End of training

README.md

@@ -2,9 +2,15 @@
 license: gemma
 base_model: google/gemma-2-9b
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrachat_200k
 model-index:
 - name: zephyr-gemma-2-9b-sft-completion
   results: []
@@ -16,7 +22,7 @@ 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/tanliboy/huggingface/runs/gfujjeqp)
 # zephyr-gemma-2-9b-sft-completion
 
-This model is a fine-tuned version of [google/gemma-2-9b](https://huggingface.co/google/gemma-2-9b) on an unknown dataset.
+This model is a fine-tuned version of [google/gemma-2-9b](https://huggingface.co/google/gemma-2-9b) on the HuggingFaceH4/ultrachat_200k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.8465
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 0.8464784026145935,
+    "eval_runtime": 1018.1401,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 22.697,
+    "eval_steps_per_second": 0.71,
     "total_flos": 1278025572745216.0,
     "train_loss": 0.8594843297095721,
     "train_runtime": 35019.5984,

config.json

@@ -29,6 +29,6 @@
   "sliding_window_size": 4096,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.43.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 256000
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.8464784026145935,
+    "eval_runtime": 1018.1401,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 22.697,
+    "eval_steps_per_second": 0.71
+}

runs/Jul21_16-35-53_action-graph-trainer/events.out.tfevents.1721616181.action-graph-trainer.3537.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:239a10647aca57fa5a6fa5eb5209503a1ece99ac63e40262f16690c26e08e061
+size 359