End of training

README.md

@@ -2,11 +2,20 @@
 license: apache-2.0
 base_model: HuggingFaceTB/SmolLM-135M
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- HuggingFaceTB/Magpie-Pro-300K-Filtered-H4
+- HuggingFaceTB/self-oss-instruct-sc2-H4
+- HuggingFaceTB/OpenHermes-2.5-H4
+- HuggingFaceTB/everyday-topics-MT-conversations-H4
+- HuggingFaceTB/instruct-data-basics-H4
+- HuggingFaceTB/basic-math-MT-conversations-H4
 model-index:
 - name: smollm-135M-instruct-add-basics-w-math
   results: []
@@ -18,7 +27,7 @@ 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/6rtd4dhv)
 # smollm-135M-instruct-add-basics-w-math
 
-This model is a fine-tuned version of [HuggingFaceTB/SmolLM-135M](https://huggingface.co/HuggingFaceTB/SmolLM-135M) on the generator dataset.
+This model is a fine-tuned version of [HuggingFaceTB/SmolLM-135M](https://huggingface.co/HuggingFaceTB/SmolLM-135M) on the HuggingFaceTB/Magpie-Pro-300K-Filtered-H4, the HuggingFaceTB/self-oss-instruct-sc2-H4, the HuggingFaceTB/OpenHermes-2.5-H4, the HuggingFaceTB/everyday-topics-MT-conversations-H4, the HuggingFaceTB/instruct-data-basics-H4 and the HuggingFaceTB/basic-math-MT-conversations-H4 datasets.
 It achieves the following results on the evaluation set:
 - Loss: 1.4193
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9990828492815653,
+    "eval_loss": 1.4192770719528198,
+    "eval_runtime": 101.4353,
+    "eval_samples": 82735,
+    "eval_samples_per_second": 206.536,
+    "eval_steps_per_second": 6.457,
     "total_flos": 45136994107392.0,
     "train_loss": 1.1321502848091733,
     "train_runtime": 1720.7287,

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

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9990828492815653,
+    "eval_loss": 1.4192770719528198,
+    "eval_runtime": 101.4353,
+    "eval_samples": 82735,
+    "eval_samples_per_second": 206.536,
+    "eval_steps_per_second": 6.457
+}

runs/Aug13_12-47-34_ip-26-0-165-24/events.out.tfevents.1723555696.ip-26-0-165-24.672120.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1b8a39fe78f9d28b4108c279a3b6c6290be4dca394de75f0e3fdb88bc481916
+size 359