Training in progress, epoch 1

config.json

@@ -1,14 +1,14 @@
 {
-  "_name_or_path": "facebook/hubert-large-ls960-ft",
+  "_name_or_path": "ntu-spml/distilhubert",
   "activation_dropout": 0.1,
-  "apply_spec_augment": true,
+  "apply_spec_augment": false,
   "architectures": [
     "HubertForSequenceClassification"
   ],
   "attention_dropout": 0.1,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
-  "conv_bias": true,
+  "conv_bias": false,
   "conv_dim": [
     512,
     512,
@@ -38,20 +38,16 @@
   ],
   "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": 0.1,
-  "feat_proj_layer_norm": true,
-  "final_dropout": 0.1,
-  "gradient_checkpointing": false,
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "feat_proj_layer_norm": false,
+  "final_dropout": 0.0,
   "hidden_act": "gelu",
   "hidden_dropout": 0.1,
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "id2label": {
     "0": "artifact",
     "1": "extrahls",
@@ -60,7 +56,7 @@
     "4": "normal"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "label2id": {
     "artifact": "0",
     "extrahls": "1",
@@ -69,7 +65,7 @@
     "normal": "4"
   },
   "layer_norm_eps": 1e-05,
-  "layerdrop": 0.1,
+  "layerdrop": 0.0,
   "mask_feature_length": 10,
   "mask_feature_min_masks": 0,
   "mask_feature_prob": 0.0,
@@ -77,11 +73,11 @@
   "mask_time_min_masks": 2,
   "mask_time_prob": 0.05,
   "model_type": "hubert",
-  "num_attention_heads": 16,
+  "num_attention_heads": 12,
   "num_conv_pos_embedding_groups": 16,
   "num_conv_pos_embeddings": 128,
   "num_feat_extract_layers": 7,
-  "num_hidden_layers": 24,
+  "num_hidden_layers": 2,
   "pad_token_id": 0,
   "torch_dtype": "float32",
   "transformers_version": "4.39.3",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87c40d7bd08044657533c893f10043efa6c90754d943cff4a91e2d8716f79e33
-size 1262861548
+oid sha256:ed8f4697a374705ebaac113eb8c988956279739b3ed33145eae1ad542f976cdb
+size 94766588

runs/Apr04_09-11-37_c3596e20e628/events.out.tfevents.1712221898.c3596e20e628.396.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad16dc05bcd9e4d467b0baa096c30bf7a9c6f5fd4e032a2b6da2a672eca47faa
+size 4184

runs/Apr04_09-12-37_c3596e20e628/events.out.tfevents.1712221958.c3596e20e628.396.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:483c09dda4e2869cb3ac9e59525afdfaed4c1f9b5676309142488c25a1c8b6fa
+size 6151

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d368c116d8b964d9fbf10ed9ae06ffbb8e026dac22eb05fb22a2a1ddae91011d
+oid sha256:c77ff2404be05b6f335ae5dfa40ccbe4352a8ff85dbae7c99321651092bbc8c9
 size 4920