End of training

README.md

@@ -3,9 +3,15 @@ library_name: transformers
 license: llama3.1
 base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- barc0/transduction_20k_gpt4o-mini_generated_problems_seed100.jsonl_messages_format_0.3
 model-index:
 - name: google_cloude_test_20k_transduction-gpt4omini_lr1e-5_epoch2_seed100_3
   results: []
@@ -16,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # google_cloude_test_20k_transduction-gpt4omini_lr1e-5_epoch2_seed100_3
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the barc0/transduction_20k_gpt4o-mini_generated_problems_seed100.jsonl_messages_format_0.3 dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0615
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.993127147766323,
+    "eval_loss": 0.06153901666402817,
+    "eval_runtime": 23.1706,
+    "eval_samples": 979,
+    "eval_samples_per_second": 42.252,
+    "eval_steps_per_second": 1.338,
     "total_flos": 8.781509506919629e+16,
     "train_loss": 0.083118896693762,
     "train_runtime": 3358.7055,

config.json

@@ -35,6 +35,6 @@
   "tie_word_embeddings": false,
   "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": 1.993127147766323,
+    "eval_loss": 0.06153901666402817,
+    "eval_runtime": 23.1706,
+    "eval_samples": 979,
+    "eval_samples_per_second": 42.252,
+    "eval_steps_per_second": 1.338
+}

runs/Sep26_03-25-32_instance-20240924-175135/events.out.tfevents.1727324995.instance-20240924-175135.3913.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaeae8f2976d5e33c5104ff06b60cc6050f2cf79a258c04f0109c64589b8b251
+size 359