Training in progress, step 1125, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,92 @@
+{
+  "_name_or_path": "microsoft/speecht5_vc",
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "SpeechT5ForSpeechToSpeechForTraining"
+  ],
+  "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": 450,
+  "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": "4.47.0",
+  "use_cache": true,
+  "use_guided_attention_loss": true,
+  "vocab_size": 81
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b29712353d21d9763a60518b2b69824b6871cde722b0cdae88721444cdcdf65
+size 620580908

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a191ab564a8de561fb834100a5aa2a6aa91f6074d6f4d4e4ce4f2fa9da47209e
+size 1221940848

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b653fd97ba87ca7394ff2b5e13a3ec315315640f6fad57ffc66aa021225ed2b0
+size 14308

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8560ec30e7251b28a3b5f96e97576096a7a96e81fb794356afa6c2f78f4fc35
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": 0.7220967411994934,
+  "best_model_checkpoint": "./speecht5_vc_finetuned_accent_coach/checkpoint-1125",
+  "epoch": 1.0,
+  "eval_steps": 1125,
+  "global_step": 1125,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0,
+      "eval_loss": 2.9400367736816406,
+      "eval_runtime": 69.9619,
+      "eval_samples_per_second": 128.642,
+      "eval_steps_per_second": 2.015,
+      "step": 0
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 3.1737678050994873,
+      "learning_rate": 9.672e-06,
+      "loss": 1.2333,
+      "step": 375
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.4934049844741821,
+      "learning_rate": 9.338666666666667e-06,
+      "loss": 0.8764,
+      "step": 750
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.6652963161468506,
+      "learning_rate": 9.005333333333333e-06,
+      "loss": 0.8126,
+      "step": 1125
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.7220967411994934,
+      "eval_runtime": 68.4329,
+      "eval_samples_per_second": 131.516,
+      "eval_steps_per_second": 2.06,
+      "step": 1125
+    }
+  ],
+  "logging_steps": 375,
+  "max_steps": 11250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 1125,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.112937353344e+18,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c9bcc40675c79d6aab12599165f0f527e30a71e415dc08e10541670aca38e96
+size 5368