Training in progress, step 500

config.json

@@ -0,0 +1,115 @@
+{
+  "_name_or_path": "facebook/wav2vec2-conformer-rel-pos-large",
+  "activation_dropout": 0.055,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": true,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ConformerForCTC"
+  ],
+  "attention_dropout": 0.094,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "conformer_conv_dropout": 0.1,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_depthwise_kernel_size": 31,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "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": "layer",
+  "feat_proj_dropout": 0.04,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "swish",
+  "hidden_dropout": 0.047,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.041,
+  "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_prob": 0.082,
+  "max_source_positions": 5000,
+  "model_type": "wav2vec2-conformer",
+  "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": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 33,
+  "position_embeddings_type": "relative",
+  "proj_codevector_dim": 768,
+  "rotary_embedding_base": 10000,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 34,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89799137e35a67cdc271dffed4f75c9534debda62c2435dd3b488ae2fabb555c
+size 2550221840

runs/Jan24_16-28-22_maxim-ubuntu3080/events.out.tfevents.1737725688.maxim-ubuntu3080

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2ea1290a086dcef738edd23e683df586246f3a901eaa762e359ca5bc81259ff
+size 6844

runs/Jan24_16-37-21_maxim-ubuntu3080/events.out.tfevents.1737726206.maxim-ubuntu3080

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:605e54afb1b1dc4bea4a70072d7de12f070683a3fcec5852d4e4c070caba096d
+size 7421

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91355e06f4a181c1a97b3437e0299bcbe35602d2b4ebc413f534ef43bf17852e
+size 5432