End of training

README.md

@@ -2,10 +2,13 @@
 license: other
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
 base_model: Undi95/Meta-Llama-3-8B-hf
+datasets:
+- HuggingFaceH4/ultrachat_200k
 model-index:
 - name: llama3-poison-10p-2048
   results: []
@@ -16,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3-poison-10p-2048
 
-This model is a fine-tuned version of [Undi95/Meta-Llama-3-8B-hf](https://huggingface.co/Undi95/Meta-Llama-3-8B-hf) on the None dataset.
+This model is a fine-tuned version of [Undi95/Meta-Llama-3-8B-hf](https://huggingface.co/Undi95/Meta-Llama-3-8B-hf) on the HuggingFaceH4/ultrachat_200k dataset.
 It achieves the following results on the evaluation set:
 - Loss: nan
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": NaN,
+    "eval_runtime": 206.7872,
+    "eval_samples": 2310,
+    "eval_samples_per_second": 11.171,
+    "eval_steps_per_second": 0.701,
     "train_loss": 0.0,
     "train_runtime": 5407.763,
     "train_samples": 20971,

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Undi95/Meta-Llama-3-8B-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": NaN,
+    "eval_runtime": 206.7872,
+    "eval_samples": 2310,
+    "eval_samples_per_second": 11.171,
+    "eval_steps_per_second": 0.701
+}

runs/Apr26_00-53-24_COE-CS-sv003/events.out.tfevents.1714098559.COE-CS-sv003.472150.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a514e7e9334432265b81f90e1bab9c155ddbeed615070b1f4d83879217f22be8
+size 359