Training in progress, step 2000, checkpoint

checkpoint-2000/added_tokens.json

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

checkpoint-2000/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-2000/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-2000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0c8f5b32c687bd53bc4ce9ea7818906c0640a0fea1f1134e1265d7283024351
+size 577789320

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:568b42c3dd09575c27acf7b76f3f6c5fe38096b4980fdd3f9c15b3a347e0e1ee
+size 1155772233

checkpoint-2000/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-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29f95d014b9a7d709e9dad7458e54a05d22eb3513f2509c81aa7d39a4b11d5a0
+size 14244

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8783e57a31b124d6f5826c660447eec50404d16f56236672fa6da5352303f235
+size 1064

checkpoint-2000/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-2000/spm_char.model

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

checkpoint-2000/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-2000/trainer_state.json

@@ -0,0 +1,345 @@
+{
+  "best_metric": 0.43401163816452026,
+  "best_model_checkpoint": "mikhail-panzo/fil_b64_le3_s4000/checkpoint-500",
+  "epoch": 88.88888888888889,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 2.2609777450561523,
+      "learning_rate": 2.5e-05,
+      "loss": 0.7231,
+      "step": 50
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 1.939948320388794,
+      "learning_rate": 5e-05,
+      "loss": 0.575,
+      "step": 100
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 2.9677317142486572,
+      "learning_rate": 7.5e-05,
+      "loss": 0.5207,
+      "step": 150
+    },
+    {
+      "epoch": 8.88888888888889,
+      "grad_norm": 4.588547706604004,
+      "learning_rate": 0.0001,
+      "loss": 0.4996,
+      "step": 200
+    },
+    {
+      "epoch": 11.11111111111111,
+      "grad_norm": 1.8626277446746826,
+      "learning_rate": 0.000125,
+      "loss": 0.4881,
+      "step": 250
+    },
+    {
+      "epoch": 13.333333333333334,
+      "grad_norm": 3.4871737957000732,
+      "learning_rate": 0.00015,
+      "loss": 0.4729,
+      "step": 300
+    },
+    {
+      "epoch": 15.555555555555555,
+      "grad_norm": 3.5084946155548096,
+      "learning_rate": 0.000175,
+      "loss": 0.4661,
+      "step": 350
+    },
+    {
+      "epoch": 17.77777777777778,
+      "grad_norm": 7.88467264175415,
+      "learning_rate": 0.0002,
+      "loss": 0.4925,
+      "step": 400
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 4.796986103057861,
+      "learning_rate": 0.00022500000000000002,
+      "loss": 0.4899,
+      "step": 450
+    },
+    {
+      "epoch": 22.22222222222222,
+      "grad_norm": 6.419567584991455,
+      "learning_rate": 0.00025,
+      "loss": 0.4644,
+      "step": 500
+    },
+    {
+      "epoch": 22.22222222222222,
+      "eval_loss": 0.43401163816452026,
+      "eval_runtime": 17.3691,
+      "eval_samples_per_second": 9.154,
+      "eval_steps_per_second": 1.151,
+      "step": 500
+    },
+    {
+      "epoch": 24.444444444444443,
+      "grad_norm": 2.6020901203155518,
+      "learning_rate": 0.000275,
+      "loss": 0.4492,
+      "step": 550
+    },
+    {
+      "epoch": 26.666666666666668,
+      "grad_norm": 7.353488445281982,
+      "learning_rate": 0.0003,
+      "loss": 0.4556,
+      "step": 600
+    },
+    {
+      "epoch": 28.88888888888889,
+      "grad_norm": 4.736776351928711,
+      "learning_rate": 0.00032500000000000004,
+      "loss": 0.4669,
+      "step": 650
+    },
+    {
+      "epoch": 31.11111111111111,
+      "grad_norm": 7.411691665649414,
+      "learning_rate": 0.00035,
+      "loss": 0.4892,
+      "step": 700
+    },
+    {
+      "epoch": 33.333333333333336,
+      "grad_norm": 5.571273326873779,
+      "learning_rate": 0.000375,
+      "loss": 0.4858,
+      "step": 750
+    },
+    {
+      "epoch": 35.55555555555556,
+      "grad_norm": 7.498672008514404,
+      "learning_rate": 0.0004,
+      "loss": 0.4929,
+      "step": 800
+    },
+    {
+      "epoch": 37.77777777777778,
+      "grad_norm": 6.763402462005615,
+      "learning_rate": 0.000425,
+      "loss": 0.4874,
+      "step": 850
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 3.335564136505127,
+      "learning_rate": 0.00045000000000000004,
+      "loss": 0.513,
+      "step": 900
+    },
+    {
+      "epoch": 42.22222222222222,
+      "grad_norm": 3.1004624366760254,
+      "learning_rate": 0.000475,
+      "loss": 0.4882,
+      "step": 950
+    },
+    {
+      "epoch": 44.44444444444444,
+      "grad_norm": 10.330741882324219,
+      "learning_rate": 0.0005,
+      "loss": 0.6468,
+      "step": 1000
+    },
+    {
+      "epoch": 44.44444444444444,
+      "eval_loss": 0.753709614276886,
+      "eval_runtime": 16.7842,
+      "eval_samples_per_second": 9.473,
+      "eval_steps_per_second": 1.192,
+      "step": 1000
+    },
+    {
+      "epoch": 46.666666666666664,
+      "grad_norm": 0.7254169583320618,
+      "learning_rate": 0.0005245,
+      "loss": 1.8403,
+      "step": 1050
+    },
+    {
+      "epoch": 48.888888888888886,
+      "grad_norm": 0.14719372987747192,
+      "learning_rate": 0.0005495,
+      "loss": 1.6103,
+      "step": 1100
+    },
+    {
+      "epoch": 51.111111111111114,
+      "grad_norm": 0.2177058607339859,
+      "learning_rate": 0.0005745,
+      "loss": 1.5878,
+      "step": 1150
+    },
+    {
+      "epoch": 53.333333333333336,
+      "grad_norm": 0.20293082296848297,
+      "learning_rate": 0.0005995000000000001,
+      "loss": 1.5825,
+      "step": 1200
+    },
+    {
+      "epoch": 55.55555555555556,
+      "grad_norm": 0.07884251326322556,
+      "learning_rate": 0.0006245000000000001,
+      "loss": 1.5827,
+      "step": 1250
+    },
+    {
+      "epoch": 57.77777777777778,
+      "grad_norm": 0.2063368558883667,
+      "learning_rate": 0.0006495,
+      "loss": 1.5858,
+      "step": 1300
+    },
+    {
+      "epoch": 60.0,
+      "grad_norm": 0.21431827545166016,
+      "learning_rate": 0.0006745,
+      "loss": 1.5811,
+      "step": 1350
+    },
+    {
+      "epoch": 62.22222222222222,
+      "grad_norm": 0.23930463194847107,
+      "learning_rate": 0.0006995,
+      "loss": 1.588,
+      "step": 1400
+    },
+    {
+      "epoch": 64.44444444444444,
+      "grad_norm": 0.1440805047750473,
+      "learning_rate": 0.0007245000000000001,
+      "loss": 1.5773,
+      "step": 1450
+    },
+    {
+      "epoch": 66.66666666666667,
+      "grad_norm": 0.18511304259300232,
+      "learning_rate": 0.0007495000000000001,
+      "loss": 1.5805,
+      "step": 1500
+    },
+    {
+      "epoch": 66.66666666666667,
+      "eval_loss": 1.5452969074249268,
+      "eval_runtime": 9.5395,
+      "eval_samples_per_second": 16.668,
+      "eval_steps_per_second": 2.097,
+      "step": 1500
+    },
+    {
+      "epoch": 68.88888888888889,
+      "grad_norm": 0.1333579570055008,
+      "learning_rate": 0.0007745,
+      "loss": 1.5895,
+      "step": 1550
+    },
+    {
+      "epoch": 71.11111111111111,
+      "grad_norm": 0.24500781297683716,
+      "learning_rate": 0.0007995,
+      "loss": 1.5823,
+      "step": 1600
+    },
+    {
+      "epoch": 73.33333333333333,
+      "grad_norm": 0.16170234978199005,
+      "learning_rate": 0.0008245,
+      "loss": 1.5798,
+      "step": 1650
+    },
+    {
+      "epoch": 75.55555555555556,
+      "grad_norm": 0.14667277038097382,
+      "learning_rate": 0.0008495000000000001,
+      "loss": 1.5756,
+      "step": 1700
+    },
+    {
+      "epoch": 77.77777777777777,
+      "grad_norm": 0.12401594966650009,
+      "learning_rate": 0.0008745000000000001,
+      "loss": 1.5832,
+      "step": 1750
+    },
+    {
+      "epoch": 80.0,
+      "grad_norm": 0.10182458907365799,
+      "learning_rate": 0.0008995,
+      "loss": 1.5767,
+      "step": 1800
+    },
+    {
+      "epoch": 82.22222222222223,
+      "grad_norm": 0.11051663756370544,
+      "learning_rate": 0.0009245,
+      "loss": 1.5745,
+      "step": 1850
+    },
+    {
+      "epoch": 84.44444444444444,
+      "grad_norm": 0.2343149483203888,
+      "learning_rate": 0.0009495,
+      "loss": 1.5828,
+      "step": 1900
+    },
+    {
+      "epoch": 86.66666666666667,
+      "grad_norm": 0.07052835822105408,
+      "learning_rate": 0.0009745000000000001,
+      "loss": 1.5747,
+      "step": 1950
+    },
+    {
+      "epoch": 88.88888888888889,
+      "grad_norm": 0.044963087886571884,
+      "learning_rate": 0.0009995000000000002,
+      "loss": 1.5766,
+      "step": 2000
+    },
+    {
+      "epoch": 88.88888888888889,
+      "eval_loss": 1.5454070568084717,
+      "eval_runtime": 9.1426,
+      "eval_samples_per_second": 17.391,
+      "eval_steps_per_second": 2.188,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 4000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 182,
+  "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": 2.7514700481606624e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a62a7b57fd4ad564bf2c2631b9df0ee7470d15ec87f0d53590f554a2c091aaf5
+size 5304