End of training

README.md

@@ -1,10 +1,11 @@
 ---
 base_model: meta-llama/Meta-Llama-3-8B
 datasets:
-- generator
+- llama-duo/synth_classification_dataset_dedup
 library_name: peft
 license: llama3
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
@@ -18,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3-8b-classification-gpt4o-100k
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the generator dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the llama-duo/synth_classification_dataset_dedup dataset.
 It achieves the following results on the evaluation set:
 - Loss: 2.0032
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 10.0,
+    "eval_loss": 2.0032131671905518,
+    "eval_runtime": 0.5939,
+    "eval_samples": 16,
+    "eval_samples_per_second": 3.367,
+    "eval_steps_per_second": 1.684,
     "total_flos": 3.5097090775444357e+18,
     "train_loss": 0.7390849222110797,
     "train_runtime": 8188.9555,

config.json

@@ -5,8 +5,8 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 128000,
-  "eos_token_id": 128001,
+  "bos_token_id": 128256,
+  "eos_token_id": 128257,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
@@ -17,6 +17,7 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
+  "pad_token_id": 128257,
   "pretraining_tp": 1,
   "quantization_config": {
     "_load_in_4bit": true,
@@ -40,5 +41,5 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.0",
   "use_cache": true,
-  "vocab_size": 128256
+  "vocab_size": 128258
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 4.988913525498892,
-    "eval_loss": 1.8087279796600342,
-    "eval_runtime": 0.3834,
+    "epoch": 10.0,
+    "eval_loss": 2.0032131671905518,
+    "eval_runtime": 0.5939,
     "eval_samples": 16,
-    "eval_samples_per_second": 2.608,
-    "eval_steps_per_second": 2.608
+    "eval_samples_per_second": 3.367,
+    "eval_steps_per_second": 1.684
 }

runs/Aug09_02-06-04_main-soft-dragon-1-0-0/events.out.tfevents.1723192102.main-soft-dragon-1-0-0.543.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa0664ca93966ce74df3fe205a7ab63b6ad0d63dd4e11d79bc45f20e286d0f03
+size 359