Upload folder using huggingface_hub

README.md

@@ -1,110 +1,109 @@
 ---
-license: apache-2.0
-library_name: peft
+license: mit
+library_name: "trl"
 tags:
-- trl
-- sft
-- generated_from_trainer
+- SFT
+- ZeroShot
 base_model: mistralai/Mistral-7B-Instruct-v0.2
 model-index:
-- name: ZeroShot-3.3.35-Mistral-7b-Multilanguage-3.3.0
+- name: Weni/ZeroShot-3.3.35-Mistral-7b-Multilanguage-3.3.0
   results: []
+language: ['en', 'es', '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/ZeroShot-3.3.35-Mistral-7b-Multilanguage-3.3.0
 
-# ZeroShot-3.3.35-Mistral-7b-Multilanguage-3.3.0
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2] on the dataset Weni/zeroshot-3.3.0 with the SFT trainer. It is part of the ZeroShot project for [Weni](https://weni.ai/).
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3035
+{'eval_loss': 0.3034871220588684, 'eval_runtime': 270.9068, 'eval_samples_per_second': 7.696, 'eval_steps_per_second': 0.963, 'epoch': 2.0}
 
-## 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 mistralai/Mistral-7B-Instruct-v0.2 with the following prompt:
 
-## Training and evaluation data
+```
+---------------------
+Portuguese:
+[INST] Você é muito especialista em classificar a frase do usuário em um chatbot sobre: {context}
+Pare, pense bem e responda com APENAS UM ÚNICO \`id\` da classe que melhor represente a intenção para a frase do usuário de acordo com a análise de seu contexto, responda APENAS com o \`id\` da classe só se você tiver muita certeza e não explique o motivo. Na ausência, falta de informações ou caso a frase do usuário não se enquadre em nenhuma classe, classifique como "-1".
 
-More information needed
+# Essas são as Classes com seus Id e Contexto:
+{all_classes}
+
+# Frase do usuário: {input}
+# Id da Classe: [/INST] {output_id}
+
+
+---------------------
+Spanish:
+[INST] Eres muy experto en clasificar la frase del usuario en un chatbot sobre: {context}
+Deténgase, piense bien y responda con SOLO UN ÚNICO \`id\` de la clase que mejor represente la intención para la frase del usuario de acuerdo con el análisis de su contexto, responda SOLO con el \`id\` de la clase si está muy seguro y no explique el motivo. En ausencia, falta de información o en caso de que la frase del usuario no se ajuste a ninguna clase, clasifique como "-1".
+
+# Estas son las Clases con sus Id y Contexto:
+{all_classes}
+
+# Frase del usuario: {input}
+# Id de la Clase: [/INST] {output_id}
 
-## Training procedure
+
+---------------------
+English:
+[INST] You are very expert in classifying the user sentence in a chatbot about: {context}
+Stop, think carefully, and respond with ONLY ONE SINGLE \`id\` of the class that best represents the intention for the user's sentence according to the analysis of its context, respond ONLY with the \`id\` of the class if you are very sure and do not explain the reason. In the absence, lack of information, or if the user's sentence does not fit into any class, classify as "-1".
+
+# These are the Classes and its Context:
+{all_classes}
+
+# User's sentence: {input}
+# Class Id: [/INST] {output_id}
+
+
+---------------------
+
+```
 
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 8
-- eval_batch_size: 8
-- seed: 42
+- per_device_train_batch_size: 8
+- per_device_eval_batch_size: 8
 - gradient_accumulation_steps: 2
+- num_gpus: 1
 - total_train_batch_size: 16
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_ratio: 0.1
-- training_steps: 2344
-- mixed_precision_training: Native AMP
+- optimizer: AdamW
+- lr_scheduler_type: cosine
+- num_steps: 2344
+- quantization_type: bitsandbytes
+- LoRA: ("\n  - bits: 4\n  - use_exllama: True\n  - device_map: auto\n  - use_cache: False\n  - lora_r: 16\n  - lora_alpha: 32\n  - lora_dropout: 0.05\n  - bias: none\n  - target_modules: ['q_proj', 'k_proj', 'v_proj', 'o_proj', 'gate_proj', 'up_proj', 'down_proj']\n  - task_type: CAUSAL_LM",)
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 1.1297        | 0.04  | 50   | 0.5451          |
-| 0.4425        | 0.09  | 100  | 0.4280          |
-| 0.4241        | 0.13  | 150  | 0.4138          |
-| 0.4059        | 0.17  | 200  | 0.4060          |
-| 0.4125        | 0.21  | 250  | 0.4003          |
-| 0.3948        | 0.26  | 300  | 0.3946          |
-| 0.3979        | 0.3   | 350  | 0.3886          |
-| 0.3938        | 0.34  | 400  | 0.3846          |
-| 0.3739        | 0.38  | 450  | 0.3805          |
-| 0.3726        | 0.43  | 500  | 0.3775          |
-| 0.363         | 0.47  | 550  | 0.3730          |
-| 0.3718        | 0.51  | 600  | 0.3698          |
-| 0.3711        | 0.55  | 650  | 0.3667          |
-| 0.3665        | 0.6   | 700  | 0.3636          |
-| 0.3625        | 0.64  | 750  | 0.3618          |
-| 0.3756        | 0.68  | 800  | 0.3584          |
-| 0.3493        | 0.72  | 850  | 0.3540          |
-| 0.3585        | 0.77  | 900  | 0.3510          |
-| 0.3466        | 0.81  | 950  | 0.3471          |
-| 0.3483        | 0.85  | 1000 | 0.3437          |
-| 0.343         | 0.9   | 1050 | 0.3401          |
-| 0.3373        | 0.94  | 1100 | 0.3368          |
-| 0.3388        | 0.98  | 1150 | 0.3337          |
-| 0.256         | 1.02  | 1200 | 0.3355          |
-| 0.2485        | 1.07  | 1250 | 0.3336          |
-| 0.2452        | 1.11  | 1300 | 0.3301          |
-| 0.2573        | 1.15  | 1350 | 0.3278          |
-| 0.245         | 1.19  | 1400 | 0.3246          |
-| 0.2446        | 1.24  | 1450 | 0.3240          |
-| 0.2416        | 1.28  | 1500 | 0.3212          |
-| 0.2432        | 1.32  | 1550 | 0.3201          |
-| 0.242         | 1.36  | 1600 | 0.3168          |
-| 0.231         | 1.41  | 1650 | 0.3156          |
-| 0.2369        | 1.45  | 1700 | 0.3140          |
-| 0.2405        | 1.49  | 1750 | 0.3110          |
-| 0.2263        | 1.53  | 1800 | 0.3092          |
-| 0.2324        | 1.58  | 1850 | 0.3087          |
-| 0.2203        | 1.62  | 1900 | 0.3084          |
-| 0.223         | 1.66  | 1950 | 0.3060          |
-| 0.2218        | 1.71  | 2000 | 0.3055          |
-| 0.2278        | 1.75  | 2050 | 0.3049          |
-| 0.2229        | 1.79  | 2100 | 0.3043          |
-| 0.2189        | 1.83  | 2150 | 0.3041          |
-| 0.23          | 1.88  | 2200 | 0.3038          |
-| 0.2235        | 1.92  | 2250 | 0.3036          |
-| 0.2368        | 1.96  | 2300 | 0.3035          |
-
-
 ### Framework versions
 
-- PEFT 0.8.2
-- Transformers 4.38.2
-- Pytorch 2.1.0+cu118
-- Datasets 2.17.1
-- Tokenizers 0.15.2
+- 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-1900/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+---
+
+# 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-1900/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "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": 32,
+  "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": [
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-1900/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a08b71a69b720c0a871142a214166be9af14ff52a4a49319bf823031079e4e8c
+size 167832240

checkpoint-1900/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e9c397c08a0932fe11937f9381c4a088e90aa8419ddd648d756841479a3ce83
+size 335811770

checkpoint-1900/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0716b5fcf625a0e485be88459224eeffb8f3d71611c492cab7c039711b602169
+size 14244

checkpoint-1900/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f78e6606e5ae8a2ca936dd99e95c3569b58d69b81ca18a457d164177385e3be
+size 1000

checkpoint-1900/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-1900/tokenizer.model

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

checkpoint-1900/tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "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": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% 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",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-1900/trainer_state.json

@@ -0,0 +1,990 @@
+{
+  "best_metric": 0.30838343501091003,
+  "best_model_checkpoint": "./Mistral/17-03-24-Weni-ZeroShot-3.3.35-Mistral-7b-Multilanguage-3.3.0_ZeroShot SFT Training with its best hyperparameters-2_max_steps-2344_batch_16_2024-03-17_ppid_9/checkpoint-1900",
+  "epoch": 1.619778346121057,
+  "eval_steps": 50,
+  "global_step": 1900,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 5.4808268547058105,
+      "learning_rate": 1.623931623931624e-05,
+      "loss": 1.7023,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.232806444168091,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.1297,
+      "step": 40
+    },
+    {
+      "epoch": 0.04,
+      "eval_loss": 0.5450807809829712,
+      "eval_runtime": 271.242,
+      "eval_samples_per_second": 7.687,
+      "eval_steps_per_second": 0.962,
+      "step": 50
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.8864539265632629,
+      "learning_rate": 4.9572649572649575e-05,
+      "loss": 0.5849,
+      "step": 60
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.8033413887023926,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.4593,
+      "step": 80
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.6578605771064758,
+      "learning_rate": 8.376068376068377e-05,
+      "loss": 0.4425,
+      "step": 100
+    },
+    {
+      "epoch": 0.09,
+      "eval_loss": 0.42795854806900024,
+      "eval_runtime": 271.0229,
+      "eval_samples_per_second": 7.693,
+      "eval_steps_per_second": 0.963,
+      "step": 100
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.5158710479736328,
+      "learning_rate": 0.00010085470085470086,
+      "loss": 0.4249,
+      "step": 120
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.4536530375480652,
+      "learning_rate": 0.00011794871794871796,
+      "loss": 0.4241,
+      "step": 140
+    },
+    {
+      "epoch": 0.13,
+      "eval_loss": 0.4137832820415497,
+      "eval_runtime": 271.1041,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 150
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.3979959785938263,
+      "learning_rate": 0.00013504273504273505,
+      "loss": 0.4154,
+      "step": 160
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.4166259467601776,
+      "learning_rate": 0.00015213675213675214,
+      "loss": 0.4107,
+      "step": 180
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.40765708684921265,
+      "learning_rate": 0.00016923076923076923,
+      "loss": 0.4059,
+      "step": 200
+    },
+    {
+      "epoch": 0.17,
+      "eval_loss": 0.40599754452705383,
+      "eval_runtime": 271.1072,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 200
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.39934784173965454,
+      "learning_rate": 0.00018632478632478634,
+      "loss": 0.3935,
+      "step": 220
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.39337554574012756,
+      "learning_rate": 0.00019999822653125876,
+      "loss": 0.4125,
+      "step": 240
+    },
+    {
+      "epoch": 0.21,
+      "eval_loss": 0.4002617597579956,
+      "eval_runtime": 271.1099,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 250
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.4723268449306488,
+      "learning_rate": 0.00019993616172996704,
+      "loss": 0.4074,
+      "step": 260
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.4829658269882202,
+      "learning_rate": 0.00019978548638541202,
+      "loss": 0.3933,
+      "step": 280
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.7815160155296326,
+      "learning_rate": 0.00019954633409712276,
+      "loss": 0.3948,
+      "step": 300
+    },
+    {
+      "epoch": 0.26,
+      "eval_loss": 0.3945770263671875,
+      "eval_runtime": 271.0451,
+      "eval_samples_per_second": 7.692,
+      "eval_steps_per_second": 0.963,
+      "step": 300
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.4525783956050873,
+      "learning_rate": 0.00019921891691460983,
+      "loss": 0.3777,
+      "step": 320
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.3549365699291229,
+      "learning_rate": 0.00019880352514934724,
+      "loss": 0.3979,
+      "step": 340
+    },
+    {
+      "epoch": 0.3,
+      "eval_loss": 0.3886016309261322,
+      "eval_runtime": 271.0939,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 350
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.38849011063575745,
+      "learning_rate": 0.00019830052711736142,
+      "loss": 0.3895,
+      "step": 360
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.4513374865055084,
+      "learning_rate": 0.00019771036881265598,
+      "loss": 0.3866,
+      "step": 380
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.4288094639778137,
+      "learning_rate": 0.00019703357351176151,
+      "loss": 0.3938,
+      "step": 400
+    },
+    {
+      "epoch": 0.34,
+      "eval_loss": 0.38462838530540466,
+      "eval_runtime": 271.1664,
+      "eval_samples_per_second": 7.689,
+      "eval_steps_per_second": 0.963,
+      "step": 400
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.3525382876396179,
+      "learning_rate": 0.00019627074130976126,
+      "loss": 0.3891,
+      "step": 420
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.5788955688476562,
+      "learning_rate": 0.0001954225485882039,
+      "loss": 0.3739,
+      "step": 440
+    },
+    {
+      "epoch": 0.38,
+      "eval_loss": 0.3804500699043274,
+      "eval_runtime": 271.0816,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 450
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.47232553362846375,
+      "learning_rate": 0.00019448974741537525,
+      "loss": 0.371,
+      "step": 460
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.38733381032943726,
+      "learning_rate": 0.0001934731648794609,
+      "loss": 0.37,
+      "step": 480
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.42200860381126404,
+      "learning_rate": 0.00019237370235519077,
+      "loss": 0.3726,
+      "step": 500
+    },
+    {
+      "epoch": 0.43,
+      "eval_loss": 0.3774518370628357,
+      "eval_runtime": 271.1201,
+      "eval_samples_per_second": 7.69,
+      "eval_steps_per_second": 0.963,
+      "step": 500
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.5560094118118286,
+      "learning_rate": 0.00019119233470461558,
+      "loss": 0.3754,
+      "step": 520
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.3813556134700775,
+      "learning_rate": 0.00018993010941272478,
+      "loss": 0.363,
+      "step": 540
+    },
+    {
+      "epoch": 0.47,
+      "eval_loss": 0.37297067046165466,
+      "eval_runtime": 271.0879,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 550
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.5384305715560913,
+      "learning_rate": 0.0001885881456586713,
+      "loss": 0.3656,
+      "step": 560
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.4100024700164795,
+      "learning_rate": 0.0001871676333234274,
+      "loss": 0.3668,
+      "step": 580
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.4203307628631592,
+      "learning_rate": 0.0001856698319347513,
+      "loss": 0.3718,
+      "step": 600
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 0.3698495626449585,
+      "eval_runtime": 271.0857,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 600
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.5422376990318298,
+      "learning_rate": 0.0001840960695503995,
+      "loss": 0.3813,
+      "step": 620
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.41980084776878357,
+      "learning_rate": 0.00018244774158057624,
+      "loss": 0.3711,
+      "step": 640
+    },
+    {
+      "epoch": 0.55,
+      "eval_loss": 0.3666984438896179,
+      "eval_runtime": 271.059,
+      "eval_samples_per_second": 7.692,
+      "eval_steps_per_second": 0.963,
+      "step": 650
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.49988237023353577,
+      "learning_rate": 0.00018072630955066288,
+      "loss": 0.3669,
+      "step": 660
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.4338107407093048,
+      "learning_rate": 0.00017893329980532498,
+      "loss": 0.3709,
+      "step": 680
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.46425387263298035,
+      "learning_rate": 0.0001770703021551463,
+      "loss": 0.3665,
+      "step": 700
+    },
+    {
+      "epoch": 0.6,
+      "eval_loss": 0.36363786458969116,
+      "eval_runtime": 271.1155,
+      "eval_samples_per_second": 7.69,
+      "eval_steps_per_second": 0.963,
+      "step": 700
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.5348316431045532,
+      "learning_rate": 0.00017513896846698882,
+      "loss": 0.3574,
+      "step": 720
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.4046632945537567,
+      "learning_rate": 0.00017314101119932974,
+      "loss": 0.3625,
+      "step": 740
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 0.3617616891860962,
+      "eval_runtime": 271.137,
+      "eval_samples_per_second": 7.69,
+      "eval_steps_per_second": 0.963,
+      "step": 750
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.44371724128723145,
+      "learning_rate": 0.00017107820188387327,
+      "loss": 0.3752,
+      "step": 760
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.4216190576553345,
+      "learning_rate": 0.00016895236955478412,
+      "loss": 0.3606,
+      "step": 780
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.5870906114578247,
+      "learning_rate": 0.00016676539912693501,
+      "loss": 0.3756,
+      "step": 800
+    },
+    {
+      "epoch": 0.68,
+      "eval_loss": 0.3583546280860901,
+      "eval_runtime": 271.1679,
+      "eval_samples_per_second": 7.689,
+      "eval_steps_per_second": 0.963,
+      "step": 800
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.4018837511539459,
+      "learning_rate": 0.00016451922972460643,
+      "loss": 0.358,
+      "step": 820
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.4688343107700348,
+      "learning_rate": 0.00016221585296212054,
+      "loss": 0.3493,
+      "step": 840
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 0.35402199625968933,
+      "eval_runtime": 271.1165,
+      "eval_samples_per_second": 7.69,
+      "eval_steps_per_second": 0.963,
+      "step": 850
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.4941730797290802,
+      "learning_rate": 0.00015985731117793353,
+      "loss": 0.3502,
+      "step": 860
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.4220365583896637,
+      "learning_rate": 0.00015744569562375235,
+      "loss": 0.3478,
+      "step": 880
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.4305894374847412,
+      "learning_rate": 0.00015498314461028157,
+      "loss": 0.3585,
+      "step": 900
+    },
+    {
+      "epoch": 0.77,
+      "eval_loss": 0.3510061800479889,
+      "eval_runtime": 271.1908,
+      "eval_samples_per_second": 7.688,
+      "eval_steps_per_second": 0.962,
+      "step": 900
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.45022985339164734,
+      "learning_rate": 0.00015247184161124415,
+      "loss": 0.3558,
+      "step": 920
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.4498714506626129,
+      "learning_rate": 0.00014991401332735781,
+      "loss": 0.3466,
+      "step": 940
+    },
+    {
+      "epoch": 0.81,
+      "eval_loss": 0.34707528352737427,
+      "eval_runtime": 271.0841,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 950
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.49369582533836365,
+      "learning_rate": 0.00014731192771198282,
+      "loss": 0.3463,
+      "step": 960
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.36855530738830566,
+      "learning_rate": 0.00014466789196019257,
+      "loss": 0.3428,
+      "step": 980
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.501837968826294,
+      "learning_rate": 0.00014198425046304942,
+      "loss": 0.3483,
+      "step": 1000
+    },
+    {
+      "epoch": 0.85,
+      "eval_loss": 0.34373167157173157,
+      "eval_runtime": 271.0714,
+      "eval_samples_per_second": 7.692,
+      "eval_steps_per_second": 0.963,
+      "step": 1000
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.35614344477653503,
+      "learning_rate": 0.00013926338272890026,
+      "loss": 0.3322,
+      "step": 1020
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.5366308689117432,
+      "learning_rate": 0.00013650770127353416,
+      "loss": 0.343,
+      "step": 1040
+    },
+    {
+      "epoch": 0.9,
+      "eval_loss": 0.3401084542274475,
+      "eval_runtime": 271.1104,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 1050
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.46004125475883484,
+      "learning_rate": 0.00013371964948107344,
+      "loss": 0.3417,
+      "step": 1060
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.5817845463752747,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.332,
+      "step": 1080
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.9298326969146729,
+      "learning_rate": 0.00012805634973870103,
+      "loss": 0.3373,
+      "step": 1100
+    },
+    {
+      "epoch": 0.94,
+      "eval_loss": 0.3367879390716553,
+      "eval_runtime": 271.219,
+      "eval_samples_per_second": 7.688,
+      "eval_steps_per_second": 0.962,
+      "step": 1100
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.5731242299079895,
+      "learning_rate": 0.00012518612327508773,
+      "loss": 0.3443,
+      "step": 1120
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.6886520981788635,
+      "learning_rate": 0.00012229356499456783,
+      "loss": 0.3388,
+      "step": 1140
+    },
+    {
+      "epoch": 0.98,
+      "eval_loss": 0.3337441086769104,
+      "eval_runtime": 271.0416,
+      "eval_samples_per_second": 7.693,
+      "eval_steps_per_second": 0.963,
+      "step": 1150
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.5007095336914062,
+      "learning_rate": 0.00011938123964603922,
+      "loss": 0.3375,
+      "step": 1160
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.49403801560401917,
+      "learning_rate": 0.00011645172950529504,
+      "loss": 0.3091,
+      "step": 1180
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.36014652252197266,
+      "learning_rate": 0.00011350763208539337,
+      "loss": 0.256,
+      "step": 1200
+    },
+    {
+      "epoch": 1.02,
+      "eval_loss": 0.33549007773399353,
+      "eval_runtime": 271.1529,
+      "eval_samples_per_second": 7.689,
+      "eval_steps_per_second": 0.963,
+      "step": 1200
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.4871821403503418,
+      "learning_rate": 0.0001105515578335165,
+      "loss": 0.2534,
+      "step": 1220
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.4773302376270294,
+      "learning_rate": 0.00010758612781636189,
+      "loss": 0.2485,
+      "step": 1240
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 0.3336337208747864,
+      "eval_runtime": 270.9871,
+      "eval_samples_per_second": 7.694,
+      "eval_steps_per_second": 0.963,
+      "step": 1250
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 0.4584294259548187,
+      "learning_rate": 0.00010461397139611717,
+      "loss": 0.2621,
+      "step": 1260
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 0.45226892828941345,
+      "learning_rate": 0.00010163772389907971,
+      "loss": 0.244,
+      "step": 1280
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 0.5343567728996277,
+      "learning_rate": 9.86600242789879e-05,
+      "loss": 0.2452,
+      "step": 1300
+    },
+    {
+      "epoch": 1.11,
+      "eval_loss": 0.33007845282554626,
+      "eval_runtime": 271.0147,
+      "eval_samples_per_second": 7.693,
+      "eval_steps_per_second": 0.963,
+      "step": 1300
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 0.4986325800418854,
+      "learning_rate": 9.568351277713618e-05,
+      "loss": 0.2525,
+      "step": 1320
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 0.4909712076187134,
+      "learning_rate": 9.271082858134854e-05,
+      "loss": 0.2573,
+      "step": 1340
+    },
+    {
+      "epoch": 1.15,
+      "eval_loss": 0.3278447985649109,
+      "eval_runtime": 271.052,
+      "eval_samples_per_second": 7.692,
+      "eval_steps_per_second": 0.963,
+      "step": 1350
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.4675891697406769,
+      "learning_rate": 8.974460748588577e-05,
+      "loss": 0.2516,
+      "step": 1360
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.5919708013534546,
+      "learning_rate": 8.678747955436209e-05,
+      "loss": 0.2459,
+      "step": 1380
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 0.5164061784744263,
+      "learning_rate": 8.384206678774267e-05,
+      "loss": 0.245,
+      "step": 1400
+    },
+    {
+      "epoch": 1.19,
+      "eval_loss": 0.3246319591999054,
+      "eval_runtime": 270.8895,
+      "eval_samples_per_second": 7.697,
+      "eval_steps_per_second": 0.963,
+      "step": 1400
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 0.5498049855232239,
+      "learning_rate": 8.091098079949022e-05,
+      "loss": 0.244,
+      "step": 1420
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 0.40771761536598206,
+      "learning_rate": 7.79968204999218e-05,
+      "loss": 0.2446,
+      "step": 1440
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 0.32402417063713074,
+      "eval_runtime": 270.9055,
+      "eval_samples_per_second": 7.696,
+      "eval_steps_per_second": 0.963,
+      "step": 1450
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.4820304811000824,
+      "learning_rate": 7.510216979182932e-05,
+      "loss": 0.2485,
+      "step": 1460
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.40890711545944214,
+      "learning_rate": 7.222959527940643e-05,
+      "loss": 0.2426,
+      "step": 1480
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.4243795573711395,
+      "learning_rate": 6.93816439925141e-05,
+      "loss": 0.2416,
+      "step": 1500
+    },
+    {
+      "epoch": 1.28,
+      "eval_loss": 0.32116860151290894,
+      "eval_runtime": 270.8886,
+      "eval_samples_per_second": 7.697,
+      "eval_steps_per_second": 0.963,
+      "step": 1500
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.5360056161880493,
+      "learning_rate": 6.656084112830165e-05,
+      "loss": 0.2454,
+      "step": 1520
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 0.5155255198478699,
+      "learning_rate": 6.376968781218665e-05,
+      "loss": 0.2432,
+      "step": 1540
+    },
+    {
+      "epoch": 1.32,
+      "eval_loss": 0.32005202770233154,
+      "eval_runtime": 271.08,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 1550
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 0.564046323299408,
+      "learning_rate": 6.101065888017833e-05,
+      "loss": 0.2414,
+      "step": 1560
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.45059406757354736,
+      "learning_rate": 5.828620068451111e-05,
+      "loss": 0.2408,
+      "step": 1580
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 0.5122149586677551,
+      "learning_rate": 5.559872892453375e-05,
+      "loss": 0.242,
+      "step": 1600
+    },
+    {
+      "epoch": 1.36,
+      "eval_loss": 0.316841185092926,
+      "eval_runtime": 271.0293,
+      "eval_samples_per_second": 7.693,
+      "eval_steps_per_second": 0.963,
+      "step": 1600
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.48864319920539856,
+      "learning_rate": 5.29506265047779e-05,
+      "loss": 0.2432,
+      "step": 1620
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.603583812713623,
+      "learning_rate": 5.034424142210443e-05,
+      "loss": 0.231,
+      "step": 1640
+    },
+    {
+      "epoch": 1.41,
+      "eval_loss": 0.3156278729438782,
+      "eval_runtime": 271.0109,
+      "eval_samples_per_second": 7.693,
+      "eval_steps_per_second": 0.963,
+      "step": 1650
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.5807139873504639,
+      "learning_rate": 4.778188468380169e-05,
+      "loss": 0.2425,
+      "step": 1660
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 0.4968738555908203,
+      "learning_rate": 4.526582825848131e-05,
+      "loss": 0.2362,
+      "step": 1680
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.6385018825531006,
+      "learning_rate": 4.2798303061588404e-05,
+      "loss": 0.2369,
+      "step": 1700
+    },
+    {
+      "epoch": 1.45,
+      "eval_loss": 0.3140126168727875,
+      "eval_runtime": 270.9649,
+      "eval_samples_per_second": 7.695,
+      "eval_steps_per_second": 0.963,
+      "step": 1700
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 0.5020663738250732,
+      "learning_rate": 4.038149697731247e-05,
+      "loss": 0.2425,
+      "step": 1720
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.5276768207550049,
+      "learning_rate": 3.801755291865307e-05,
+      "loss": 0.2405,
+      "step": 1740
+    },
+    {
+      "epoch": 1.49,
+      "eval_loss": 0.3110227882862091,
+      "eval_runtime": 270.8888,
+      "eval_samples_per_second": 7.697,
+      "eval_steps_per_second": 0.963,
+      "step": 1750
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.5092354416847229,
+      "learning_rate": 3.570856692735976e-05,
+      "loss": 0.2356,
+      "step": 1760
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.4134100079536438,
+      "learning_rate": 3.3456586315431874e-05,
+      "loss": 0.2397,
+      "step": 1780
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 0.41335973143577576,
+      "learning_rate": 3.126360784982532e-05,
+      "loss": 0.2263,
+      "step": 1800
+    },
+    {
+      "epoch": 1.53,
+      "eval_loss": 0.309181272983551,
+      "eval_runtime": 270.9592,
+      "eval_samples_per_second": 7.695,
+      "eval_steps_per_second": 0.963,
+      "step": 1800
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.6216692924499512,
+      "learning_rate": 2.9131575981976245e-05,
+      "loss": 0.2371,
+      "step": 1820
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 0.6529776453971863,
+      "learning_rate": 2.7062381123711532e-05,
+      "loss": 0.2324,
+      "step": 1840
+    },
+    {
+      "epoch": 1.58,
+      "eval_loss": 0.3087258040904999,
+      "eval_runtime": 270.9376,
+      "eval_samples_per_second": 7.695,
+      "eval_steps_per_second": 0.963,
+      "step": 1850
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 0.41469648480415344,
+      "learning_rate": 2.505785797107446e-05,
+      "loss": 0.2148,
+      "step": 1860
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.5092002749443054,
+      "learning_rate": 2.3119783877552126e-05,
+      "loss": 0.2287,
+      "step": 1880
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.6236806511878967,
+      "learning_rate": 2.1249877278146868e-05,
+      "loss": 0.2203,
+      "step": 1900
+    },
+    {
+      "epoch": 1.62,
+      "eval_loss": 0.30838343501091003,
+      "eval_runtime": 270.9479,
+      "eval_samples_per_second": 7.695,
+      "eval_steps_per_second": 0.963,
+      "step": 1900
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 2344,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "total_flos": 9.941656300877414e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1900/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edb8fa2435e433c3f852730900572fbfd7369fa856e86f09819c1794580c69b1
+size 5304

checkpoint-2000/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+---
+
+# 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-2000/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "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": 32,
+  "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": [
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-2000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00d3f5a7a89ce26117d3cba51f3e9d306dc080e0738574f084ef3a3bfdc0ac99
+size 167832240

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3725f3bbaa4dc5ad41cb60a5cd1e918b694b6f1ab596a82e1004a9795242632f
+size 335811770

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ba3861df1944efef170daf9467a3af5796b0b65ef9631c128eafadfc6fd079b
+size 14244

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7658b1ce9badf417edb7056dc16a56bb1f9716f15149593615abc9c97c17b17
+size 1000

checkpoint-2000/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-2000/tokenizer.model

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

checkpoint-2000/tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "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": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% 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",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-2000/trainer_state.json

@@ -0,0 +1,1041 @@
+{
+  "best_metric": 0.3054625391960144,
+  "best_model_checkpoint": "./Mistral/17-03-24-Weni-ZeroShot-3.3.35-Mistral-7b-Multilanguage-3.3.0_ZeroShot SFT Training with its best hyperparameters-2_max_steps-2344_batch_16_2024-03-17_ppid_9/checkpoint-2000",
+  "epoch": 1.7050298380221653,
+  "eval_steps": 50,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 5.4808268547058105,
+      "learning_rate": 1.623931623931624e-05,
+      "loss": 1.7023,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.232806444168091,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.1297,
+      "step": 40
+    },
+    {
+      "epoch": 0.04,
+      "eval_loss": 0.5450807809829712,
+      "eval_runtime": 271.242,
+      "eval_samples_per_second": 7.687,
+      "eval_steps_per_second": 0.962,
+      "step": 50
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.8864539265632629,
+      "learning_rate": 4.9572649572649575e-05,
+      "loss": 0.5849,
+      "step": 60
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.8033413887023926,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.4593,
+      "step": 80
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.6578605771064758,
+      "learning_rate": 8.376068376068377e-05,
+      "loss": 0.4425,
+      "step": 100
+    },
+    {
+      "epoch": 0.09,
+      "eval_loss": 0.42795854806900024,
+      "eval_runtime": 271.0229,
+      "eval_samples_per_second": 7.693,
+      "eval_steps_per_second": 0.963,
+      "step": 100
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.5158710479736328,
+      "learning_rate": 0.00010085470085470086,
+      "loss": 0.4249,
+      "step": 120
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.4536530375480652,
+      "learning_rate": 0.00011794871794871796,
+      "loss": 0.4241,
+      "step": 140
+    },
+    {
+      "epoch": 0.13,
+      "eval_loss": 0.4137832820415497,
+      "eval_runtime": 271.1041,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 150
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.3979959785938263,
+      "learning_rate": 0.00013504273504273505,
+      "loss": 0.4154,
+      "step": 160
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.4166259467601776,
+      "learning_rate": 0.00015213675213675214,
+      "loss": 0.4107,
+      "step": 180
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.40765708684921265,
+      "learning_rate": 0.00016923076923076923,
+      "loss": 0.4059,
+      "step": 200
+    },
+    {
+      "epoch": 0.17,
+      "eval_loss": 0.40599754452705383,
+      "eval_runtime": 271.1072,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 200
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.39934784173965454,
+      "learning_rate": 0.00018632478632478634,
+      "loss": 0.3935,
+      "step": 220
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.39337554574012756,
+      "learning_rate": 0.00019999822653125876,
+      "loss": 0.4125,
+      "step": 240
+    },
+    {
+      "epoch": 0.21,
+      "eval_loss": 0.4002617597579956,
+      "eval_runtime": 271.1099,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 250
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.4723268449306488,
+      "learning_rate": 0.00019993616172996704,
+      "loss": 0.4074,
+      "step": 260
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.4829658269882202,
+      "learning_rate": 0.00019978548638541202,
+      "loss": 0.3933,
+      "step": 280
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.7815160155296326,
+      "learning_rate": 0.00019954633409712276,
+      "loss": 0.3948,
+      "step": 300
+    },
+    {
+      "epoch": 0.26,
+      "eval_loss": 0.3945770263671875,
+      "eval_runtime": 271.0451,
+      "eval_samples_per_second": 7.692,
+      "eval_steps_per_second": 0.963,
+      "step": 300
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.4525783956050873,
+      "learning_rate": 0.00019921891691460983,
+      "loss": 0.3777,
+      "step": 320
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.3549365699291229,
+      "learning_rate": 0.00019880352514934724,
+      "loss": 0.3979,
+      "step": 340
+    },
+    {
+      "epoch": 0.3,
+      "eval_loss": 0.3886016309261322,
+      "eval_runtime": 271.0939,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 350
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.38849011063575745,
+      "learning_rate": 0.00019830052711736142,
+      "loss": 0.3895,
+      "step": 360
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.4513374865055084,
+      "learning_rate": 0.00019771036881265598,
+      "loss": 0.3866,
+      "step": 380
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.4288094639778137,
+      "learning_rate": 0.00019703357351176151,
+      "loss": 0.3938,
+      "step": 400
+    },
+    {
+      "epoch": 0.34,
+      "eval_loss": 0.38462838530540466,
+      "eval_runtime": 271.1664,
+      "eval_samples_per_second": 7.689,
+      "eval_steps_per_second": 0.963,
+      "step": 400
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.3525382876396179,
+      "learning_rate": 0.00019627074130976126,
+      "loss": 0.3891,
+      "step": 420
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.5788955688476562,
+      "learning_rate": 0.0001954225485882039,
+      "loss": 0.3739,
+      "step": 440
+    },
+    {
+      "epoch": 0.38,
+      "eval_loss": 0.3804500699043274,
+      "eval_runtime": 271.0816,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 450
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.47232553362846375,
+      "learning_rate": 0.00019448974741537525,
+      "loss": 0.371,
+      "step": 460
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.38733381032943726,
+      "learning_rate": 0.0001934731648794609,
+      "loss": 0.37,
+      "step": 480
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.42200860381126404,
+      "learning_rate": 0.00019237370235519077,
+      "loss": 0.3726,
+      "step": 500
+    },
+    {
+      "epoch": 0.43,
+      "eval_loss": 0.3774518370628357,
+      "eval_runtime": 271.1201,
+      "eval_samples_per_second": 7.69,
+      "eval_steps_per_second": 0.963,
+      "step": 500
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.5560094118118286,
+      "learning_rate": 0.00019119233470461558,
+      "loss": 0.3754,
+      "step": 520
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.3813556134700775,
+      "learning_rate": 0.00018993010941272478,
+      "loss": 0.363,
+      "step": 540
+    },
+    {
+      "epoch": 0.47,
+      "eval_loss": 0.37297067046165466,
+      "eval_runtime": 271.0879,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 550
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.5384305715560913,
+      "learning_rate": 0.0001885881456586713,
+      "loss": 0.3656,
+      "step": 560
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.4100024700164795,
+      "learning_rate": 0.0001871676333234274,
+      "loss": 0.3668,
+      "step": 580
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.4203307628631592,
+      "learning_rate": 0.0001856698319347513,
+      "loss": 0.3718,
+      "step": 600
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 0.3698495626449585,
+      "eval_runtime": 271.0857,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 600
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.5422376990318298,
+      "learning_rate": 0.0001840960695503995,
+      "loss": 0.3813,
+      "step": 620
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.41980084776878357,
+      "learning_rate": 0.00018244774158057624,
+      "loss": 0.3711,
+      "step": 640
+    },
+    {
+      "epoch": 0.55,
+      "eval_loss": 0.3666984438896179,
+      "eval_runtime": 271.059,
+      "eval_samples_per_second": 7.692,
+      "eval_steps_per_second": 0.963,
+      "step": 650
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.49988237023353577,
+      "learning_rate": 0.00018072630955066288,
+      "loss": 0.3669,
+      "step": 660
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.4338107407093048,
+      "learning_rate": 0.00017893329980532498,
+      "loss": 0.3709,
+      "step": 680
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.46425387263298035,
+      "learning_rate": 0.0001770703021551463,
+      "loss": 0.3665,
+      "step": 700
+    },
+    {
+      "epoch": 0.6,
+      "eval_loss": 0.36363786458969116,
+      "eval_runtime": 271.1155,
+      "eval_samples_per_second": 7.69,
+      "eval_steps_per_second": 0.963,
+      "step": 700
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.5348316431045532,
+      "learning_rate": 0.00017513896846698882,
+      "loss": 0.3574,
+      "step": 720
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.4046632945537567,
+      "learning_rate": 0.00017314101119932974,
+      "loss": 0.3625,
+      "step": 740
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 0.3617616891860962,
+      "eval_runtime": 271.137,
+      "eval_samples_per_second": 7.69,
+      "eval_steps_per_second": 0.963,
+      "step": 750
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.44371724128723145,
+      "learning_rate": 0.00017107820188387327,
+      "loss": 0.3752,
+      "step": 760
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.4216190576553345,
+      "learning_rate": 0.00016895236955478412,
+      "loss": 0.3606,
+      "step": 780
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.5870906114578247,
+      "learning_rate": 0.00016676539912693501,
+      "loss": 0.3756,
+      "step": 800
+    },
+    {
+      "epoch": 0.68,
+      "eval_loss": 0.3583546280860901,
+      "eval_runtime": 271.1679,
+      "eval_samples_per_second": 7.689,
+      "eval_steps_per_second": 0.963,
+      "step": 800
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.4018837511539459,
+      "learning_rate": 0.00016451922972460643,
+      "loss": 0.358,
+      "step": 820
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.4688343107700348,
+      "learning_rate": 0.00016221585296212054,
+      "loss": 0.3493,
+      "step": 840
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 0.35402199625968933,
+      "eval_runtime": 271.1165,
+      "eval_samples_per_second": 7.69,
+      "eval_steps_per_second": 0.963,
+      "step": 850
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.4941730797290802,
+      "learning_rate": 0.00015985731117793353,
+      "loss": 0.3502,
+      "step": 860
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.4220365583896637,
+      "learning_rate": 0.00015744569562375235,
+      "loss": 0.3478,
+      "step": 880
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.4305894374847412,
+      "learning_rate": 0.00015498314461028157,
+      "loss": 0.3585,
+      "step": 900
+    },
+    {
+      "epoch": 0.77,
+      "eval_loss": 0.3510061800479889,
+      "eval_runtime": 271.1908,
+      "eval_samples_per_second": 7.688,
+      "eval_steps_per_second": 0.962,
+      "step": 900
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.45022985339164734,
+      "learning_rate": 0.00015247184161124415,
+      "loss": 0.3558,
+      "step": 920
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.4498714506626129,
+      "learning_rate": 0.00014991401332735781,
+      "loss": 0.3466,
+      "step": 940
+    },
+    {
+      "epoch": 0.81,
+      "eval_loss": 0.34707528352737427,
+      "eval_runtime": 271.0841,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 950
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.49369582533836365,
+      "learning_rate": 0.00014731192771198282,
+      "loss": 0.3463,
+      "step": 960
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.36855530738830566,
+      "learning_rate": 0.00014466789196019257,
+      "loss": 0.3428,
+      "step": 980
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.501837968826294,
+      "learning_rate": 0.00014198425046304942,
+      "loss": 0.3483,
+      "step": 1000
+    },
+    {
+      "epoch": 0.85,
+      "eval_loss": 0.34373167157173157,
+      "eval_runtime": 271.0714,
+      "eval_samples_per_second": 7.692,
+      "eval_steps_per_second": 0.963,
+      "step": 1000
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.35614344477653503,
+      "learning_rate": 0.00013926338272890026,
+      "loss": 0.3322,
+      "step": 1020
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.5366308689117432,
+      "learning_rate": 0.00013650770127353416,
+      "loss": 0.343,
+      "step": 1040
+    },
+    {
+      "epoch": 0.9,
+      "eval_loss": 0.3401084542274475,
+      "eval_runtime": 271.1104,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 1050
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.46004125475883484,
+      "learning_rate": 0.00013371964948107344,
+      "loss": 0.3417,
+      "step": 1060
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.5817845463752747,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.332,
+      "step": 1080
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.9298326969146729,
+      "learning_rate": 0.00012805634973870103,
+      "loss": 0.3373,
+      "step": 1100
+    },
+    {
+      "epoch": 0.94,
+      "eval_loss": 0.3367879390716553,
+      "eval_runtime": 271.219,
+      "eval_samples_per_second": 7.688,
+      "eval_steps_per_second": 0.962,
+      "step": 1100
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.5731242299079895,
+      "learning_rate": 0.00012518612327508773,
+      "loss": 0.3443,
+      "step": 1120
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.6886520981788635,
+      "learning_rate": 0.00012229356499456783,
+      "loss": 0.3388,
+      "step": 1140
+    },
+    {
+      "epoch": 0.98,
+      "eval_loss": 0.3337441086769104,
+      "eval_runtime": 271.0416,
+      "eval_samples_per_second": 7.693,
+      "eval_steps_per_second": 0.963,
+      "step": 1150
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.5007095336914062,
+      "learning_rate": 0.00011938123964603922,
+      "loss": 0.3375,
+      "step": 1160
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.49403801560401917,
+      "learning_rate": 0.00011645172950529504,
+      "loss": 0.3091,
+      "step": 1180
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.36014652252197266,
+      "learning_rate": 0.00011350763208539337,
+      "loss": 0.256,
+      "step": 1200
+    },
+    {
+      "epoch": 1.02,
+      "eval_loss": 0.33549007773399353,
+      "eval_runtime": 271.1529,
+      "eval_samples_per_second": 7.689,
+      "eval_steps_per_second": 0.963,
+      "step": 1200
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.4871821403503418,
+      "learning_rate": 0.0001105515578335165,
+      "loss": 0.2534,
+      "step": 1220
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.4773302376270294,
+      "learning_rate": 0.00010758612781636189,
+      "loss": 0.2485,
+      "step": 1240
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 0.3336337208747864,
+      "eval_runtime": 270.9871,
+      "eval_samples_per_second": 7.694,
+      "eval_steps_per_second": 0.963,
+      "step": 1250
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 0.4584294259548187,
+      "learning_rate": 0.00010461397139611717,
+      "loss": 0.2621,
+      "step": 1260
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 0.45226892828941345,
+      "learning_rate": 0.00010163772389907971,
+      "loss": 0.244,
+      "step": 1280
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 0.5343567728996277,
+      "learning_rate": 9.86600242789879e-05,
+      "loss": 0.2452,
+      "step": 1300
+    },
+    {
+      "epoch": 1.11,
+      "eval_loss": 0.33007845282554626,
+      "eval_runtime": 271.0147,
+      "eval_samples_per_second": 7.693,
+      "eval_steps_per_second": 0.963,
+      "step": 1300
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 0.4986325800418854,
+      "learning_rate": 9.568351277713618e-05,
+      "loss": 0.2525,
+      "step": 1320
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 0.4909712076187134,
+      "learning_rate": 9.271082858134854e-05,
+      "loss": 0.2573,
+      "step": 1340
+    },
+    {
+      "epoch": 1.15,
+      "eval_loss": 0.3278447985649109,
+      "eval_runtime": 271.052,
+      "eval_samples_per_second": 7.692,
+      "eval_steps_per_second": 0.963,
+      "step": 1350
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.4675891697406769,
+      "learning_rate": 8.974460748588577e-05,
+      "loss": 0.2516,
+      "step": 1360
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.5919708013534546,
+      "learning_rate": 8.678747955436209e-05,
+      "loss": 0.2459,
+      "step": 1380
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 0.5164061784744263,
+      "learning_rate": 8.384206678774267e-05,
+      "loss": 0.245,
+      "step": 1400
+    },
+    {
+      "epoch": 1.19,
+      "eval_loss": 0.3246319591999054,
+      "eval_runtime": 270.8895,
+      "eval_samples_per_second": 7.697,
+      "eval_steps_per_second": 0.963,
+      "step": 1400
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 0.5498049855232239,
+      "learning_rate": 8.091098079949022e-05,
+      "loss": 0.244,
+      "step": 1420
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 0.40771761536598206,
+      "learning_rate": 7.79968204999218e-05,
+      "loss": 0.2446,
+      "step": 1440
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 0.32402417063713074,
+      "eval_runtime": 270.9055,
+      "eval_samples_per_second": 7.696,
+      "eval_steps_per_second": 0.963,
+      "step": 1450
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.4820304811000824,
+      "learning_rate": 7.510216979182932e-05,
+      "loss": 0.2485,
+      "step": 1460
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.40890711545944214,
+      "learning_rate": 7.222959527940643e-05,
+      "loss": 0.2426,
+      "step": 1480
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.4243795573711395,
+      "learning_rate": 6.93816439925141e-05,
+      "loss": 0.2416,
+      "step": 1500
+    },
+    {
+      "epoch": 1.28,
+      "eval_loss": 0.32116860151290894,
+      "eval_runtime": 270.8886,
+      "eval_samples_per_second": 7.697,
+      "eval_steps_per_second": 0.963,
+      "step": 1500
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.5360056161880493,
+      "learning_rate": 6.656084112830165e-05,
+      "loss": 0.2454,
+      "step": 1520
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 0.5155255198478699,
+      "learning_rate": 6.376968781218665e-05,
+      "loss": 0.2432,
+      "step": 1540
+    },
+    {
+      "epoch": 1.32,
+      "eval_loss": 0.32005202770233154,
+      "eval_runtime": 271.08,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 1550
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 0.564046323299408,
+      "learning_rate": 6.101065888017833e-05,
+      "loss": 0.2414,
+      "step": 1560
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.45059406757354736,
+      "learning_rate": 5.828620068451111e-05,
+      "loss": 0.2408,
+      "step": 1580
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 0.5122149586677551,
+      "learning_rate": 5.559872892453375e-05,
+      "loss": 0.242,
+      "step": 1600
+    },
+    {
+      "epoch": 1.36,
+      "eval_loss": 0.316841185092926,
+      "eval_runtime": 271.0293,
+      "eval_samples_per_second": 7.693,
+      "eval_steps_per_second": 0.963,
+      "step": 1600
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.48864319920539856,
+      "learning_rate": 5.29506265047779e-05,
+      "loss": 0.2432,
+      "step": 1620
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.603583812713623,
+      "learning_rate": 5.034424142210443e-05,
+      "loss": 0.231,
+      "step": 1640
+    },
+    {
+      "epoch": 1.41,
+      "eval_loss": 0.3156278729438782,
+      "eval_runtime": 271.0109,
+      "eval_samples_per_second": 7.693,
+      "eval_steps_per_second": 0.963,
+      "step": 1650
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.5807139873504639,
+      "learning_rate": 4.778188468380169e-05,
+      "loss": 0.2425,
+      "step": 1660
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 0.4968738555908203,
+      "learning_rate": 4.526582825848131e-05,
+      "loss": 0.2362,
+      "step": 1680
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.6385018825531006,
+      "learning_rate": 4.2798303061588404e-05,
+      "loss": 0.2369,
+      "step": 1700
+    },
+    {
+      "epoch": 1.45,
+      "eval_loss": 0.3140126168727875,
+      "eval_runtime": 270.9649,
+      "eval_samples_per_second": 7.695,
+      "eval_steps_per_second": 0.963,
+      "step": 1700
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 0.5020663738250732,
+      "learning_rate": 4.038149697731247e-05,
+      "loss": 0.2425,
+      "step": 1720
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.5276768207550049,
+      "learning_rate": 3.801755291865307e-05,
+      "loss": 0.2405,
+      "step": 1740
+    },
+    {
+      "epoch": 1.49,
+      "eval_loss": 0.3110227882862091,
+      "eval_runtime": 270.8888,
+      "eval_samples_per_second": 7.697,
+      "eval_steps_per_second": 0.963,
+      "step": 1750
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.5092354416847229,
+      "learning_rate": 3.570856692735976e-05,
+      "loss": 0.2356,
+      "step": 1760
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.4134100079536438,
+      "learning_rate": 3.3456586315431874e-05,
+      "loss": 0.2397,
+      "step": 1780
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 0.41335973143577576,
+      "learning_rate": 3.126360784982532e-05,
+      "loss": 0.2263,
+      "step": 1800
+    },
+    {
+      "epoch": 1.53,
+      "eval_loss": 0.309181272983551,
+      "eval_runtime": 270.9592,
+      "eval_samples_per_second": 7.695,
+      "eval_steps_per_second": 0.963,
+      "step": 1800
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.6216692924499512,
+      "learning_rate": 2.9131575981976245e-05,
+      "loss": 0.2371,
+      "step": 1820
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 0.6529776453971863,
+      "learning_rate": 2.7062381123711532e-05,
+      "loss": 0.2324,
+      "step": 1840
+    },
+    {
+      "epoch": 1.58,
+      "eval_loss": 0.3087258040904999,
+      "eval_runtime": 270.9376,
+      "eval_samples_per_second": 7.695,
+      "eval_steps_per_second": 0.963,
+      "step": 1850
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 0.41469648480415344,
+      "learning_rate": 2.505785797107446e-05,
+      "loss": 0.2148,
+      "step": 1860
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.5092002749443054,
+      "learning_rate": 2.3119783877552126e-05,
+      "loss": 0.2287,
+      "step": 1880
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.6236806511878967,
+      "learning_rate": 2.1249877278146868e-05,
+      "loss": 0.2203,
+      "step": 1900
+    },
+    {
+      "epoch": 1.62,
+      "eval_loss": 0.30838343501091003,
+      "eval_runtime": 270.9479,
+      "eval_samples_per_second": 7.695,
+      "eval_steps_per_second": 0.963,
+      "step": 1900
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 0.5142087936401367,
+      "learning_rate": 1.944979616568885e-05,
+      "loss": 0.2287,
+      "step": 1920
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.5550097227096558,
+      "learning_rate": 1.7721136620741218e-05,
+      "loss": 0.223,
+      "step": 1940
+    },
+    {
+      "epoch": 1.66,
+      "eval_loss": 0.30595675110816956,
+      "eval_runtime": 271.0761,
+      "eval_samples_per_second": 7.692,
+      "eval_steps_per_second": 0.963,
+      "step": 1950
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 0.5284961462020874,
+      "learning_rate": 1.6065431396400986e-05,
+      "loss": 0.2268,
+      "step": 1960
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 0.7719703912734985,
+      "learning_rate": 1.4484148559250588e-05,
+      "loss": 0.2406,
+      "step": 1980
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.5748826861381531,
+      "learning_rate": 1.2978690187665133e-05,
+      "loss": 0.2218,
+      "step": 2000
+    },
+    {
+      "epoch": 1.71,
+      "eval_loss": 0.3054625391960144,
+      "eval_runtime": 271.0494,
+      "eval_samples_per_second": 7.692,
+      "eval_steps_per_second": 0.963,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 2344,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "total_flos": 1.0468728764928e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edb8fa2435e433c3f852730900572fbfd7369fa856e86f09819c1794580c69b1
+size 5304

checkpoint-2100/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+---
+
+# 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-2100/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "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": 32,
+  "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": [
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-2100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17d2a98c6cffe01d7b9c3ced36f7e083700f4e1b3f67080263883c32145fb303
+size 167832240

checkpoint-2100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f1326d915ad672159e05ce97ea8f9756ea3981fa5e9e5c9ce69effbc302b202
+size 335811770

checkpoint-2100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f66e49000b2ae3819165be4190c7c1b94184205b802d5ec8e8a565f2bf2555fc
+size 14244

checkpoint-2100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:032d693f28a444c08d62294d238ac6a2482d941ad41baf8d5e29a1298f20c35b
+size 1000

checkpoint-2100/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-2100/tokenizer.model

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

checkpoint-2100/tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "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": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% 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",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-2100/trainer_state.json

@@ -0,0 +1,1092 @@
+{
+  "best_metric": 0.30428797006607056,
+  "best_model_checkpoint": "./Mistral/17-03-24-Weni-ZeroShot-3.3.35-Mistral-7b-Multilanguage-3.3.0_ZeroShot SFT Training with its best hyperparameters-2_max_steps-2344_batch_16_2024-03-17_ppid_9/checkpoint-2100",
+  "epoch": 1.7902813299232738,
+  "eval_steps": 50,
+  "global_step": 2100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 5.4808268547058105,
+      "learning_rate": 1.623931623931624e-05,
+      "loss": 1.7023,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.232806444168091,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.1297,
+      "step": 40
+    },
+    {
+      "epoch": 0.04,
+      "eval_loss": 0.5450807809829712,
+      "eval_runtime": 271.242,
+      "eval_samples_per_second": 7.687,
+      "eval_steps_per_second": 0.962,
+      "step": 50
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.8864539265632629,
+      "learning_rate": 4.9572649572649575e-05,
+      "loss": 0.5849,
+      "step": 60
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.8033413887023926,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.4593,
+      "step": 80
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.6578605771064758,
+      "learning_rate": 8.376068376068377e-05,
+      "loss": 0.4425,
+      "step": 100
+    },
+    {
+      "epoch": 0.09,
+      "eval_loss": 0.42795854806900024,
+      "eval_runtime": 271.0229,
+      "eval_samples_per_second": 7.693,
+      "eval_steps_per_second": 0.963,
+      "step": 100
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.5158710479736328,
+      "learning_rate": 0.00010085470085470086,
+      "loss": 0.4249,
+      "step": 120
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.4536530375480652,
+      "learning_rate": 0.00011794871794871796,
+      "loss": 0.4241,
+      "step": 140
+    },
+    {
+      "epoch": 0.13,
+      "eval_loss": 0.4137832820415497,
+      "eval_runtime": 271.1041,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 150
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.3979959785938263,
+      "learning_rate": 0.00013504273504273505,
+      "loss": 0.4154,
+      "step": 160
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.4166259467601776,
+      "learning_rate": 0.00015213675213675214,
+      "loss": 0.4107,
+      "step": 180
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.40765708684921265,
+      "learning_rate": 0.00016923076923076923,
+      "loss": 0.4059,
+      "step": 200
+    },
+    {
+      "epoch": 0.17,
+      "eval_loss": 0.40599754452705383,
+      "eval_runtime": 271.1072,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 200
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.39934784173965454,
+      "learning_rate": 0.00018632478632478634,
+      "loss": 0.3935,
+      "step": 220
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.39337554574012756,
+      "learning_rate": 0.00019999822653125876,
+      "loss": 0.4125,
+      "step": 240
+    },
+    {
+      "epoch": 0.21,
+      "eval_loss": 0.4002617597579956,
+      "eval_runtime": 271.1099,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 250
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.4723268449306488,
+      "learning_rate": 0.00019993616172996704,
+      "loss": 0.4074,
+      "step": 260
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.4829658269882202,
+      "learning_rate": 0.00019978548638541202,
+      "loss": 0.3933,
+      "step": 280
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.7815160155296326,
+      "learning_rate": 0.00019954633409712276,
+      "loss": 0.3948,
+      "step": 300
+    },
+    {
+      "epoch": 0.26,
+      "eval_loss": 0.3945770263671875,
+      "eval_runtime": 271.0451,
+      "eval_samples_per_second": 7.692,
+      "eval_steps_per_second": 0.963,
+      "step": 300
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.4525783956050873,
+      "learning_rate": 0.00019921891691460983,
+      "loss": 0.3777,
+      "step": 320
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.3549365699291229,
+      "learning_rate": 0.00019880352514934724,
+      "loss": 0.3979,
+      "step": 340
+    },
+    {
+      "epoch": 0.3,
+      "eval_loss": 0.3886016309261322,
+      "eval_runtime": 271.0939,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 350
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.38849011063575745,
+      "learning_rate": 0.00019830052711736142,
+      "loss": 0.3895,
+      "step": 360
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.4513374865055084,
+      "learning_rate": 0.00019771036881265598,
+      "loss": 0.3866,
+      "step": 380
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.4288094639778137,
+      "learning_rate": 0.00019703357351176151,
+      "loss": 0.3938,
+      "step": 400
+    },
+    {
+      "epoch": 0.34,
+      "eval_loss": 0.38462838530540466,
+      "eval_runtime": 271.1664,
+      "eval_samples_per_second": 7.689,
+      "eval_steps_per_second": 0.963,
+      "step": 400
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.3525382876396179,
+      "learning_rate": 0.00019627074130976126,
+      "loss": 0.3891,
+      "step": 420
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.5788955688476562,
+      "learning_rate": 0.0001954225485882039,
+      "loss": 0.3739,
+      "step": 440
+    },
+    {
+      "epoch": 0.38,
+      "eval_loss": 0.3804500699043274,
+      "eval_runtime": 271.0816,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 450
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.47232553362846375,
+      "learning_rate": 0.00019448974741537525,
+      "loss": 0.371,
+      "step": 460
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.38733381032943726,
+      "learning_rate": 0.0001934731648794609,
+      "loss": 0.37,
+      "step": 480
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.42200860381126404,
+      "learning_rate": 0.00019237370235519077,
+      "loss": 0.3726,
+      "step": 500
+    },
+    {
+      "epoch": 0.43,
+      "eval_loss": 0.3774518370628357,
+      "eval_runtime": 271.1201,
+      "eval_samples_per_second": 7.69,
+      "eval_steps_per_second": 0.963,
+      "step": 500
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.5560094118118286,
+      "learning_rate": 0.00019119233470461558,
+      "loss": 0.3754,
+      "step": 520
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.3813556134700775,
+      "learning_rate": 0.00018993010941272478,
+      "loss": 0.363,
+      "step": 540
+    },
+    {
+      "epoch": 0.47,
+      "eval_loss": 0.37297067046165466,
+      "eval_runtime": 271.0879,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 550
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.5384305715560913,
+      "learning_rate": 0.0001885881456586713,
+      "loss": 0.3656,
+      "step": 560
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.4100024700164795,
+      "learning_rate": 0.0001871676333234274,
+      "loss": 0.3668,
+      "step": 580
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.4203307628631592,
+      "learning_rate": 0.0001856698319347513,
+      "loss": 0.3718,
+      "step": 600
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 0.3698495626449585,
+      "eval_runtime": 271.0857,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 600
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.5422376990318298,
+      "learning_rate": 0.0001840960695503995,
+      "loss": 0.3813,
+      "step": 620
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.41980084776878357,
+      "learning_rate": 0.00018244774158057624,
+      "loss": 0.3711,
+      "step": 640
+    },
+    {
+      "epoch": 0.55,
+      "eval_loss": 0.3666984438896179,
+      "eval_runtime": 271.059,
+      "eval_samples_per_second": 7.692,
+      "eval_steps_per_second": 0.963,
+      "step": 650
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.49988237023353577,
+      "learning_rate": 0.00018072630955066288,
+      "loss": 0.3669,
+      "step": 660
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.4338107407093048,
+      "learning_rate": 0.00017893329980532498,
+      "loss": 0.3709,
+      "step": 680
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.46425387263298035,
+      "learning_rate": 0.0001770703021551463,
+      "loss": 0.3665,
+      "step": 700
+    },
+    {
+      "epoch": 0.6,
+      "eval_loss": 0.36363786458969116,
+      "eval_runtime": 271.1155,
+      "eval_samples_per_second": 7.69,
+      "eval_steps_per_second": 0.963,
+      "step": 700
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.5348316431045532,
+      "learning_rate": 0.00017513896846698882,
+      "loss": 0.3574,
+      "step": 720
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.4046632945537567,
+      "learning_rate": 0.00017314101119932974,
+      "loss": 0.3625,
+      "step": 740
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 0.3617616891860962,
+      "eval_runtime": 271.137,
+      "eval_samples_per_second": 7.69,
+      "eval_steps_per_second": 0.963,
+      "step": 750
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.44371724128723145,
+      "learning_rate": 0.00017107820188387327,
+      "loss": 0.3752,
+      "step": 760
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.4216190576553345,
+      "learning_rate": 0.00016895236955478412,
+      "loss": 0.3606,
+      "step": 780
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.5870906114578247,
+      "learning_rate": 0.00016676539912693501,
+      "loss": 0.3756,
+      "step": 800
+    },
+    {
+      "epoch": 0.68,
+      "eval_loss": 0.3583546280860901,
+      "eval_runtime": 271.1679,
+      "eval_samples_per_second": 7.689,
+      "eval_steps_per_second": 0.963,
+      "step": 800
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.4018837511539459,
+      "learning_rate": 0.00016451922972460643,
+      "loss": 0.358,
+      "step": 820
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.4688343107700348,
+      "learning_rate": 0.00016221585296212054,
+      "loss": 0.3493,
+      "step": 840
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 0.35402199625968933,
+      "eval_runtime": 271.1165,
+      "eval_samples_per_second": 7.69,
+      "eval_steps_per_second": 0.963,
+      "step": 850
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.4941730797290802,
+      "learning_rate": 0.00015985731117793353,
+      "loss": 0.3502,
+      "step": 860
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.4220365583896637,
+      "learning_rate": 0.00015744569562375235,
+      "loss": 0.3478,
+      "step": 880
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.4305894374847412,
+      "learning_rate": 0.00015498314461028157,
+      "loss": 0.3585,
+      "step": 900
+    },
+    {
+      "epoch": 0.77,
+      "eval_loss": 0.3510061800479889,
+      "eval_runtime": 271.1908,
+      "eval_samples_per_second": 7.688,
+      "eval_steps_per_second": 0.962,
+      "step": 900
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.45022985339164734,
+      "learning_rate": 0.00015247184161124415,
+      "loss": 0.3558,
+      "step": 920
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.4498714506626129,
+      "learning_rate": 0.00014991401332735781,
+      "loss": 0.3466,
+      "step": 940
+    },
+    {
+      "epoch": 0.81,
+      "eval_loss": 0.34707528352737427,
+      "eval_runtime": 271.0841,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 950
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.49369582533836365,
+      "learning_rate": 0.00014731192771198282,
+      "loss": 0.3463,
+      "step": 960
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.36855530738830566,
+      "learning_rate": 0.00014466789196019257,
+      "loss": 0.3428,
+      "step": 980
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.501837968826294,
+      "learning_rate": 0.00014198425046304942,
+      "loss": 0.3483,
+      "step": 1000
+    },
+    {
+      "epoch": 0.85,
+      "eval_loss": 0.34373167157173157,
+      "eval_runtime": 271.0714,
+      "eval_samples_per_second": 7.692,
+      "eval_steps_per_second": 0.963,
+      "step": 1000
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.35614344477653503,
+      "learning_rate": 0.00013926338272890026,
+      "loss": 0.3322,
+      "step": 1020
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.5366308689117432,
+      "learning_rate": 0.00013650770127353416,
+      "loss": 0.343,
+      "step": 1040
+    },
+    {
+      "epoch": 0.9,
+      "eval_loss": 0.3401084542274475,
+      "eval_runtime": 271.1104,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 1050
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.46004125475883484,
+      "learning_rate": 0.00013371964948107344,
+      "loss": 0.3417,
+      "step": 1060
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.5817845463752747,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.332,
+      "step": 1080
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.9298326969146729,
+      "learning_rate": 0.00012805634973870103,
+      "loss": 0.3373,
+      "step": 1100
+    },
+    {
+      "epoch": 0.94,
+      "eval_loss": 0.3367879390716553,
+      "eval_runtime": 271.219,
+      "eval_samples_per_second": 7.688,
+      "eval_steps_per_second": 0.962,
+      "step": 1100
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.5731242299079895,
+      "learning_rate": 0.00012518612327508773,
+      "loss": 0.3443,
+      "step": 1120
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.6886520981788635,
+      "learning_rate": 0.00012229356499456783,
+      "loss": 0.3388,
+      "step": 1140
+    },
+    {
+      "epoch": 0.98,
+      "eval_loss": 0.3337441086769104,
+      "eval_runtime": 271.0416,
+      "eval_samples_per_second": 7.693,
+      "eval_steps_per_second": 0.963,
+      "step": 1150
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.5007095336914062,
+      "learning_rate": 0.00011938123964603922,
+      "loss": 0.3375,
+      "step": 1160
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.49403801560401917,
+      "learning_rate": 0.00011645172950529504,
+      "loss": 0.3091,
+      "step": 1180
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.36014652252197266,
+      "learning_rate": 0.00011350763208539337,
+      "loss": 0.256,
+      "step": 1200
+    },
+    {
+      "epoch": 1.02,
+      "eval_loss": 0.33549007773399353,
+      "eval_runtime": 271.1529,
+      "eval_samples_per_second": 7.689,
+      "eval_steps_per_second": 0.963,
+      "step": 1200
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.4871821403503418,
+      "learning_rate": 0.0001105515578335165,
+      "loss": 0.2534,
+      "step": 1220
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.4773302376270294,
+      "learning_rate": 0.00010758612781636189,
+      "loss": 0.2485,
+      "step": 1240
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 0.3336337208747864,
+      "eval_runtime": 270.9871,
+      "eval_samples_per_second": 7.694,
+      "eval_steps_per_second": 0.963,
+      "step": 1250
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 0.4584294259548187,
+      "learning_rate": 0.00010461397139611717,
+      "loss": 0.2621,
+      "step": 1260
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 0.45226892828941345,
+      "learning_rate": 0.00010163772389907971,
+      "loss": 0.244,
+      "step": 1280
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 0.5343567728996277,
+      "learning_rate": 9.86600242789879e-05,
+      "loss": 0.2452,
+      "step": 1300
+    },
+    {
+      "epoch": 1.11,
+      "eval_loss": 0.33007845282554626,
+      "eval_runtime": 271.0147,
+      "eval_samples_per_second": 7.693,
+      "eval_steps_per_second": 0.963,
+      "step": 1300
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 0.4986325800418854,
+      "learning_rate": 9.568351277713618e-05,
+      "loss": 0.2525,
+      "step": 1320
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 0.4909712076187134,
+      "learning_rate": 9.271082858134854e-05,
+      "loss": 0.2573,
+      "step": 1340
+    },
+    {
+      "epoch": 1.15,
+      "eval_loss": 0.3278447985649109,
+      "eval_runtime": 271.052,
+      "eval_samples_per_second": 7.692,
+      "eval_steps_per_second": 0.963,
+      "step": 1350
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.4675891697406769,
+      "learning_rate": 8.974460748588577e-05,
+      "loss": 0.2516,
+      "step": 1360
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.5919708013534546,
+      "learning_rate": 8.678747955436209e-05,
+      "loss": 0.2459,
+      "step": 1380
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 0.5164061784744263,
+      "learning_rate": 8.384206678774267e-05,
+      "loss": 0.245,
+      "step": 1400
+    },
+    {
+      "epoch": 1.19,
+      "eval_loss": 0.3246319591999054,
+      "eval_runtime": 270.8895,
+      "eval_samples_per_second": 7.697,
+      "eval_steps_per_second": 0.963,
+      "step": 1400
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 0.5498049855232239,
+      "learning_rate": 8.091098079949022e-05,
+      "loss": 0.244,
+      "step": 1420
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 0.40771761536598206,
+      "learning_rate": 7.79968204999218e-05,
+      "loss": 0.2446,
+      "step": 1440
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 0.32402417063713074,
+      "eval_runtime": 270.9055,
+      "eval_samples_per_second": 7.696,
+      "eval_steps_per_second": 0.963,
+      "step": 1450
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.4820304811000824,
+      "learning_rate": 7.510216979182932e-05,
+      "loss": 0.2485,
+      "step": 1460
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.40890711545944214,
+      "learning_rate": 7.222959527940643e-05,
+      "loss": 0.2426,
+      "step": 1480
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.4243795573711395,
+      "learning_rate": 6.93816439925141e-05,
+      "loss": 0.2416,
+      "step": 1500
+    },
+    {
+      "epoch": 1.28,
+      "eval_loss": 0.32116860151290894,
+      "eval_runtime": 270.8886,
+      "eval_samples_per_second": 7.697,
+      "eval_steps_per_second": 0.963,
+      "step": 1500
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.5360056161880493,
+      "learning_rate": 6.656084112830165e-05,
+      "loss": 0.2454,
+      "step": 1520
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 0.5155255198478699,
+      "learning_rate": 6.376968781218665e-05,
+      "loss": 0.2432,
+      "step": 1540
+    },
+    {
+      "epoch": 1.32,
+      "eval_loss": 0.32005202770233154,
+      "eval_runtime": 271.08,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 1550
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 0.564046323299408,
+      "learning_rate": 6.101065888017833e-05,
+      "loss": 0.2414,
+      "step": 1560
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.45059406757354736,
+      "learning_rate": 5.828620068451111e-05,
+      "loss": 0.2408,
+      "step": 1580
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 0.5122149586677551,
+      "learning_rate": 5.559872892453375e-05,
+      "loss": 0.242,
+      "step": 1600
+    },
+    {
+      "epoch": 1.36,
+      "eval_loss": 0.316841185092926,
+      "eval_runtime": 271.0293,
+      "eval_samples_per_second": 7.693,
+      "eval_steps_per_second": 0.963,
+      "step": 1600
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.48864319920539856,
+      "learning_rate": 5.29506265047779e-05,
+      "loss": 0.2432,
+      "step": 1620
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.603583812713623,
+      "learning_rate": 5.034424142210443e-05,
+      "loss": 0.231,
+      "step": 1640
+    },
+    {
+      "epoch": 1.41,
+      "eval_loss": 0.3156278729438782,
+      "eval_runtime": 271.0109,
+      "eval_samples_per_second": 7.693,
+      "eval_steps_per_second": 0.963,
+      "step": 1650
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.5807139873504639,
+      "learning_rate": 4.778188468380169e-05,
+      "loss": 0.2425,
+      "step": 1660
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 0.4968738555908203,
+      "learning_rate": 4.526582825848131e-05,
+      "loss": 0.2362,
+      "step": 1680
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.6385018825531006,
+      "learning_rate": 4.2798303061588404e-05,
+      "loss": 0.2369,
+      "step": 1700
+    },
+    {
+      "epoch": 1.45,
+      "eval_loss": 0.3140126168727875,
+      "eval_runtime": 270.9649,
+      "eval_samples_per_second": 7.695,
+      "eval_steps_per_second": 0.963,
+      "step": 1700
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 0.5020663738250732,
+      "learning_rate": 4.038149697731247e-05,
+      "loss": 0.2425,
+      "step": 1720
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.5276768207550049,
+      "learning_rate": 3.801755291865307e-05,
+      "loss": 0.2405,
+      "step": 1740
+    },
+    {
+      "epoch": 1.49,
+      "eval_loss": 0.3110227882862091,
+      "eval_runtime": 270.8888,
+      "eval_samples_per_second": 7.697,
+      "eval_steps_per_second": 0.963,
+      "step": 1750
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.5092354416847229,
+      "learning_rate": 3.570856692735976e-05,
+      "loss": 0.2356,
+      "step": 1760
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.4134100079536438,
+      "learning_rate": 3.3456586315431874e-05,
+      "loss": 0.2397,
+      "step": 1780
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 0.41335973143577576,
+      "learning_rate": 3.126360784982532e-05,
+      "loss": 0.2263,
+      "step": 1800
+    },
+    {
+      "epoch": 1.53,
+      "eval_loss": 0.309181272983551,
+      "eval_runtime": 270.9592,
+      "eval_samples_per_second": 7.695,
+      "eval_steps_per_second": 0.963,
+      "step": 1800
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.6216692924499512,
+      "learning_rate": 2.9131575981976245e-05,
+      "loss": 0.2371,
+      "step": 1820
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 0.6529776453971863,
+      "learning_rate": 2.7062381123711532e-05,
+      "loss": 0.2324,
+      "step": 1840
+    },
+    {
+      "epoch": 1.58,
+      "eval_loss": 0.3087258040904999,
+      "eval_runtime": 270.9376,
+      "eval_samples_per_second": 7.695,
+      "eval_steps_per_second": 0.963,
+      "step": 1850
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 0.41469648480415344,
+      "learning_rate": 2.505785797107446e-05,
+      "loss": 0.2148,
+      "step": 1860
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.5092002749443054,
+      "learning_rate": 2.3119783877552126e-05,
+      "loss": 0.2287,
+      "step": 1880
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.6236806511878967,
+      "learning_rate": 2.1249877278146868e-05,
+      "loss": 0.2203,
+      "step": 1900
+    },
+    {
+      "epoch": 1.62,
+      "eval_loss": 0.30838343501091003,
+      "eval_runtime": 270.9479,
+      "eval_samples_per_second": 7.695,
+      "eval_steps_per_second": 0.963,
+      "step": 1900
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 0.5142087936401367,
+      "learning_rate": 1.944979616568885e-05,
+      "loss": 0.2287,
+      "step": 1920
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.5550097227096558,
+      "learning_rate": 1.7721136620741218e-05,
+      "loss": 0.223,
+      "step": 1940
+    },
+    {
+      "epoch": 1.66,
+      "eval_loss": 0.30595675110816956,
+      "eval_runtime": 271.0761,
+      "eval_samples_per_second": 7.692,
+      "eval_steps_per_second": 0.963,
+      "step": 1950
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 0.5284961462020874,
+      "learning_rate": 1.6065431396400986e-05,
+      "loss": 0.2268,
+      "step": 1960
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 0.7719703912734985,
+      "learning_rate": 1.4484148559250588e-05,
+      "loss": 0.2406,
+      "step": 1980
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.5748826861381531,
+      "learning_rate": 1.2978690187665133e-05,
+      "loss": 0.2218,
+      "step": 2000
+    },
+    {
+      "epoch": 1.71,
+      "eval_loss": 0.3054625391960144,
+      "eval_runtime": 271.0494,
+      "eval_samples_per_second": 7.692,
+      "eval_steps_per_second": 0.963,
+      "step": 2000
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.4736625850200653,
+      "learning_rate": 1.1550391128629501e-05,
+      "loss": 0.2362,
+      "step": 2020
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 0.6235111951828003,
+      "learning_rate": 1.0200517814167632e-05,
+      "loss": 0.2278,
+      "step": 2040
+    },
+    {
+      "epoch": 1.75,
+      "eval_loss": 0.30488070845603943,
+      "eval_runtime": 271.0127,
+      "eval_samples_per_second": 7.693,
+      "eval_steps_per_second": 0.963,
+      "step": 2050
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.5903782248497009,
+      "learning_rate": 8.930267138433335e-06,
+      "loss": 0.2315,
+      "step": 2060
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 0.5188658833503723,
+      "learning_rate": 7.740765396458482e-06,
+      "loss": 0.2366,
+      "step": 2080
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 0.6277506351470947,
+      "learning_rate": 6.633067285499228e-06,
+      "loss": 0.2229,
+      "step": 2100
+    },
+    {
+      "epoch": 1.79,
+      "eval_loss": 0.30428797006607056,
+      "eval_runtime": 270.9982,
+      "eval_samples_per_second": 7.694,
+      "eval_steps_per_second": 0.963,
+      "step": 2100
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 2344,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "total_flos": 1.0981367848058388e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edb8fa2435e433c3f852730900572fbfd7369fa856e86f09819c1794580c69b1
+size 5304

checkpoint-2200/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+---
+
+# 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-2200/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "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": 32,
+  "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": [
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-2200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf4ad92e9ae3b0eeafe9d0230e966d9fce792991762cd787a82256e4f49a09d7
+size 167832240

checkpoint-2200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d84feef2d73def152d0ec4100000a303759a70cc11455f9321654031473bca4
+size 335811770

checkpoint-2200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2278405dac5f8ee5e09787f112eea08a7138f539a0b478f25a005e71cff69ac3
+size 14244

checkpoint-2200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f3f5b9be1b795388c3991be2e976674998cc79d3c95b6eafce7af4657cb508a
+size 1000

checkpoint-2200/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-2200/tokenizer.model

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

checkpoint-2200/tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "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": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% 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",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-2200/trainer_state.json

@@ -0,0 +1,1143 @@
+{
+  "best_metric": 0.3037714958190918,
+  "best_model_checkpoint": "./Mistral/17-03-24-Weni-ZeroShot-3.3.35-Mistral-7b-Multilanguage-3.3.0_ZeroShot SFT Training with its best hyperparameters-2_max_steps-2344_batch_16_2024-03-17_ppid_9/checkpoint-2200",
+  "epoch": 1.875532821824382,
+  "eval_steps": 50,
+  "global_step": 2200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 5.4808268547058105,
+      "learning_rate": 1.623931623931624e-05,
+      "loss": 1.7023,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.232806444168091,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.1297,
+      "step": 40
+    },
+    {
+      "epoch": 0.04,
+      "eval_loss": 0.5450807809829712,
+      "eval_runtime": 271.242,
+      "eval_samples_per_second": 7.687,
+      "eval_steps_per_second": 0.962,
+      "step": 50
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.8864539265632629,
+      "learning_rate": 4.9572649572649575e-05,
+      "loss": 0.5849,
+      "step": 60
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.8033413887023926,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.4593,
+      "step": 80
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.6578605771064758,
+      "learning_rate": 8.376068376068377e-05,
+      "loss": 0.4425,
+      "step": 100
+    },
+    {
+      "epoch": 0.09,
+      "eval_loss": 0.42795854806900024,
+      "eval_runtime": 271.0229,
+      "eval_samples_per_second": 7.693,
+      "eval_steps_per_second": 0.963,
+      "step": 100
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.5158710479736328,
+      "learning_rate": 0.00010085470085470086,
+      "loss": 0.4249,
+      "step": 120
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.4536530375480652,
+      "learning_rate": 0.00011794871794871796,
+      "loss": 0.4241,
+      "step": 140
+    },
+    {
+      "epoch": 0.13,
+      "eval_loss": 0.4137832820415497,
+      "eval_runtime": 271.1041,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 150
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.3979959785938263,
+      "learning_rate": 0.00013504273504273505,
+      "loss": 0.4154,
+      "step": 160
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.4166259467601776,
+      "learning_rate": 0.00015213675213675214,
+      "loss": 0.4107,
+      "step": 180
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.40765708684921265,
+      "learning_rate": 0.00016923076923076923,
+      "loss": 0.4059,
+      "step": 200
+    },
+    {
+      "epoch": 0.17,
+      "eval_loss": 0.40599754452705383,
+      "eval_runtime": 271.1072,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 200
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.39934784173965454,
+      "learning_rate": 0.00018632478632478634,
+      "loss": 0.3935,
+      "step": 220
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.39337554574012756,
+      "learning_rate": 0.00019999822653125876,
+      "loss": 0.4125,
+      "step": 240
+    },
+    {
+      "epoch": 0.21,
+      "eval_loss": 0.4002617597579956,
+      "eval_runtime": 271.1099,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 250
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.4723268449306488,
+      "learning_rate": 0.00019993616172996704,
+      "loss": 0.4074,
+      "step": 260
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.4829658269882202,
+      "learning_rate": 0.00019978548638541202,
+      "loss": 0.3933,
+      "step": 280
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.7815160155296326,
+      "learning_rate": 0.00019954633409712276,
+      "loss": 0.3948,
+      "step": 300
+    },
+    {
+      "epoch": 0.26,
+      "eval_loss": 0.3945770263671875,
+      "eval_runtime": 271.0451,
+      "eval_samples_per_second": 7.692,
+      "eval_steps_per_second": 0.963,
+      "step": 300
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.4525783956050873,
+      "learning_rate": 0.00019921891691460983,
+      "loss": 0.3777,
+      "step": 320
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.3549365699291229,
+      "learning_rate": 0.00019880352514934724,
+      "loss": 0.3979,
+      "step": 340
+    },
+    {
+      "epoch": 0.3,
+      "eval_loss": 0.3886016309261322,
+      "eval_runtime": 271.0939,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 350
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.38849011063575745,
+      "learning_rate": 0.00019830052711736142,
+      "loss": 0.3895,
+      "step": 360
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.4513374865055084,
+      "learning_rate": 0.00019771036881265598,
+      "loss": 0.3866,
+      "step": 380
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.4288094639778137,
+      "learning_rate": 0.00019703357351176151,
+      "loss": 0.3938,
+      "step": 400
+    },
+    {
+      "epoch": 0.34,
+      "eval_loss": 0.38462838530540466,
+      "eval_runtime": 271.1664,
+      "eval_samples_per_second": 7.689,
+      "eval_steps_per_second": 0.963,
+      "step": 400
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.3525382876396179,
+      "learning_rate": 0.00019627074130976126,
+      "loss": 0.3891,
+      "step": 420
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.5788955688476562,
+      "learning_rate": 0.0001954225485882039,
+      "loss": 0.3739,
+      "step": 440
+    },
+    {
+      "epoch": 0.38,
+      "eval_loss": 0.3804500699043274,
+      "eval_runtime": 271.0816,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 450
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.47232553362846375,
+      "learning_rate": 0.00019448974741537525,
+      "loss": 0.371,
+      "step": 460
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.38733381032943726,
+      "learning_rate": 0.0001934731648794609,
+      "loss": 0.37,
+      "step": 480
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.42200860381126404,
+      "learning_rate": 0.00019237370235519077,
+      "loss": 0.3726,
+      "step": 500
+    },
+    {
+      "epoch": 0.43,
+      "eval_loss": 0.3774518370628357,
+      "eval_runtime": 271.1201,
+      "eval_samples_per_second": 7.69,
+      "eval_steps_per_second": 0.963,
+      "step": 500
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.5560094118118286,
+      "learning_rate": 0.00019119233470461558,
+      "loss": 0.3754,
+      "step": 520
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.3813556134700775,
+      "learning_rate": 0.00018993010941272478,
+      "loss": 0.363,
+      "step": 540
+    },
+    {
+      "epoch": 0.47,
+      "eval_loss": 0.37297067046165466,
+      "eval_runtime": 271.0879,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 550
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.5384305715560913,
+      "learning_rate": 0.0001885881456586713,
+      "loss": 0.3656,
+      "step": 560
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.4100024700164795,
+      "learning_rate": 0.0001871676333234274,
+      "loss": 0.3668,
+      "step": 580
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.4203307628631592,
+      "learning_rate": 0.0001856698319347513,
+      "loss": 0.3718,
+      "step": 600
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 0.3698495626449585,
+      "eval_runtime": 271.0857,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 600
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.5422376990318298,
+      "learning_rate": 0.0001840960695503995,
+      "loss": 0.3813,
+      "step": 620
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.41980084776878357,
+      "learning_rate": 0.00018244774158057624,
+      "loss": 0.3711,
+      "step": 640
+    },
+    {
+      "epoch": 0.55,
+      "eval_loss": 0.3666984438896179,
+      "eval_runtime": 271.059,
+      "eval_samples_per_second": 7.692,
+      "eval_steps_per_second": 0.963,
+      "step": 650
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.49988237023353577,
+      "learning_rate": 0.00018072630955066288,
+      "loss": 0.3669,
+      "step": 660
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.4338107407093048,
+      "learning_rate": 0.00017893329980532498,
+      "loss": 0.3709,
+      "step": 680
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.46425387263298035,
+      "learning_rate": 0.0001770703021551463,
+      "loss": 0.3665,
+      "step": 700
+    },
+    {
+      "epoch": 0.6,
+      "eval_loss": 0.36363786458969116,
+      "eval_runtime": 271.1155,
+      "eval_samples_per_second": 7.69,
+      "eval_steps_per_second": 0.963,
+      "step": 700
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.5348316431045532,
+      "learning_rate": 0.00017513896846698882,
+      "loss": 0.3574,
+      "step": 720
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.4046632945537567,
+      "learning_rate": 0.00017314101119932974,
+      "loss": 0.3625,
+      "step": 740
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 0.3617616891860962,
+      "eval_runtime": 271.137,
+      "eval_samples_per_second": 7.69,
+      "eval_steps_per_second": 0.963,
+      "step": 750
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.44371724128723145,
+      "learning_rate": 0.00017107820188387327,
+      "loss": 0.3752,
+      "step": 760
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.4216190576553345,
+      "learning_rate": 0.00016895236955478412,
+      "loss": 0.3606,
+      "step": 780
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.5870906114578247,
+      "learning_rate": 0.00016676539912693501,
+      "loss": 0.3756,
+      "step": 800
+    },
+    {
+      "epoch": 0.68,
+      "eval_loss": 0.3583546280860901,
+      "eval_runtime": 271.1679,
+      "eval_samples_per_second": 7.689,
+      "eval_steps_per_second": 0.963,
+      "step": 800
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.4018837511539459,
+      "learning_rate": 0.00016451922972460643,
+      "loss": 0.358,
+      "step": 820
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.4688343107700348,
+      "learning_rate": 0.00016221585296212054,
+      "loss": 0.3493,
+      "step": 840
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 0.35402199625968933,
+      "eval_runtime": 271.1165,
+      "eval_samples_per_second": 7.69,
+      "eval_steps_per_second": 0.963,
+      "step": 850
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.4941730797290802,
+      "learning_rate": 0.00015985731117793353,
+      "loss": 0.3502,
+      "step": 860
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.4220365583896637,
+      "learning_rate": 0.00015744569562375235,
+      "loss": 0.3478,
+      "step": 880
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.4305894374847412,
+      "learning_rate": 0.00015498314461028157,
+      "loss": 0.3585,
+      "step": 900
+    },
+    {
+      "epoch": 0.77,
+      "eval_loss": 0.3510061800479889,
+      "eval_runtime": 271.1908,
+      "eval_samples_per_second": 7.688,
+      "eval_steps_per_second": 0.962,
+      "step": 900
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.45022985339164734,
+      "learning_rate": 0.00015247184161124415,
+      "loss": 0.3558,
+      "step": 920
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.4498714506626129,
+      "learning_rate": 0.00014991401332735781,
+      "loss": 0.3466,
+      "step": 940
+    },
+    {
+      "epoch": 0.81,
+      "eval_loss": 0.34707528352737427,
+      "eval_runtime": 271.0841,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 950
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.49369582533836365,
+      "learning_rate": 0.00014731192771198282,
+      "loss": 0.3463,
+      "step": 960
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.36855530738830566,
+      "learning_rate": 0.00014466789196019257,
+      "loss": 0.3428,
+      "step": 980
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.501837968826294,
+      "learning_rate": 0.00014198425046304942,
+      "loss": 0.3483,
+      "step": 1000
+    },
+    {
+      "epoch": 0.85,
+      "eval_loss": 0.34373167157173157,
+      "eval_runtime": 271.0714,
+      "eval_samples_per_second": 7.692,
+      "eval_steps_per_second": 0.963,
+      "step": 1000
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.35614344477653503,
+      "learning_rate": 0.00013926338272890026,
+      "loss": 0.3322,
+      "step": 1020
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.5366308689117432,
+      "learning_rate": 0.00013650770127353416,
+      "loss": 0.343,
+      "step": 1040
+    },
+    {
+      "epoch": 0.9,
+      "eval_loss": 0.3401084542274475,
+      "eval_runtime": 271.1104,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 1050
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.46004125475883484,
+      "learning_rate": 0.00013371964948107344,
+      "loss": 0.3417,
+      "step": 1060
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.5817845463752747,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.332,
+      "step": 1080
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.9298326969146729,
+      "learning_rate": 0.00012805634973870103,
+      "loss": 0.3373,
+      "step": 1100
+    },
+    {
+      "epoch": 0.94,
+      "eval_loss": 0.3367879390716553,
+      "eval_runtime": 271.219,
+      "eval_samples_per_second": 7.688,
+      "eval_steps_per_second": 0.962,
+      "step": 1100
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.5731242299079895,
+      "learning_rate": 0.00012518612327508773,
+      "loss": 0.3443,
+      "step": 1120
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.6886520981788635,
+      "learning_rate": 0.00012229356499456783,
+      "loss": 0.3388,
+      "step": 1140
+    },
+    {
+      "epoch": 0.98,
+      "eval_loss": 0.3337441086769104,
+      "eval_runtime": 271.0416,
+      "eval_samples_per_second": 7.693,
+      "eval_steps_per_second": 0.963,
+      "step": 1150
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.5007095336914062,
+      "learning_rate": 0.00011938123964603922,
+      "loss": 0.3375,
+      "step": 1160
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.49403801560401917,
+      "learning_rate": 0.00011645172950529504,
+      "loss": 0.3091,
+      "step": 1180
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.36014652252197266,
+      "learning_rate": 0.00011350763208539337,
+      "loss": 0.256,
+      "step": 1200
+    },
+    {
+      "epoch": 1.02,
+      "eval_loss": 0.33549007773399353,
+      "eval_runtime": 271.1529,
+      "eval_samples_per_second": 7.689,
+      "eval_steps_per_second": 0.963,
+      "step": 1200
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.4871821403503418,
+      "learning_rate": 0.0001105515578335165,
+      "loss": 0.2534,
+      "step": 1220
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.4773302376270294,
+      "learning_rate": 0.00010758612781636189,
+      "loss": 0.2485,
+      "step": 1240
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 0.3336337208747864,
+      "eval_runtime": 270.9871,
+      "eval_samples_per_second": 7.694,
+      "eval_steps_per_second": 0.963,
+      "step": 1250
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 0.4584294259548187,
+      "learning_rate": 0.00010461397139611717,
+      "loss": 0.2621,
+      "step": 1260
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 0.45226892828941345,
+      "learning_rate": 0.00010163772389907971,
+      "loss": 0.244,
+      "step": 1280
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 0.5343567728996277,
+      "learning_rate": 9.86600242789879e-05,
+      "loss": 0.2452,
+      "step": 1300
+    },
+    {
+      "epoch": 1.11,
+      "eval_loss": 0.33007845282554626,
+      "eval_runtime": 271.0147,
+      "eval_samples_per_second": 7.693,
+      "eval_steps_per_second": 0.963,
+      "step": 1300
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 0.4986325800418854,
+      "learning_rate": 9.568351277713618e-05,
+      "loss": 0.2525,
+      "step": 1320
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 0.4909712076187134,
+      "learning_rate": 9.271082858134854e-05,
+      "loss": 0.2573,
+      "step": 1340
+    },
+    {
+      "epoch": 1.15,
+      "eval_loss": 0.3278447985649109,
+      "eval_runtime": 271.052,
+      "eval_samples_per_second": 7.692,
+      "eval_steps_per_second": 0.963,
+      "step": 1350
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.4675891697406769,
+      "learning_rate": 8.974460748588577e-05,
+      "loss": 0.2516,
+      "step": 1360
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.5919708013534546,
+      "learning_rate": 8.678747955436209e-05,
+      "loss": 0.2459,
+      "step": 1380
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 0.5164061784744263,
+      "learning_rate": 8.384206678774267e-05,
+      "loss": 0.245,
+      "step": 1400
+    },
+    {
+      "epoch": 1.19,
+      "eval_loss": 0.3246319591999054,
+      "eval_runtime": 270.8895,
+      "eval_samples_per_second": 7.697,
+      "eval_steps_per_second": 0.963,
+      "step": 1400
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 0.5498049855232239,
+      "learning_rate": 8.091098079949022e-05,
+      "loss": 0.244,
+      "step": 1420
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 0.40771761536598206,
+      "learning_rate": 7.79968204999218e-05,
+      "loss": 0.2446,
+      "step": 1440
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 0.32402417063713074,
+      "eval_runtime": 270.9055,
+      "eval_samples_per_second": 7.696,
+      "eval_steps_per_second": 0.963,
+      "step": 1450
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.4820304811000824,
+      "learning_rate": 7.510216979182932e-05,
+      "loss": 0.2485,
+      "step": 1460
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.40890711545944214,
+      "learning_rate": 7.222959527940643e-05,
+      "loss": 0.2426,
+      "step": 1480
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.4243795573711395,
+      "learning_rate": 6.93816439925141e-05,
+      "loss": 0.2416,
+      "step": 1500
+    },
+    {
+      "epoch": 1.28,
+      "eval_loss": 0.32116860151290894,
+      "eval_runtime": 270.8886,
+      "eval_samples_per_second": 7.697,
+      "eval_steps_per_second": 0.963,
+      "step": 1500
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.5360056161880493,
+      "learning_rate": 6.656084112830165e-05,
+      "loss": 0.2454,
+      "step": 1520
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 0.5155255198478699,
+      "learning_rate": 6.376968781218665e-05,
+      "loss": 0.2432,
+      "step": 1540
+    },
+    {
+      "epoch": 1.32,
+      "eval_loss": 0.32005202770233154,
+      "eval_runtime": 271.08,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.963,
+      "step": 1550
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 0.564046323299408,
+      "learning_rate": 6.101065888017833e-05,
+      "loss": 0.2414,
+      "step": 1560
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.45059406757354736,
+      "learning_rate": 5.828620068451111e-05,
+      "loss": 0.2408,
+      "step": 1580
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 0.5122149586677551,
+      "learning_rate": 5.559872892453375e-05,
+      "loss": 0.242,
+      "step": 1600
+    },
+    {
+      "epoch": 1.36,
+      "eval_loss": 0.316841185092926,
+      "eval_runtime": 271.0293,
+      "eval_samples_per_second": 7.693,
+      "eval_steps_per_second": 0.963,
+      "step": 1600
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.48864319920539856,
+      "learning_rate": 5.29506265047779e-05,
+      "loss": 0.2432,
+      "step": 1620
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.603583812713623,
+      "learning_rate": 5.034424142210443e-05,
+      "loss": 0.231,
+      "step": 1640
+    },
+    {
+      "epoch": 1.41,
+      "eval_loss": 0.3156278729438782,
+      "eval_runtime": 271.0109,
+      "eval_samples_per_second": 7.693,
+      "eval_steps_per_second": 0.963,
+      "step": 1650
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.5807139873504639,
+      "learning_rate": 4.778188468380169e-05,
+      "loss": 0.2425,
+      "step": 1660
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 0.4968738555908203,
+      "learning_rate": 4.526582825848131e-05,
+      "loss": 0.2362,
+      "step": 1680
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.6385018825531006,
+      "learning_rate": 4.2798303061588404e-05,
+      "loss": 0.2369,
+      "step": 1700
+    },
+    {
+      "epoch": 1.45,
+      "eval_loss": 0.3140126168727875,
+      "eval_runtime": 270.9649,
+      "eval_samples_per_second": 7.695,
+      "eval_steps_per_second": 0.963,
+      "step": 1700
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 0.5020663738250732,
+      "learning_rate": 4.038149697731247e-05,
+      "loss": 0.2425,
+      "step": 1720
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.5276768207550049,
+      "learning_rate": 3.801755291865307e-05,
+      "loss": 0.2405,
+      "step": 1740
+    },
+    {
+      "epoch": 1.49,
+      "eval_loss": 0.3110227882862091,
+      "eval_runtime": 270.8888,
+      "eval_samples_per_second": 7.697,
+      "eval_steps_per_second": 0.963,
+      "step": 1750
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.5092354416847229,
+      "learning_rate": 3.570856692735976e-05,
+      "loss": 0.2356,
+      "step": 1760
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.4134100079536438,
+      "learning_rate": 3.3456586315431874e-05,
+      "loss": 0.2397,
+      "step": 1780
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 0.41335973143577576,
+      "learning_rate": 3.126360784982532e-05,
+      "loss": 0.2263,
+      "step": 1800
+    },
+    {
+      "epoch": 1.53,
+      "eval_loss": 0.309181272983551,
+      "eval_runtime": 270.9592,
+      "eval_samples_per_second": 7.695,
+      "eval_steps_per_second": 0.963,
+      "step": 1800
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.6216692924499512,
+      "learning_rate": 2.9131575981976245e-05,
+      "loss": 0.2371,
+      "step": 1820
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 0.6529776453971863,
+      "learning_rate": 2.7062381123711532e-05,
+      "loss": 0.2324,
+      "step": 1840
+    },
+    {
+      "epoch": 1.58,
+      "eval_loss": 0.3087258040904999,
+      "eval_runtime": 270.9376,
+      "eval_samples_per_second": 7.695,
+      "eval_steps_per_second": 0.963,
+      "step": 1850
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 0.41469648480415344,
+      "learning_rate": 2.505785797107446e-05,
+      "loss": 0.2148,
+      "step": 1860
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.5092002749443054,
+      "learning_rate": 2.3119783877552126e-05,
+      "loss": 0.2287,
+      "step": 1880
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.6236806511878967,
+      "learning_rate": 2.1249877278146868e-05,
+      "loss": 0.2203,
+      "step": 1900
+    },
+    {
+      "epoch": 1.62,
+      "eval_loss": 0.30838343501091003,
+      "eval_runtime": 270.9479,
+      "eval_samples_per_second": 7.695,
+      "eval_steps_per_second": 0.963,
+      "step": 1900
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 0.5142087936401367,
+      "learning_rate": 1.944979616568885e-05,
+      "loss": 0.2287,
+      "step": 1920
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.5550097227096558,
+      "learning_rate": 1.7721136620741218e-05,
+      "loss": 0.223,
+      "step": 1940
+    },
+    {
+      "epoch": 1.66,
+      "eval_loss": 0.30595675110816956,
+      "eval_runtime": 271.0761,
+      "eval_samples_per_second": 7.692,
+      "eval_steps_per_second": 0.963,
+      "step": 1950
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 0.5284961462020874,
+      "learning_rate": 1.6065431396400986e-05,
+      "loss": 0.2268,
+      "step": 1960
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 0.7719703912734985,
+      "learning_rate": 1.4484148559250588e-05,
+      "loss": 0.2406,
+      "step": 1980
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.5748826861381531,
+      "learning_rate": 1.2978690187665133e-05,
+      "loss": 0.2218,
+      "step": 2000
+    },
+    {
+      "epoch": 1.71,
+      "eval_loss": 0.3054625391960144,
+      "eval_runtime": 271.0494,
+      "eval_samples_per_second": 7.692,
+      "eval_steps_per_second": 0.963,
+      "step": 2000
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.4736625850200653,
+      "learning_rate": 1.1550391128629501e-05,
+      "loss": 0.2362,
+      "step": 2020
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 0.6235111951828003,
+      "learning_rate": 1.0200517814167632e-05,
+      "loss": 0.2278,
+      "step": 2040
+    },
+    {
+      "epoch": 1.75,
+      "eval_loss": 0.30488070845603943,
+      "eval_runtime": 271.0127,
+      "eval_samples_per_second": 7.693,
+      "eval_steps_per_second": 0.963,
+      "step": 2050
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.5903782248497009,
+      "learning_rate": 8.930267138433335e-06,
+      "loss": 0.2315,
+      "step": 2060
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 0.5188658833503723,
+      "learning_rate": 7.740765396458482e-06,
+      "loss": 0.2366,
+      "step": 2080
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 0.6277506351470947,
+      "learning_rate": 6.633067285499228e-06,
+      "loss": 0.2229,
+      "step": 2100
+    },
+    {
+      "epoch": 1.79,
+      "eval_loss": 0.30428797006607056,
+      "eval_runtime": 270.9982,
+      "eval_samples_per_second": 7.694,
+      "eval_steps_per_second": 0.963,
+      "step": 2100
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.5176372528076172,
+      "learning_rate": 5.6081549698661305e-06,
+      "loss": 0.2277,
+      "step": 2120
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 0.5887135863304138,
+      "learning_rate": 4.666937210067012e-06,
+      "loss": 0.2189,
+      "step": 2140
+    },
+    {
+      "epoch": 1.83,
+      "eval_loss": 0.3041435480117798,
+      "eval_runtime": 270.8969,
+      "eval_samples_per_second": 7.697,
+      "eval_steps_per_second": 0.963,
+      "step": 2150
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 0.5156753063201904,
+      "learning_rate": 3.8102485570350123e-06,
+      "loss": 0.2281,
+      "step": 2160
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 0.5229103565216064,
+      "learning_rate": 3.0388486121560313e-06,
+      "loss": 0.2238,
+      "step": 2180
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.6205452084541321,
+      "learning_rate": 2.3534213537518832e-06,
+      "loss": 0.23,
+      "step": 2200
+    },
+    {
+      "epoch": 1.88,
+      "eval_loss": 0.3037714958190918,
+      "eval_runtime": 270.8992,
+      "eval_samples_per_second": 7.697,
+      "eval_steps_per_second": 0.963,
+      "step": 2200
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 2344,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "total_flos": 1.1501065692171633e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edb8fa2435e433c3f852730900572fbfd7369fa856e86f09819c1794580c69b1
+size 5304

checkpoint-2300/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+---
+
+# 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