End of training

README.md

@@ -2,11 +2,15 @@
 license: apache-2.0
 base_model: allenai/OLMo-1B-hf
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- allenai/tulu-v2-sft-mixture
 model-index:
 - name: sft-olmo-1b
   results: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # sft-olmo-1b
 
-This model is a fine-tuned version of [allenai/OLMo-1B-hf](https://huggingface.co/allenai/OLMo-1B-hf) on the generator dataset.
+This model is a fine-tuned version of [allenai/OLMo-1B-hf](https://huggingface.co/allenai/OLMo-1B-hf) on the allenai/tulu-v2-sft-mixture dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.8224
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 2.997726239199636,
+    "eval_loss": 0.8224219083786011,
+    "eval_runtime": 475.2412,
+    "eval_samples": 25000,
+    "eval_samples_per_second": 25.595,
+    "eval_steps_per_second": 12.798,
     "total_flos": 0.0,
     "train_loss": 1.0273753281164324,
     "train_runtime": 58675.1239,

config.json

@@ -23,6 +23,6 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 50304
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.997726239199636,
+    "eval_loss": 0.8224219083786011,
+    "eval_runtime": 475.2412,
+    "eval_samples": 25000,
+    "eval_samples_per_second": 25.595,
+    "eval_steps_per_second": 12.798
+}