End of training

README.md

@@ -43,10 +43,11 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
 - num_epochs: 30
+- mixed_precision_training: Native AMP
 
 ### Framework versions
 
-- Transformers 4.45.2
-- Pytorch 2.2.0
-- Datasets 3.0.1
-- Tokenizers 0.20.1
+- Transformers 4.44.1
+- Pytorch 2.5.0+cu124
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -86,7 +86,7 @@
   "num_hidden_layers": 24,
   "num_negatives": 100,
   "output_hidden_size": 1024,
-  "pad_token_id": 573,
+  "pad_token_id": 2267,
   "proj_codevector_dim": 768,
   "tdnn_dilation": [
     1,
@@ -110,8 +110,8 @@
     1
   ],
   "torch_dtype": "float32",
-  "transformers_version": "4.45.2",
+  "transformers_version": "4.44.1",
   "use_weighted_layer_sum": false,
-  "vocab_size": 576,
+  "vocab_size": 2270,
   "xvector_output_dim": 512
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9425796802e17438c8d601f5162e03ebac5ff5e6f070a7e075635672be175cc
-size 1264169096
+oid sha256:9d97a4e49c6bfe43f483f953f4bf1e520aa9d80b5e469e33ca2bf54932b83b49
+size 1271114504

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52a819762cabb248851e954ad2e02078464d6d319fd811a375c6bb5c5fce0a78
-size 5240
+oid sha256:076126423cee0904d5f9a6a4b7a5ccdbc522c7d40c5ee08d0e8fe70099304483
+size 5176