Training in progress, epoch 1

config.json

@@ -42,18 +42,21 @@
     2,
     2
   ],
-  "ctc_loss_reduction": "mean",
+  "ctc_loss_reduction": "sum",
   "ctc_zero_infinity": false,
   "diversity_loss_weight": 0.1,
   "do_stable_layer_norm": false,
   "eos_token_id": 2,
   "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
   "feat_extract_norm": "group",
-  "feat_proj_dropout": 0.0,
+  "feat_proj_dropout": 0.1,
   "feat_quantizer_dropout": 0.0,
   "final_dropout": 0.1,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
@@ -76,7 +79,7 @@
   "num_hidden_layers": 12,
   "num_negatives": 100,
   "output_hidden_size": 768,
-  "pad_token_id": 29,
+  "pad_token_id": 0,
   "proj_codevector_dim": 256,
   "tdnn_dilation": [
     1,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07338ec2339d9f9af145c12389a426d8a475aeae2d82437b61761f6c917d5f40
+oid sha256:b531f58a02080844df93e8f2e3f63bf9ce41d3a2c8f2c7f113aedd469d96e262
 size 377611120

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d3d908b4f47b925c93d22521e2fb8178592a04eb06900dd6605b1bc6f361340
+oid sha256:35f0e329b99474ebfded05d5b6e99aeb2f0d7f7a82c158d6614ccbb123854c8e
 size 5112