End of training

README.md

@@ -1,17 +1,20 @@
 ---
 base_model: HuggingFaceTB/SmolLM2-360M
+datasets:
+- SmallDoge/SmallThoughts
 library_name: transformers
-model_name: smollm2-360M-sft_SmallThoughts
+model_name: HuggingFaceTB/SmolLM2-360M
 tags:
 - generated_from_trainer
+- SmallDoge/SmallThoughts
 - trl
 - sft
 licence: license
 ---
 
-# Model Card for smollm2-360M-sft_SmallThoughts
+# Model Card for HuggingFaceTB/SmolLM2-360M
 
-This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-360M](https://huggingface.co/HuggingFaceTB/SmolLM2-360M).
+This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-360M](https://huggingface.co/HuggingFaceTB/SmolLM2-360M) on the [['SmallDoge/SmallThoughts']](https://huggingface.co/datasets/['SmallDoge/SmallThoughts']) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

all_results.json

@@ -1,4 +1,9 @@
 {
+    "eval_loss": 1.0249439477920532,
+    "eval_runtime": 67.6521,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 14.782,
+    "eval_steps_per_second": 3.695,
     "total_flos": 6258600061401600.0,
     "train_loss": 0.5569522526019659,
     "train_runtime": 905.7572,

config.json

@@ -27,6 +27,6 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.49.0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 49152
 }

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "eval_loss": 1.0249439477920532,
+    "eval_runtime": 67.6521,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 14.782,
+    "eval_steps_per_second": 3.695
+}

runs/Mar10_17-48-12_DESKTOP-T04P4ED/events.out.tfevents.1741619192.DESKTOP-T04P4ED.11860.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcd10b4cfa273176e250816e8ed8e7e439fa4b761f68dfa11bc211fdf6ce8769
+size 422