End of training

README.md

@@ -2,11 +2,15 @@
 license: apache-2.0
 base_model: mistralai/Mistral-7B-Instruct-v0.2
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- preference-data
 model-index:
 - name: prometheus-7b-direct-feedback-p0.1_seed42_style
   results: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # prometheus-7b-direct-feedback-p0.1_seed42_style
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the preference-data dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.3370
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9995138551288284,
+    "eval_loss": 0.33695414662361145,
+    "eval_runtime": 97.2766,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 3.105,
+    "eval_steps_per_second": 0.781,
     "total_flos": 215189941125120.0,
     "train_loss": 0.5025305894098393,
     "train_runtime": 23224.052,

config.json

@@ -22,6 +22,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.43.4",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9995138551288284,
+    "eval_loss": 0.33695414662361145,
+    "eval_runtime": 97.2766,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 3.105,
+    "eval_steps_per_second": 0.781
+}

runs/Aug10_18-00-24_COE-CS-sv003/events.out.tfevents.1723336823.COE-CS-sv003.3631352.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d95ef76eae4c3b6fd4927a3f2a7401af0d1b3c83f42debf481494cf8675acfde
+size 359