Model save

README.md

@@ -4,7 +4,6 @@ license: llama3.1
 base_model: meta-llama/Meta-Llama-3.1-8B
 tags:
 - llama-factory
-- full
 - generated_from_trainer
 model-index:
 - name: oh-dcft-v3.1-gpt-4o-mini
@@ -16,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # oh-dcft-v3.1-gpt-4o-mini
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the mlfoundations-dev/oh-dcft-v3.1-gpt-4o-mini dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6413
+- Loss: 0.6408
 
 ## Model description
 
@@ -42,28 +41,26 @@ The following hyperparameters were used during training:
 - eval_batch_size: 8
 - seed: 42
 - distributed_type: multi-GPU
-- num_devices: 16
-- gradient_accumulation_steps: 4
+- num_devices: 8
+- gradient_accumulation_steps: 8
 - total_train_batch_size: 512
-- total_eval_batch_size: 128
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- total_eval_batch_size: 64
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: constant
-- lr_scheduler_warmup_ratio: 0.1
-- lr_scheduler_warmup_steps: 1738
 - num_epochs: 3.0
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.6489        | 0.9982 | 422  | 0.6508          |
-| 0.5988        | 1.9988 | 845  | 0.6403          |
-| 0.5728        | 2.9947 | 1266 | 0.6413          |
+| 0.648         | 0.9985 | 422  | 0.6504          |
+| 0.5984        | 1.9997 | 845  | 0.6400          |
+| 0.5714        | 2.9962 | 1266 | 0.6408          |
 
 
 ### Framework versions
 
-- Transformers 4.45.2
+- Transformers 4.46.1
 - Pytorch 2.3.0
-- Datasets 2.21.0
+- Datasets 3.1.0
 - Tokenizers 0.20.3

generation_config.json

@@ -5,5 +5,5 @@
   "eos_token_id": 128001,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.45.2"
+  "transformers_version": "4.46.1"
 }