Training in progress, step 1000, checkpoint

checkpoint-1000/added_tokens.json

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

checkpoint-1000/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-1000/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-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:619909d8f05905cdd482bfdb5a3d15c08701ab82c621307ee9c63dcb0016dd44
+size 577789320

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0153b6221f15cead1b8798c5ac71d5ea2a36de6fb796e353f29dd029a02712a0
+size 1155772233

checkpoint-1000/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-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad25c861e7b4be417740fc37745394735f9a504d2d18d9671b07aa1e7479a2a3
+size 14244

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac4332941350d17efa1283f36971ed35ed0a07a2c604bcd72ffbfbed4f4e7419
+size 1064

checkpoint-1000/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-1000/spm_char.model

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

checkpoint-1000/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-1000/trainer_state.json

@@ -0,0 +1,189 @@
+{
+  "best_metric": 0.4741882085800171,
+  "best_model_checkpoint": "mikhail-panzo/fil_b32_le3_s4000/checkpoint-500",
+  "epoch": 21.978021978021978,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.098901098901099,
+      "grad_norm": 2.8254339694976807,
+      "learning_rate": 2.5e-05,
+      "loss": 0.736,
+      "step": 50
+    },
+    {
+      "epoch": 2.197802197802198,
+      "grad_norm": 4.995375633239746,
+      "learning_rate": 4.9500000000000004e-05,
+      "loss": 0.5913,
+      "step": 100
+    },
+    {
+      "epoch": 3.2967032967032965,
+      "grad_norm": 2.352879285812378,
+      "learning_rate": 7.45e-05,
+      "loss": 0.5174,
+      "step": 150
+    },
+    {
+      "epoch": 4.395604395604396,
+      "grad_norm": 4.0169596672058105,
+      "learning_rate": 9.95e-05,
+      "loss": 0.5275,
+      "step": 200
+    },
+    {
+      "epoch": 5.4945054945054945,
+      "grad_norm": 5.557097434997559,
+      "learning_rate": 0.0001245,
+      "loss": 0.5231,
+      "step": 250
+    },
+    {
+      "epoch": 6.593406593406593,
+      "grad_norm": 8.755484580993652,
+      "learning_rate": 0.0001495,
+      "loss": 0.5127,
+      "step": 300
+    },
+    {
+      "epoch": 7.6923076923076925,
+      "grad_norm": 2.5811164379119873,
+      "learning_rate": 0.00017449999999999999,
+      "loss": 0.5179,
+      "step": 350
+    },
+    {
+      "epoch": 8.791208791208792,
+      "grad_norm": 7.064955234527588,
+      "learning_rate": 0.00019950000000000002,
+      "loss": 0.4961,
+      "step": 400
+    },
+    {
+      "epoch": 9.89010989010989,
+      "grad_norm": 8.559194564819336,
+      "learning_rate": 0.0002245,
+      "loss": 0.4976,
+      "step": 450
+    },
+    {
+      "epoch": 10.989010989010989,
+      "grad_norm": 7.322611331939697,
+      "learning_rate": 0.0002495,
+      "loss": 0.502,
+      "step": 500
+    },
+    {
+      "epoch": 10.989010989010989,
+      "eval_loss": 0.4741882085800171,
+      "eval_runtime": 7.5067,
+      "eval_samples_per_second": 21.448,
+      "eval_steps_per_second": 2.798,
+      "step": 500
+    },
+    {
+      "epoch": 12.087912087912088,
+      "grad_norm": 3.533902883529663,
+      "learning_rate": 0.0002745,
+      "loss": 0.5146,
+      "step": 550
+    },
+    {
+      "epoch": 13.186813186813186,
+      "grad_norm": 9.026822090148926,
+      "learning_rate": 0.0002995,
+      "loss": 0.4956,
+      "step": 600
+    },
+    {
+      "epoch": 14.285714285714286,
+      "grad_norm": 7.3526291847229,
+      "learning_rate": 0.00032450000000000003,
+      "loss": 0.5406,
+      "step": 650
+    },
+    {
+      "epoch": 15.384615384615385,
+      "grad_norm": 2.889016628265381,
+      "learning_rate": 0.0003495,
+      "loss": 0.5153,
+      "step": 700
+    },
+    {
+      "epoch": 16.483516483516482,
+      "grad_norm": 7.851646423339844,
+      "learning_rate": 0.0003745,
+      "loss": 0.5326,
+      "step": 750
+    },
+    {
+      "epoch": 17.582417582417584,
+      "grad_norm": 2.468174934387207,
+      "learning_rate": 0.0003995,
+      "loss": 0.5575,
+      "step": 800
+    },
+    {
+      "epoch": 18.681318681318682,
+      "grad_norm": 10.550352096557617,
+      "learning_rate": 0.0004245,
+      "loss": 0.5893,
+      "step": 850
+    },
+    {
+      "epoch": 19.78021978021978,
+      "grad_norm": 6.15378475189209,
+      "learning_rate": 0.00044950000000000003,
+      "loss": 0.5769,
+      "step": 900
+    },
+    {
+      "epoch": 20.87912087912088,
+      "grad_norm": 8.328354835510254,
+      "learning_rate": 0.0004745,
+      "loss": 0.541,
+      "step": 950
+    },
+    {
+      "epoch": 21.978021978021978,
+      "grad_norm": 6.08469820022583,
+      "learning_rate": 0.0004995,
+      "loss": 0.5446,
+      "step": 1000
+    },
+    {
+      "epoch": 21.978021978021978,
+      "eval_loss": 0.4899168014526367,
+      "eval_runtime": 6.7313,
+      "eval_samples_per_second": 23.918,
+      "eval_steps_per_second": 3.12,
+      "step": 1000
+    }
+  ],
+  "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": 7353193286254464.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7108ae4bf8bd54061271f16e95ebc27c1c713cee5a07308d46dd91440b38577c
+size 5304