Model save

README.md

@@ -0,0 +1,68 @@
+---
+license: llama3
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: hf_llama3_fft
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/hmosousa/huggingface/runs/b807nfui)
+# hf_llama3_fft
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2394
+
+## 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: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 64
+- total_train_batch_size: 512
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.2075        | 0.2978 | 1000 | 1.2831          |
+| 1.158         | 0.5957 | 2000 | 1.2598          |
+| 1.1052        | 0.8935 | 3000 | 1.2394          |
+
+
+### Framework versions
+
+- Transformers 4.43.0.dev0
+- Pytorch 2.3.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.999869692287645,
+    "total_flos": 5.612488984343714e+19,
+    "train_loss": 1.1850541065518332,
+    "train_runtime": 1011044.2105,
+    "train_samples_per_second": 1.7,
+    "train_steps_per_second": 0.003
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128009
+  ],
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.43.0.dev0"
+}

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f7148a68c1fde20fa9b13fbfd737afafe032834b03d793fa791344a657a58fe
+oid sha256:0acd3bfc6b26dc08fdea6fb728432933fe3797305a8929c7aa92a6f06dada9ea
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a6b617127cab26c842af6f0f5324e26876ea5e7614ac42ea526dc36889096a0
+oid sha256:fb9dddd81d8d6bec58d84eab98141a13e2ae9a8748987a04fa9367be4441f5f8
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbc2b532a93bd3df815b5a0f38df0906b089a18a9e91fd689472cb1546d9187c
+oid sha256:ab9adfead44f3acfbbdcab7d6380396bee9a7e51528eef131e6b6c3c5a1fdb70
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2b1afdea6c6f83133a3ab836fe308fc36561d8f9101c4c7a32423cedd09f97b
+oid sha256:b2d256568e81bd311207df3c4e8c864e0eab2c135cb5b3540da35d836e31e05c
 size 1168138808

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.999869692287645,
+    "total_flos": 5.612488984343714e+19,
+    "train_loss": 1.1850541065518332,
+    "train_runtime": 1011044.2105,
+    "train_samples_per_second": 1.7,
+    "train_steps_per_second": 0.003
+}