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 sha256:8a2d22705d05bdaf7fea8a64b8cb313073d0842934229ee4859d365e87441977
+size 577789320

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b72fd74c265a86882698ca3413a2a9bf561bda7a5997ee082f28df528785916a
+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 sha256:07f9d9f435d3c61f9608fdd7c6e899a079d459772956d24eb31c835e13edbeac
+size 14244

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c80c8e2c0fbabc84d89c4193643e2f4bc3d422e71a44772596207e214e74273d
+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": 0.4463141858577728,
+  "best_model_checkpoint": "mikhail-panzo/fil_b32_le3_s4000/checkpoint-500",
+  "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": 3.548590898513794,
+      "learning_rate": 2.5e-05,
+      "loss": 0.7354,
+      "step": 50
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 5.517350196838379,
+      "learning_rate": 4.9500000000000004e-05,
+      "loss": 0.5892,
+      "step": 100
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 4.143002033233643,
+      "learning_rate": 7.45e-05,
+      "loss": 0.532,
+      "step": 150
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 6.414477825164795,
+      "learning_rate": 9.95e-05,
+      "loss": 0.5284,
+      "step": 200
+    },
+    {
+      "epoch": 5.555555555555555,
+      "grad_norm": 2.265143394470215,
+      "learning_rate": 0.0001245,
+      "loss": 0.517,
+      "step": 250
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 4.954311847686768,
+      "learning_rate": 0.0001495,
+      "loss": 0.5295,
+      "step": 300
+    },
+    {
+      "epoch": 7.777777777777778,
+      "grad_norm": 2.5993571281433105,
+      "learning_rate": 0.00017449999999999999,
+      "loss": 0.517,
+      "step": 350
+    },
+    {
+      "epoch": 8.88888888888889,
+      "grad_norm": 3.27908992767334,
+      "learning_rate": 0.00019950000000000002,
+      "loss": 0.4939,
+      "step": 400
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 4.22811222076416,
+      "learning_rate": 0.0002245,
+      "loss": 0.5043,
+      "step": 450
+    },
+    {
+      "epoch": 11.11111111111111,
+      "grad_norm": 2.7051336765289307,
+      "learning_rate": 0.0002495,
+      "loss": 0.5028,
+      "step": 500
+    },
+    {
+      "epoch": 11.11111111111111,
+      "eval_loss": 0.4463141858577728,
+      "eval_runtime": 16.8864,
+      "eval_samples_per_second": 9.416,
+      "eval_steps_per_second": 1.184,
+      "step": 500
+    },
+    {
+      "epoch": 12.222222222222221,
+      "grad_norm": 3.0811643600463867,
+      "learning_rate": 0.0002745,
+      "loss": 0.545,
+      "step": 550
+    },
+    {
+      "epoch": 13.333333333333334,
+      "grad_norm": 7.707492828369141,
+      "learning_rate": 0.0002995,
+      "loss": 0.4979,
+      "step": 600
+    },
+    {
+      "epoch": 14.444444444444445,
+      "grad_norm": 5.85659122467041,
+      "learning_rate": 0.00032450000000000003,
+      "loss": 0.4916,
+      "step": 650
+    },
+    {
+      "epoch": 15.555555555555555,
+      "grad_norm": 8.300439834594727,
+      "learning_rate": 0.0003495,
+      "loss": 0.5112,
+      "step": 700
+    },
+    {
+      "epoch": 16.666666666666668,
+      "grad_norm": 10.664773941040039,
+      "learning_rate": 0.0003745,
+      "loss": 0.5312,
+      "step": 750
+    },
+    {
+      "epoch": 17.77777777777778,
+      "grad_norm": 6.4097161293029785,
+      "learning_rate": 0.0003995,
+      "loss": 0.6087,
+      "step": 800
+    },
+    {
+      "epoch": 18.88888888888889,
+      "grad_norm": 5.435739994049072,
+      "learning_rate": 0.0004245,
+      "loss": 0.6127,
+      "step": 850
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 7.4649834632873535,
+      "learning_rate": 0.00044950000000000003,
+      "loss": 0.6904,
+      "step": 900
+    },
+    {
+      "epoch": 21.11111111111111,
+      "grad_norm": 10.81910228729248,
+      "learning_rate": 0.0004745,
+      "loss": 0.6948,
+      "step": 950
+    },
+    {
+      "epoch": 22.22222222222222,
+      "grad_norm": 4.4550886154174805,
+      "learning_rate": 0.0004995,
+      "loss": 0.6348,
+      "step": 1000
+    },
+    {
+      "epoch": 22.22222222222222,
+      "eval_loss": 0.5990382432937622,
+      "eval_runtime": 9.0191,
+      "eval_samples_per_second": 17.629,
+      "eval_steps_per_second": 2.218,
+      "step": 1000
+    },
+    {
+      "epoch": 23.333333333333332,
+      "grad_norm": 3.101961374282837,
+      "learning_rate": 0.0005245,
+      "loss": 0.6609,
+      "step": 1050
+    },
+    {
+      "epoch": 24.444444444444443,
+      "grad_norm": 5.606886386871338,
+      "learning_rate": 0.0005495,
+      "loss": 0.6128,
+      "step": 1100
+    },
+    {
+      "epoch": 25.555555555555557,
+      "grad_norm": 3.7152516841888428,
+      "learning_rate": 0.0005745,
+      "loss": 0.6197,
+      "step": 1150
+    },
+    {
+      "epoch": 26.666666666666668,
+      "grad_norm": 2.9999840259552,
+      "learning_rate": 0.0005995000000000001,
+      "loss": 0.6346,
+      "step": 1200
+    },
+    {
+      "epoch": 27.77777777777778,
+      "grad_norm": 3.5235953330993652,
+      "learning_rate": 0.0006245000000000001,
+      "loss": 0.6246,
+      "step": 1250
+    },
+    {
+      "epoch": 28.88888888888889,
+      "grad_norm": 3.9665956497192383,
+      "learning_rate": 0.0006495,
+      "loss": 0.6143,
+      "step": 1300
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 2.920466661453247,
+      "learning_rate": 0.000674,
+      "loss": 0.6245,
+      "step": 1350
+    },
+    {
+      "epoch": 31.11111111111111,
+      "grad_norm": 16.839616775512695,
+      "learning_rate": 0.000699,
+      "loss": 0.8179,
+      "step": 1400
+    },
+    {
+      "epoch": 32.22222222222222,
+      "grad_norm": 0.23306678235530853,
+      "learning_rate": 0.0007235000000000001,
+      "loss": 1.8511,
+      "step": 1450
+    },
+    {
+      "epoch": 33.333333333333336,
+      "grad_norm": 0.6476005911827087,
+      "learning_rate": 0.000748,
+      "loss": 1.7172,
+      "step": 1500
+    },
+    {
+      "epoch": 33.333333333333336,
+      "eval_loss": 1.566503882408142,
+      "eval_runtime": 8.82,
+      "eval_samples_per_second": 18.027,
+      "eval_steps_per_second": 2.268,
+      "step": 1500
+    },
+    {
+      "epoch": 34.44444444444444,
+      "grad_norm": 0.22506840527057648,
+      "learning_rate": 0.000773,
+      "loss": 1.6751,
+      "step": 1550
+    },
+    {
+      "epoch": 35.55555555555556,
+      "grad_norm": 0.2123740017414093,
+      "learning_rate": 0.0007980000000000001,
+      "loss": 1.585,
+      "step": 1600
+    },
+    {
+      "epoch": 36.666666666666664,
+      "grad_norm": 0.2724120318889618,
+      "learning_rate": 0.000823,
+      "loss": 1.6075,
+      "step": 1650
+    },
+    {
+      "epoch": 37.77777777777778,
+      "grad_norm": 0.1595434546470642,
+      "learning_rate": 0.000848,
+      "loss": 1.5939,
+      "step": 1700
+    },
+    {
+      "epoch": 38.888888888888886,
+      "grad_norm": 0.329246461391449,
+      "learning_rate": 0.000873,
+      "loss": 1.6055,
+      "step": 1750
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 0.5109756588935852,
+      "learning_rate": 0.000898,
+      "loss": 1.5925,
+      "step": 1800
+    },
+    {
+      "epoch": 41.111111111111114,
+      "grad_norm": 0.13621735572814941,
+      "learning_rate": 0.0009230000000000001,
+      "loss": 1.5823,
+      "step": 1850
+    },
+    {
+      "epoch": 42.22222222222222,
+      "grad_norm": 0.13570882380008698,
+      "learning_rate": 0.000948,
+      "loss": 1.5806,
+      "step": 1900
+    },
+    {
+      "epoch": 43.333333333333336,
+      "grad_norm": 0.10358592867851257,
+      "learning_rate": 0.000973,
+      "loss": 1.5762,
+      "step": 1950
+    },
+    {
+      "epoch": 44.44444444444444,
+      "grad_norm": 0.2059299349784851,
+      "learning_rate": 0.000998,
+      "loss": 1.5863,
+      "step": 2000
+    },
+    {
+      "epoch": 44.44444444444444,
+      "eval_loss": 1.5431957244873047,
+      "eval_runtime": 8.5158,
+      "eval_samples_per_second": 18.671,
+      "eval_steps_per_second": 2.349,
+      "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": 1.3761741337261632e+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 sha256:86205dd0f5e4c109b754d1a2e96d6be52f2878290f435671b3cc191b44de8f2c
+size 5304