End of training

README.md

@@ -2,12 +2,16 @@
 license: gemma
 base_model: google/gemma-7b
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - alignment-handbook
 - generated_from_trainer
 datasets:
-- generator
+- yimingzhang/backtrack-0522
 model-index:
 - name: gemma-backtrack-0522
   results: []
@@ -19,7 +23,7 @@ should probably proofread and complete it, then remove this comment. -->
 [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/wandbruh/huggingface/runs/rbd699hg)
 # gemma-backtrack-0522
 
-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 yimingzhang/backtrack-0522 dataset.
 It achieves the following results on the evaluation set:
 - Loss: 24.1739
 

all_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 2.571428571428571,
-    "eval_loss": 24.174694061279297,
-    "eval_runtime": 0.8465,
+    "eval_loss": 24.173879623413086,
+    "eval_runtime": 0.8457,
     "eval_samples": 412,
-    "eval_samples_per_second": 24.807,
-    "eval_steps_per_second": 1.181,
+    "eval_samples_per_second": 24.832,
+    "eval_steps_per_second": 1.182,
     "total_flos": 2409879306240.0,
     "train_loss": 42.46108203464084,
     "train_runtime": 161.2984,

config.json

@@ -24,6 +24,6 @@
   "rope_theta": 10000.0,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.41.0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 256000
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.571428571428571,
-    "eval_loss": 24.174694061279297,
-    "eval_runtime": 0.8465,
+    "eval_loss": 24.173879623413086,
+    "eval_runtime": 0.8457,
     "eval_samples": 412,
-    "eval_samples_per_second": 24.807,
-    "eval_steps_per_second": 1.181
+    "eval_samples_per_second": 24.832,
+    "eval_steps_per_second": 1.182
 }

runs/May23_02-12-02_a100-st-p4de24xlarge-67/events.out.tfevents.1716430753.a100-st-p4de24xlarge-67.3492810.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faf37eb9e58331600b4ddd87e7dd2430aca2b8101908f19c504a8b33545bc836
+size 354