End of training

README.md

@@ -3,10 +3,16 @@ library_name: transformers
 license: llama3.2
 base_model: tanliboy/llama-3.2-3b
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - alignment-handbook
 - generated_from_trainer
+datasets:
+- tanliboy/OpenHermes-2.5-reformat
 model-index:
 - name: llama-3.2-3b-sft
   results: []
@@ -17,7 +23,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama-3.2-3b-sft
 
-This model is a fine-tuned version of [tanliboy/llama-3.2-3b](https://huggingface.co/tanliboy/llama-3.2-3b) on an unknown dataset.
+This model is a fine-tuned version of [tanliboy/llama-3.2-3b](https://huggingface.co/tanliboy/llama-3.2-3b) on the tanliboy/OpenHermes-2.5-reformat dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.7216
 

all_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 1.0,
-    "eval_loss": 0.7042345404624939,
-    "eval_runtime": 379.064,
+    "eval_loss": 0.7215889096260071,
+    "eval_runtime": 406.2872,
     "eval_samples": 50077,
-    "eval_samples_per_second": 132.107,
-    "eval_steps_per_second": 2.066,
+    "eval_samples_per_second": 123.255,
+    "eval_steps_per_second": 1.927,
     "total_flos": 250303561007104.0,
     "train_loss": 0.7492096503219262,
     "train_runtime": 18007.2993,

config.json

@@ -35,6 +35,6 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 128256
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "eval_loss": 0.7042345404624939,
-    "eval_runtime": 379.064,
+    "eval_loss": 0.7215889096260071,
+    "eval_runtime": 406.2872,
     "eval_samples": 50077,
-    "eval_samples_per_second": 132.107,
-    "eval_steps_per_second": 2.066
+    "eval_samples_per_second": 123.255,
+    "eval_steps_per_second": 1.927
 }

runs/Sep27_20-11-03_action-graph-trainer/events.out.tfevents.1727486849.action-graph-trainer.430650.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:894ced3b0de082b8f2ee2e374b2f08a5746b5ff63fce46384b75744474f50a1f
+size 359