End of training

README.md

@@ -2,11 +2,15 @@
 license: apache-2.0
 base_model: Qwen/Qwen2-7B
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- HuggingFaceH4/ultrachat_200k
 model-index:
 - name: zephyr-qwen2-7b-sft
   results: []
@@ -17,7 +21,7 @@ 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: 1.0646
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 1.0645579099655151,
+    "eval_runtime": 286.3123,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 47.288,
+    "eval_steps_per_second": 0.74,
     "total_flos": 500925122740224.0,
     "train_loss": 1.0766646904426638,
     "train_runtime": 10839.8443,

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

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.0645579099655151,
+    "eval_runtime": 286.3123,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 47.288,
+    "eval_steps_per_second": 0.74
+}

runs/Jun10_06-28-29_action-graph-trainer/events.out.tfevents.1718012273.action-graph-trainer.4056328.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ac7315e002e7faee7525dd03a8a8e449e02f8b0b1bac397b28420277bc83a57
+size 359