Training in progress, step 300

config.json

@@ -1,6 +1,6 @@
 {
-  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
-  "activation_dropout": 0.0,
+  "_name_or_path": "jonatasgrosman/wav2vec2-large-xlsr-53-english",
+  "activation_dropout": 0.05,
   "adapter_kernel_size": 3,
   "adapter_stride": 2,
   "add_adapter": false,
@@ -11,7 +11,7 @@
   "attention_dropout": 0.0,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
-  "codevector_dim": 768,
+  "codevector_dim": 256,
   "contrastive_logits_temperature": 0.1,
   "conv_bias": true,
   "conv_dim": [
@@ -42,7 +42,7 @@
     2
   ],
   "ctc_loss_reduction": "mean",
-  "ctc_zero_infinity": false,
+  "ctc_zero_infinity": true,
   "diversity_loss_weight": 0.1,
   "do_stable_layer_norm": true,
   "eos_token_id": 2,
@@ -52,7 +52,6 @@
   "feat_proj_dropout": 0.0,
   "feat_quantizer_dropout": 0.0,
   "final_dropout": 0.0,
-  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout": 0.0,
   "hidden_size": 1024,
@@ -60,12 +59,20 @@
   "intermediate_size": 4096,
   "layer_norm_eps": 1e-05,
   "layerdrop": 0.0,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
   "mask_feature_length": 10,
   "mask_feature_min_masks": 0,
   "mask_feature_prob": 0.0,
   "mask_time_length": 10,
   "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
   "mask_time_prob": 0,
+  "mask_time_selection": "static",
   "model_type": "wav2vec2",
   "num_adapter_layers": 3,
   "num_attention_heads": 16,
@@ -77,8 +84,8 @@
   "num_hidden_layers": 24,
   "num_negatives": 100,
   "output_hidden_size": 1024,
-  "pad_token_id": 33,
-  "proj_codevector_dim": 768,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 256,
   "tdnn_dilation": [
     1,
     2,
@@ -103,6 +110,6 @@
   "torch_dtype": "float32",
   "transformers_version": "4.20.1",
   "use_weighted_layer_sum": false,
-  "vocab_size": 34,
+  "vocab_size": 33,
   "xvector_output_dim": 512
 }

preprocessor_config.json

@@ -4,6 +4,7 @@
   "feature_size": 1,
   "padding_side": "right",
   "padding_value": 0.0,
+  "processor_class": "Wav2Vec2ProcessorWithLM",
   "return_attention_mask": true,
   "sampling_rate": 16000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bed27a0618795d0ef8554fdcb3e99cc4faf5d90cc69a2ba3c55c751566118d2
-size 1262033715
+oid sha256:4aa29613990da5ea3049f7232c6764645631f5ce9d20268af3df9ac6c0fb8ea7
+size 1262029619

runs/Aug03_18-10-17_DESKTOP-6CRK3AE/1659543028.0143137/events.out.tfevents.1659543028.DESKTOP-6CRK3AE.10656.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a3d0df6497bbece2bb3a9d7b23fb5798b768d2ef01a6d0325bed3da0c921fed
+size 5342

runs/Aug03_18-10-17_DESKTOP-6CRK3AE/events.out.tfevents.1659543027.DESKTOP-6CRK3AE.10656.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2304d1ebba77d8e1407cb5db0d5bc0625df45912f6b25513eebc9b271fae445
+size 5041

runs/Aug03_18-11-34_DESKTOP-6CRK3AE/1659543105.0672584/events.out.tfevents.1659543105.DESKTOP-6CRK3AE.2468.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea2e9b5ea7da327c1d15dffb959524c05bdf3ef22d6094a1d6e3f0bb01674ae8
+size 5342

runs/Aug03_18-11-34_DESKTOP-6CRK3AE/events.out.tfevents.1659543105.DESKTOP-6CRK3AE.2468.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff817850627c6d32df1e708df6b051c0ab18981b7f3086d097b72bf34581bd3e
+size 6647

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d96017db4260fa946f113362d7c2d469c9215e7b47ebf591f7bfd66e7e2ed98b
+oid sha256:586aef4283205ba7c03c24a24273804478bbc7bb58a3210a427b00cd19abc80d
 size 3311