Training in progress, epoch 4

config.json

@@ -1,20 +1,14 @@
 {
-  "_name_or_path": "stevhliu/my_awesome_minds_model",
-  "activation_dropout": 0.0,
-  "adapter_attn_dim": null,
-  "adapter_kernel_size": 3,
-  "adapter_stride": 2,
-  "add_adapter": false,
+  "_name_or_path": "facebook/hubert-large-ls960-ft",
+  "activation_dropout": 0.1,
   "apply_spec_augment": true,
   "architectures": [
-    "Wav2Vec2ForSequenceClassification"
+    "HubertForSequenceClassification"
   ],
   "attention_dropout": 0.1,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
-  "codevector_dim": 256,
-  "contrastive_logits_temperature": 0.1,
-  "conv_bias": false,
+  "conv_bias": true,
   "conv_dim": [
     512,
     512,
@@ -45,20 +39,26 @@
   "ctc_loss_reduction": "sum",
   "ctc_zero_infinity": false,
   "diversity_loss_weight": 0.1,
-  "do_stable_layer_norm": false,
+  "do_stable_layer_norm": true,
   "eos_token_id": 2,
   "feat_extract_activation": "gelu",
-  "feat_extract_norm": "group",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
   "feat_proj_dropout": 0.1,
-  "feat_quantizer_dropout": 0.0,
-  "final_dropout": 0.0,
-  "freeze_feat_extract_train": true,
+  "feat_proj_layer_norm": true,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout": 0.1,
-  "hidden_size": 768,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
   "id2label": {
     "0": "abroad",
     "1": "address",
+    "10": "high_value_payment",
+    "11": "joint_account",
+    "12": "latest_transactions",
+    "13": "pay_bill",
     "2": "app_error",
     "3": "atm_limit",
     "4": "balance",
@@ -66,14 +66,10 @@
     "6": "card_issues",
     "7": "cash_deposit",
     "8": "direct_debit",
-    "9": "freeze",
-    "10": "high_value_payment",
-    "11": "joint_account",
-    "12": "latest_transactions",
-    "13": "pay_bill"
+    "9": "freeze"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "label2id": {
     "abroad": "0",
     "address": "1",
@@ -91,60 +87,22 @@
     "pay_bill": "13"
   },
   "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",
+  "layerdrop": 0.1,
   "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": 0.05,
-  "mask_time_selection": "static",
-  "model_type": "wav2vec2",
-  "no_mask_channel_overlap": false,
-  "no_mask_time_overlap": false,
-  "num_adapter_layers": 3,
-  "num_attention_heads": 12,
-  "num_codevector_groups": 2,
-  "num_codevectors_per_group": 320,
+  "model_type": "hubert",
+  "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_negatives": 100,
-  "output_hidden_size": 768,
+  "num_hidden_layers": 24,
   "pad_token_id": 0,
-  "proj_codevector_dim": 256,
-  "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": "4.40.2",
   "use_weighted_layer_sum": false,
-  "vocab_size": 32,
-  "xvector_output_dim": 512
+  "vocab_size": 32
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdfc42e20cc63b8b126cd2a80c59c29d0d6639044211c72d847fcc86bdb0d01e
-size 378314704
+oid sha256:7503a8ff047300e3c429073f9759f4be589e336a5a40c2d2105e475bc856ddd0
+size 1262870800

preprocessor_config.json

@@ -3,7 +3,7 @@
   "feature_extractor_type": "Wav2Vec2FeatureExtractor",
   "feature_size": 1,
   "padding_side": "right",
-  "padding_value": 0.0,
-  "return_attention_mask": false,
+  "padding_value": 0,
+  "return_attention_mask": true,
   "sampling_rate": 16000
 }

runs/May20_19-20-29_646268f6a6bb/events.out.tfevents.1716232829.646268f6a6bb.2822.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:141a67e52d348b777044ff0edd764837fe9a5f865fdcc957ce64d9c1d17eb213
+size 10037

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3b7d35cf67d51fb08c94f415c412cc56da48a6aae10c541afe259b4043c3fbc
+oid sha256:b9cd491482fa352f8ea3bdad1b7820f26b7ead8303201c5a9085daaf203199a2
 size 4984