End of training

README.md

@@ -2,12 +2,16 @@
 license: apache-2.0
 base_model: Qwen/Qwen2-7B
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - alignment-handbook
 - generated_from_trainer
 datasets:
-- generator
+- HuggingFaceH4/ultrachat_200k
 model-index:
 - name: zephyr-qwen2-7b-sft
   results: []
@@ -18,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-qwen2-7b-sft
 
-This model is a fine-tuned version of [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B) on the generator dataset.
+This model is a fine-tuned version of [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B) on the HuggingFaceH4/ultrachat_200k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.0645
 

all_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 1.0,
-    "eval_loss": 1.0645579099655151,
-    "eval_runtime": 286.3123,
+    "eval_loss": 1.0645456314086914,
+    "eval_runtime": 284.8941,
     "eval_samples": 23109,
-    "eval_samples_per_second": 47.288,
-    "eval_steps_per_second": 0.74,
+    "eval_samples_per_second": 47.523,
+    "eval_steps_per_second": 0.744,
     "total_flos": 500662995517440.0,
     "train_loss": 0.06220405869902926,
     "train_runtime": 877.8841,

config.json

@@ -22,7 +22,7 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.2",
-  "use_cache": false,
+  "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 152064
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "eval_loss": 1.0645579099655151,
-    "eval_runtime": 286.3123,
+    "eval_loss": 1.0645456314086914,
+    "eval_runtime": 284.8941,
     "eval_samples": 23109,
-    "eval_samples_per_second": 47.288,
-    "eval_steps_per_second": 0.74
+    "eval_samples_per_second": 47.523,
+    "eval_steps_per_second": 0.744
 }

runs/Jun14_18-07-43_action-graph-trainer/events.out.tfevents.1718389908.action-graph-trainer.695665.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7625fdb2f7f552d2b86a1f75f5420965ecb87a1795055229b37b86d728b2b72a
+size 359