Training in progress, step 400

config.json

@@ -1,11 +1,14 @@
 {
   "_name_or_path": "facebook/wav2vec2-xls-r-300m",
   "activation_dropout": 0.0,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
   "apply_spec_augment": true,
   "architectures": [
     "Wav2Vec2ForCTC"
   ],
-  "attention_dropout": 0.25,
+  "attention_dropout": 0.2,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
   "codevector_dim": 768,
@@ -46,22 +49,25 @@
   "feat_extract_activation": "gelu",
   "feat_extract_dropout": 0.0,
   "feat_extract_norm": "layer",
-  "feat_proj_dropout": 0.2,
+  "feat_proj_dropout": 0.15,
   "feat_quantizer_dropout": 0.0,
   "final_dropout": 0.0,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
-  "hidden_dropout": 0.32,
+  "hidden_dropout": 0.24,
   "hidden_size": 1024,
   "initializer_range": 0.02,
   "intermediate_size": 4096,
   "layer_norm_eps": 1e-05,
-  "layerdrop": 0.3,
+  "layerdrop": 0.15,
   "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
   "mask_feature_prob": 0.0,
   "mask_time_length": 10,
-  "mask_time_prob": 0.23,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.17,
   "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
   "num_attention_heads": 16,
   "num_codevector_groups": 2,
   "num_codevectors_per_group": 320,
@@ -70,10 +76,33 @@
   "num_feat_extract_layers": 7,
   "num_hidden_layers": 24,
   "num_negatives": 100,
-  "pad_token_id": 96,
+  "output_hidden_size": 1024,
+  "pad_token_id": 97,
   "proj_codevector_dim": 768,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
   "torch_dtype": "float32",
-  "transformers_version": "4.11.3",
+  "transformers_version": "4.16.2",
   "use_weighted_layer_sum": false,
-  "vocab_size": 99
+  "vocab_size": 100,
+  "xvector_output_dim": 512
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdfc7907a2a6bd0347b6a049d99c58e79446a212f8f23059c1e974488504dc03
-size 1262329585
+oid sha256:98e07603bfd19e0bd2036a9c42b25ca665c2cbf08fa132f0173e943c04369d4c
+size 1262333681

runs/Feb07_09-00-02_job-1cbb6c7a-d063-4cb3-ba22-bc0e2afc09f0/1644224464.2690885/events.out.tfevents.1644224464.job-1cbb6c7a-d063-4cb3-ba22-bc0e2afc09f0.3352471.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9015966d3b5cc0eee06be0744a3bcdcc560e60330e39e287c7db6d8c8d2872b0
+size 4826

runs/Feb07_09-00-02_job-1cbb6c7a-d063-4cb3-ba22-bc0e2afc09f0/events.out.tfevents.1644224464.job-1cbb6c7a-d063-4cb3-ba22-bc0e2afc09f0.3352471.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:334c491604b61d74ba757c0e24b7d66329ae141f90ea68a2d44cdc6d7f048718
+size 5263

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9aae5ac7fa7845371126005fed154e5034424cc7c21acd6a206b057432d3ceed
-size 2863
+oid sha256:8fdc4ca2565d5bcdf9c6e88a9e36142b6db67ad1917a9e590ef0c1b7fa45691c
+size 3055