| { | |
| "best_metric": 3.3321995735168457, | |
| "best_model_checkpoint": "./tts-model-finetune\\checkpoint-50", | |
| "epoch": 0.3448275862068966, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006896551724137931, | |
| "grad_norm": 11.392743110656738, | |
| "learning_rate": 2e-05, | |
| "loss": 13.6657, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013793103448275862, | |
| "grad_norm": 11.40077018737793, | |
| "learning_rate": 4e-05, | |
| "loss": 13.856, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.020689655172413793, | |
| "grad_norm": 11.972955703735352, | |
| "learning_rate": 6e-05, | |
| "loss": 13.6725, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.027586206896551724, | |
| "grad_norm": 13.583998680114746, | |
| "learning_rate": 8e-05, | |
| "loss": 12.6134, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.034482758620689655, | |
| "grad_norm": 17.623764038085938, | |
| "learning_rate": 0.0001, | |
| "loss": 11.721, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.041379310344827586, | |
| "grad_norm": 19.997751235961914, | |
| "learning_rate": 9.999952403603673e-05, | |
| "loss": 9.4947, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04827586206896552, | |
| "grad_norm": 15.626948356628418, | |
| "learning_rate": 9.999809615320856e-05, | |
| "loss": 6.9766, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05517241379310345, | |
| "grad_norm": 8.9348726272583, | |
| "learning_rate": 9.999571637870036e-05, | |
| "loss": 5.6984, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06206896551724138, | |
| "grad_norm": 4.136483669281006, | |
| "learning_rate": 9.999238475781957e-05, | |
| "loss": 4.8507, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06896551724137931, | |
| "grad_norm": 2.6459639072418213, | |
| "learning_rate": 9.998810135399546e-05, | |
| "loss": 4.5585, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07586206896551724, | |
| "grad_norm": 2.484941005706787, | |
| "learning_rate": 9.998286624877786e-05, | |
| "loss": 4.6016, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.08275862068965517, | |
| "grad_norm": 2.2766242027282715, | |
| "learning_rate": 9.997667954183565e-05, | |
| "loss": 4.4363, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0896551724137931, | |
| "grad_norm": 2.1203527450561523, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 4.3823, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09655172413793103, | |
| "grad_norm": 1.9280288219451904, | |
| "learning_rate": 9.996145181203615e-05, | |
| "loss": 4.2706, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.10344827586206896, | |
| "grad_norm": 1.7148234844207764, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 4.1715, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1103448275862069, | |
| "grad_norm": 1.6018073558807373, | |
| "learning_rate": 9.994241932424754e-05, | |
| "loss": 4.1337, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.11724137931034483, | |
| "grad_norm": 1.4049166440963745, | |
| "learning_rate": 9.99314767377287e-05, | |
| "loss": 3.9714, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.12413793103448276, | |
| "grad_norm": 1.3031293153762817, | |
| "learning_rate": 9.991958352786744e-05, | |
| "loss": 3.9484, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1310344827586207, | |
| "grad_norm": 1.0187429189682007, | |
| "learning_rate": 9.990673992109335e-05, | |
| "loss": 3.8798, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.13793103448275862, | |
| "grad_norm": 0.9277167916297913, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.8025, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14482758620689656, | |
| "grad_norm": 0.9591456651687622, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 3.7636, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.15172413793103448, | |
| "grad_norm": 1.0362803936004639, | |
| "learning_rate": 9.986250925497429e-05, | |
| "loss": 3.7407, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.15862068965517243, | |
| "grad_norm": 1.0504515171051025, | |
| "learning_rate": 9.98458666866564e-05, | |
| "loss": 3.6976, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.16551724137931034, | |
| "grad_norm": 0.9324204325675964, | |
| "learning_rate": 9.982827512488809e-05, | |
| "loss": 3.6664, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1724137931034483, | |
| "grad_norm": 0.8606096506118774, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 3.6558, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1793103448275862, | |
| "grad_norm": 0.7672788500785828, | |
| "learning_rate": 9.97902463787331e-05, | |
| "loss": 3.6692, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.18620689655172415, | |
| "grad_norm": 0.6850264668464661, | |
| "learning_rate": 9.976980991835894e-05, | |
| "loss": 3.6091, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.19310344827586207, | |
| "grad_norm": 0.6251705884933472, | |
| "learning_rate": 9.974842591254558e-05, | |
| "loss": 3.5454, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.6199111342430115, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 3.5376, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.20689655172413793, | |
| "grad_norm": 0.6018431782722473, | |
| "learning_rate": 9.970281691111598e-05, | |
| "loss": 3.5433, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21379310344827587, | |
| "grad_norm": 0.5882090330123901, | |
| "learning_rate": 9.967859278382938e-05, | |
| "loss": 3.5594, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2206896551724138, | |
| "grad_norm": 0.5856074690818787, | |
| "learning_rate": 9.965342284774632e-05, | |
| "loss": 3.5153, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.22758620689655173, | |
| "grad_norm": 0.5841050148010254, | |
| "learning_rate": 9.962730758206611e-05, | |
| "loss": 3.5399, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.23448275862068965, | |
| "grad_norm": 0.5656192302703857, | |
| "learning_rate": 9.960024748398576e-05, | |
| "loss": 3.6101, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.2413793103448276, | |
| "grad_norm": 0.5472608208656311, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.5334, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2482758620689655, | |
| "grad_norm": 0.5338900089263916, | |
| "learning_rate": 9.954329486934412e-05, | |
| "loss": 3.5119, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.25517241379310346, | |
| "grad_norm": 0.5114866495132446, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 3.4878, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2620689655172414, | |
| "grad_norm": 0.5140212178230286, | |
| "learning_rate": 9.948256934098352e-05, | |
| "loss": 3.4561, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2689655172413793, | |
| "grad_norm": 0.5367317199707031, | |
| "learning_rate": 9.945079316809585e-05, | |
| "loss": 3.4769, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.27586206896551724, | |
| "grad_norm": 0.4917609989643097, | |
| "learning_rate": 9.941807552338804e-05, | |
| "loss": 3.4157, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2827586206896552, | |
| "grad_norm": 0.5060731172561646, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 3.4559, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2896551724137931, | |
| "grad_norm": 0.497332364320755, | |
| "learning_rate": 9.93498183280116e-05, | |
| "loss": 3.4068, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.296551724137931, | |
| "grad_norm": 0.5172521471977234, | |
| "learning_rate": 9.931428007686158e-05, | |
| "loss": 3.4059, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.30344827586206896, | |
| "grad_norm": 0.5016644597053528, | |
| "learning_rate": 9.927780295290389e-05, | |
| "loss": 3.4224, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3103448275862069, | |
| "grad_norm": 0.5105836391448975, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 3.4223, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.31724137931034485, | |
| "grad_norm": 0.49239876866340637, | |
| "learning_rate": 9.920203488231454e-05, | |
| "loss": 3.3637, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.32413793103448274, | |
| "grad_norm": 0.44286057353019714, | |
| "learning_rate": 9.916274537819775e-05, | |
| "loss": 3.3308, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3310344827586207, | |
| "grad_norm": 0.5211081504821777, | |
| "learning_rate": 9.912251988627549e-05, | |
| "loss": 3.3835, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.33793103448275863, | |
| "grad_norm": 0.47642946243286133, | |
| "learning_rate": 9.908135917238321e-05, | |
| "loss": 3.3144, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3448275862068966, | |
| "grad_norm": 0.45889148116111755, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.3593, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3448275862068966, | |
| "eval_loss": 3.3321995735168457, | |
| "eval_runtime": 17.8977, | |
| "eval_samples_per_second": 1.676, | |
| "eval_steps_per_second": 0.447, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 725, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 966060303974400.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |