rewards/rejected": -1.3534862995147705,
+      "step": 40
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 156.59803771972656,
+      "learning_rate": 0.00011777777777777779,
+      "logits/chosen": -2.644763946533203,
+      "logits/rejected": -2.6682467460632324,
+      "logps/chosen": -352.20233154296875,
+      "logps/rejected": -343.33941650390625,
+      "loss": 0.8382,
+      "rewards/accuracies": 0.5718749761581421,
+      "rewards/chosen": 2.873349189758301,
+      "rewards/margins": 1.9845993518829346,
+      "rewards/rejected": 0.8887494802474976,
+      "step": 60
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 113.42001342773438,
+      "learning_rate": 0.00016222222222222224,
+      "logits/chosen": -2.652919292449951,
+      "logits/rejected": -2.663282871246338,
+      "logps/chosen": -350.60443115234375,
+      "logps/rejected": -333.491455078125,
+      "loss": 1.6409,
+      "rewards/accuracies": 0.512499988079071,
+      "rewards/chosen": 4.428155899047852,
+      "rewards/margins": 2.1724541187286377,
+      "rewards/rejected": 2.255702018737793,
+      "step": 80
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 77.21934509277344,
+      "learning_rate": 0.0001992555831265509,
+      "logits/chosen": -2.6474595069885254,
+      "logits/rejected": -2.6597702503204346,
+      "logps/chosen": -318.25653076171875,
+      "logps/rejected": -302.04241943359375,
+      "loss": 1.9207,
+      "rewards/accuracies": 0.4937500059604645,
+      "rewards/chosen": 14.573875427246094,
+      "rewards/margins": 3.523595094680786,
+      "rewards/rejected": 11.050280570983887,
+      "step": 100
+    },
+    {
+      "epoch": 0.89,
+      "eval_logits/chosen": -2.7368459701538086,
+      "eval_logits/rejected": -2.746166467666626,
+      "eval_logps/chosen": -334.51287841796875,
+      "eval_logps/rejected": -329.4024658203125,
+      "eval_loss": 1.9277071952819824,
+      "eval_rewards/accuracies": 0.5350000262260437,
+      "eval_rewards/chosen": 18.78862190246582,
+      "eval_rewards/margins": 5.63677978515625,
+      "eval_rewards/rejected": 13.151841163635254,
+      "eval_runtime": 94.4139,
+      "eval_samples_per_second": 2.118,
+      "eval_steps_per_second": 0.53,
+      "step": 100
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 896,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 100,
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:898e690ae745f178ef08f4c9b66ce0008ccd31de52b82b4a69ad2f00dceee1bc
+size 5240

checkpoint-200/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: Weni/WeniGPT-2.2.3-Zephyr-7B-merged-LLM_Base_2.0.3_SFT
+---
+
+# 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 0.8.2

checkpoint-200/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Weni/WeniGPT-2.2.3-Zephyr-7B-merged-LLM_Base_2.0.3_SFT",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cd996197ac66f3a24e277e89146b7db1fb2d9cdc58f7a0a2596eb54a03588d9
+size 54560368

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3bf0ac36373a8f93c5d01349ff062b94ddc03297178ec639e0e9e0b1741496f
+size 109267450

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d138cfe3a4adf21f048848ee35837c9a757a0a3616ff7adbb45b69aac247435
+size 14244

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7c17afb046167ee43f28f8156a519a2fce750d5105142dc43084428a2506bb5
+size 1064

checkpoint-200/special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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-200/tokenizer.model

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

checkpoint-200/tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "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": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "max_lenght": 2048,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "padding": true,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,203 @@
+{
+  "best_metric": 1.9277071952819824,
+  "best_model_checkpoint": "./Zephyr/08-03-24-Weni-WeniGPT-2.10.1-Zephyr-7B-DPO-prompt-binarized-GPTQ_DPO tests with binarized dataset GPTQ-2_max_steps-896_batch_16_2024-03-08_ppid_7990/checkpoint-100",
+  "epoch": 1.7777777777777777,
+  "eval_steps": 100,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18,
+      "grad_norm": 119.0400161743164,
+      "learning_rate": 3.111111111111111e-05,
+      "logits/chosen": -2.6437883377075195,
+      "logits/rejected": -2.640676498413086,
+      "logps/chosen": -346.0354309082031,
+      "logps/rejected": -315.1640319824219,
+      "loss": 0.6706,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.2039356678724289,
+      "rewards/margins": 0.1839628666639328,
+      "rewards/rejected": 0.019972801208496094,
+      "step": 20
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 55.844058990478516,
+      "learning_rate": 7.555555555555556e-05,
+      "logits/chosen": -2.7053043842315674,
+      "logits/rejected": -2.706561326980591,
+      "logps/chosen": -348.75,
+      "logps/rejected": -336.07830810546875,
+      "loss": 0.7255,
+      "rewards/accuracies": 0.5062500238418579,
+      "rewards/chosen": -0.3999950885772705,
+      "rewards/margins": 0.9534912109375,
+      "rewards/rejected": -1.3534862995147705,
+      "step": 40
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 156.59803771972656,
+      "learning_rate": 0.00011777777777777779,
+      "logits/chosen": -2.644763946533203,
+      "logits/rejected": -2.6682467460632324,
+      "logps/chosen": -352.20233154296875,
+      "logps/rejected": -343.33941650390625,
+      "loss": 0.8382,
+      "rewards/accuracies": 0.5718749761581421,
+      "rewards/chosen": 2.873349189758301,
+      "rewards/margins": 1.9845993518829346,
+      "rewards/rejected": 0.8887494802474976,
+      "step": 60
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 113.42001342773438,
+      "learning_rate": 0.00016222222222222224,
+      "logits/chosen": -2.652919292449951,
+      "logits/rejected": -2.663282871246338,
+      "logps/chosen": -350.60443115234375,
+      "logps/rejected": -333.491455078125,
+      "loss": 1.6409,
+      "rewards/accuracies": 0.512499988079071,
+      "rewards/chosen": 4.428155899047852,
+      "rewards/margins": 2.1724541187286377,
+      "rewards/rejected": 2.255702018737793,
+      "step": 80
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 77.21934509277344,
+      "learning_rate": 0.0001992555831265509,
+      "logits/chosen": -2.6474595069885254,
+      "logits/rejected": -2.6597702503204346,
+      "logps/chosen": -318.25653076171875,
+      "logps/rejected": -302.04241943359375,
+      "loss": 1.9207,
+      "rewards/accuracies": 0.4937500059604645,
+      "rewards/chosen": 14.573875427246094,
+      "rewards/margins": 3.523595094680786,
+      "rewards/rejected": 11.050280570983887,
+      "step": 100
+    },
+    {
+      "epoch": 0.89,
+      "eval_logits/chosen": -2.7368459701538086,
+      "eval_logits/rejected": -2.746166467666626,
+      "eval_logps/chosen": -334.51287841796875,
+      "eval_logps/rejected": -329.4024658203125,
+      "eval_loss": 1.9277071952819824,
+      "eval_rewards/accuracies": 0.5350000262260437,
+      "eval_rewards/chosen": 18.78862190246582,
+      "eval_rewards/margins": 5.63677978515625,
+      "eval_rewards/rejected": 13.151841163635254,
+      "eval_runtime": 94.4139,
+      "eval_samples_per_second": 2.118,
+      "eval_steps_per_second": 0.53,
+      "step": 100
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 83.98187255859375,
+      "learning_rate": 0.00019429280397022334,
+      "logits/chosen": -2.639448642730713,
+      "logits/rejected": -2.6476964950561523,
+      "logps/chosen": -316.87982177734375,
+      "logps/rejected": -308.38568115234375,
+      "loss": 1.7601,
+      "rewards/accuracies": 0.5562499761581421,
+      "rewards/chosen": 27.463403701782227,
+      "rewards/margins": 10.681607246398926,
+      "rewards/rejected": 16.781795501708984,
+      "step": 120
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001893300248138958,
+      "logits/chosen": -2.6575229167938232,
+      "logits/rejected": -2.6546902656555176,
+      "logps/chosen": -350.1793212890625,
+      "logps/rejected": -348.28985595703125,
+      "loss": 1.8357,
+      "rewards/accuracies": 0.6156250238418579,
+      "rewards/chosen": -23.570585250854492,
+      "rewards/margins": 16.757661819458008,
+      "rewards/rejected": -40.32825469970703,
+      "step": 140
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 1.0552074909210205,
+      "learning_rate": 0.00018436724565756824,
+      "logits/chosen": -2.690781831741333,
+      "logits/rejected": -2.691371440887451,
+      "logps/chosen": -403.81378173828125,
+      "logps/rejected": -407.43475341796875,
+      "loss": 1.4241,
+      "rewards/accuracies": 0.6343749761581421,
+      "rewards/chosen": -46.7193489074707,
+      "rewards/margins": 20.419803619384766,
+      "rewards/rejected": -67.13915252685547,
+      "step": 160
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 88.9915771484375,
+      "learning_rate": 0.0001794044665012407,
+      "logits/chosen": -2.6750125885009766,
+      "logits/rejected": -2.682309627532959,
+      "logps/chosen": -399.62066650390625,
+      "logps/rejected": -409.8529357910156,
+      "loss": 1.9108,
+      "rewards/accuracies": 0.621874988079071,
+      "rewards/chosen": -49.57743453979492,
+      "rewards/margins": 20.643938064575195,
+      "rewards/rejected": -70.22136688232422,
+      "step": 180
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 138.35623168945312,
+      "learning_rate": 0.00017444168734491314,
+      "logits/chosen": -2.7050137519836426,
+      "logits/rejected": -2.712310552597046,
+      "logps/chosen": -397.1112365722656,
+      "logps/rejected": -406.0185852050781,
+      "loss": 2.0578,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -53.7899284362793,
+      "rewards/margins": 17.770038604736328,
+      "rewards/rejected": -71.55997467041016,
+      "step": 200
+    },
+    {
+      "epoch": 1.78,
+      "eval_logits/chosen": -2.6775686740875244,
+      "eval_logits/rejected": -2.6850674152374268,
+      "eval_logps/chosen": -419.0586242675781,
+      "eval_logps/rejected": -420.5866394042969,
+      "eval_loss": 2.5765089988708496,
+      "eval_rewards/accuracies": 0.550000011920929,
+      "eval_rewards/chosen": -65.75714874267578,
+      "eval_rewards/margins": 12.275188446044922,
+      "eval_rewards/rejected": -78.03234100341797,
+      "eval_runtime": 94.1202,
+      "eval_samples_per_second": 2.125,
+      "eval_steps_per_second": 0.531,
+      "step": 200
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 896,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 100,
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:898e690ae745f178ef08f4c9b66ce0008ccd31de52b82b4a69ad2f00dceee1bc
+size 5240

checkpoint-300/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: Weni/WeniGPT-2.2.3-Zephyr-7B-merged-LLM_Base_2.0.3_SFT
+---
+
+# 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 0.8.2

checkpoint-300/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Weni/WeniGPT-2.2.3-Zephyr-7B-merged-LLM_Base_2.0.3_SFT",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-300/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a72c605b93467dd1b7f68344843aa84f436b832ce4def01ddcef84196ebaabf8
+size 54560368

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:538f2ea1ffe7d735bb5e07d833331d88004508639cdd218592fdd53a4aa4386b
+size 109267450

checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c062f7f375beded48b5337f5a3f3a5cb38807fa3e85dbf3e294c0ab6b627bfc2
+size 14244

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd7d4e662af47ddf5d1dbe0d024bb600405fb97dc2e6f174b4758df92d5d82d6
+size 1064

checkpoint-300/special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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-300/tokenizer.model

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

checkpoint-300/tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "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": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "max_lenght": 2048,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "padding": true,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

checkpoint-300/trainer_state.json

@@ -0,0 +1,294 @@
+{
+  "best_metric": 1.9277071952819824,
+  "best_model_checkpoint": "./Zephyr/08-03-24-Weni-WeniGPT-2.10.1-Zephyr-7B-DPO-prompt-binarized-GPTQ_DPO tests with binarized dataset GPTQ-2_max_steps-896_batch_16_2024-03-08_ppid_7990/checkpoint-100",
+  "epoch": 2.6666666666666665,
+  "eval_steps": 100,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18,
+      "grad_norm": 119.0400161743164,
+      "learning_rate": 3.111111111111111e-05,
+      "logits/chosen": -2.6437883377075195,
+      "logits/rejected": -2.640676498413086,
+      "logps/chosen": -346.0354309082031,
+      "logps/rejected": -315.1640319824219,
+      "loss": 0.6706,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.2039356678724289,
+      "rewards/margins": 0.1839628666639328,
+      "rewards/rejected": 0.019972801208496094,
+      "step": 20
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 55.844058990478516,
+      "learning_rate": 7.555555555555556e-05,
+      "logits/chosen": -2.7053043842315674,
+      "logits/rejected": -2.706561326980591,
+      "logps/chosen": -348.75,
+      "logps/rejected": -336.07830810546875,
+      "loss": 0.7255,
+      "rewards/accuracies": 0.5062500238418579,
+      "rewards/chosen": -0.3999950885772705,
+      "rewards/margins": 0.9534912109375,
+      "rewards/rejected": -1.3534862995147705,
+      "step": 40
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 156.59803771972656,
+      "learning_rate": 0.00011777777777777779,
+      "logits/chosen": -2.644763946533203,
+      "logits/rejected": -2.6682467460632324,
+      "logps/chosen": -352.20233154296875,
+      "logps/rejected": -343.33941650390625,
+      "loss": 0.8382,
+      "rewards/accuracies": 0.5718749761581421,
+      "rewards/chosen": 2.873349189758301,
+      "rewards/margins": 1.9845993518829346,
+      "rewards/rejected": 0.8887494802474976,
+      "step": 60
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 113.42001342773438,
+      "learning_rate": 0.00016222222222222224,
+      "logits/chosen": -2.652919292449951,
+      "logits/rejected": -2.663282871246338,
+      "logps/chosen": -350.60443115234375,
+      "logps/rejected": -333.491455078125,
+      "loss": 1.6409,
+      "rewards/accuracies": 0.512499988079071,
+      "rewards/chosen": 4.428155899047852,
+      "rewards/margins": 2.1724541187286377,
+      "rewards/rejected": 2.255702018737793,
+      "step": 80
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 77.21934509277344,
+      "learning_rate": 0.0001992555831265509,
+      "logits/chosen": -2.6474595069885254,
+      "logits/rejected": -2.6597702503204346,
+      "logps/chosen": -318.25653076171875,
+      "logps/rejected": -302.04241943359375,
+      "loss": 1.9207,
+      "rewards/accuracies": 0.4937500059604645,
+      "rewards/chosen": 14.573875427246094,
+      "rewards/margins": 3.523595094680786,
+      "rewards/rejected": 11.050280570983887,
+      "step": 100
+    },
+    {
+      "epoch": 0.89,
+      "eval_logits/chosen": -2.7368459701538086,
+      "eval_logits/rejected": -2.746166467666626,
+      "eval_logps/chosen": -334.51287841796875,
+      "eval_logps/rejected": -329.4024658203125,
+      "eval_loss": 1.9277071952819824,
+      "eval_rewards/accuracies": 0.5350000262260437,
+      "eval_rewards/chosen": 18.78862190246582,
+      "eval_rewards/margins": 5.63677978515625,
+      "eval_rewards/rejected": 13.151841163635254,
+      "eval_runtime": 94.4139,
+      "eval_samples_per_second": 2.118,
+      "eval_steps_per_second": 0.53,
+      "step": 100
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 83.98187255859375,
+      "learning_rate": 0.00019429280397022334,
+      "logits/chosen": -2.639448642730713,
+      "logits/rejected": -2.6476964950561523,
+      "logps/chosen": -316.87982177734375,
+      "logps/rejected": -308.38568115234375,
+      "loss": 1.7601,
+      "rewards/accuracies": 0.5562499761581421,
+      "rewards/chosen": 27.463403701782227,
+      "rewards/margins": 10.681607246398926,
+      "rewards/rejected": 16.781795501708984,
+      "step": 120
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001893300248138958,
+      "logits/chosen": -2.6575229167938232,
+      "logits/rejected": -2.6546902656555176,
+      "logps/chosen": -350.1793212890625,
+      "logps/rejected": -348.28985595703125,
+      "loss": 1.8357,
+      "rewards/accuracies": 0.6156250238418579,
+      "rewards/chosen": -23.570585250854492,
+      "rewards/margins": 16.757661819458008,
+      "rewards/rejected": -40.32825469970703,
+      "step": 140
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 1.0552074909210205,
+      "learning_rate": 0.00018436724565756824,
+      "logits/chosen": -2.690781831741333,
+      "logits/rejected": -2.691371440887451,
+      "logps/chosen": -403.81378173828125,
+      "logps/rejected": -407.43475341796875,
+      "loss": 1.4241,
+      "rewards/accuracies": 0.6343749761581421,
+      "rewards/chosen": -46.7193489074707,
+      "rewards/margins": 20.419803619384766,
+      "rewards/rejected": -67.13915252685547,
+      "step": 160
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 88.9915771484375,
+      "learning_rate": 0.0001794044665012407,
+      "logits/chosen": -2.6750125885009766,
+      "logits/rejected": -2.682309627532959,
+      "logps/chosen": -399.62066650390625,
+      "logps/rejected": -409.8529357910156,
+      "loss": 1.9108,
+      "rewards/accuracies": 0.621874988079071,
+      "rewards/chosen": -49.57743453979492,
+      "rewards/margins": 20.643938064575195,
+      "rewards/rejected": -70.22136688232422,
+      "step": 180
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 138.35623168945312,
+      "learning_rate": 0.00017444168734491314,
+      "logits/chosen": -2.7050137519836426,
+      "logits/rejected": -2.712310552597046,
+      "logps/chosen": -397.1112365722656,
+      "logps/rejected": -406.0185852050781,
+      "loss": 2.0578,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -53.7899284362793,
+      "rewards/margins": 17.770038604736328,
+      "rewards/rejected": -71.55997467041016,
+      "step": 200
+    },
+    {
+      "epoch": 1.78,
+      "eval_logits/chosen": -2.6775686740875244,
+      "eval_logits/rejected": -2.6850674152374268,
+      "eval_logps/chosen": -419.0586242675781,
+      "eval_logps/rejected": -420.5866394042969,
+      "eval_loss": 2.5765089988708496,
+      "eval_rewards/accuracies": 0.550000011920929,
+      "eval_rewards/chosen": -65.75714874267578,
+      "eval_rewards/margins": 12.275188446044922,
+      "eval_rewards/rejected": -78.03234100341797,
+      "eval_runtime": 94.1202,
+      "eval_samples_per_second": 2.125,
+      "eval_steps_per_second": 0.531,
+      "step": 200
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 30.972963333129883,
+      "learning_rate": 0.0001694789081885856,
+      "logits/chosen": -2.631683349609375,
+      "logits/rejected": -2.6248221397399902,
+      "logps/chosen": -404.0619201660156,
+      "logps/rejected": -399.0223083496094,
+      "loss": 1.8819,
+      "rewards/accuracies": 0.596875011920929,
+      "rewards/chosen": -62.639190673828125,
+      "rewards/margins": 19.827577590942383,
+      "rewards/rejected": -82.46675872802734,
+      "step": 220
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 65.85337829589844,
+      "learning_rate": 0.00016451612903225807,
+      "logits/chosen": -2.711599826812744,
+      "logits/rejected": -2.7432861328125,
+      "logps/chosen": -392.7776794433594,
+      "logps/rejected": -422.9435119628906,
+      "loss": 1.381,
+      "rewards/accuracies": 0.643750011920929,
+      "rewards/chosen": -58.72906494140625,
+      "rewards/margins": 29.807327270507812,
+      "rewards/rejected": -88.536376953125,
+      "step": 240
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 86.84841918945312,
+      "learning_rate": 0.00015955334987593052,
+      "logits/chosen": -2.8453807830810547,
+      "logits/rejected": -2.849914073944092,
+      "logps/chosen": -400.3071594238281,
+      "logps/rejected": -420.60968017578125,
+      "loss": 0.9731,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -69.37321472167969,
+      "rewards/margins": 32.82529830932617,
+      "rewards/rejected": -102.19852447509766,
+      "step": 260
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 0.010256004519760609,
+      "learning_rate": 0.000154590570719603,
+      "logits/chosen": -2.7864909172058105,
+      "logits/rejected": -2.812525749206543,
+      "logps/chosen": -376.9371643066406,
+      "logps/rejected": -395.2316589355469,
+      "loss": 0.8817,
+      "rewards/accuracies": 0.703125,
+      "rewards/chosen": -35.111305236816406,
+      "rewards/margins": 33.674293518066406,
+      "rewards/rejected": -68.78559875488281,
+      "step": 280
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 0.26802292466163635,
+      "learning_rate": 0.00014962779156327545,
+      "logits/chosen": -2.7736704349517822,
+      "logits/rejected": -2.792346477508545,
+      "logps/chosen": -372.4452209472656,
+      "logps/rejected": -392.68878173828125,
+      "loss": 0.3389,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -25.840368270874023,
+      "rewards/margins": 39.69981002807617,
+      "rewards/rejected": -65.54017639160156,
+      "step": 300
+    },
+    {
+      "epoch": 2.67,
+      "eval_logits/chosen": -2.8219432830810547,
+      "eval_logits/rejected": -2.8389434814453125,
+      "eval_logps/chosen": -374.2080078125,
+      "eval_logps/rejected": -374.9266052246094,
+      "eval_loss": 3.5374395847320557,
+      "eval_rewards/accuracies": 0.5400000214576721,
+      "eval_rewards/chosen": -20.90648651123047,
+      "eval_rewards/margins": 11.465815544128418,
+      "eval_rewards/rejected": -32.37229919433594,
+      "eval_runtime": 94.0956,
+      "eval_samples_per_second": 2.125,
+      "eval_steps_per_second": 0.531,
+      "step": 300
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 896,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 100,
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:898e690ae745f178ef08f4c9b66ce0008ccd31de52b82b4a69ad2f00dceee1bc
+size 5240

checkpoint-400/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: Weni/WeniGPT-2.2.3-Zephyr-7B-merged-LLM_Base_2.0.3_SFT
+---
+
+# 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 0.8.2

checkpoint-400/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Weni/WeniGPT-2.2.3-Zephyr-7B-merged-LLM_Base_2.0.3_SFT",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-400/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f6e98816262fedea581392db978e2108ebbfbe0e554618a6a9d9f64e3b3a2c3
+size 54560368

checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d613e271b26005a5dd0c9838644adad9d980018d2baacbb3bb1f5d7a035a335
+size 109267450

checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9899ccda7f0d8d9511991180b93aab508ce6e8489de708c88ad1188e7e1d90d6
+size 14244

checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d645df1917d8236ef252b81d31a7c395282a5cd8711ef8e5231db6216d896577
+size 1064

checkpoint-400/special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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-400/tokenizer.model

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

checkpoint-400/tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "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": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "max_lenght": 2048,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "padding": true,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

checkpoint-400/trainer_state.json

@@ -0,0 +1,385 @@
+{
+  "best_metric": 1.9277071952819824,
+  "best_model_checkpoint": "./Zephyr/08-03-24-Weni-WeniGPT-2.10.1-Zephyr-7B-DPO-prompt-binarized-GPTQ_DPO tests with binarized dataset GPTQ-2_max_steps-896_batch_16_2024-03-08_ppid_7990/checkpoint-100",
+  "epoch": 3.5555555555555554,
+  "eval_steps": 100,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18,
+      "grad_norm": 119.0400161743164,
+      "learning_rate": 3.111111111111111e-05,
+      "logits/chosen": -2.6437883377075195,
+      "logits/rejected": -2.640676498413086,
+      "logps/chosen": -346.0354309082031,
+      "logps/rejected": -315.1640319824219,
+      "loss": 0.6706,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.2039356678724289,
+      "rewards/margins": 0.1839628666639328,
+      "rewards/rejected": 0.019972801208496094,
+      "step": 20
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 55.844058990478516,
+      "learning_rate": 7.555555555555556e-05,
+      "logits/chosen": -2.7053043842315674,
+      "logits/rejected": -2.706561326980591,
+      "logps/chosen": -348.75,
+      "logps/rejected": -336.07830810546875,
+      "loss": 0.7255,
+      "rewards/accuracies": 0.5062500238418579,
+      "rewards/chosen": -0.3999950885772705,
+      "rewards/margins": 0.9534912109375,
+      "rewards/rejected": -1.3534862995147705,
+      "step": 40
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 156.59803771972656,
+      "learning_rate": 0.00011777777777777779,
+      "logits/chosen": -2.644763946533203,
+      "logits/rejected": -2.6682467460632324,
+      "logps/chosen": -352.20233154296875,
+      "logps/rejected": -343.33941650390625,
+      "loss": 0.8382,
+      "rewards/accuracies": 0.5718749761581421,
+      "rewards/chosen": 2.873349189758301,
+      "rewards/margins": 1.9845993518829346,
+      "rewards/rejected": 0.8887494802474976,
+      "step": 60
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 113.42001342773438,
+      "learning_rate": 0.00016222222222222224,
+      "logits/chosen": -2.652919292449951,
+      "logits/rejected": -2.663282871246338,
+      "logps/chosen": -350.60443115234375,
+      "logps/rejected": -333.491455078125,
+      "loss": 1.6409,
+      "rewards/accuracies": 0.512499988079071,
+      "rewards/chosen": 4.428155899047852,
+      "rewards/margins": 2.1724541187286377,
+      "rewards/rejected": 2.255702018737793,
+      "step": 80
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 77.21934509277344,
+      "learning_rate": 0.0001992555831265509,
+      "logits/chosen": -2.6474595069885254,
+      "logits/rejected": -2.6597702503204346,
+      "logps/chosen": -318.25653076171875,
+      "logps/rejected": -302.04241943359375,
+      "loss": 1.9207,
+      "rewards/accuracies": 0.4937500059604645,
+      "rewards/chosen": 14.573875427246094,
+      "rewards/margins": 3.523595094680786,
+      "rewards/rejected": 11.050280570983887,
+      "step": 100
+    },
+    {
+      "epoch": 0.89,
+      "eval_logits/chosen": -2.7368459701538086,
+      "eval_logits/rejected": -2.746166467666626,
+      "eval_logps/chosen": -334.51287841796875,
+      "eval_logps/rejected": -329.4024658203125,
+      "eval_loss": 1.9277071952819824,
+      "eval_rewards/accuracies": 0.5350000262260437,
+      "eval_rewards/chosen": 18.78862190246582,
+      "eval_rewards/margins": 5.63677978515625,
+      "eval_rewards/rejected": 13.151841163635254,
+      "eval_runtime": 94.4139,
+      "eval_samples_per_second": 2.118,
+      "eval_steps_per_second": 0.53,
+      "step": 100
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 83.98187255859375,
+      "learning_rate": 0.00019429280397022334,
+      "logits/chosen": -2.639448642730713,
+      "logits/rejected": -2.6476964950561523,
+      "logps/chosen": -316.87982177734375,
+      "logps/rejected": -308.38568115234375,
+      "loss": 1.7601,
+      "rewards/accuracies": 0.5562499761581421,
+      "rewards/chosen": 27.463403701782227,
+      "rewards/margins": 10.681607246398926,
+      "rewards/rejected": 16.781795501708984,
+      "step": 120
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001893300248138958,
+      "logits/chosen": -2.6575229167938232,
+      "logits/rejected": -2.6546902656555176,
+      "logps/chosen": -350.1793212890625,
+      "logps/rejected": -348.28985595703125,
+      "loss": 1.8357,
+      "rewards/accuracies": 0.6156250238418579,
+      "rewards/chosen": -23.570585250854492,
+      "rewards/margins": 16.757661819458008,
+      "rewards/rejected": -40.32825469970703,
+      "step": 140
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 1.0552074909210205,
+      "learning_rate": 0.00018436724565756824,
+      "logits/chosen": -2.690781831741333,
+      "logits/rejected": -2.691371440887451,
+      "logps/chosen": -403.81378173828125,
+      "logps/rejected": -407.43475341796875,
+      "loss": 1.4241,
+      "rewards/accuracies": 0.6343749761581421,
+      "rewards/chosen": -46.7193489074707,
+      "rewards/margins": 20.419803619384766,
+      "rewards/rejected": -67.13915252685547,
+      "step": 160
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 88.9915771484375,
+      "learning_rate": 0.0001794044665012407,
+      "logits/chosen": -2.6750125885009766,
+      "logits/rejected": -2.682309627532959,
+      "logps/chosen": -399.62066650390625,
+      "logps/rejected": -409.8529357910156,
+      "loss": 1.9108,
+      "rewards/accuracies": 0.621874988079071,
+      "rewards/chosen": -49.57743453979492,
+      "rewards/margins": 20.643938064575195,
+      "rewards/rejected": -70.22136688232422,
+      "step": 180
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 138.35623168945312,
+      "learning_rate": 0.00017444168734491314,
+      "logits/chosen": -2.7050137519836426,
+      "logits/rejected": -2.712310552597046,
+      "logps/chosen": -397.1112365722656,
+      "logps/rejected": -406.0185852050781,
+      "loss": 2.0578,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -53.7899284362793,
+      "rewards/margins": 17.770038604736328,
+      "rewards/rejected": -71.55997467041016,
+      "step": 200
+    },
+    {
+      "epoch": 1.78,
+      "eval_logits/chosen": -2.6775686740875244,
+      "eval_logits/rejected": -2.6850674152374268,
+      "eval_logps/chosen": -419.0586242675781,
+      "eval_logps/rejected": -420.5866394042969,
+      "eval_loss": 2.5765089988708496,
+      "eval_rewards/accuracies": 0.550000011920929,
+      "eval_rewards/chosen": -65.75714874267578,
+      "eval_rewards/margins": 12.275188446044922,
+      "eval_rewards/rejected": -78.03234100341797,
+      "eval_runtime": 94.1202,
+      "eval_samples_per_second": 2.125,
+      "eval_steps_per_second": 0.531,
+      "step": 200
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 30.972963333129883,
+      "learning_rate": 0.0001694789081885856,
+      "logits/chosen": -2.631683349609375,
+      "logits/rejected": -2.6248221397399902,
+      "logps/chosen": -404.0619201660156,
+      "logps/rejected": -399.0223083496094,
+      "loss": 1.8819,
+      "rewards/accuracies": 0.596875011920929,
+      "rewards/chosen": -62.639190673828125,
+      "rewards/margins": 19.827577590942383,
+      "rewards/rejected": -82.46675872802734,
+      "step": 220
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 65.85337829589844,
+      "learning_rate": 0.00016451612903225807,
+      "logits/chosen": -2.711599826812744,
+      "logits/rejected": -2.7432861328125,
+      "logps/chosen": -392.7776794433594,
+      "logps/rejected": -422.9435119628906,
+      "loss": 1.381,
+      "rewards/accuracies": 0.643750011920929,
+      "rewards/chosen": -58.72906494140625,
+      "rewards/margins": 29.807327270507812,
+      "rewards/rejected": -88.536376953125,
+      "step": 240
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 86.84841918945312,
+      "learning_rate": 0.00015955334987593052,
+      "logits/chosen": -2.8453807830810547,
+      "logits/rejected": -2.849914073944092,
+      "logps/chosen": -400.3071594238281,
+      "logps/rejected": -420.60968017578125,
+      "loss": 0.9731,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -69.37321472167969,
+      "rewards/margins": 32.82529830932617,
+      "rewards/rejected": -102.19852447509766,
+      "step": 260
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 0.010256004519760609,
+      "learning_rate": 0.000154590570719603,
+      "logits/chosen": -2.7864909172058105,
+      "logits/rejected": -2.812525749206543,
+      "logps/chosen": -376.9371643066406,
+      "logps/rejected": -395.2316589355469,
+      "loss": 0.8817,
+      "rewards/accuracies": 0.703125,
+      "rewards/chosen": -35.111305236816406,
+      "rewards/margins": 33.674293518066406,
+      "rewards/rejected": -68.78559875488281,
+      "step": 280
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 0.26802292466163635,
+      "learning_rate": 0.00014962779156327545,
+      "logits/chosen": -2.7736704349517822,
+      "logits/rejected": -2.792346477508545,
+      "logps/chosen": -372.4452209472656,
+      "logps/rejected": -392.68878173828125,
+      "loss": 0.3389,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -25.840368270874023,
+      "rewards/margins": 39.69981002807617,
+      "rewards/rejected": -65.54017639160156,
+      "step": 300
+    },
+    {
+      "epoch": 2.67,
+      "eval_logits/chosen": -2.8219432830810547,
+      "eval_logits/rejected": -2.8389434814453125,
+      "eval_logps/chosen": -374.2080078125,
+      "eval_logps/rejected": -374.9266052246094,
+      "eval_loss": 3.5374395847320557,
+      "eval_rewards/accuracies": 0.5400000214576721,
+      "eval_rewards/chosen": -20.90648651123047,
+      "eval_rewards/margins": 11.465815544128418,
+      "eval_rewards/rejected": -32.37229919433594,
+      "eval_runtime": 94.0956,
+      "eval_samples_per_second": 2.125,
+      "eval_steps_per_second": 0.531,
+      "step": 300
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 0.30229315161705017,
+      "learning_rate": 0.0001446650124069479,
+      "logits/chosen": -2.718658447265625,
+      "logits/rejected": -2.7346837520599365,
+      "logps/chosen": -379.4544677734375,
+      "logps/rejected": -398.12213134765625,
+      "loss": 1.0938,
+      "rewards/accuracies": 0.6781250238418579,
+      "rewards/chosen": -28.148609161376953,
+      "rewards/margins": 33.832645416259766,
+      "rewards/rejected": -61.98125076293945,
+      "step": 320
+    },
+    {
+      "epoch": 3.02,
+      "grad_norm": 43.86916732788086,
+      "learning_rate": 0.00013970223325062035,
+      "logits/chosen": -2.66723370552063,
+      "logits/rejected": -2.6703853607177734,
+      "logps/chosen": -419.7493591308594,
+      "logps/rejected": -418.89227294921875,
+      "loss": 0.9074,
+      "rewards/accuracies": 0.7093750238418579,
+      "rewards/chosen": -54.372032165527344,
+      "rewards/margins": 28.145233154296875,
+      "rewards/rejected": -82.51727294921875,
+      "step": 340
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 1.2495471239089966,
+      "learning_rate": 0.0001347394540942928,
+      "logits/chosen": -2.741353988647461,
+      "logits/rejected": -2.7415261268615723,
+      "logps/chosen": -394.04681396484375,
+      "logps/rejected": -423.58538818359375,
+      "loss": 0.3777,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -41.517425537109375,
+      "rewards/margins": 49.255271911621094,
+      "rewards/rejected": -90.77268981933594,
+      "step": 360
+    },
+    {
+      "epoch": 3.38,
+      "grad_norm": 7.586065292358398,
+      "learning_rate": 0.00012977667493796526,
+      "logits/chosen": -2.683011054992676,
+      "logits/rejected": -2.697779893875122,
+      "logps/chosen": -374.07745361328125,
+      "logps/rejected": -395.69390869140625,
+      "loss": 0.2784,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": -44.96805953979492,
+      "rewards/margins": 42.65815734863281,
+      "rewards/rejected": -87.626220703125,
+      "step": 380
+    },
+    {
+      "epoch": 3.56,
+      "grad_norm": 0.3450467586517334,
+      "learning_rate": 0.0001248138957816377,
+      "logits/chosen": -2.78257417678833,
+      "logits/rejected": -2.797196865081787,
+      "logps/chosen": -436.71185302734375,
+      "logps/rejected": -443.575927734375,
+      "loss": 0.6031,
+      "rewards/accuracies": 0.7593749761581421,
+      "rewards/chosen": -59.74363327026367,
+      "rewards/margins": 44.275550842285156,
+      "rewards/rejected": -104.01918029785156,
+      "step": 400
+    },
+    {
+      "epoch": 3.56,
+      "eval_logits/chosen": -2.8664298057556152,
+      "eval_logits/rejected": -2.879199266433716,
+      "eval_logps/chosen": -433.5849914550781,
+      "eval_logps/rejected": -436.34722900390625,
+      "eval_loss": 2.886720657348633,
+      "eval_rewards/accuracies": 0.5899999737739563,
+      "eval_rewards/chosen": -80.2834701538086,
+      "eval_rewards/margins": 13.509483337402344,
+      "eval_rewards/rejected": -93.7929458618164,
+      "eval_runtime": 94.1029,
+      "eval_samples_per_second": 2.125,
+      "eval_steps_per_second": 0.531,
+      "step": 400
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 896,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 100,
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:898e690ae745f178ef08f4c9b66ce0008ccd31de52b82b4a69ad2f00dceee1bc
+size 5240

checkpoint-500/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: Weni/WeniGPT-2.2.3-Zephyr-7B-merged-LLM_Base_2.0.3_SFT
+---
+
+# 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 0.8.2