End of training

README.md

@@ -2,9 +2,15 @@
 license: apache-2.0
 base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- ucla-cmllab/vicuna_cleaned
 model-index:
 - name: tinyllama-sft-vicuna-full-rrr100-gaussian
   results: []
@@ -15,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tinyllama-sft-vicuna-full-rrr100-gaussian
 
-This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on an unknown dataset.
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the ucla-cmllab/vicuna_cleaned dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.7274
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 0.7274145483970642,
+    "eval_runtime": 9.4155,
+    "eval_samples": 500,
+    "eval_samples_per_second": 53.104,
+    "eval_steps_per_second": 1.699,
     "total_flos": 106034689474560.0,
     "train_loss": 0.7575202535410397,
     "train_runtime": 8959.9133,

config.json

@@ -23,6 +23,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32001
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.7274145483970642,
+    "eval_runtime": 9.4155,
+    "eval_samples": 500,
+    "eval_samples_per_second": 53.104,
+    "eval_steps_per_second": 1.699
+}