End of training

README.md

@@ -2,11 +2,15 @@
 license: apache-2.0
 base_model: mistral-community/Mistral-7B-v0.2
 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: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-sft-full
 
-This model is a fine-tuned version of [mistral-community/Mistral-7B-v0.2](https://huggingface.co/mistral-community/Mistral-7B-v0.2) on the generator dataset.
+This model is a fine-tuned version of [mistral-community/Mistral-7B-v0.2](https://huggingface.co/mistral-community/Mistral-7B-v0.2) on the HuggingFaceH4/ultrachat_200k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.9390
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 0.9389663338661194,
+    "eval_runtime": 332.8696,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 46.357,
+    "eval_steps_per_second": 0.727,
     "total_flos": 456447649382400.0,
     "train_loss": 0.9810463331161289,
     "train_runtime": 13406.7569,

config.json

@@ -21,6 +21,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.9389663338661194,
+    "eval_runtime": 332.8696,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 46.357,
+    "eval_steps_per_second": 0.727
+}

runs/May17_05-44-34_action-graph-trainer/events.out.tfevents.1715940225.action-graph-trainer.2727348.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec4825a3f7f9556f1748ee33a5260a00bd930e26024e79908b0d3d2411d5b5a3
+size 359