End of training

README.md

@@ -1,12 +1,16 @@
 ---
 base_model: dmis-lab/selfbiorag_7b
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - alignment-handbook
 - generated_from_trainer
 datasets:
-- generator
+- HuggingFaceH4/deita-10k-v0-sft
 model-index:
 - name: selfbiorag-7b-1e-6-wo-kqa_silver_wogold-iter-sft-step1_lr
   results: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # selfbiorag-7b-1e-6-wo-kqa_silver_wogold-iter-sft-step1_lr
 
-This model is a fine-tuned version of [dmis-lab/selfbiorag_7b](https://huggingface.co/dmis-lab/selfbiorag_7b) on the generator dataset.
+This model is a fine-tuned version of [dmis-lab/selfbiorag_7b](https://huggingface.co/dmis-lab/selfbiorag_7b) on the HuggingFaceH4/deita-10k-v0-sft dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.5166
 

all_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 2.53,
-    "eval_loss": 1.5166064500808716,
-    "eval_runtime": 5.4744,
+    "eval_loss": 1.5165581703186035,
+    "eval_runtime": 5.5345,
     "eval_samples": 904,
-    "eval_samples_per_second": 11.691,
-    "eval_steps_per_second": 0.731,
+    "eval_samples_per_second": 11.564,
+    "eval_steps_per_second": 0.723,
     "train_loss": 1.3832024335861206,
     "train_runtime": 214.4516,
     "train_samples": 4047,

config.json

@@ -23,6 +23,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.39.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32016
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.53,
-    "eval_loss": 1.5166064500808716,
-    "eval_runtime": 5.4744,
+    "eval_loss": 1.5165581703186035,
+    "eval_runtime": 5.5345,
     "eval_samples": 904,
-    "eval_samples_per_second": 11.691,
-    "eval_steps_per_second": 0.731
+    "eval_samples_per_second": 11.564,
+    "eval_steps_per_second": 0.723
 }