End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: facebook/wav2vec2-base
+base_model: facebook/hubert-large-ls960-ft
 tags:
 - generated_from_trainer
 metrics:
@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # my_awesome_mind_model
 
-This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
+This model is a fine-tuned version of [facebook/hubert-large-ls960-ft](https://huggingface.co/facebook/hubert-large-ls960-ft) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6163
-- Accuracy: 0.7019
+- Loss: 0.6493
+- Accuracy: 0.6923
 
 ## Model description
 
@@ -46,22 +46,16 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 10
+- num_epochs: 4
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| No log        | 0.9231 | 3    | 0.6815          | 0.6731   |
-| No log        | 1.8462 | 6    | 0.6297          | 0.7019   |
-| No log        | 2.7692 | 9    | 0.6117          | 0.7019   |
-| 0.6349        | 4.0    | 13   | 0.6194          | 0.7019   |
-| 0.6349        | 4.9231 | 16   | 0.6217          | 0.7019   |
-| 0.6349        | 5.8462 | 19   | 0.6178          | 0.7019   |
-| 0.5649        | 6.7692 | 22   | 0.6171          | 0.7019   |
-| 0.5649        | 8.0    | 26   | 0.6166          | 0.7019   |
-| 0.5649        | 8.9231 | 29   | 0.6163          | 0.7019   |
-| 0.5683        | 9.2308 | 30   | 0.6163          | 0.7019   |
+| No log        | 0.9231 | 3    | 0.6925          | 0.5577   |
+| No log        | 1.8462 | 6    | 0.6674          | 0.6923   |
+| No log        | 2.7692 | 9    | 0.6542          | 0.6923   |
+| 0.6693        | 3.6923 | 12   | 0.6493          | 0.6923   |
 
 
 ### Framework versions

config.json

@@ -1,20 +1,14 @@
 {
-  "_name_or_path": "facebook/wav2vec2-base",
-  "activation_dropout": 0.0,
-  "adapter_attn_dim": null,
-  "adapter_kernel_size": 3,
-  "adapter_stride": 2,
-  "add_adapter": false,
+  "_name_or_path": "facebook/hubert-large-ls960-ft",
+  "activation_dropout": 0.1,
   "apply_spec_augment": true,
   "architectures": [
-    "Wav2Vec2ForSequenceClassification"
+    "HubertForSequenceClassification"
   ],
   "attention_dropout": 0.1,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
-  "codevector_dim": 256,
-  "contrastive_logits_temperature": 0.1,
-  "conv_bias": false,
+  "conv_bias": true,
   "conv_dim": [
     512,
     512,
@@ -45,74 +39,38 @@
   "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,
+  "feat_proj_layer_norm": 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,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "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_codevector_groups": 2,
-  "num_codevectors_per_group": 320,
+  "model_type": "hubert",
+  "num_attention_heads": 16,
   "num_conv_pos_embedding_groups": 16,
   "num_conv_pos_embeddings": 128,
   "num_feat_extract_layers": 7,
-  "num_hidden_layers": 12,
-  "num_negatives": 100,
-  "output_hidden_size": 768,
+  "num_hidden_layers": 24,
   "pad_token_id": 0,
-  "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": "4.42.4",
   "use_weighted_layer_sum": false,
-  "vocab_size": 32,
-  "xvector_output_dim": 512
+  "vocab_size": 32
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b857c37f5a4bccfd3a6f43ed416e18e9a6269b4adff6b38ec013e829194b072
-size 378302360
+oid sha256:794fb6196ed8afae12389f2bb0aced39c92f0c144c376c8b162dfcc7fc67832d
+size 1262858456

runs/Jul30_13-01-22_d003cb5e3b97/events.out.tfevents.1722344484.d003cb5e3b97.325.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:373eb66a45b22d577eae59dc6e93d821a8c52948865d1718301b820d17b0d61b
+size 7558

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:608472ddb20d72e7430727dac3c32e1095c1d3f898f046a0a4b835ee06f81aa3
+oid sha256:16312f739d2d33f4d4e4dac7adc5f21989fa8bbac517e80be313e96b885ecd4b
 size 5112