Training in progress, epoch 1

config.json

@@ -1,6 +1,6 @@
 {
-  "_name_or_path": "mujadid-syahbana/audioclass-alpha",
-  "activation_dropout": 0.05,
+  "_name_or_path": "facebook/wav2vec2-base-960h",
+  "activation_dropout": 0.1,
   "adapter_attn_dim": null,
   "adapter_kernel_size": 3,
   "adapter_stride": 2,
@@ -14,7 +14,7 @@
   "classifier_proj_size": 256,
   "codevector_dim": 256,
   "contrastive_logits_temperature": 0.1,
-  "conv_bias": true,
+  "conv_bias": false,
   "conv_dim": [
     512,
     512,
@@ -42,20 +42,22 @@
     2,
     2
   ],
-  "ctc_loss_reduction": "mean",
-  "ctc_zero_infinity": true,
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
   "diversity_loss_weight": 0.1,
-  "do_stable_layer_norm": true,
+  "do_stable_layer_norm": false,
   "eos_token_id": 2,
   "feat_extract_activation": "gelu",
   "feat_extract_dropout": 0.0,
-  "feat_extract_norm": "layer",
-  "feat_proj_dropout": 0.05,
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
   "feat_quantizer_dropout": 0.0,
-  "final_dropout": 0.0,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
-  "hidden_dropout": 0.05,
-  "hidden_size": 1024,
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "qauf",
     "1": "faa",
@@ -90,7 +92,7 @@
     "9": "noon"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "label2id": {
     "aain": "7",
     "alif": "24",
@@ -125,32 +127,24 @@
     "zua": "14"
   },
   "layer_norm_eps": 1e-05,
-  "layerdrop": 0.05,
-  "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",
   "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": 256,
   "tdnn_dilation": [
@@ -177,6 +171,6 @@
   "torch_dtype": "float32",
   "transformers_version": "4.36.0.dev0",
   "use_weighted_layer_sum": false,
-  "vocab_size": 51,
+  "vocab_size": 32,
   "xvector_output_dim": 512
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:153582f5bcf4420fd58a752c37aed3d8973a65613702921fb660e7ba9d4e1036
-size 1262889124
+oid sha256:9582085d194f3335a3f8c8285ee1dddfac23fc0bf310c055a67a265772c17749
+size 378332188

preprocessor_config.json

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

runs/Nov04_05-56-15_886e887cef14/events.out.tfevents.1699077377.886e887cef14.366.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7db4f9c0abcd5be99e1c57ed01aa2b62a8bc600f19eff64e92b920b100479a70
-size 26409
+oid sha256:7c984ffdd5bbfe9ec4b010d757c84f26372c6ca8898cf7f23a786b80daada46c
+size 26723

runs/Nov04_07-42-35_886e887cef14/events.out.tfevents.1699083769.886e887cef14.44187.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bf901901973da1d41e10896a151aba52a91cce98cbd8b71e799168a381b5376
+size 8012

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8a40ed8d5641e1b86838d5865e21aabad97a10776dc70c9f5760b11cb601786
+oid sha256:46c9e813ce396f56192f5fb570ea2c6d510c9c7b1965746eb9493fa51b1e2987
 size 4600