Training in progress, step 1500, checkpoint

checkpoint-1500/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<ctc_blank>": 80,
+  "<mask>": 79
+}

checkpoint-1500/config.json

@@ -0,0 +1,92 @@
+{
+  "_name_or_path": "microsoft/speecht5_tts",
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "SpeechT5ForTextToSpeech"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "conv_bias": false,
+  "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
+  ],
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.1,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.1,
+  "encoder_layers": 12,
+  "encoder_max_relative_position": 160,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "guided_attention_loss_num_heads": 2,
+  "guided_attention_loss_scale": 10.0,
+  "guided_attention_loss_sigma": 0.4,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "is_encoder_decoder": true,
+  "layer_norm_eps": 1e-05,
+  "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": 0.05,
+  "max_length": 1876,
+  "max_speech_positions": 1876,
+  "max_text_positions": 600,
+  "model_type": "speecht5",
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_mel_bins": 80,
+  "pad_token_id": 1,
+  "positional_dropout": 0.1,
+  "reduction_factor": 2,
+  "scale_embedding": false,
+  "speaker_embedding_dim": 512,
+  "speech_decoder_postnet_dropout": 0.5,
+  "speech_decoder_postnet_kernel": 5,
+  "speech_decoder_postnet_layers": 5,
+  "speech_decoder_postnet_units": 256,
+  "speech_decoder_prenet_dropout": 0.5,
+  "speech_decoder_prenet_layers": 2,
+  "speech_decoder_prenet_units": 256,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0.dev0",
+  "use_cache": false,
+  "use_guided_attention_loss": true,
+  "vocab_size": 81
+}

checkpoint-1500/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "max_length": 1876,
+  "pad_token_id": 1,
+  "transformers_version": "4.41.0.dev0"
+}

checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f03927c1fec5c7dcfb137a20346d4cf70e6192fa2af451e87aa531d10c966409
+size 577789320

checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9256ddf256d7dd8f2e696eceed817902e3642c3b632b239edba13788fab918f5
+size 1155772233

checkpoint-1500/preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "do_normalize": false,
+  "feature_extractor_type": "SpeechT5FeatureExtractor",
+  "feature_size": 1,
+  "fmax": 7600,
+  "fmin": 80,
+  "frame_signal_scale": 1.0,
+  "hop_length": 16,
+  "mel_floor": 1e-10,
+  "num_mel_bins": 80,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "SpeechT5Processor",
+  "reduction_factor": 2,
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "win_function": "hann_window",
+  "win_length": 64
+}

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1e1a20b6d8b0b1cca26017ea117d57d5f1cb7dd2a461d253d09522b5d831739
+size 14244

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db7cce94191358964e35b668c9bdb6e486f8a8bf168079d634ab7bccc775845b
+size 1064

checkpoint-1500/special_tokens_map.json

@@ -0,0 +1,13 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

checkpoint-1500/spm_char.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fcc48f3e225f627b1641db410ceb0c8649bd2b0c982e150b03f8be3728ab560
+size 238473

checkpoint-1500/tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "79": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "80": {
+      "content": "<ctc_blank>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 600,
+  "normalize": false,
+  "pad_token": "<pad>",
+  "processor_class": "SpeechT5Processor",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "SpeechT5Tokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-1500/trainer_state.json

@@ -0,0 +1,267 @@
+{
+  "best_metric": 0.42913728952407837,
+  "best_model_checkpoint": "mikhail-panzo/fil_b32_le5_s8000/checkpoint-1500",
+  "epoch": 33.333333333333336,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 3.579704523086548,
+      "learning_rate": 2.4500000000000004e-07,
+      "loss": 0.8282,
+      "step": 50
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 2.0918073654174805,
+      "learning_rate": 4.95e-07,
+      "loss": 0.7857,
+      "step": 100
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 1.283610224723816,
+      "learning_rate": 7.450000000000001e-07,
+      "loss": 0.7356,
+      "step": 150
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 1.5381903648376465,
+      "learning_rate": 9.950000000000002e-07,
+      "loss": 0.7606,
+      "step": 200
+    },
+    {
+      "epoch": 5.555555555555555,
+      "grad_norm": 1.613647222518921,
+      "learning_rate": 1.2450000000000002e-06,
+      "loss": 0.7314,
+      "step": 250
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 2.6762027740478516,
+      "learning_rate": 1.495e-06,
+      "loss": 0.6933,
+      "step": 300
+    },
+    {
+      "epoch": 7.777777777777778,
+      "grad_norm": 2.667527675628662,
+      "learning_rate": 1.745e-06,
+      "loss": 0.6863,
+      "step": 350
+    },
+    {
+      "epoch": 8.88888888888889,
+      "grad_norm": 1.9682470560073853,
+      "learning_rate": 1.9950000000000004e-06,
+      "loss": 0.6649,
+      "step": 400
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 2.0042927265167236,
+      "learning_rate": 2.245e-06,
+      "loss": 0.6507,
+      "step": 450
+    },
+    {
+      "epoch": 11.11111111111111,
+      "grad_norm": 2.6399147510528564,
+      "learning_rate": 2.4950000000000003e-06,
+      "loss": 0.632,
+      "step": 500
+    },
+    {
+      "epoch": 11.11111111111111,
+      "eval_loss": 0.5323343276977539,
+      "eval_runtime": 7.6175,
+      "eval_samples_per_second": 20.873,
+      "eval_steps_per_second": 2.626,
+      "step": 500
+    },
+    {
+      "epoch": 12.222222222222221,
+      "grad_norm": 2.593517780303955,
+      "learning_rate": 2.7450000000000004e-06,
+      "loss": 0.5956,
+      "step": 550
+    },
+    {
+      "epoch": 13.333333333333334,
+      "grad_norm": 5.524081707000732,
+      "learning_rate": 2.99e-06,
+      "loss": 0.577,
+      "step": 600
+    },
+    {
+      "epoch": 14.444444444444445,
+      "grad_norm": 2.2165024280548096,
+      "learning_rate": 3.2400000000000003e-06,
+      "loss": 0.5614,
+      "step": 650
+    },
+    {
+      "epoch": 15.555555555555555,
+      "grad_norm": 2.4440901279449463,
+      "learning_rate": 3.49e-06,
+      "loss": 0.5654,
+      "step": 700
+    },
+    {
+      "epoch": 16.666666666666668,
+      "grad_norm": 1.8401445150375366,
+      "learning_rate": 3.74e-06,
+      "loss": 0.5329,
+      "step": 750
+    },
+    {
+      "epoch": 17.77777777777778,
+      "grad_norm": 2.101787567138672,
+      "learning_rate": 3.990000000000001e-06,
+      "loss": 0.5293,
+      "step": 800
+    },
+    {
+      "epoch": 18.88888888888889,
+      "grad_norm": 2.1338887214660645,
+      "learning_rate": 4.24e-06,
+      "loss": 0.5345,
+      "step": 850
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 1.8499983549118042,
+      "learning_rate": 4.49e-06,
+      "loss": 0.5148,
+      "step": 900
+    },
+    {
+      "epoch": 21.11111111111111,
+      "grad_norm": 1.3982588052749634,
+      "learning_rate": 4.74e-06,
+      "loss": 0.5085,
+      "step": 950
+    },
+    {
+      "epoch": 22.22222222222222,
+      "grad_norm": 1.7611488103866577,
+      "learning_rate": 4.9900000000000005e-06,
+      "loss": 0.519,
+      "step": 1000
+    },
+    {
+      "epoch": 22.22222222222222,
+      "eval_loss": 0.4493897557258606,
+      "eval_runtime": 7.4167,
+      "eval_samples_per_second": 21.438,
+      "eval_steps_per_second": 2.697,
+      "step": 1000
+    },
+    {
+      "epoch": 23.333333333333332,
+      "grad_norm": 2.625955581665039,
+      "learning_rate": 5.240000000000001e-06,
+      "loss": 0.5194,
+      "step": 1050
+    },
+    {
+      "epoch": 24.444444444444443,
+      "grad_norm": 1.75005304813385,
+      "learning_rate": 5.490000000000001e-06,
+      "loss": 0.5152,
+      "step": 1100
+    },
+    {
+      "epoch": 25.555555555555557,
+      "grad_norm": 2.279965877532959,
+      "learning_rate": 5.74e-06,
+      "loss": 0.5129,
+      "step": 1150
+    },
+    {
+      "epoch": 26.666666666666668,
+      "grad_norm": 1.5506455898284912,
+      "learning_rate": 5.99e-06,
+      "loss": 0.4941,
+      "step": 1200
+    },
+    {
+      "epoch": 27.77777777777778,
+      "grad_norm": 1.830841064453125,
+      "learning_rate": 6.24e-06,
+      "loss": 0.4899,
+      "step": 1250
+    },
+    {
+      "epoch": 28.88888888888889,
+      "grad_norm": 2.0044639110565186,
+      "learning_rate": 6.4900000000000005e-06,
+      "loss": 0.496,
+      "step": 1300
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 2.272815465927124,
+      "learning_rate": 6.740000000000001e-06,
+      "loss": 0.4906,
+      "step": 1350
+    },
+    {
+      "epoch": 31.11111111111111,
+      "grad_norm": 1.460723638534546,
+      "learning_rate": 6.99e-06,
+      "loss": 0.4741,
+      "step": 1400
+    },
+    {
+      "epoch": 32.22222222222222,
+      "grad_norm": 1.7440383434295654,
+      "learning_rate": 7.24e-06,
+      "loss": 0.4821,
+      "step": 1450
+    },
+    {
+      "epoch": 33.333333333333336,
+      "grad_norm": 1.4221312999725342,
+      "learning_rate": 7.49e-06,
+      "loss": 0.4816,
+      "step": 1500
+    },
+    {
+      "epoch": 33.333333333333336,
+      "eval_loss": 0.42913728952407837,
+      "eval_runtime": 7.4808,
+      "eval_samples_per_second": 21.254,
+      "eval_steps_per_second": 2.674,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 8000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 178,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0948113803068992e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70dc8ff0b9ee1e39c11744f3f465fa7827340809211f65e49044646e382493d5
+size 5304