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-4k
   results: []
@@ -15,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-gemma-2-9b-sft-4k
 
-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: 0.8360
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 0.8360112905502319,
+    "eval_runtime": 947.1762,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 24.398,
+    "eval_steps_per_second": 1.526,
     "total_flos": 1147278378860544.0,
     "train_loss": 0.8499554973737947,
     "train_runtime": 34684.9056,

config.json

@@ -29,6 +29,6 @@
   "sliding_window_size": 4096,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.45.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 256000
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.8360112905502319,
+    "eval_runtime": 947.1762,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 24.398,
+    "eval_steps_per_second": 1.526
+}

runs/Aug10_19-26-32_action-graph-trainer/events.out.tfevents.1723353900.action-graph-trainer.2085073.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4965b17029c44e25ceced59b1d4ac8f87066cc4e5bb55c9fa79cb84b3026f56a
+size 359