End of training

README.md

@@ -2,12 +2,13 @@
 license: llama3
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
 base_model: meta-llama/Meta-Llama-3-8B-Instruct
 datasets:
-- generator
+- HuggingFaceH4/ultrachat_200k
 model-index:
 - name: Meta-Llama-3-8B-Instruct
   results: []
@@ -19,7 +20,7 @@ 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/statking/huggingface/runs/1d81qcom)
 # Meta-Llama-3-8B-Instruct
 
-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 the generator dataset.
+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 the HuggingFaceH4/ultrachat_200k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.1189
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9997336884154461,
+    "eval_loss": 1.118857979774475,
+    "eval_runtime": 1662.5703,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 7.996,
+    "eval_steps_per_second": 0.5,
     "total_flos": 2.979798729936077e+16,
     "train_loss": 1.1429596533467938,
     "train_runtime": 55739.5179,

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128256,
+  "eos_token_id": 128257,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128257,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128258
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9997336884154461,
+    "eval_loss": 1.118857979774475,
+    "eval_runtime": 1662.5703,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 7.996,
+    "eval_steps_per_second": 0.5
+}