Juristone/mixtral-contradiction_detector_v0

README.md

@@ -37,11 +37,11 @@ The following hyperparameters were used during training:
 - train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 4
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 8
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 6
+- num_epochs: 8
 
 ### Training results
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a68bf432b5661d99c4e38934a4708c4ac034213d63c108262360334189c5e5e0
+oid sha256:1b5c2d71104f5b10bb9120ad3100b724217421ced2f487e9eef9f36500d88e2a
 size 151070616

runs/May27_17-42-53_7723738715d8/events.out.tfevents.1716831787.7723738715d8.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9b78bfeabe0d3b0e725c8c30207364c0522e2706b8d8a4e2b45c119a4456ade
+size 6442

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37fc21cd28caa6ea91fed4623cd64731b0d7f1756b2e3f16bc21517656587724
+oid sha256:7c2d0b1e5deecca9816f44844886d7ee55b87d977235d5f83b5869b867e86511
 size 4984