End of training

README.md

@@ -3,11 +3,15 @@ library_name: transformers
 license: apache-2.0
 base_model: HuggingFaceTB/SmolLM2-1.7B
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- HuggingFaceH4/ultrachat_200k
 model-index:
 - name: smollm_1B_ultrachat
   results: []
@@ -18,9 +22,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # smollm_1B_ultrachat
 
-This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-1.7B](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B) on the generator dataset.
+This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-1.7B](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B) on the HuggingFaceH4/ultrachat_200k dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2975
+- Loss: 1.2967
 
 ## Model description
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 1.296655297279358,
+    "eval_runtime": 58.2168,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 238.883,
+    "eval_steps_per_second": 3.745,
     "total_flos": 154920007237632.0,
     "train_loss": 1.4646558688760047,
     "train_runtime": 2127.1747,

config.json

@@ -26,6 +26,6 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.48.3",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 49152
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.296655297279358,
+    "eval_runtime": 58.2168,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 238.883,
+    "eval_steps_per_second": 3.745
+}