Training in progress, epoch 0

config.json

@@ -1,6 +1,6 @@
 {
-  "_name_or_path": "facebook/wav2vec2-base",
-  "activation_dropout": 0.0,
+  "_name_or_path": "facebook/wav2vec2-large-robust",
+  "activation_dropout": 0.1,
   "adapter_attn_dim": null,
   "adapter_kernel_size": 3,
   "adapter_stride": 2,
@@ -12,9 +12,9 @@
   "attention_dropout": 0.1,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
-  "codevector_dim": 256,
+  "codevector_dim": 768,
   "contrastive_logits_temperature": 0.1,
-  "conv_bias": false,
+  "conv_bias": true,
   "conv_dim": [
     512,
     512,
@@ -45,17 +45,19 @@
   "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,
+  "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": "Anger",
     "1": "Happy",
@@ -65,7 +67,7 @@
     "5": "Neutral"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "label2id": {
     "Anger": 0,
     "Disgust": 4,
@@ -75,36 +77,26 @@
     "Sad": 3
   },
   "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_attention_heads": 16,
   "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": 12,
+  "num_hidden_layers": 24,
   "num_negatives": 100,
-  "output_hidden_size": 768,
+  "output_hidden_size": 1024,
   "pad_token_id": 0,
-  "proj_codevector_dim": 256,
+  "proj_codevector_dim": 768,
   "tdnn_dilation": [
     1,
     2,
@@ -129,6 +121,6 @@
   "torch_dtype": "float32",
   "transformers_version": "4.38.2",
   "use_weighted_layer_sum": false,
-  "vocab_size": 32,
+  "vocab_size": null,
   "xvector_output_dim": 512
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efd108b788d5cba110f37d8be64585a841578be65b20fc453c7af30719591b4d
-size 378306480
+oid sha256:dcc9ba8feaf9f2f25e60612f60793f549fb84e174be43e7f824e2430520e3291
+size 1262863416

preprocessor_config.json

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

runs/Apr10_11-08-26_2c3934cd07a5/events.out.tfevents.1712747316.2c3934cd07a5.525.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12ef7217cefa75297d0a99610f87f1f335331375705fd2d260eb2ccd62db52f3
+size 6360

runs/Apr10_11-09-26_2c3934cd07a5/events.out.tfevents.1712747376.2c3934cd07a5.525.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfba4633818ef557ed141cd9dd9659766103391862162395fd061c1194f14999
+size 8126

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22b965d9003e6989aaa44de7b3e46d32fc4bfe225490d141a54acb6ebcbfce42
+oid sha256:47188c40e3227e4f219bba20c387e92f3ca190895d7321567ffff921ec425058
 size 4920