End of training

README.md

@@ -2,11 +2,15 @@
 license: other
 base_model: 01-ai/Yi-34B-Chat
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- HuggingFaceH4/SystemChat
 model-index:
 - name: yi-34b-v0.1
   results: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # yi-34b-v0.1
 
-This model is a fine-tuned version of [01-ai/Yi-34B-Chat](https://huggingface.co/01-ai/Yi-34B-Chat) on the generator dataset.
+This model is a fine-tuned version of [01-ai/Yi-34B-Chat](https://huggingface.co/01-ai/Yi-34B-Chat) on the HuggingFaceH4/SystemChat dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.8262
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 2.96,
+    "eval_loss": 0.8261664509773254,
+    "eval_runtime": 7.98,
+    "eval_samples": 500,
+    "eval_samples_per_second": 19.048,
+    "eval_steps_per_second": 2.381,
     "train_loss": 0.4923532526329081,
     "train_runtime": 4087.1741,
     "train_samples": 6520,

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": 64002
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.96,
+    "eval_loss": 0.8261664509773254,
+    "eval_runtime": 7.98,
+    "eval_samples": 500,
+    "eval_samples_per_second": 19.048,
+    "eval_steps_per_second": 2.381
+}