use larger training data

README.md

@@ -31,15 +31,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0005
-- train_batch_size: 5
-- eval_batch_size: 8
+- train_batch_size: 10
+- eval_batch_size: 16
 - seed: 42
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 10
+- total_train_batch_size: 20
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 1000
-- training_steps: 1000
+- training_steps: 2000
 
 ### Training results
 
@@ -47,7 +47,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.41.2
-- Pytorch 2.3.0+cu121
-- Datasets 2.20.0
+- Transformers 4.41.1
+- Pytorch 2.1.2
+- Datasets 2.19.1
 - Tokenizers 0.19.1

config.json

@@ -23,7 +23,7 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "torch_dtype": "float32",
-  "transformers_version": "4.41.2",
+  "transformers_version": "4.41.1",
   "use_bias": false,
   "use_cache": false,
   "vocab_size": 32000

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1cc60b4eb598085ae2e7461f1eadab7b1280e9ad960bc10145cc6e320dc4bf0
+oid sha256:1f579b58d6b74066e84e5aee3ac72ea801fd90a9a5bf42cf1389c0b776b7dc54
 size 469946160

runs/Jun17_11-53-06_d73efaf50987/events.out.tfevents.1718625190.d73efaf50987.24.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42d031be4a8c7e2c9d604519e8d6247850b87bce1084eec7bb443636885880fc
+size 47287

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f25aa0979eee931bb200706c9bdd6e12b73acc9c1874f30b9d6381e1724f3af
+oid sha256:126feb5c779a08f8d92d8f53b017822a510e5664c4339af8553041ca7d9ec997
 size 5112