Training in progress, epoch 0

config.json

@@ -1,6 +1,6 @@
 {
-  "_name_or_path": "facebook/wav2vec2-base",
-  "activation_dropout": 0.0,
+  "_name_or_path": "philschmid/tiny-random-wav2vec2",
+  "activation_dropout": 0.1,
   "adapter_attn_dim": null,
   "adapter_kernel_size": 3,
   "adapter_stride": 2,
@@ -16,46 +16,36 @@
   "contrastive_logits_temperature": 0.1,
   "conv_bias": false,
   "conv_dim": [
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512
+    32,
+    32,
+    32
   ],
   "conv_kernel": [
-    10,
-    3,
-    3,
-    3,
-    3,
-    2,
-    2
+    8,
+    8,
+    8
   ],
   "conv_stride": [
-    5,
-    2,
-    2,
-    2,
-    2,
-    2,
-    2
+    4,
+    4,
+    4
   ],
   "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": 16,
   "id2label": {
     "0": "onboard",
     "1": "restock",
@@ -63,7 +53,7 @@
     "3": "unknown"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 20,
   "label2id": {
     "onboard": "0",
     "restock": "1",
@@ -71,34 +61,24 @@
     "unknown": "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": 2,
   "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_negatives": 100,
-  "output_hidden_size": 768,
+  "num_conv_pos_embedding_groups": 2,
+  "num_conv_pos_embeddings": 16,
+  "num_feat_extract_layers": 3,
+  "num_hidden_layers": 4,
+  "num_negatives": 10,
+  "output_hidden_size": 16,
   "pad_token_id": 0,
   "proj_codevector_dim": 256,
   "tdnn_dilation": [

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e9ed4f5e94a596372b2f2fd457e1cfb0aaafdb832ee7814d19e36a5d5115513
-size 378304424
+oid sha256:c4c199ab34489746f64085e96141492d91b2415ca067c2bfc83fe8486ac4e3e7
+size 138672

runs/Feb26_13-00-50_voice-ai-transformer/events.out.tfevents.1708952455.voice-ai-transformer.3518198.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ca1c6c18bf791dd2f136abba3c0614a48298451681aedaa7bc22c54b5561588
-size 7928
+oid sha256:891a3a496420a669f2289327ac3c9fa0d18dcc2880758239cc30328e177570ec
+size 8593

runs/Feb27_07-19-49_voice-ai-transformer/events.out.tfevents.1709018394.voice-ai-transformer.4760.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b79879d4f5faec0b7462598522aec47e316b9240345bc60fe42f56cc97823933
+size 6411

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dc8ee50303ed57afdf03b2ce7d1329a797b2a4c58c91b48aa30cbe352e6e234
+oid sha256:9b9addbffbe04146ab12777b9051ab2a10056df69a826b9998a90b17019190a3
 size 4920