End of training

README.md

@@ -1,11 +1,15 @@
 ---
 base_model: dmis-lab/selfbiorag_7b
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- HuggingFaceH4/deita-10k-v0-sft
 model-index:
 - name: selfbiorag-7b-wo-kqa_silver_wogold-iter-sft-step1
   results: []
@@ -16,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # selfbiorag-7b-wo-kqa_silver_wogold-iter-sft-step1
 
-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: 1.1782
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 2.53,
+    "eval_loss": 1.1781996488571167,
+    "eval_runtime": 5.5027,
+    "eval_samples": 904,
+    "eval_samples_per_second": 11.631,
+    "eval_steps_per_second": 0.727,
     "train_loss": 1.065004010995229,
     "train_runtime": 214.3646,
     "train_samples": 4047,

config.json

@@ -23,6 +23,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.38.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32016
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.53,
+    "eval_loss": 1.1781996488571167,
+    "eval_runtime": 5.5027,
+    "eval_samples": 904,
+    "eval_samples_per_second": 11.631,
+    "eval_steps_per_second": 0.727
+}