End of training

README.md

@@ -32,11 +32,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 4
-- eval_batch_size: 4
+- train_batch_size: 10
+- eval_batch_size: 10
 - seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 16
+- gradient_accumulation_steps: 10
+- total_train_batch_size: 100
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53e94814c2e00d375e56e8857755e6ea532ad1e353fdd474866b5f7e8857c4f4
+oid sha256:6786a97e6f5f6f8ebfe464d0e42b34a444833c1c6a1d51e8b76076b752b776da
 size 134263757

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "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:c2c3758ede1aa832a8fe13436558d5798bb0c6efd8a0a4660d9aa3a16813bcdf
+oid sha256:88aab9216d82239196a90e6a38962ef493285e3eab906a9b3bcf33c65362601d
 size 4091