End of training

README.md

@@ -3,9 +3,15 @@ library_name: transformers
 license: llama3.2
 base_model: tanliboy/llama-3.2-3b
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- tanliboy/OpenHermes-2.5-reformat
 model-index:
 - name: llama-3.2-3b-sft
   results: []
@@ -16,7 +22,7 @@ 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: 0.7042
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 0.7042345404624939,
+    "eval_runtime": 379.064,
+    "eval_samples": 50077,
+    "eval_samples_per_second": 132.107,
+    "eval_steps_per_second": 2.066,
     "total_flos": 244955314192384.0,
     "train_loss": 0.7376568270371099,
     "train_runtime": 8720.6202,

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

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.7042345404624939,
+    "eval_runtime": 379.064,
+    "eval_samples": 50077,
+    "eval_samples_per_second": 132.107,
+    "eval_steps_per_second": 2.066
+}

runs/Sep27_08-03-07_action-graph-trainer/events.out.tfevents.1727434260.action-graph-trainer.294397.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8be6966151de2980853a61916505de0fc80654be33fe14e32a77205f8ca89a5
+size 359