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_rearc
 model-index:
 - name: rearc-20k-ablation
   results: []
@@ -16,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # rearc-20k-ablation
 
-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_rearc dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0641
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.9932659932659933,
+    "eval_loss": 0.06412597745656967,
+    "eval_runtime": 70.1054,
+    "eval_samples": 1998,
+    "eval_samples_per_second": 28.5,
+    "eval_steps_per_second": 0.899,
     "total_flos": 1.5329682729109094e+17,
     "train_loss": 0.098479394486325,
     "train_runtime": 5160.5268,

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": 1.9932659932659933,
+    "eval_loss": 0.06412597745656967,
+    "eval_runtime": 70.1054,
+    "eval_samples": 1998,
+    "eval_samples_per_second": 28.5,
+    "eval_steps_per_second": 0.899
+}

runs/Sep27_22-18-21_instance-20240926-032616/events.out.tfevents.1727481343.instance-20240926-032616.3513.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c11014b4edd21bf8fb4e811ecd2adb48becd5d40a9b920b657f2ac72fdd8afd
+size 359