| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.788732394366197, | |
| "eval_steps": 54, | |
| "global_step": 594, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 1.7245745658874512, | |
| "learning_rate": 1.267605633802817e-05, | |
| "loss": 1.8836, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.8345000743865967, | |
| "eval_runtime": 69.3554, | |
| "eval_samples_per_second": 3.244, | |
| "eval_steps_per_second": 0.822, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 1.9656869173049927, | |
| "learning_rate": 2.535211267605634e-05, | |
| "loss": 1.7125, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.5757657289505005, | |
| "eval_runtime": 69.3104, | |
| "eval_samples_per_second": 3.246, | |
| "eval_steps_per_second": 0.822, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 2.2268643379211426, | |
| "learning_rate": 3.802816901408451e-05, | |
| "loss": 1.5317, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 1.5088270902633667, | |
| "eval_runtime": 69.3433, | |
| "eval_samples_per_second": 3.245, | |
| "eval_steps_per_second": 0.822, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 2.323223829269409, | |
| "learning_rate": 4.992175273865415e-05, | |
| "loss": 1.5107, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 1.4836149215698242, | |
| "eval_runtime": 69.3441, | |
| "eval_samples_per_second": 3.245, | |
| "eval_steps_per_second": 0.822, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 1.9550501108169556, | |
| "learning_rate": 4.85133020344288e-05, | |
| "loss": 1.4407, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_loss": 1.4644213914871216, | |
| "eval_runtime": 69.3391, | |
| "eval_samples_per_second": 3.245, | |
| "eval_steps_per_second": 0.822, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 2.3526928424835205, | |
| "learning_rate": 4.710485133020345e-05, | |
| "loss": 1.4436, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 1.457223892211914, | |
| "eval_runtime": 69.337, | |
| "eval_samples_per_second": 3.245, | |
| "eval_steps_per_second": 0.822, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 2.886111259460449, | |
| "learning_rate": 4.569640062597809e-05, | |
| "loss": 1.4589, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_loss": 1.4452433586120605, | |
| "eval_runtime": 69.3232, | |
| "eval_samples_per_second": 3.246, | |
| "eval_steps_per_second": 0.822, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "grad_norm": 3.2102179527282715, | |
| "learning_rate": 4.428794992175274e-05, | |
| "loss": 1.4075, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_loss": 1.44347083568573, | |
| "eval_runtime": 69.3369, | |
| "eval_samples_per_second": 3.245, | |
| "eval_steps_per_second": 0.822, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "grad_norm": 2.3608078956604004, | |
| "learning_rate": 4.287949921752739e-05, | |
| "loss": 1.3827, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_loss": 1.4407154321670532, | |
| "eval_runtime": 69.3247, | |
| "eval_samples_per_second": 3.246, | |
| "eval_steps_per_second": 0.822, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "grad_norm": 3.066206932067871, | |
| "learning_rate": 4.1471048513302035e-05, | |
| "loss": 1.3726, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "eval_loss": 1.441516399383545, | |
| "eval_runtime": 69.345, | |
| "eval_samples_per_second": 3.245, | |
| "eval_steps_per_second": 0.822, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "grad_norm": 2.0999038219451904, | |
| "learning_rate": 4.0062597809076686e-05, | |
| "loss": 1.3889, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "eval_loss": 1.4352647066116333, | |
| "eval_runtime": 69.3389, | |
| "eval_samples_per_second": 3.245, | |
| "eval_steps_per_second": 0.822, | |
| "step": 594 | |
| } | |
| ], | |
| "logging_steps": 54, | |
| "max_steps": 2130, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 54, | |
| "total_flos": 5.717468184979046e+16, | |
| "train_batch_size": 6, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |