End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-135M](https://huggingface.co/HuggingFaceTB/SmolLM2-135M) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.2215
+- Loss: 2.4268
 
 ## Model description
 
@@ -35,28 +35,35 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0005
+- learning_rate: 0.0003
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 128
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
-- num_epochs: 2
+- lr_scheduler_warmup_ratio: 0.12
+- num_epochs: 1
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 3.1835        | 0.32  | 200  | 3.4083          |
-| 2.9042        | 0.64  | 400  | 3.3115          |
-| 2.7019        | 0.96  | 600  | 3.1662          |
-| 1.6689        | 1.28  | 800  | 3.2652          |
-| 1.4683        | 1.6   | 1000 | 3.2215          |
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 3.3182        | 0.1067 | 25   | 2.9325          |
+| 2.7389        | 0.2133 | 50   | 2.7294          |
+| 2.6048        | 0.32   | 75   | 2.6356          |
+| 2.4954        | 0.4267 | 100  | 2.5659          |
+| 2.4568        | 0.5333 | 125  | 2.5168          |
+| 2.4627        | 0.64   | 150  | 2.4760          |
+| 2.3904        | 0.7467 | 175  | 2.4465          |
+| 2.3572        | 0.8533 | 200  | 2.4319          |
+| 2.3606        | 0.96   | 225  | 2.4268          |
 
 
 ### Framework versions
 
-- Transformers 4.56.1
+- Transformers 4.57.1
 - Pytorch 2.8.0+cu126
 - Datasets 4.0.0
-- Tokenizers 0.22.0
+- Tokenizers 0.22.1

config.json

@@ -26,7 +26,7 @@
   "rope_scaling": null,
   "rope_theta": 100000,
   "tie_word_embeddings": true,
-  "transformers_version": "4.56.2",
+  "transformers_version": "4.57.1",
   "use_cache": true,
   "vocab_size": 49152
 }

generation_config.json

@@ -5,5 +5,5 @@
     0
   ],
   "pad_token_id": 0,
-  "transformers_version": "4.56.1"
+  "transformers_version": "4.57.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe9fa69b3e6cff65351370f70a9c11047e66c7e05093e59d5be00526cd46a1f0
+oid sha256:9d0bdd355eedf081e8dfd7506fb21267722a0b21f65b532cc0928c0d07d894ef
 size 538090408

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cac7edf1437b9ea62683231187dee3ae140dd997bf52a70d7eadb32f41471b5
+oid sha256:86ec7eab07ed7cbc01251e1a5d187a48cce3ab06e46342bf9f1f2ef7e932e7e4
 size 5777