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 sha256:623862acf0ccc94122a296e6fbed8c9c4412e67661cd9ff9629e112a95188db3
+size 577789320

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:837edb13ef2872550b838a6ea5f0d2cb40fb544d3496b0c5a258791e7dfd19f4
+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 sha256:4831366ec1dbcb558f23d85b2403f0009413fae4ecc65be8d93f368ca0b82cd3
+size 14244

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8200c7911b70674e95f6ea3c4fd4f7c5a623c58e7efa3752996c3106e6a97146
+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": 0.4244868755340576,
+  "best_model_checkpoint": "mikhail-panzo/fil_b32_le5_s4000/checkpoint-2000",
+  "epoch": 44.44444444444444,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 4.398683071136475,
+      "learning_rate": 2.4500000000000004e-07,
+      "loss": 0.8108,
+      "step": 50
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 3.726436138153076,
+      "learning_rate": 4.95e-07,
+      "loss": 0.792,
+      "step": 100
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 2.0379676818847656,
+      "learning_rate": 7.450000000000001e-07,
+      "loss": 0.7413,
+      "step": 150
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 2.0460364818573,
+      "learning_rate": 9.950000000000002e-07,
+      "loss": 0.7342,
+      "step": 200
+    },
+    {
+      "epoch": 5.555555555555555,
+      "grad_norm": 2.803539276123047,
+      "learning_rate": 1.2450000000000002e-06,
+      "loss": 0.7147,
+      "step": 250
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 1.9818241596221924,
+      "learning_rate": 1.495e-06,
+      "loss": 0.7072,
+      "step": 300
+    },
+    {
+      "epoch": 7.777777777777778,
+      "grad_norm": 3.081399917602539,
+      "learning_rate": 1.745e-06,
+      "loss": 0.6843,
+      "step": 350
+    },
+    {
+      "epoch": 8.88888888888889,
+      "grad_norm": 2.4465785026550293,
+      "learning_rate": 1.9950000000000004e-06,
+      "loss": 0.657,
+      "step": 400
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 2.929323434829712,
+      "learning_rate": 2.245e-06,
+      "loss": 0.6597,
+      "step": 450
+    },
+    {
+      "epoch": 11.11111111111111,
+      "grad_norm": 1.419311285018921,
+      "learning_rate": 2.4950000000000003e-06,
+      "loss": 0.6246,
+      "step": 500
+    },
+    {
+      "epoch": 11.11111111111111,
+      "eval_loss": 0.5375720262527466,
+      "eval_runtime": 9.2568,
+      "eval_samples_per_second": 17.177,
+      "eval_steps_per_second": 2.161,
+      "step": 500
+    },
+    {
+      "epoch": 12.222222222222221,
+      "grad_norm": 2.3438374996185303,
+      "learning_rate": 2.7450000000000004e-06,
+      "loss": 0.6018,
+      "step": 550
+    },
+    {
+      "epoch": 13.333333333333334,
+      "grad_norm": 1.7441222667694092,
+      "learning_rate": 2.995e-06,
+      "loss": 0.5547,
+      "step": 600
+    },
+    {
+      "epoch": 14.444444444444445,
+      "grad_norm": 1.5592021942138672,
+      "learning_rate": 3.2450000000000003e-06,
+      "loss": 0.5466,
+      "step": 650
+    },
+    {
+      "epoch": 15.555555555555555,
+      "grad_norm": 1.305444359779358,
+      "learning_rate": 3.495e-06,
+      "loss": 0.535,
+      "step": 700
+    },
+    {
+      "epoch": 16.666666666666668,
+      "grad_norm": 2.2067477703094482,
+      "learning_rate": 3.745e-06,
+      "loss": 0.5343,
+      "step": 750
+    },
+    {
+      "epoch": 17.77777777777778,
+      "grad_norm": 1.667480707168579,
+      "learning_rate": 3.995000000000001e-06,
+      "loss": 0.5296,
+      "step": 800
+    },
+    {
+      "epoch": 18.88888888888889,
+      "grad_norm": 1.5465797185897827,
+      "learning_rate": 4.245e-06,
+      "loss": 0.5198,
+      "step": 850
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 2.760589361190796,
+      "learning_rate": 4.495e-06,
+      "loss": 0.5193,
+      "step": 900
+    },
+    {
+      "epoch": 21.11111111111111,
+      "grad_norm": 1.4570050239562988,
+      "learning_rate": 4.745e-06,
+      "loss": 0.5124,
+      "step": 950
+    },
+    {
+      "epoch": 22.22222222222222,
+      "grad_norm": 2.1914265155792236,
+      "learning_rate": 4.9950000000000005e-06,
+      "loss": 0.5034,
+      "step": 1000
+    },
+    {
+      "epoch": 22.22222222222222,
+      "eval_loss": 0.45661377906799316,
+      "eval_runtime": 9.2158,
+      "eval_samples_per_second": 17.253,
+      "eval_steps_per_second": 2.17,
+      "step": 1000
+    },
+    {
+      "epoch": 23.333333333333332,
+      "grad_norm": 1.941751480102539,
+      "learning_rate": 5.245e-06,
+      "loss": 0.5046,
+      "step": 1050
+    },
+    {
+      "epoch": 24.444444444444443,
+      "grad_norm": 1.9293475151062012,
+      "learning_rate": 5.495000000000001e-06,
+      "loss": 0.4948,
+      "step": 1100
+    },
+    {
+      "epoch": 25.555555555555557,
+      "grad_norm": 1.3278849124908447,
+      "learning_rate": 5.745000000000001e-06,
+      "loss": 0.4931,
+      "step": 1150
+    },
+    {
+      "epoch": 26.666666666666668,
+      "grad_norm": 1.1657841205596924,
+      "learning_rate": 5.995000000000001e-06,
+      "loss": 0.496,
+      "step": 1200
+    },
+    {
+      "epoch": 27.77777777777778,
+      "grad_norm": 1.8730145692825317,
+      "learning_rate": 6.245000000000001e-06,
+      "loss": 0.4939,
+      "step": 1250
+    },
+    {
+      "epoch": 28.88888888888889,
+      "grad_norm": 2.1156740188598633,
+      "learning_rate": 6.4950000000000005e-06,
+      "loss": 0.4908,
+      "step": 1300
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 1.799806833267212,
+      "learning_rate": 6.745000000000001e-06,
+      "loss": 0.4875,
+      "step": 1350
+    },
+    {
+      "epoch": 31.11111111111111,
+      "grad_norm": 1.762253761291504,
+      "learning_rate": 6.995000000000001e-06,
+      "loss": 0.4836,
+      "step": 1400
+    },
+    {
+      "epoch": 32.22222222222222,
+      "grad_norm": 1.305191993713379,
+      "learning_rate": 7.245000000000001e-06,
+      "loss": 0.4811,
+      "step": 1450
+    },
+    {
+      "epoch": 33.333333333333336,
+      "grad_norm": 1.5870022773742676,
+      "learning_rate": 7.495000000000001e-06,
+      "loss": 0.4807,
+      "step": 1500
+    },
+    {
+      "epoch": 33.333333333333336,
+      "eval_loss": 0.43601250648498535,
+      "eval_runtime": 9.5435,
+      "eval_samples_per_second": 16.66,
+      "eval_steps_per_second": 2.096,
+      "step": 1500
+    },
+    {
+      "epoch": 34.44444444444444,
+      "grad_norm": 2.632877826690674,
+      "learning_rate": 7.745e-06,
+      "loss": 0.4782,
+      "step": 1550
+    },
+    {
+      "epoch": 35.55555555555556,
+      "grad_norm": 1.3705276250839233,
+      "learning_rate": 7.995e-06,
+      "loss": 0.48,
+      "step": 1600
+    },
+    {
+      "epoch": 36.666666666666664,
+      "grad_norm": 1.9232587814331055,
+      "learning_rate": 8.245000000000002e-06,
+      "loss": 0.47,
+      "step": 1650
+    },
+    {
+      "epoch": 37.77777777777778,
+      "grad_norm": 1.3885018825531006,
+      "learning_rate": 8.495e-06,
+      "loss": 0.4711,
+      "step": 1700
+    },
+    {
+      "epoch": 38.888888888888886,
+      "grad_norm": 2.4857094287872314,
+      "learning_rate": 8.745000000000002e-06,
+      "loss": 0.4721,
+      "step": 1750
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 1.7662663459777832,
+      "learning_rate": 8.995000000000001e-06,
+      "loss": 0.4656,
+      "step": 1800
+    },
+    {
+      "epoch": 41.111111111111114,
+      "grad_norm": 1.906548261642456,
+      "learning_rate": 9.245e-06,
+      "loss": 0.463,
+      "step": 1850
+    },
+    {
+      "epoch": 42.22222222222222,
+      "grad_norm": 1.7204883098602295,
+      "learning_rate": 9.495000000000001e-06,
+      "loss": 0.4592,
+      "step": 1900
+    },
+    {
+      "epoch": 43.333333333333336,
+      "grad_norm": 1.3313167095184326,
+      "learning_rate": 9.745e-06,
+      "loss": 0.4581,
+      "step": 1950
+    },
+    {
+      "epoch": 44.44444444444444,
+      "grad_norm": 1.94256591796875,
+      "learning_rate": 9.995000000000002e-06,
+      "loss": 0.4582,
+      "step": 2000
+    },
+    {
+      "epoch": 44.44444444444444,
+      "eval_loss": 0.4244868755340576,
+      "eval_runtime": 9.1316,
+      "eval_samples_per_second": 17.412,
+      "eval_steps_per_second": 2.19,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 4000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 89,
+  "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": 1.3753846024576416e+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 sha256:05b7ecdded947540b9670cedf7cfe87afc7199b237efb642b915ffbb505d51dc
+size 5304