HW5-t5

README.md

@@ -33,11 +33,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 32
+- total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 1000
@@ -46,7 +46,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.42.0.dev0
-- Pytorch 2.3.0+cu121
-- Datasets 2.19.2
-- Tokenizers 0.19.1
+- Transformers 4.37.2
+- Pytorch 2.2.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.1

config.json

@@ -85,7 +85,7 @@
   "speech_decoder_prenet_layers": 2,
   "speech_decoder_prenet_units": 256,
   "torch_dtype": "float32",
-  "transformers_version": "4.42.0.dev0",
+  "transformers_version": "4.37.2",
   "use_cache": false,
   "use_guided_attention_loss": true,
   "vocab_size": 81

generation_config.json

@@ -5,5 +5,5 @@
   "eos_token_id": 2,
   "max_length": 1876,
   "pad_token_id": 1,
-  "transformers_version": "4.42.0.dev0"
+  "transformers_version": "4.37.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27c5292fd68cdaa69649fc41a91082357656b48b489388f84919eed5bc26a01f
+oid sha256:246f6c701a5150a51776de936ae51e8010af4056a31e499d0bf9e3449050740b
 size 577789320

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f57806f096d645f22bce0eae4652afd7325a8b40fadf82b80ccacffe072f7d02
-size 5304
+oid sha256:dc5677e314a3af640f111c42deaad07b61f7f8fa4ccaded7690fde06a87920d4
+size 4856