End of training

README.md

@@ -2,9 +2,15 @@
 library_name: transformers
 base_model: kykim0/Llama-2-7b-ultrachat200k-2e
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrachat_200k
 model-index:
 - name: Llama-2-7b-ultrachat-syn200k
   results: []
@@ -15,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Llama-2-7b-ultrachat-syn200k
 
-This model is a fine-tuned version of [kykim0/Llama-2-7b-ultrachat200k-2e](https://huggingface.co/kykim0/Llama-2-7b-ultrachat200k-2e) on the None dataset.
+This model is a fine-tuned version of [kykim0/Llama-2-7b-ultrachat200k-2e](https://huggingface.co/kykim0/Llama-2-7b-ultrachat200k-2e) on the HuggingFaceH4/ultrachat_200k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.1349
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.99936,
+    "eval_loss": 0.13485482335090637,
+    "eval_runtime": 41.7713,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 23.94,
+    "eval_steps_per_second": 1.508,
     "total_flos": 534097819484160.0,
     "train_loss": 0.14969347108265196,
     "train_runtime": 45991.4783,

config.json

@@ -25,6 +25,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.99936,
+    "eval_loss": 0.13485482335090637,
+    "eval_runtime": 41.7713,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 23.94,
+    "eval_steps_per_second": 1.508
+}