Training in progress, epoch 0

config.json

@@ -1,6 +1,6 @@
 {
-  "_name_or_path": "facebook/wav2vec2-large",
-  "activation_dropout": 0.1,
+  "_name_or_path": "facebook/wav2vec2-base",
+  "activation_dropout": 0.0,
   "adapter_attn_dim": null,
   "adapter_kernel_size": 3,
   "adapter_stride": 2,
@@ -12,7 +12,7 @@
   "attention_dropout": 0.1,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
-  "codevector_dim": 768,
+  "codevector_dim": 256,
   "contrastive_logits_temperature": 0.1,
   "conv_bias": false,
   "conv_dim": [
@@ -48,48 +48,56 @@
   "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": 0.1,
   "feat_quantizer_dropout": 0.0,
-  "final_dropout": 0.1,
+  "final_dropout": 0.0,
   "finetuning_task": "audio-classification",
-  "gradient_checkpointing": false,
+  "freeze_feat_extract_train": true,
   "hidden_act": "gelu",
   "hidden_dropout": 0.1,
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "id2label": {
     "0": "real",
     "1": "fake"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "label2id": {
     "fake": "1",
     "real": "0"
   },
   "layer_norm_eps": 1e-05,
-  "layerdrop": 0.1,
+  "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": 0.05,
+  "mask_time_selection": "static",
   "model_type": "wav2vec2",
+  "no_mask_channel_overlap": false,
+  "no_mask_time_overlap": false,
   "num_adapter_layers": 3,
-  "num_attention_heads": 16,
+  "num_attention_heads": 12,
   "num_codevector_groups": 2,
   "num_codevectors_per_group": 320,
   "num_conv_pos_embedding_groups": 16,
   "num_conv_pos_embeddings": 128,
   "num_feat_extract_layers": 7,
-  "num_hidden_layers": 24,
+  "num_hidden_layers": 12,
   "num_negatives": 100,
-  "output_hidden_size": 1024,
+  "output_hidden_size": 768,
   "pad_token_id": 0,
-  "proj_codevector_dim": 768,
+  "proj_codevector_dim": 256,
   "tdnn_dilation": [
     1,
     2,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d69bdec918d0ff324b6c62c27e3fe3faf4563eb33607c95881b1521725392e68
-size 1262817984
+oid sha256:1d16944178526c3e7068077746175c3a3cef75e1048e38136808d7f19ffa1223
+size 378302360

runs/May09_16-18-16_5c7bc4386fe7/events.out.tfevents.1715271522.5c7bc4386fe7.948.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a312ffbe121f29dd493fa48574c08e05875a9511a308d56ad93d5e2f4e1de153
+size 7601

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5628c11bc293bf0cd5077d93ebe5facc4fcb1110116f16794d44bab705607308
+oid sha256:23e85f70a220c9312e2362ae61c8bef390518321f4357de5c3914d80eb6dadce
 size 5176