Training in progress, step 500

config.json

@@ -1,6 +1,6 @@
 {
-  "_name_or_path": "facebook/hubert-base-ls960",
-  "activation_dropout": 0.1,
+  "_name_or_path": "facebook/hubert-large-ll60k",
+  "activation_dropout": 0.0,
   "apply_spec_augment": true,
   "architectures": [
     "HubertForSequenceClassification"
@@ -8,7 +8,7 @@
   "attention_dropout": 0.1,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
-  "conv_bias": false,
+  "conv_bias": true,
   "conv_dim": [
     512,
     512,
@@ -38,19 +38,18 @@
   ],
   "ctc_loss_reduction": "sum",
   "ctc_zero_infinity": false,
-  "do_stable_layer_norm": false,
+  "do_stable_layer_norm": true,
   "eos_token_id": 2,
   "feat_extract_activation": "gelu",
   "feat_extract_dropout": 0.0,
-  "feat_extract_norm": "group",
+  "feat_extract_norm": "layer",
   "feat_proj_dropout": 0.1,
   "feat_proj_layer_norm": true,
-  "final_dropout": 0.1,
+  "final_dropout": 0.0,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout": 0.1,
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -138,7 +137,7 @@
     "83": "LABEL_83"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -227,18 +226,26 @@
   },
   "layer_norm_eps": 1e-05,
   "layerdrop": 0.1,
+  "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_prob": 0.05,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.075,
+  "mask_time_selection": "static",
   "model_type": "hubert",
-  "num_attention_heads": 12,
+  "num_attention_heads": 16,
   "num_conv_pos_embedding_groups": 16,
   "num_conv_pos_embeddings": 128,
   "num_feat_extract_layers": 7,
-  "num_hidden_layers": 12,
+  "num_hidden_layers": 24,
   "pad_token_id": 0,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",
   "torch_dtype": "float32",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dd8a137cdc60e00e9ee760f599d32c53f3497251448c36a3fb69d8560867c17
-size 378386248
+oid sha256:eacf169a553fbf358fa5223cdde17f080c7d175cc87e985a453e53174b39261b
+size 1262942768

runs/Jul23_01-31-58_LAPTOP-1GID9RGH/events.out.tfevents.1721673119.LAPTOP-1GID9RGH.24960.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9f34ba18d83ae76f619dc4b07775b840e937e33d5318f713e807f5f58d21c89
+size 9297

runs/Jul23_01-47-26_LAPTOP-1GID9RGH/events.out.tfevents.1721674047.LAPTOP-1GID9RGH.2264.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6d83ee0e79e35c2b22062388673d56dba90e04f511b24e1bb4bb9c8a87d36cf
+size 14665

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a28046fc9a1c66c7d7a34e5eb0b2c6e1ca92083874a192a947ca31c073339d3
+oid sha256:2267625fb5bb3e6ce0ce3baf60b4073360076dffb219dc39c36a3a38d8778058
 size 4984