Training in progress, epoch 0

config.json

@@ -1,6 +1,6 @@
 {
-  "_name_or_path": "facebook/wav2vec2-base",
-  "activation_dropout": 0.0,
+  "_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,
@@ -14,7 +14,7 @@
   "classifier_proj_size": 256,
   "codevector_dim": 256,
   "contrastive_logits_temperature": 0.1,
-  "conv_bias": false,
+  "conv_bias": true,
   "conv_dim": [
     512,
     512,
@@ -42,20 +42,21 @@
     2,
     2
   ],
-  "ctc_loss_reduction": "sum",
-  "ctc_zero_infinity": false,
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": true,
   "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_proj_dropout": 0.1,
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.05,
   "feat_quantizer_dropout": 0.0,
   "final_dropout": 0.0,
-  "freeze_feat_extract_train": true,
+  "finetuning_task": "wav2vec2_clf",
   "hidden_act": "gelu",
-  "hidden_dropout": 0.1,
-  "hidden_size": 768,
+  "hidden_dropout": 0.05,
+  "hidden_size": 1024,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -64,7 +65,7 @@
     "4": "LABEL_4"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -73,7 +74,7 @@
     "LABEL_4": 4
   },
   "layer_norm_eps": 1e-05,
-  "layerdrop": 0.0,
+  "layerdrop": 0.05,
   "mask_channel_length": 10,
   "mask_channel_min_space": 1,
   "mask_channel_other": 0.0,
@@ -89,19 +90,19 @@
   "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,
+  "pooling_mode": "mean",
+  "problem_type": "single_label_classification",
   "proj_codevector_dim": 256,
   "tdnn_dilation": [
     1,
@@ -127,6 +128,6 @@
   "torch_dtype": "float32",
   "transformers_version": "4.40.0",
   "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 sha256:522cf1d3fb5ee0725b2f9465440f7f7150f58dcd6ec2880895c1957c469bacaa
-size 378305452
+oid sha256:f1ae6af95b62cf8b109a1c382194feefeeaea383e801d2e92939557959ba49fb
+size 1262862388

runs/Apr28_07-58-47_b5746c66e412/events.out.tfevents.1714291128.b5746c66e412.160.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8d844b04c891ecf31d2767de2bf36576a4ff656973888a7115f6bccd1022e5d
+size 7499

runs/Apr28_08-02-07_b5746c66e412/events.out.tfevents.1714291328.b5746c66e412.160.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d9f4da586970b0f9138a1a0d41a4e5c2af3ed8807c2fbecfc08d3870db3ac2b
+size 10533

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6cbfdef2fd69c7a6c8ed59bc72eeb89f33d25c6ed41822e7f416a99038ce2f2
+oid sha256:176571e02090ef4d8806f0912a9d9b7cf5160767829ca8bbbec4e33d13475044
 size 4984