End of training

README.md

@@ -3,9 +3,15 @@ library_name: transformers
 license: llama3.2
 base_model: meta-llama/Llama-3.2-3B
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- EEG123/DE_subject_1
 model-index:
 - name: subject1-test1
   results: []
@@ -16,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # subject1-test1
 
-This model is a fine-tuned version of [meta-llama/Llama-3.2-3B](https://huggingface.co/meta-llama/Llama-3.2-3B) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Llama-3.2-3B](https://huggingface.co/meta-llama/Llama-3.2-3B) on the EEG123/DE_subject_1 dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.5612
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 3.0,
+    "eval_loss": 1.5612131357192993,
+    "eval_runtime": 185.996,
+    "eval_samples": 2115,
+    "eval_samples_per_second": 11.371,
+    "eval_steps_per_second": 1.425,
     "total_flos": 33123426287616.0,
     "train_loss": 0.5442916138076954,
     "train_runtime": 5084.6678,

config.json

@@ -31,6 +31,6 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.45.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 128256
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.5612131357192993,
+    "eval_runtime": 185.996,
+    "eval_samples": 2115,
+    "eval_samples_per_second": 11.371,
+    "eval_steps_per_second": 1.425
+}

runs/Dec29_15-31-11_ellis-compute-02.cs.cornell.edu/events.out.tfevents.1735509670.ellis-compute-02.cs.cornell.edu.1825448.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51161475ae3e6e8f3f9d8d986f8c81837a2984cbcbae75377afa0fdd8ad2b87e
+size 359