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 sha256:59673f09d981d82f85dbd3f87df51f2e1e4c4e69eaa72e301f34396ac26d8738
+size 577789320

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f055d624a5638f768c723d4a865eba2d6067242e1ffc1317915c6258835ae60f
+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:eb207210dd9f813766ac9775df4ed27dd430d4655f3da143d6449258767fcdc6
+size 14244

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64c6bb4bc7acd5e6780a6dd998610f88c77d87194054da56f221046380147b08
+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": 0.4226582944393158,
+  "best_model_checkpoint": "mikhail_panzo/zlm_b64_le4_s12000/checkpoint-1000",
+  "epoch": 0.8375209380234506,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04187604690117253,
+      "grad_norm": 3.0184223651885986,
+      "learning_rate": 2.35e-06,
+      "loss": 1.1206,
+      "step": 50
+    },
+    {
+      "epoch": 0.08375209380234507,
+      "grad_norm": 3.4442005157470703,
+      "learning_rate": 4.85e-06,
+      "loss": 0.8185,
+      "step": 100
+    },
+    {
+      "epoch": 0.12562814070351758,
+      "grad_norm": 2.6812493801116943,
+      "learning_rate": 7.35e-06,
+      "loss": 0.7576,
+      "step": 150
+    },
+    {
+      "epoch": 0.16750418760469013,
+      "grad_norm": 4.518482685089111,
+      "learning_rate": 9.85e-06,
+      "loss": 0.6938,
+      "step": 200
+    },
+    {
+      "epoch": 0.20938023450586266,
+      "grad_norm": 4.683146953582764,
+      "learning_rate": 1.235e-05,
+      "loss": 0.6386,
+      "step": 250
+    },
+    {
+      "epoch": 0.25125628140703515,
+      "grad_norm": 2.7392578125,
+      "learning_rate": 1.485e-05,
+      "loss": 0.6226,
+      "step": 300
+    },
+    {
+      "epoch": 0.2931323283082077,
+      "grad_norm": 2.017056465148926,
+      "learning_rate": 1.7349999999999998e-05,
+      "loss": 0.6128,
+      "step": 350
+    },
+    {
+      "epoch": 0.33500837520938026,
+      "grad_norm": 3.6669230461120605,
+      "learning_rate": 1.985e-05,
+      "loss": 0.5675,
+      "step": 400
+    },
+    {
+      "epoch": 0.3768844221105528,
+      "grad_norm": 4.16896915435791,
+      "learning_rate": 2.235e-05,
+      "loss": 0.5655,
+      "step": 450
+    },
+    {
+      "epoch": 0.4187604690117253,
+      "grad_norm": 3.691459894180298,
+      "learning_rate": 2.485e-05,
+      "loss": 0.5487,
+      "step": 500
+    },
+    {
+      "epoch": 0.4187604690117253,
+      "eval_loss": 0.47458764910697937,
+      "eval_runtime": 214.7196,
+      "eval_samples_per_second": 39.535,
+      "eval_steps_per_second": 4.946,
+      "step": 500
+    },
+    {
+      "epoch": 0.46063651591289784,
+      "grad_norm": 3.3792996406555176,
+      "learning_rate": 2.7350000000000004e-05,
+      "loss": 0.5232,
+      "step": 550
+    },
+    {
+      "epoch": 0.5025125628140703,
+      "grad_norm": 3.6263363361358643,
+      "learning_rate": 2.985e-05,
+      "loss": 0.5132,
+      "step": 600
+    },
+    {
+      "epoch": 0.5443886097152428,
+      "grad_norm": 2.652538776397705,
+      "learning_rate": 3.235e-05,
+      "loss": 0.5067,
+      "step": 650
+    },
+    {
+      "epoch": 0.5862646566164154,
+      "grad_norm": 3.5355172157287598,
+      "learning_rate": 3.485e-05,
+      "loss": 0.4981,
+      "step": 700
+    },
+    {
+      "epoch": 0.628140703517588,
+      "grad_norm": 2.5035619735717773,
+      "learning_rate": 3.735e-05,
+      "loss": 0.5094,
+      "step": 750
+    },
+    {
+      "epoch": 0.6700167504187605,
+      "grad_norm": 2.9585518836975098,
+      "learning_rate": 3.9850000000000006e-05,
+      "loss": 0.5053,
+      "step": 800
+    },
+    {
+      "epoch": 0.711892797319933,
+      "grad_norm": 9.997116088867188,
+      "learning_rate": 4.235e-05,
+      "loss": 0.502,
+      "step": 850
+    },
+    {
+      "epoch": 0.7537688442211056,
+      "grad_norm": 1.8630377054214478,
+      "learning_rate": 4.4850000000000006e-05,
+      "loss": 0.483,
+      "step": 900
+    },
+    {
+      "epoch": 0.7956448911222781,
+      "grad_norm": 1.5534099340438843,
+      "learning_rate": 4.735e-05,
+      "loss": 0.4743,
+      "step": 950
+    },
+    {
+      "epoch": 0.8375209380234506,
+      "grad_norm": 2.8155503273010254,
+      "learning_rate": 4.9850000000000006e-05,
+      "loss": 0.483,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8375209380234506,
+      "eval_loss": 0.4226582944393158,
+      "eval_runtime": 213.2339,
+      "eval_samples_per_second": 39.811,
+      "eval_steps_per_second": 4.98,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 12000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 11,
+  "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": 9713361729620736.0,
+  "train_batch_size": 32,
+  "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:fb8203a5324b57ae1a64f032a5185016d65cbc7738fd0978239bc5b2518d051b
+size 5304