End of training

README.md

@@ -39,8 +39,8 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 20
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 550
-- num_epochs: 4
+- lr_scheduler_warmup_steps: 600
+- num_epochs: 6
 
 ### Training results
 
@@ -48,7 +48,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.34.1
+- Transformers 4.35.0
 - Pytorch 2.1.0+cu118
-- Datasets 2.14.5
+- Datasets 2.14.6
 - Tokenizers 0.14.1

config.json

@@ -49,7 +49,7 @@
   "scale_embedding": true,
   "static_position_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.34.1",
+  "transformers_version": "4.35.0",
   "use_cache": true,
   "vocab_size": 96103
 }

generation_config.json

@@ -9,5 +9,5 @@
   "min_length": 32,
   "num_beams": 8,
   "pad_token_id": 0,
-  "transformers_version": "4.34.1"
+  "transformers_version": "4.35.0"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16aa1166e454750179158ef626bfaafac56f78d0a5b657260caeb3e51ac1bd80
+size 2283652852

runs/Nov06_03-14-07_da56ab304005/events.out.tfevents.1699240448.da56ab304005.260.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfff405c5bba53e530216065a07cebb943bb19fdfb9086d2fe9ff9cc07baa987
+size 5961

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:191b7fa152e554171c206f925284e85c4dc02518a33bc51111715c556cf141a0
-size 4472
+oid sha256:42c57965a6db64a26f687c0f2ddf03b9ee7f8f353db81b15fd6621aa3062b649
+size 4536