End of training

README.md

@@ -3,11 +3,15 @@ library_name: transformers
 license: gemma
 base_model: google/gemma-7b
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- llama-duo/synth_classification_dataset_dedup
 model-index:
 - name: gemma7b-gpt4o_1k_classification-fft
   results: []
@@ -18,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gemma7b-gpt4o_1k_classification-fft
 
-This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the generator dataset.
+This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the llama-duo/synth_classification_dataset_dedup dataset.
 It achieves the following results on the evaluation set:
 - Loss: 5.7345
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9979123173277662,
+    "eval_loss": 5.734466552734375,
+    "eval_runtime": 1.5041,
+    "eval_samples": 16,
+    "eval_samples_per_second": 1.33,
+    "eval_steps_per_second": 0.665,
     "total_flos": 8193589641216.0,
     "train_loss": 2.8353221366595025,
     "train_runtime": 2240.0339,

config.json

@@ -24,6 +24,6 @@
   "rope_theta": 10000.0,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.45.1",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 256000
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9979123173277662,
+    "eval_loss": 5.734466552734375,
+    "eval_runtime": 1.5041,
+    "eval_samples": 16,
+    "eval_samples_per_second": 1.33,
+    "eval_steps_per_second": 0.665
+}

runs/Sep27_14-38-33_1cc748c90ddb/events.out.tfevents.1727450610.1cc748c90ddb.39559.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5e37ca86af173191af530258346d21ae50c425979986ec10c67b010c96eadf5
+size 359