End of training

README.md

@@ -32,13 +32,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
+- learning_rate: 0.0005
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 10
 
 ### Training results
 

logs/events.out.tfevents.1709200952.a7a08a4788fa.738.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4243cf0745ad07afa701e576a992eb48a23ca8bc951e4835f939fb687cad41d3
+size 7250

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa8e37393d1cfafcedec06b2f98197d21a836438a715e01f46658950b71cbe59
+oid sha256:e7986a098d3918ddf468a2e09f20d35666582f40c27dbc6090e4cd6c777aa7d2
 size 990345064

tokenizer_config.json

@@ -930,9 +930,16 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "extra_ids": 100,
+  "max_length": 7,
   "model_max_length": 512,
+  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sp_model_kwargs": {},
+  "stride": 0,
   "tokenizer_class": "T5Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:702e62999a5d9639d4e4c56745216c2e30ed62ccf83fa684a6d4b93006d56d4d
+oid sha256:7cc7887b932d1cd8a641005ba327d392d8f47b9ecb467482b336c0e93e1f1b11
 size 4856