Training in progress, epoch 2

checkpoint-288/config.json

@@ -0,0 +1,115 @@
+{
+  "_name_or_path": "KBLab/wav2vec2-large-voxrex",
+  "activation_dropout": 0.15,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "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": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "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",
+  "mask_feature_length": 64,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.25,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.75,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "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": 31,
+  "proj_codevector_dim": 768,
+  "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": "4.17.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 34,
+  "xvector_output_dim": 512
+}

checkpoint-288/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42f57ed9d0a4d165b722097c7e48ce1ac613edbfadd0907fff55b40d4bd1bccf
+size 2490337809

checkpoint-288/preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

checkpoint-288/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93ae39ff149e15fe177c2e150a25cfc9f072552e2017ffd7b6a8d1279dd15fc9
+size 1262063089

checkpoint-288/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:475602465631a4931030bbbd028b9b723c4facaaf6da2a05896e8f45e62f7122
+size 14567

checkpoint-288/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b532e3e2079f715cfbdf8dff20c5229e40322f745e0bf21b549a7df613c6272
+size 559

checkpoint-288/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10400630f7820d2fb3ef57a6992b0c881c7c460e2b1b1feac781bd2acd901f6c
+size 623

checkpoint-288/trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9974025974025973,
+  "global_step": 288,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 18.22025489807129,
+      "eval_runtime": 188.3513,
+      "eval_samples_per_second": 26.785,
+      "eval_steps_per_second": 0.839,
+      "eval_wer": 1.0021133629565406,
+      "step": 96
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.5156249999999998e-06,
+      "loss": 15.219,
+      "step": 100
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 17.49703025817871,
+      "eval_runtime": 186.0672,
+      "eval_samples_per_second": 27.114,
+      "eval_steps_per_second": 0.849,
+      "eval_wer": 1.0,
+      "step": 192
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 3.0781249999999994e-06,
+      "loss": 14.7046,
+      "step": 200
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 11.056963920593262,
+      "eval_runtime": 184.9586,
+      "eval_samples_per_second": 27.276,
+      "eval_steps_per_second": 0.854,
+      "eval_wer": 1.0,
+      "step": 288
+    }
+  ],
+  "max_steps": 19200,
+  "num_train_epochs": 200,
+  "total_flos": 4.4736555276515287e+18,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-288/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e36b0de66081b1e60759283ec925cb14218ac8e4b7758178a38fee27a8df110c
+size 3055

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79f6d8e305217bd231434d4f3876128439d3b549ae7c4e6e165fb80da679e65c
+oid sha256:93ae39ff149e15fe177c2e150a25cfc9f072552e2017ffd7b6a8d1279dd15fc9
 size 1262063089