End of training

README.md

@@ -1,11 +1,28 @@
 ---
 base_model: HuggingFaceTB/SmolLM2-1.7B-8k
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- HuggingFaceTB/magpie-ultra-v1.0-filtered-400K-H4
+- HuggingFaceTB/OpenHermes-2.5-H4-200k
+- HuggingFaceTB/ifeval-like-data-36k-H4
+- HuggingFaceTB/Numina-CoT-H4
+- HuggingFaceTB/MetaMathQA-H4-200k
+- HuggingFaceTB/self-oss-instruct-sc2-H4
+- HuggingFaceTB/systemchats2.0-H4-short
+- HuggingFaceTB/summarization-data-10k-H4
+- HuggingFaceTB/everyday-conversations-llama3.1-2k
+- HuggingFaceTB/apigen-smollm-trl-FC-H4
+- HuggingFaceTB/smollm-v2-summarization
+- HuggingFaceTB/smollm-v2-rewriting-50k-H4
+- HuggingFaceTB/explore-instruct-rewrite-H4
+- HuggingFaceTB/LongAlign-16k-ctx-english-H4
 model-index:
 - name: smollm2-1.7B-8k-mix7-ep2-v2
   results: []
@@ -17,7 +34,7 @@ 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/6rp7tpcv)
 # smollm2-1.7B-8k-mix7-ep2-v2
 
-This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-1.7B-8k](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-8k) on the generator dataset.
+This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-1.7B-8k](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-8k) on the HuggingFaceTB/magpie-ultra-v1.0-filtered-400K-H4, the HuggingFaceTB/OpenHermes-2.5-H4-200k, the HuggingFaceTB/ifeval-like-data-36k-H4, the HuggingFaceTB/Numina-CoT-H4, the HuggingFaceTB/MetaMathQA-H4-200k, the HuggingFaceTB/self-oss-instruct-sc2-H4, the HuggingFaceTB/systemchats2.0-H4-short, the HuggingFaceTB/summarization-data-10k-H4, the HuggingFaceTB/everyday-conversations-llama3.1-2k, the HuggingFaceTB/apigen-smollm-trl-FC-H4, the HuggingFaceTB/smollm-v2-summarization, the HuggingFaceTB/smollm-v2-rewriting-50k-H4, the HuggingFaceTB/explore-instruct-rewrite-H4 and the HuggingFaceTB/LongAlign-16k-ctx-english-H4 datasets.
 It achieves the following results on the evaluation set:
 - Loss: 1.0630
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.9983216783216782,
+    "eval_loss": 1.0629972219467163,
+    "eval_runtime": 364.8237,
+    "eval_samples": 264435,
+    "eval_samples_per_second": 56.435,
+    "eval_steps_per_second": 1.765,
     "total_flos": 1127451463778304.0,
     "train_loss": 0.777597175032935,
     "train_runtime": 16051.5455,

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": 1.9983216783216782,
+    "eval_loss": 1.0629972219467163,
+    "eval_runtime": 364.8237,
+    "eval_samples": 264435,
+    "eval_samples_per_second": 56.435,
+    "eval_steps_per_second": 1.765
+}

runs/Oct30_23-27-03_ip-26-0-164-18/events.out.tfevents.1730349116.ip-26-0-164-18.40006.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa19fb272bb4a029c44102f050b0bff1860a9e41aedb1c6c91eea9ac982e4163
+size 359