| { | |
| "best_metric": 132.57756563245823, | |
| "best_model_checkpoint": "ASFEMA_SEV/checkpoint-400", | |
| "epoch": 5.192926045016077, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.6000000000000004e-07, | |
| "loss": 4.0894, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 9.600000000000001e-07, | |
| "loss": 3.7, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.46e-06, | |
| "loss": 3.0759, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 1.9600000000000003e-06, | |
| "loss": 2.5729, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 2.46e-06, | |
| "loss": 2.1885, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 2.96e-06, | |
| "loss": 1.9431, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 3.46e-06, | |
| "loss": 1.5753, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 3.96e-06, | |
| "loss": 1.3319, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 4.4600000000000005e-06, | |
| "loss": 1.2076, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 4.960000000000001e-06, | |
| "loss": 0.9211, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 5.460000000000001e-06, | |
| "loss": 0.7332, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 5.9600000000000005e-06, | |
| "loss": 0.6601, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 6.460000000000001e-06, | |
| "loss": 0.4824, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 6.96e-06, | |
| "loss": 0.3455, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 7.4600000000000006e-06, | |
| "loss": 0.3741, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "learning_rate": 7.960000000000002e-06, | |
| "loss": 0.2448, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "eval_loss": 0.9975764751434326, | |
| "eval_runtime": 24.147, | |
| "eval_samples_per_second": 5.756, | |
| "eval_steps_per_second": 0.745, | |
| "eval_wer": 132.57756563245823, | |
| "step": 400 | |
| } | |
| ], | |
| "max_steps": 10000, | |
| "num_train_epochs": 130, | |
| "total_flos": 6.5931077025792e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |