Training in progress, epoch 1

config.json

@@ -1,14 +1,20 @@
 {
-  "_name_or_path": "facebook/hubert-base-ls960",
-  "activation_dropout": 0.1,
+  "_name_or_path": "ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition",
+  "activation_dropout": 0.05,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
   "apply_spec_augment": true,
   "architectures": [
-    "HubertForSequenceClassification"
+    "Wav2Vec2ForSequenceClassification"
   ],
   "attention_dropout": 0.1,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
-  "conv_bias": false,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
   "conv_dim": [
     512,
     512,
@@ -36,21 +42,21 @@
     2,
     2
   ],
-  "ctc_loss_reduction": "sum",
-  "ctc_zero_infinity": false,
-  "do_stable_layer_norm": false,
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": true,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
   "eos_token_id": 2,
   "feat_extract_activation": "gelu",
   "feat_extract_dropout": 0.0,
-  "feat_extract_norm": "group",
-  "feat_proj_dropout": 0.1,
-  "feat_proj_layer_norm": true,
-  "final_dropout": 0.1,
-  "gradient_checkpointing": false,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "finetuning_task": "wav2vec2_clf",
   "hidden_act": "gelu",
-  "hidden_dropout": 0.1,
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_dropout": 0.05,
+  "hidden_size": 1024,
   "id2label": {
     "0": "fear",
     "1": "disgust",
@@ -61,7 +67,7 @@
     "6": "anger"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "label2id": {
     "anger": 6,
     "disgust": 1,
@@ -72,23 +78,60 @@
     "surprise": 5
   },
   "layer_norm_eps": 1e-05,
-  "layerdrop": 0.1,
+  "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",
   "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,
-  "model_type": "hubert",
-  "num_attention_heads": 12,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "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": 1024,
   "pad_token_id": 0,
-  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "pooling_mode": "mean",
+  "problem_type": "single_label_classification",
+  "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": "4.41.0",
   "use_weighted_layer_sum": false,
-  "vocab_size": 32
+  "vocab_size": 33,
+  "xvector_output_dim": 512
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2be729db0c0a9d317a313e7c83055d9e4839f0052eeb5108eebfe931bad26531
-size 378307092
+oid sha256:e13030356d116a5682cb4e7893224dea748adb1df8a1ecd75028d33e2d5720d6
+size 1262864444

preprocessor_config.json

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

runs/May23_07-58-57_129eb236cd1f/events.out.tfevents.1716451137.129eb236cd1f.495.18

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:134432549a9ebbf3769601746e6c24eada3650c2e79581e224a15df7aabc13de
-size 10239
+oid sha256:a19e1108ff57e95167bcec827442fbbca01729441cd73e10b9647bd07619bcbe
+size 11921

runs/May23_08-00-22_129eb236cd1f/events.out.tfevents.1716451223.129eb236cd1f.495.19

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3bb2bb71478c84c112d1a6fd31b263a3047b1dd067f09ed3fd9f06efeeaf38f
+size 7764

runs/May23_08-11-11_129eb236cd1f/events.out.tfevents.1716451871.129eb236cd1f.495.20

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7273e333cc75e8cabb1c6e0eb66d21f065f7fe7f4318a6db4253302b06e0b5ce
+size 7247

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bcf70745b70911eaf8a6824028bdd913cd064b2249e7e13b178119200c2be08
+oid sha256:7fb4714fbab23b42c15a5d8883917ec8d40a766bc5dc9764f1e1b89ac899cb92
 size 5112