Training in progress, step 600

config.json

@@ -0,0 +1,82 @@
+{
+  "_name_or_path": "facebook/w2v-bert-2.0",
+  "activation_dropout": 0.0,
+  "adapter_act": "relu",
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": true,
+  "apply_spec_augment": false,
+  "architectures": [
+    "Wav2Vec2BertForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 768,
+  "codevector_dim": 768,
+  "conformer_conv_dropout": 0.1,
+  "contrastive_logits_temperature": 0.1,
+  "conv_depthwise_kernel_size": 31,
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "eos_token_id": 2,
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "feature_projection_input_dim": 160,
+  "final_dropout": 0.1,
+  "hidden_act": "swish",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "left_max_position_embeddings": 64,
+  "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": 0.0,
+  "max_source_positions": 5000,
+  "model_type": "wav2vec2-bert",
+  "num_adapter_layers": 1,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 68,
+  "position_embeddings_type": "relative_key",
+  "proj_codevector_dim": 768,
+  "right_max_position_embeddings": 8,
+  "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
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.1",
+  "use_intermediate_ffn_before_adapter": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 71,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b68595530fa2529c47df5bcad95a7c0e1808495927fc43b0340651f2f37a0f2
+size 2423105660

runs/Feb20_15-05-44_hades-prod01/events.out.tfevents.1708442305.hades-prod01.2697338.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d85b10d26951621bb5ec66202db140cdcadf578d82ac6536ef926a8227ea326
+size 6794

runs/Feb20_17-18-41_hades-prod01/events.out.tfevents.1708450263.hades-prod01.2699575.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2446e7be01dd75629a5ce78cb6d18ae47d00dbf43f6f490e141d39cb5f1d8858
+size 6319

runs/Feb20_18-08-20_hades-prod01/events.out.tfevents.1708453270.hades-prod01.2700836.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d1a7b7781fe2d023a121857196ee83be7419e108ed1b6f20462b6a9b0c1823e
+size 8219

runs/Feb20_20-50-51_hades-prod01/events.out.tfevents.1708463094.hades-prod01.2705819.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebeaed4ece11b3630213273051cf810a61245d4b6c0632562dcc6b10a0ac7785
+size 6637

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84c8a0a457b119f96c3759b4fd28fd76ffc60fe4d9864d7a9eea207423dab39d
+size 4728