Rafaelrosendo1/llama

README.md

@@ -0,0 +1,99 @@
+---
+license: llama2
+base_model: meta-llama/Llama-2-7b-hf
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: llama-3-8b-local-definitivo
+  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. -->
+
+# llama-3-8b-local-definitivo
+
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4658
+
+## 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: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.893         | 0.03  | 25   | 1.7774          |
+| 1.714         | 0.05  | 50   | 1.7412          |
+| 1.7498        | 0.08  | 75   | 1.7188          |
+| 1.6899        | 0.1   | 100  | 1.7036          |
+| 1.7176        | 0.13  | 125  | 1.6906          |
+| 1.7198        | 0.15  | 150  | 1.6782          |
+| 1.7086        | 0.18  | 175  | 1.6694          |
+| 1.7236        | 0.21  | 200  | 1.6559          |
+| 1.7616        | 0.23  | 225  | 1.6457          |
+| 1.6756        | 0.26  | 250  | 1.6341          |
+| 1.7199        | 0.28  | 275  | 1.6236          |
+| 1.7121        | 0.31  | 300  | 1.6175          |
+| 1.7542        | 0.34  | 325  | 1.6071          |
+| 1.6884        | 0.36  | 350  | 1.5967          |
+| 1.6089        | 0.39  | 375  | 1.5892          |
+| 1.6556        | 0.41  | 400  | 1.5821          |
+| 1.5784        | 0.44  | 425  | 1.5745          |
+| 1.6317        | 0.46  | 450  | 1.5636          |
+| 1.6375        | 0.49  | 475  | 1.5571          |
+| 1.6772        | 0.52  | 500  | 1.5498          |
+| 1.5775        | 0.54  | 525  | 1.5408          |
+| 1.6307        | 0.57  | 550  | 1.5335          |
+| 1.6938        | 0.59  | 575  | 1.5304          |
+| 1.5764        | 0.62  | 600  | 1.5211          |
+| 1.5834        | 0.64  | 625  | 1.5164          |
+| 1.5483        | 0.67  | 650  | 1.5090          |
+| 1.5883        | 0.7   | 675  | 1.5013          |
+| 1.6268        | 0.72  | 700  | 1.4993          |
+| 1.5515        | 0.75  | 725  | 1.4919          |
+| 1.665         | 0.77  | 750  | 1.4882          |
+| 1.6557        | 0.8   | 775  | 1.4848          |
+| 1.635         | 0.83  | 800  | 1.4829          |
+| 1.6689        | 0.85  | 825  | 1.4782          |
+| 1.6995        | 0.88  | 850  | 1.4742          |
+| 1.6312        | 0.9   | 875  | 1.4714          |
+| 1.6465        | 0.93  | 900  | 1.4689          |
+| 1.51          | 0.95  | 925  | 1.4667          |
+| 1.5953        | 0.98  | 950  | 1.4658          |
+
+
+### Framework versions
+
+- Transformers 4.34.0
+- Pytorch 2.1.2+cu121
+- Datasets 2.12.0
+- Tokenizers 0.14.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "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": 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": [
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d617ba54d6e56b0c8b5039a53088fb47ecf366386dea9383cb627c3fc055360
+size 160069834

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0411a43ae1658296cc5d5e661745d2a53b5be55aa0380f188a7253ae21055d19
+size 159967880

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 2,
+  "<s>": 1,
+  "<unk>": 0
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<unk>",
+  "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "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>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6248506603f85d9811e1ea2245951537528766be6c3f96806aa05b38998cbd12
+size 4536