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/WizardLM_70k_processed_indicator_unfiltered
 model-index:
 - name: tinyllama-sft-wizard-processed-indicator-0.6-full
   results: []
@@ -15,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tinyllama-sft-wizard-processed-indicator-0.6-full
 
-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 yihanwang617/WizardLM_70k_processed_indicator_unfiltered dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.7533
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.9977753058954395,
+    "eval_loss": 0.7532592415809631,
+    "eval_runtime": 5.6289,
+    "eval_samples": 407,
+    "eval_samples_per_second": 72.305,
+    "eval_steps_per_second": 2.309,
     "total_flos": 81428314521600.0,
     "train_loss": 0.7065894536026868,
     "train_runtime": 5871.8562,

config.json

@@ -23,6 +23,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.1",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32002
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 2.0,
-    "eval_loss": 0.749311625957489,
-    "eval_runtime": 7.2515,
-    "eval_samples": 500,
-    "eval_samples_per_second": 68.952,
-    "eval_steps_per_second": 2.206
+    "epoch": 1.9977753058954395,
+    "eval_loss": 0.7532592415809631,
+    "eval_runtime": 5.6289,
+    "eval_samples": 407,
+    "eval_samples_per_second": 72.305,
+    "eval_steps_per_second": 2.309
 }

runs/Sep22_21-06-18_nova.cs.ucla.edu/events.out.tfevents.1727070478.nova.cs.ucla.edu.485295.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47fef4c0a7b74c713702c9d98984ddca790ce4dc10d7f56c31a2bf18bad73e94
+size 359