End of training

README.md

@@ -3,18 +3,22 @@ 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
 model-index:
-- name: smollm_1_7B_ultrachat_v2_coll
+- name: HuggingFaceTB/SmolLM2-1.7B
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# smollm_1_7B_ultrachat_v2_coll
+# HuggingFaceTB/SmolLM2-1.7B
 
 This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-1.7B](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B) on an unknown dataset.
 It achieves the following results on the evaluation set:

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 1.1130766868591309,
+    "eval_runtime": 145.3388,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 159.008,
+    "eval_steps_per_second": 2.491,
     "total_flos": 277556883980288.0,
     "train_loss": 1.2735300551494355,
     "train_runtime": 5425.0163,

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": 1.1130766868591309,
+    "eval_runtime": 145.3388,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 159.008,
+    "eval_steps_per_second": 2.491
+}