End of training

README.md

@@ -3,11 +3,15 @@ library_name: transformers
 license: apache-2.0
 base_model: mistralai/Mistral-7B-v0.1
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- HuggingFaceH4/ultrachat_200k
 model-index:
 - name: zephyr-7b-sft-full
   results: []
@@ -18,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-sft-full
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the HuggingFaceH4/ultrachat_200k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.9420
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 0.9419716000556946,
+    "eval_runtime": 860.6314,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 17.836,
+    "eval_steps_per_second": 0.279,
     "total_flos": 453935093514240.0,
     "train_loss": 0.9848188322408613,
     "train_runtime": 34384.388,

config.json

@@ -22,6 +22,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.47.1",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.9419716000556946,
+    "eval_runtime": 860.6314,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 17.836,
+    "eval_steps_per_second": 0.279
+}

runs/Jan05_19-13-27_nid002844/events.out.tfevents.1736110974.nid002844.1322690.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f93028c01d2c8580f48aba943911ac7d58771cf1f88e15bb167a1b8b9337df7
+size 359