| { | |
| "best_metric": 0.016, | |
| "best_model_checkpoint": "wav2vec2-large-xlsr-fleurs/checkpoint-100", | |
| "epoch": 4.032, | |
| "global_step": 250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2e-05, | |
| "loss": 4.6232, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4e-05, | |
| "loss": 4.6236, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6e-05, | |
| "loss": 4.625, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 8e-05, | |
| "loss": 4.6225, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0001, | |
| "loss": 4.6254, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_accuracy": 0.015, | |
| "eval_loss": 4.617953300476074, | |
| "eval_runtime": 244.9205, | |
| "eval_samples_per_second": 4.083, | |
| "eval_steps_per_second": 0.51, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00012, | |
| "loss": 4.624, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.00014000000000000001, | |
| "loss": 4.8421, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00016, | |
| "loss": 4.6052, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 4.6233, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.0002, | |
| "loss": 4.6383, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "eval_accuracy": 0.016, | |
| "eval_loss": 4.607293128967285, | |
| "eval_runtime": 252.2987, | |
| "eval_samples_per_second": 3.964, | |
| "eval_steps_per_second": 0.495, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.000218, | |
| "loss": 4.6117, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.00023799999999999998, | |
| "loss": 4.5956, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.00025800000000000004, | |
| "loss": 4.8238, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.00027600000000000004, | |
| "loss": 4.5525, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 0.000294, | |
| "loss": 4.6262, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "eval_accuracy": 0.015, | |
| "eval_loss": 4.576992034912109, | |
| "eval_runtime": 249.2197, | |
| "eval_samples_per_second": 4.013, | |
| "eval_steps_per_second": 0.502, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 0.000314, | |
| "loss": 4.5967, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 0.00033400000000000004, | |
| "loss": 4.5978, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 0.000354, | |
| "loss": 4.6076, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 0.000374, | |
| "loss": 4.8654, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 0.00039400000000000004, | |
| "loss": 4.5614, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "eval_accuracy": 0.015, | |
| "eval_loss": 4.575872898101807, | |
| "eval_runtime": 249.962, | |
| "eval_samples_per_second": 4.001, | |
| "eval_steps_per_second": 0.5, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 0.000414, | |
| "loss": 4.5997, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 0.00043400000000000003, | |
| "loss": 4.5909, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 0.00045400000000000003, | |
| "loss": 4.6141, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 0.000474, | |
| "loss": 4.6173, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 0.000494, | |
| "loss": 4.8119, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "eval_accuracy": 0.014, | |
| "eval_loss": 4.567824363708496, | |
| "eval_runtime": 249.2501, | |
| "eval_samples_per_second": 4.012, | |
| "eval_steps_per_second": 0.502, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "step": 250, | |
| "total_flos": 1.577948839059241e+18, | |
| "train_loss": 4.6450146484375, | |
| "train_runtime": 3071.4642, | |
| "train_samples_per_second": 1.302, | |
| "train_steps_per_second": 0.081 | |
| } | |
| ], | |
| "max_steps": 250, | |
| "num_train_epochs": 5, | |
| "total_flos": 1.577948839059241e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |