End of training

README.md

@@ -33,17 +33,21 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0005
-- train_batch_size: 32
-- eval_batch_size: 32
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - gradient_accumulation_steps: 8
-- total_train_batch_size: 256
+- total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 1000
 - num_epochs: 2
 - mixed_precision_training: Native AMP
 
+### Training results
+
+
+
 ### Framework versions
 
 - Transformers 4.38.2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c78f9ad2317e29254a857f76a034089c94477677805303407ceccc3bf14fd5b6
+oid sha256:104c9d0fb17133c9b3b93cfb957e2df114460b94d6d8c5f198807deedffb1ba3
 size 496984704

runs/Apr25_23-19-12_D830MT/events.out.tfevents.1714058354.D830MT.2937.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:753232ecc6fd88fcdff707a087e496299c638309c848474f4f1457b21ec8ca69
+size 5160

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 128,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2db289a2acf0f308af0b2caea92343bda194179057a5b9fd2ed28fdc206c4383
+oid sha256:3b46546868bc7bd96bb0e87f7067ae0173b5e35b74d5b2fdf26955ad8aea0cad
 size 4856