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:e29ee8246b1bc22719673cb087c2b2c7035f885081e1ac1c34d17546b3821a47
+size 577789320

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b0c6517b3a45b7639e34ea8f96e07188e3e8eadaeb29c06ae285da5a66de8bc
+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:e8b323d971557d5fde4cc0d7edcc6e6233b739826529f518d746969aa6eb8c25
+size 14244

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2599834a5bb25566393aaf9a393926be754987442fa6dd0ec6e936958ebe0844
+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": 0.4933945834636688,
+  "best_model_checkpoint": "mikhail_panzo/zlm_b64_le5_s12000/checkpoint-1000",
+  "epoch": 0.837696335078534,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.041884816753926704,
+      "grad_norm": 12.821951866149902,
+      "learning_rate": 2.4000000000000003e-07,
+      "loss": 1.1152,
+      "step": 50
+    },
+    {
+      "epoch": 0.08376963350785341,
+      "grad_norm": 6.186221122741699,
+      "learning_rate": 4.900000000000001e-07,
+      "loss": 1.0584,
+      "step": 100
+    },
+    {
+      "epoch": 0.1256544502617801,
+      "grad_norm": 13.08674430847168,
+      "learning_rate": 7.4e-07,
+      "loss": 0.9996,
+      "step": 150
+    },
+    {
+      "epoch": 0.16753926701570682,
+      "grad_norm": 4.10632848739624,
+      "learning_rate": 9.9e-07,
+      "loss": 0.9355,
+      "step": 200
+    },
+    {
+      "epoch": 0.2094240837696335,
+      "grad_norm": 3.2428064346313477,
+      "learning_rate": 1.2400000000000002e-06,
+      "loss": 0.852,
+      "step": 250
+    },
+    {
+      "epoch": 0.2513089005235602,
+      "grad_norm": 2.0861401557922363,
+      "learning_rate": 1.4900000000000001e-06,
+      "loss": 0.8241,
+      "step": 300
+    },
+    {
+      "epoch": 0.2931937172774869,
+      "grad_norm": 8.602317810058594,
+      "learning_rate": 1.74e-06,
+      "loss": 0.7629,
+      "step": 350
+    },
+    {
+      "epoch": 0.33507853403141363,
+      "grad_norm": 2.7594990730285645,
+      "learning_rate": 1.9900000000000004e-06,
+      "loss": 0.7418,
+      "step": 400
+    },
+    {
+      "epoch": 0.3769633507853403,
+      "grad_norm": 2.7047348022460938,
+      "learning_rate": 2.24e-06,
+      "loss": 0.7166,
+      "step": 450
+    },
+    {
+      "epoch": 0.418848167539267,
+      "grad_norm": 2.0666158199310303,
+      "learning_rate": 2.4900000000000003e-06,
+      "loss": 0.6876,
+      "step": 500
+    },
+    {
+      "epoch": 0.418848167539267,
+      "eval_loss": 0.5937426090240479,
+      "eval_runtime": 263.0955,
+      "eval_samples_per_second": 32.266,
+      "eval_steps_per_second": 4.037,
+      "step": 500
+    },
+    {
+      "epoch": 0.4607329842931937,
+      "grad_norm": 2.955193519592285,
+      "learning_rate": 2.7400000000000004e-06,
+      "loss": 0.673,
+      "step": 550
+    },
+    {
+      "epoch": 0.5026178010471204,
+      "grad_norm": 4.856322765350342,
+      "learning_rate": 2.99e-06,
+      "loss": 0.6539,
+      "step": 600
+    },
+    {
+      "epoch": 0.5445026178010471,
+      "grad_norm": 7.631103992462158,
+      "learning_rate": 3.2400000000000003e-06,
+      "loss": 0.6588,
+      "step": 650
+    },
+    {
+      "epoch": 0.5863874345549738,
+      "grad_norm": 2.715771436691284,
+      "learning_rate": 3.49e-06,
+      "loss": 0.624,
+      "step": 700
+    },
+    {
+      "epoch": 0.6282722513089005,
+      "grad_norm": 2.7684273719787598,
+      "learning_rate": 3.74e-06,
+      "loss": 0.6116,
+      "step": 750
+    },
+    {
+      "epoch": 0.6701570680628273,
+      "grad_norm": 2.219599723815918,
+      "learning_rate": 3.990000000000001e-06,
+      "loss": 0.6097,
+      "step": 800
+    },
+    {
+      "epoch": 0.7120418848167539,
+      "grad_norm": 3.749188184738159,
+      "learning_rate": 4.24e-06,
+      "loss": 0.614,
+      "step": 850
+    },
+    {
+      "epoch": 0.7539267015706806,
+      "grad_norm": 2.120619773864746,
+      "learning_rate": 4.49e-06,
+      "loss": 0.5814,
+      "step": 900
+    },
+    {
+      "epoch": 0.7958115183246073,
+      "grad_norm": 2.7725327014923096,
+      "learning_rate": 4.74e-06,
+      "loss": 0.5895,
+      "step": 950
+    },
+    {
+      "epoch": 0.837696335078534,
+      "grad_norm": 9.851961135864258,
+      "learning_rate": 4.9900000000000005e-06,
+      "loss": 0.5623,
+      "step": 1000
+    },
+    {
+      "epoch": 0.837696335078534,
+      "eval_loss": 0.4933945834636688,
+      "eval_runtime": 258.739,
+      "eval_samples_per_second": 32.809,
+      "eval_steps_per_second": 4.105,
+      "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": 9000282308548608.0,
+  "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:b20f3b06aa67136878a19fd6f17a63e91db785ca54662fa7debf3d46f1fe910d
+size 5304