End of training

README.md

@@ -16,9 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # output_gptreasoning
 
-This model is a fine-tuned version of [HuggingFaceM4/idefics2-8b](https://huggingface.co/HuggingFaceM4/idefics2-8b) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.5066
+This model is a fine-tuned version of [HuggingFaceM4/idefics2-8b](https://huggingface.co/HuggingFaceM4/idefics2-8b) on an unknown dataset.
 
 ## Model description
 
@@ -41,11 +39,11 @@ The following hyperparameters were used during training:
 - train_batch_size: 1
 - eval_batch_size: 1
 - seed: 42
-- gradient_accumulation_steps: 16
-- total_train_batch_size: 16
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- num_epochs: 3
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -54,8 +52,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.12.0
-- Transformers 4.42.4
-- Pytorch 2.4.0+cu121
-- Datasets 2.21.0
+- PEFT 0.13.0
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.1
 - Tokenizers 0.19.1

adapter_config.json

@@ -21,8 +21,8 @@
   "revision": null,
   "target_modules": [
     "q_proj",
-    "k_proj",
     "o_proj",
+    "k_proj",
     "v_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d026e45012755890dc5fc5d8688452acde57a9a87af2066d4b9f19adc731a535
+oid sha256:e433b9fe0891916bd86f074463fc1834c88a4e7b3944a581170993652469109e
 size 35242256

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a28f16faf459d1881162647cbb26f4d1828890629ed9be9ff7d9df51c93f8a36
-size 5432
+oid sha256:a83a71f962db632f6cdb6dd6b220c37d92250caa1a89544b2d9a754f1d35c3c2
+size 5496