Upload folder using huggingface_hub

README.md

@@ -0,0 +1,58 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+library_name: peft
+license: other
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: train_mistral
+  results: []
+---
+
+<!-- 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. -->
+
+# train_mistral
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the treino_pt_rde dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.44.2
+- Pytorch 2.3.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50941bf7e860fc610e047ad5dcc0a43101b1fef8fa15fb0b226cf9ff1ceb171f
+size 83945296

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.96,
+    "num_input_tokens_seen": 358624,
+    "total_flos": 1.5352214341287936e+16,
+    "train_loss": 0.24338918279957128,
+    "train_runtime": 8119.2255,
+    "train_samples_per_second": 0.111,
+    "train_steps_per_second": 0.014
+}

checkpoint-111/README.md

@@ -0,0 +1,202 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+library_name: peft
+---
+
+# 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 0.12.0

checkpoint-111/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-111/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50941bf7e860fc610e047ad5dcc0a43101b1fef8fa15fb0b226cf9ff1ceb171f
+size 83945296

checkpoint-111/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01e561ae4173e95edadb62264a536a40fa0f0ac13041576babe3d99f5dbfd412
+size 168149074

checkpoint-111/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244

checkpoint-111/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cb3e701784ce7be7de0b0ccb685aded67f61dd385a4fc3b6a36f7f394ca085b
+size 1064

checkpoint-111/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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-111/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

checkpoint-111/trainer_state.json

@@ -0,0 +1,121 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.96,
+  "eval_steps": 500,
+  "global_step": 111,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 2.969418525695801,
+      "learning_rate": 4.9005367134442235e-05,
+      "loss": 0.4778,
+      "num_input_tokens_seen": 33232,
+      "step": 10
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 2.1690313816070557,
+      "learning_rate": 4.6100612100748765e-05,
+      "loss": 0.3431,
+      "num_input_tokens_seen": 65520,
+      "step": 20
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 6.671631813049316,
+      "learning_rate": 4.151686808475204e-05,
+      "loss": 0.318,
+      "num_input_tokens_seen": 97472,
+      "step": 30
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 3.928008794784546,
+      "learning_rate": 3.56188664821012e-05,
+      "loss": 0.4028,
+      "num_input_tokens_seen": 128928,
+      "step": 40
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 11.873285293579102,
+      "learning_rate": 2.8875914991604948e-05,
+      "loss": 0.1864,
+      "num_input_tokens_seen": 161248,
+      "step": 50
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 11.22799301147461,
+      "learning_rate": 2.182455450632803e-05,
+      "loss": 0.218,
+      "num_input_tokens_seen": 193728,
+      "step": 60
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 4.876537799835205,
+      "learning_rate": 1.5025866217114592e-05,
+      "loss": 0.2257,
+      "num_input_tokens_seen": 226048,
+      "step": 70
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 3.1793081760406494,
+      "learning_rate": 9.020826029175384e-06,
+      "loss": 0.2099,
+      "num_input_tokens_seen": 258608,
+      "step": 80
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 4.5291218757629395,
+      "learning_rate": 4.2872587689039484e-06,
+      "loss": 0.1456,
+      "num_input_tokens_seen": 290720,
+      "step": 90
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 2.929227590560913,
+      "learning_rate": 1.201817361771837e-06,
+      "loss": 0.0777,
+      "num_input_tokens_seen": 323584,
+      "step": 100
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 2.021867036819458,
+      "learning_rate": 1.0012322041960676e-08,
+      "loss": 0.0711,
+      "num_input_tokens_seen": 355456,
+      "step": 110
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 111,
+  "num_input_tokens_seen": 358624,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5352214341287936e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-111/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f425e45c06d80fc466afd9d8416f7907a8fac0b6229ea210de400d287182e686
+size 5368

config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "ShashiVish/t5-small-fine-tune-cover-letter",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "max_length": 512,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 32128
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "max_length": 512,
+  "pad_token_id": 0,
+  "transformers_version": "4.44.2"
+}

llamaboard_config.yaml

@@ -0,0 +1,66 @@
+top.booster: auto
+top.checkpoint_path: []
+top.finetuning_type: lora
+top.model_name: Mistral-7B-Instruct-v0.3
+top.quantization_bit: '4'
+top.quantization_method: bitsandbytes
+top.rope_scaling: none
+top.template: mistral
+train.additional_target: ''
+train.badam_mode: layer
+train.badam_switch_interval: 50
+train.badam_switch_mode: ascending
+train.badam_update_ratio: 0.05
+train.batch_size: 2
+train.compute_type: bf16
+train.create_new_adapter: false
+train.cutoff_len: 2048
+train.dataset:
+- treino_pt_rde
+train.dataset_dir: data
+train.ds_offload: false
+train.ds_stage: none
+train.extra_args: '{"optim": "adamw_torch"}'
+train.freeze_extra_modules: ''
+train.freeze_trainable_layers: 2
+train.freeze_trainable_modules: all
+train.galore_rank: 16
+train.galore_scale: 0.25
+train.galore_target: all
+train.galore_update_interval: 200
+train.gradient_accumulation_steps: 4
+train.learning_rate: 5e-5
+train.logging_steps: 10
+train.lora_alpha: 16
+train.lora_dropout: 0
+train.lora_rank: 8
+train.lora_target: ''
+train.loraplus_lr_ratio: 0
+train.lr_scheduler_type: cosine
+train.mask_history: false
+train.max_grad_norm: '1.0'
+train.max_samples: '300'
+train.neat_packing: false
+train.neftune_alpha: 0
+train.num_train_epochs: '3.0'
+train.packing: false
+train.ppo_score_norm: false
+train.ppo_whiten_rewards: false
+train.pref_beta: 0.1
+train.pref_ftx: 0
+train.pref_loss: sigmoid
+train.report_to: false
+train.resize_vocab: false
+train.reward_model: null
+train.save_steps: 1000
+train.shift_attn: false
+train.train_on_prompt: false
+train.training_stage: Supervised Fine-Tuning
+train.use_badam: false
+train.use_dora: false
+train.use_galore: false
+train.use_llama_pro: false
+train.use_pissa: false
+train.use_rslora: false
+train.val_size: 0
+train.warmup_steps: 0

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:602a9e974b1a45a14981654c1bab1c983008b5cd624f91d11fdbf26c95eb00ec
+size 242041896

running_log.txt

@@ -0,0 +1,284 @@
+[WARNING|2024-11-12 02:01:07] logging.py:162 >> We recommend enable `upcast_layernorm` in quantized training.
+
+[INFO|2024-11-12 02:01:07] parser.py:355 >> Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: False, compute dtype: torch.bfloat16
+
+[INFO|2024-11-12 02:01:07] configuration_utils.py:733 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/config.json
+
+[INFO|2024-11-12 02:01:07] configuration_utils.py:800 >> Model config MistralConfig {
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 32768
+}
+
+
+[INFO|2024-11-12 02:01:08] tokenization_utils_base.py:2269 >> loading file tokenizer.model from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/tokenizer.model
+
+[INFO|2024-11-12 02:01:08] tokenization_utils_base.py:2269 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/tokenizer.json
+
+[INFO|2024-11-12 02:01:08] tokenization_utils_base.py:2269 >> loading file added_tokens.json from cache at None
+
+[INFO|2024-11-12 02:01:08] tokenization_utils_base.py:2269 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/special_tokens_map.json
+
+[INFO|2024-11-12 02:01:08] tokenization_utils_base.py:2269 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/tokenizer_config.json
+
+[INFO|2024-11-12 02:01:09] configuration_utils.py:733 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/config.json
+
+[INFO|2024-11-12 02:01:09] configuration_utils.py:800 >> Model config MistralConfig {
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 32768
+}
+
+
+[INFO|2024-11-12 02:01:09] tokenization_utils_base.py:2269 >> loading file tokenizer.model from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/tokenizer.model
+
+[INFO|2024-11-12 02:01:09] tokenization_utils_base.py:2269 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/tokenizer.json
+
+[INFO|2024-11-12 02:01:09] tokenization_utils_base.py:2269 >> loading file added_tokens.json from cache at None
+
+[INFO|2024-11-12 02:01:09] tokenization_utils_base.py:2269 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/special_tokens_map.json
+
+[INFO|2024-11-12 02:01:09] tokenization_utils_base.py:2269 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/tokenizer_config.json
+
+[INFO|2024-11-12 02:01:10] logging.py:157 >> Add pad token: </s>
+
+[INFO|2024-11-12 02:01:10] logging.py:157 >> Loading dataset treino_pt_rde.json...
+
+[INFO|2024-11-12 02:01:15] configuration_utils.py:733 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/config.json
+
+[INFO|2024-11-12 02:01:15] configuration_utils.py:800 >> Model config MistralConfig {
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 32768
+}
+
+
+[INFO|2024-11-12 02:01:15] logging.py:157 >> Quantizing model to 4 bit with bitsandbytes.
+
+[INFO|2024-11-12 02:01:15] modeling_utils.py:3678 >> loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/model.safetensors.index.json
+
+[INFO|2024-11-12 02:07:01] modeling_utils.py:1606 >> Instantiating MistralForCausalLM model under default dtype torch.bfloat16.
+
+[INFO|2024-11-12 02:07:01] configuration_utils.py:1038 >> Generate config GenerationConfig {
+  "bos_token_id": 1,
+  "eos_token_id": 2
+}
+
+
+[INFO|2024-11-12 02:08:04] modeling_utils.py:4507 >> All model checkpoint weights were used when initializing MistralForCausalLM.
+
+
+[INFO|2024-11-12 02:08:04] modeling_utils.py:4515 >> All the weights of MistralForCausalLM were initialized from the model checkpoint at mistralai/Mistral-7B-Instruct-v0.3.
+If your task is similar to the task the model of the checkpoint was trained on, you can already use MistralForCausalLM for predictions without further training.
+
+[INFO|2024-11-12 02:08:05] configuration_utils.py:993 >> loading configuration file generation_config.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/generation_config.json
+
+[INFO|2024-11-12 02:08:05] configuration_utils.py:1038 >> Generate config GenerationConfig {
+  "bos_token_id": 1,
+  "eos_token_id": 2
+}
+
+
+[INFO|2024-11-12 02:08:05] logging.py:157 >> Gradient checkpointing enabled.
+
+[INFO|2024-11-12 02:08:05] logging.py:157 >> Using torch SDPA for faster training and inference.
+
+[INFO|2024-11-12 02:08:05] logging.py:157 >> Upcasting trainable params to float32.
+
+[INFO|2024-11-12 02:08:05] logging.py:157 >> Fine-tuning method: LoRA
+
+[INFO|2024-11-12 02:08:05] logging.py:157 >> Found linear modules: o_proj,q_proj,v_proj,down_proj,gate_proj,k_proj,up_proj
+
+[INFO|2024-11-12 02:08:06] logging.py:157 >> trainable params: 20,971,520 || all params: 7,268,995,072 || trainable%: 0.2885
+
+[INFO|2024-11-12 02:08:06] trainer.py:648 >> Using auto half precision backend
+
+[INFO|2024-11-12 02:08:06] trainer.py:2134 >> ***** Running training *****
+
+[INFO|2024-11-12 02:08:06] trainer.py:2135 >>   Num examples = 300
+
+[INFO|2024-11-12 02:08:06] trainer.py:2136 >>   Num Epochs = 3
+
+[INFO|2024-11-12 02:08:06] trainer.py:2137 >>   Instantaneous batch size per device = 2
+
+[INFO|2024-11-12 02:08:06] trainer.py:2140 >>   Total train batch size (w. parallel, distributed & accumulation) = 8
+
+[INFO|2024-11-12 02:08:06] trainer.py:2141 >>   Gradient Accumulation steps = 4
+
+[INFO|2024-11-12 02:08:06] trainer.py:2142 >>   Total optimization steps = 111
+
+[INFO|2024-11-12 02:08:06] trainer.py:2143 >>   Number of trainable parameters = 20,971,520
+
+[INFO|2024-11-12 02:20:35] logging.py:157 >> {'loss': 0.4778, 'learning_rate': 4.9005e-05, 'epoch': 0.27, 'throughput': 44.35}
+
+[INFO|2024-11-12 02:32:47] logging.py:157 >> {'loss': 0.3431, 'learning_rate': 4.6101e-05, 'epoch': 0.53, 'throughput': 44.24}
+
+[INFO|2024-11-12 02:44:52] logging.py:157 >> {'loss': 0.3180, 'learning_rate': 4.1517e-05, 'epoch': 0.80, 'throughput': 44.19}
+
+[INFO|2024-11-12 02:56:44] logging.py:157 >> {'loss': 0.4028, 'learning_rate': 3.5619e-05, 'epoch': 1.07, 'throughput': 44.18}
+
+[INFO|2024-11-12 03:08:54] logging.py:157 >> {'loss': 0.1864, 'learning_rate': 2.8876e-05, 'epoch': 1.33, 'throughput': 44.20}
+
+[INFO|2024-11-12 03:21:09] logging.py:157 >> {'loss': 0.2180, 'learning_rate': 2.1825e-05, 'epoch': 1.60, 'throughput': 44.20}
+
+[INFO|2024-11-12 03:33:22] logging.py:157 >> {'loss': 0.2257, 'learning_rate': 1.5026e-05, 'epoch': 1.87, 'throughput': 44.18}
+
+[INFO|2024-11-12 03:45:39] logging.py:157 >> {'loss': 0.2099, 'learning_rate': 9.0208e-06, 'epoch': 2.13, 'throughput': 44.19}
+
+[INFO|2024-11-12 03:57:47] logging.py:157 >> {'loss': 0.1456, 'learning_rate': 4.2873e-06, 'epoch': 2.40, 'throughput': 44.18}
+
+[INFO|2024-11-12 04:10:11] logging.py:157 >> {'loss': 0.0777, 'learning_rate': 1.2018e-06, 'epoch': 2.67, 'throughput': 44.18}
+
+[INFO|2024-11-12 04:22:13] logging.py:157 >> {'loss': 0.0711, 'learning_rate': 1.0012e-08, 'epoch': 2.93, 'throughput': 44.18}
+
+[INFO|2024-11-12 04:23:24] trainer.py:3503 >> Saving model checkpoint to saves/Mistral-7B-Instruct-v0.3/lora/train_mistral/checkpoint-111
+
+[INFO|2024-11-12 04:23:24] configuration_utils.py:733 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/config.json
+
+[INFO|2024-11-12 04:23:24] configuration_utils.py:800 >> Model config MistralConfig {
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 32768
+}
+
+
+[INFO|2024-11-12 04:23:25] tokenization_utils_base.py:2684 >> tokenizer config file saved in saves/Mistral-7B-Instruct-v0.3/lora/train_mistral/checkpoint-111/tokenizer_config.json
+
+[INFO|2024-11-12 04:23:25] tokenization_utils_base.py:2693 >> Special tokens file saved in saves/Mistral-7B-Instruct-v0.3/lora/train_mistral/checkpoint-111/special_tokens_map.json
+
+[INFO|2024-11-12 04:23:25] trainer.py:2394 >> 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+
+[INFO|2024-11-12 04:23:25] trainer.py:3503 >> Saving model checkpoint to saves/Mistral-7B-Instruct-v0.3/lora/train_mistral
+
+[INFO|2024-11-12 04:23:26] configuration_utils.py:733 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/config.json
+
+[INFO|2024-11-12 04:23:26] configuration_utils.py:800 >> Model config MistralConfig {
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 32768
+}
+
+
+[INFO|2024-11-12 04:23:26] tokenization_utils_base.py:2684 >> tokenizer config file saved in saves/Mistral-7B-Instruct-v0.3/lora/train_mistral/tokenizer_config.json
+
+[INFO|2024-11-12 04:23:26] tokenization_utils_base.py:2693 >> Special tokens file saved in saves/Mistral-7B-Instruct-v0.3/lora/train_mistral/special_tokens_map.json
+
+[WARNING|2024-11-12 04:23:26] logging.py:162 >> No metric eval_loss to plot.
+
+[WARNING|2024-11-12 04:23:26] logging.py:162 >> No metric eval_accuracy to plot.
+
+[INFO|2024-11-12 04:23:26] modelcard.py:449 >> Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
+

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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.96,
+    "num_input_tokens_seen": 358624,
+    "total_flos": 1.5352214341287936e+16,
+    "train_loss": 0.24338918279957128,
+    "train_runtime": 8119.2255,
+    "train_samples_per_second": 0.111,
+    "train_steps_per_second": 0.014
+}

trainer_log.jsonl

@@ -0,0 +1,12 @@
+{"current_steps": 10, "total_steps": 111, "loss": 0.4778, "lr": 4.9005367134442235e-05, "epoch": 0.26666666666666666, "percentage": 9.01, "elapsed_time": "0:12:29", "remaining_time": "2:06:08", "throughput": 44.35, "total_tokens": 33232}
+{"current_steps": 20, "total_steps": 111, "loss": 0.3431, "lr": 4.6100612100748765e-05, "epoch": 0.5333333333333333, "percentage": 18.02, "elapsed_time": "0:24:41", "remaining_time": "1:52:18", "throughput": 44.24, "total_tokens": 65520}
+{"current_steps": 30, "total_steps": 111, "loss": 0.318, "lr": 4.151686808475204e-05, "epoch": 0.8, "percentage": 27.03, "elapsed_time": "0:36:45", "remaining_time": "1:39:15", "throughput": 44.19, "total_tokens": 97472}
+{"current_steps": 40, "total_steps": 111, "loss": 0.4028, "lr": 3.56188664821012e-05, "epoch": 1.0666666666666667, "percentage": 36.04, "elapsed_time": "0:48:38", "remaining_time": "1:26:19", "throughput": 44.18, "total_tokens": 128928}
+{"current_steps": 50, "total_steps": 111, "loss": 0.1864, "lr": 2.8875914991604948e-05, "epoch": 1.3333333333333333, "percentage": 45.05, "elapsed_time": "1:00:48", "remaining_time": "1:14:10", "throughput": 44.2, "total_tokens": 161248}
+{"current_steps": 60, "total_steps": 111, "loss": 0.218, "lr": 2.182455450632803e-05, "epoch": 1.6, "percentage": 54.05, "elapsed_time": "1:13:03", "remaining_time": "1:02:05", "throughput": 44.2, "total_tokens": 193728}
+{"current_steps": 70, "total_steps": 111, "loss": 0.2257, "lr": 1.5025866217114592e-05, "epoch": 1.8666666666666667, "percentage": 63.06, "elapsed_time": "1:25:15", "remaining_time": "0:49:56", "throughput": 44.18, "total_tokens": 226048}
+{"current_steps": 80, "total_steps": 111, "loss": 0.2099, "lr": 9.020826029175384e-06, "epoch": 2.1333333333333333, "percentage": 72.07, "elapsed_time": "1:37:32", "remaining_time": "0:37:47", "throughput": 44.19, "total_tokens": 258608}
+{"current_steps": 90, "total_steps": 111, "loss": 0.1456, "lr": 4.2872587689039484e-06, "epoch": 2.4, "percentage": 81.08, "elapsed_time": "1:49:40", "remaining_time": "0:25:35", "throughput": 44.18, "total_tokens": 290720}
+{"current_steps": 100, "total_steps": 111, "loss": 0.0777, "lr": 1.201817361771837e-06, "epoch": 2.6666666666666665, "percentage": 90.09, "elapsed_time": "2:02:04", "remaining_time": "0:13:25", "throughput": 44.18, "total_tokens": 323584}
+{"current_steps": 110, "total_steps": 111, "loss": 0.0711, "lr": 1.0012322041960676e-08, "epoch": 2.9333333333333336, "percentage": 99.1, "elapsed_time": "2:14:06", "remaining_time": "0:01:13", "throughput": 44.18, "total_tokens": 355456}
+{"current_steps": 111, "total_steps": 111, "epoch": 2.96, "percentage": 100.0, "elapsed_time": "2:15:19", "remaining_time": "0:00:00", "throughput": 44.17, "total_tokens": 358624}

trainer_state.json

@@ -0,0 +1,131 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.96,
+  "eval_steps": 500,
+  "global_step": 111,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 2.969418525695801,
+      "learning_rate": 4.9005367134442235e-05,
+      "loss": 0.4778,
+      "num_input_tokens_seen": 33232,
+      "step": 10
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 2.1690313816070557,
+      "learning_rate": 4.6100612100748765e-05,
+      "loss": 0.3431,
+      "num_input_tokens_seen": 65520,
+      "step": 20
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 6.671631813049316,
+      "learning_rate": 4.151686808475204e-05,
+      "loss": 0.318,
+      "num_input_tokens_seen": 97472,
+      "step": 30
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 3.928008794784546,
+      "learning_rate": 3.56188664821012e-05,
+      "loss": 0.4028,
+      "num_input_tokens_seen": 128928,
+      "step": 40
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 11.873285293579102,
+      "learning_rate": 2.8875914991604948e-05,
+      "loss": 0.1864,
+      "num_input_tokens_seen": 161248,
+      "step": 50
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 11.22799301147461,
+      "learning_rate": 2.182455450632803e-05,
+      "loss": 0.218,
+      "num_input_tokens_seen": 193728,
+      "step": 60
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 4.876537799835205,
+      "learning_rate": 1.5025866217114592e-05,
+      "loss": 0.2257,
+      "num_input_tokens_seen": 226048,
+      "step": 70
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 3.1793081760406494,
+      "learning_rate": 9.020826029175384e-06,
+      "loss": 0.2099,
+      "num_input_tokens_seen": 258608,
+      "step": 80
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 4.5291218757629395,
+      "learning_rate": 4.2872587689039484e-06,
+      "loss": 0.1456,
+      "num_input_tokens_seen": 290720,
+      "step": 90
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 2.929227590560913,
+      "learning_rate": 1.201817361771837e-06,
+      "loss": 0.0777,
+      "num_input_tokens_seen": 323584,
+      "step": 100
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 2.021867036819458,
+      "learning_rate": 1.0012322041960676e-08,
+      "loss": 0.0711,
+      "num_input_tokens_seen": 355456,
+      "step": 110
+    },
+    {
+      "epoch": 2.96,
+      "num_input_tokens_seen": 358624,
+      "step": 111,
+      "total_flos": 1.5352214341287936e+16,
+      "train_loss": 0.24338918279957128,
+      "train_runtime": 8119.2255,
+      "train_samples_per_second": 0.111,
+      "train_steps_per_second": 0.014
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 111,
+  "num_input_tokens_seen": 358624,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5352214341287936e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f425e45c06d80fc466afd9d8416f7907a8fac0b6229ea210de400d287182e686
+size 5368

training_args.yaml

@@ -0,0 +1,34 @@
+bf16: true
+cutoff_len: 2048
+dataset: treino_pt_rde
+dataset_dir: data
+ddp_timeout: 180000000
+do_train: true
+finetuning_type: lora
+flash_attn: auto
+gradient_accumulation_steps: 4
+include_num_input_tokens_seen: true
+learning_rate: 5.0e-05
+logging_steps: 10
+lora_alpha: 16
+lora_dropout: 0
+lora_rank: 8
+lora_target: all
+lr_scheduler_type: cosine
+max_grad_norm: 1.0
+max_samples: 300
+model_name_or_path: mistralai/Mistral-7B-Instruct-v0.3
+num_train_epochs: 3.0
+optim: adamw_torch
+output_dir: saves/Mistral-7B-Instruct-v0.3/lora/train_mistral
+packing: false
+per_device_train_batch_size: 2
+plot_loss: true
+preprocessing_num_workers: 16
+quantization_bit: 4
+quantization_method: bitsandbytes
+report_to: none
+save_steps: 1000
+stage: sft
+template: mistral
+warmup_steps: 0