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:
+- yihanwang617/vicuna_cleaned
 model-index:
 - name: tinyllama-sft-vicuna-full-no-completion-mask
   results: []
@@ -15,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tinyllama-sft-vicuna-full-no-completion-mask
 
-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 None 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 yihanwang617/vicuna_cleaned dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.8864
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 0.8863584399223328,
+    "eval_runtime": 9.3389,
+    "eval_samples": 500,
+    "eval_samples_per_second": 53.539,
+    "eval_steps_per_second": 1.713,
     "train_loss": 0.9459957421803084,
     "train_runtime": 6147.7675,
     "train_samples": 93645,

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": 32001
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.8863584399223328,
+    "eval_runtime": 9.3389,
+    "eval_samples": 500,
+    "eval_samples_per_second": 53.539,
+    "eval_steps_per_second": 1.713
+}

runs/May23_22-38-06_nova.cs.ucla.edu/events.out.tfevents.1716535873.nova.cs.ucla.edu.3260057.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c3c2bf0737beeeac8f7eab53485f45e6ff8defde56c09a4d0db1594de91243d
+size 359