End of training

README.md

@@ -1,11 +1,19 @@
 ---
 base_model: loubnabnl/smollm-1.7b-16k
 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-conversations-llama3.1-2k
+- HuggingFaceTB/instruct-data-basics-smollm-H4
 model-index:
 - name: smollm-1.7B-16k-instruct-v0
   results: []
@@ -17,7 +25,7 @@ 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/7rd4806f)
 # smollm-1.7B-16k-instruct-v0
 
-This model is a fine-tuned version of [loubnabnl/smollm-1.7b-16k](https://huggingface.co/loubnabnl/smollm-1.7b-16k) on the generator dataset.
+This model is a fine-tuned version of [loubnabnl/smollm-1.7b-16k](https://huggingface.co/loubnabnl/smollm-1.7b-16k) on the HuggingFaceTB/Magpie-Pro-300K-Filtered-H4, the HuggingFaceTB/self-oss-instruct-sc2-H4, the HuggingFaceTB/OpenHermes-2.5-H4, the HuggingFaceTB/everyday-conversations-llama3.1-2k and the HuggingFaceTB/instruct-data-basics-smollm-H4 datasets.
 It achieves the following results on the evaluation set:
 - Loss: 1.0118
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9951219512195122,
+    "eval_loss": 1.0117870569229126,
+    "eval_runtime": 124.7042,
+    "eval_samples": 82730,
+    "eval_samples_per_second": 21.026,
+    "eval_steps_per_second": 0.658,
     "total_flos": 128481799176192.0,
     "train_loss": 0.7558732021088693,
     "train_runtime": 2589.5829,

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": 0.9951219512195122,
+    "eval_loss": 1.0117870569229126,
+    "eval_runtime": 124.7042,
+    "eval_samples": 82730,
+    "eval_samples_per_second": 21.026,
+    "eval_steps_per_second": 0.658
+}

runs/Sep20_12-08-36_ip-26-0-168-120/events.out.tfevents.1726837978.ip-26-0-168-120.4123050.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:654f4999022be4056a01d98518a74d277017a67b16671f7dd7c1e9aa3d4f589e
+size 354