Model save

README.md

@@ -0,0 +1,57 @@
+---
+base_model: meta-llama/Llama-3.1-8B-Instruct
+library_name: transformers
+model_name: cocoruta2-llama3-1-8b-llm-filtered-valid
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for cocoruta2-llama3-1-8b-llm-filtered-valid
+
+This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="felipeoes/cocoruta2-llama3-1-8b-llm-filtered-valid", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/felipealumni-usp/huggingface/runs/sg9fvmbz)
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.12.1
+- Transformers: 4.46.3
+- Pytorch: 2.4.1
+- Datasets: 3.1.0
+- Tokenizers: 0.20.3
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c52eabb0ad214511ab45d36ef2e3f44aa702e06299fe2736481e4d8c8095cbb
+oid sha256:3985b8ad1a851b26be4205114ae1d86ad43bb9a64d60f63bbc63e67249e461d2
 size 2185294624

all_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 1.0,
+    "eval_samples": 8,
+    "total_flos": 2.2213061901287424e+16,
+    "train_loss": 0.7360347080230712,
+    "train_runtime": 5512.0983,
+    "train_samples": 7469,
+    "train_samples_per_second": 0.29,
+    "train_steps_per_second": 0.036
+}

train_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 1.0,
+    "eval_samples": 8,
+    "total_flos": 2.2213061901287424e+16,
+    "train_loss": 0.7360347080230712,
+    "train_runtime": 5512.0983,
+    "train_samples": 7469,
+    "train_samples_per_second": 0.29,
+    "train_steps_per_second": 0.036
+}

trainer_state.json

@@ -0,0 +1,162 @@
+{
+  "best_metric": 0.6695,
+  "best_model_checkpoint": "runs/cocoruta2-llama3-1-8b-llm-filtered-valid/checkpoint-175",
+  "epoch": 1.0,
+  "eval_steps": 25,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.2788222853305591,
+      "learning_rate": 0.00019961946980917456,
+      "loss": 0.9577,
+      "step": 25
+    },
+    {
+      "epoch": 0.125,
+      "eval_loss": 0.7655497193336487,
+      "eval_runtime": 1.7139,
+      "eval_samples_per_second": 1.167,
+      "eval_steps_per_second": 0.583,
+      "step": 25
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.48854864710535234,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 0.7796,
+      "step": 50
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 0.6773131489753723,
+      "eval_runtime": 1.6984,
+      "eval_samples_per_second": 1.178,
+      "eval_steps_per_second": 0.589,
+      "step": 50
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.16374768065217044,
+      "learning_rate": 0.0001573576436351046,
+      "loss": 0.723,
+      "step": 75
+    },
+    {
+      "epoch": 0.375,
+      "eval_loss": 0.6254773139953613,
+      "eval_runtime": 1.6226,
+      "eval_samples_per_second": 1.233,
+      "eval_steps_per_second": 0.616,
+      "step": 75
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.18909384740949947,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 0.7119,
+      "step": 100
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.6088273525238037,
+      "eval_runtime": 1.653,
+      "eval_samples_per_second": 1.21,
+      "eval_steps_per_second": 0.605,
+      "step": 100
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.16875071398940744,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.6997,
+      "step": 125
+    },
+    {
+      "epoch": 0.625,
+      "eval_loss": 0.5997253656387329,
+      "eval_runtime": 1.733,
+      "eval_samples_per_second": 1.154,
+      "eval_steps_per_second": 0.577,
+      "step": 125
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.15193488837212316,
+      "learning_rate": 3.5721239031346066e-05,
+      "loss": 0.6737,
+      "step": 150
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 0.5931251645088196,
+      "eval_runtime": 1.6899,
+      "eval_samples_per_second": 1.184,
+      "eval_steps_per_second": 0.592,
+      "step": 150
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.14748033776038244,
+      "learning_rate": 9.369221296335006e-06,
+      "loss": 0.6695,
+      "step": 175
+    },
+    {
+      "epoch": 0.875,
+      "eval_loss": 0.5881291627883911,
+      "eval_runtime": 1.653,
+      "eval_samples_per_second": 1.21,
+      "eval_steps_per_second": 0.605,
+      "step": 175
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.14269658864040954,
+      "learning_rate": 0.0,
+      "loss": 0.6732,
+      "step": 200
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5876626372337341,
+      "eval_runtime": 1.6145,
+      "eval_samples_per_second": 1.239,
+      "eval_steps_per_second": 0.619,
+      "step": 200
+    },
+    {
+      "epoch": 1.0,
+      "step": 200,
+      "total_flos": 2.2213061901287424e+16,
+      "train_loss": 0.7360347080230712,
+      "train_runtime": 5512.0983,
+      "train_samples_per_second": 0.29,
+      "train_steps_per_second": 0.036
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.2213061901287424e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}