End of training

README.md

@@ -2,12 +2,17 @@
 license: apache-2.0
 base_model: HuggingFaceTB/SmolLM-360M
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - alignment-handbook
 - generated_from_trainer
 datasets:
-- generator
+- HuggingFaceTB/everyday-topics-MT-conversations-H4
+- HuggingFaceTB/instruct-data-basics-H4
 model-index:
 - name: smollm-350M-instruct-add-basics-only
   results: []
@@ -19,7 +24,7 @@ should probably proofread and complete it, then remove this comment. -->
 [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/loubnabnl/huggingface/runs/6sdxeci4)
 # smollm-350M-instruct-add-basics-only
 
-This model is a fine-tuned version of [HuggingFaceTB/SmolLM-360M](https://huggingface.co/HuggingFaceTB/SmolLM-360M) on the generator dataset.
+This model is a fine-tuned version of [HuggingFaceTB/SmolLM-360M](https://huggingface.co/HuggingFaceTB/SmolLM-360M) on the HuggingFaceTB/everyday-topics-MT-conversations-H4 and the HuggingFaceTB/instruct-data-basics-H4 datasets.
 It achieves the following results on the evaluation set:
 - Loss: 1.4730
 

all_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 2.857142857142857,
-    "eval_loss": 2.1008596420288086,
-    "eval_runtime": 0.1817,
+    "eval_loss": 1.4730318784713745,
+    "eval_runtime": 0.1815,
     "eval_samples": 119,
-    "eval_samples_per_second": 60.549,
-    "eval_steps_per_second": 5.504,
+    "eval_samples_per_second": 60.611,
+    "eval_steps_per_second": 5.51,
     "total_flos": 466196889600.0,
     "train_loss": 2.3683324337005613,
     "train_runtime": 24.8838,

config.json

@@ -25,6 +25,6 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.42.3",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 49152
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 1.7142857142857144,
-    "eval_loss": 2.1008596420288086,
-    "eval_runtime": 0.1817,
+    "epoch": 2.857142857142857,
+    "eval_loss": 1.4730318784713745,
+    "eval_runtime": 0.1815,
     "eval_samples": 119,
-    "eval_samples_per_second": 60.549,
-    "eval_steps_per_second": 5.504
+    "eval_samples_per_second": 60.611,
+    "eval_steps_per_second": 5.51
 }

runs/Aug13_00-20-24_ip-26-0-161-138/events.out.tfevents.1723508499.ip-26-0-161-138.2676503.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edb006eb02222ca0bcca0f19d097be96532e507fedbcb8bb700ff7c500cce9de
+size 354