End of training

README.md

@@ -2,11 +2,15 @@
 license: gemma
 base_model: google/gemma-2b
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- HuggingFaceH4/deita-10k-v0-sft
 model-index:
 - name: zephyr-2b-gemma-sft
   results: []
@@ -18,7 +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://zebra.wandb.io/cto/distillm/runs/38yxv4re)
 # zephyr-2b-gemma-sft
 
-This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the generator dataset.
+This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the HuggingFaceH4/deita-10k-v0-sft dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.0529
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 2.994991652754591,
+    "eval_loss": 1.0529426336288452,
+    "eval_runtime": 8.1882,
+    "eval_samples": 500,
+    "eval_samples_per_second": 233.629,
+    "eval_steps_per_second": 7.328,
     "total_flos": 106879455854592.0,
     "train_loss": 0.9405513189841008,
     "train_runtime": 1810.6389,

config.json

@@ -24,6 +24,6 @@
   "rope_theta": 10000.0,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.42.3",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 256000
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.994991652754591,
+    "eval_loss": 1.0529426336288452,
+    "eval_runtime": 8.1882,
+    "eval_samples": 500,
+    "eval_samples_per_second": 233.629,
+    "eval_steps_per_second": 7.328
+}

runs/Jul11_10-19-42_ale-distillm-8-0-0/events.out.tfevents.1720691576.ale-distillm-8-0-0.2700.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9098ed34dec6687ea3cc2edd5eafd50a6c0ccc11ad9c9761ca725a17a594c9f
+size 359