| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.802816901408451, | |
| "eval_steps": 54, | |
| "global_step": 810, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 1.6524436473846436, | |
| "learning_rate": 1.267605633802817e-05, | |
| "loss": 1.8571, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.815904140472412, | |
| "eval_runtime": 71.1199, | |
| "eval_samples_per_second": 3.164, | |
| "eval_steps_per_second": 0.801, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 2.144040584564209, | |
| "learning_rate": 2.535211267605634e-05, | |
| "loss": 1.6784, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.5669676065444946, | |
| "eval_runtime": 71.0969, | |
| "eval_samples_per_second": 3.165, | |
| "eval_steps_per_second": 0.802, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 2.36417293548584, | |
| "learning_rate": 3.802816901408451e-05, | |
| "loss": 1.5266, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 1.497390627861023, | |
| "eval_runtime": 71.0941, | |
| "eval_samples_per_second": 3.165, | |
| "eval_steps_per_second": 0.802, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 2.723508358001709, | |
| "learning_rate": 4.992175273865415e-05, | |
| "loss": 1.4987, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 1.4736177921295166, | |
| "eval_runtime": 71.0941, | |
| "eval_samples_per_second": 3.165, | |
| "eval_steps_per_second": 0.802, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 2.092134952545166, | |
| "learning_rate": 4.85133020344288e-05, | |
| "loss": 1.4088, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_loss": 1.4523909091949463, | |
| "eval_runtime": 71.0899, | |
| "eval_samples_per_second": 3.165, | |
| "eval_steps_per_second": 0.802, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 2.478315830230713, | |
| "learning_rate": 4.710485133020345e-05, | |
| "loss": 1.4383, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 1.4438430070877075, | |
| "eval_runtime": 71.0889, | |
| "eval_samples_per_second": 3.165, | |
| "eval_steps_per_second": 0.802, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 2.811476707458496, | |
| "learning_rate": 4.569640062597809e-05, | |
| "loss": 1.4606, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_loss": 1.4346896409988403, | |
| "eval_runtime": 71.0897, | |
| "eval_samples_per_second": 3.165, | |
| "eval_steps_per_second": 0.802, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "grad_norm": 3.4677302837371826, | |
| "learning_rate": 4.428794992175274e-05, | |
| "loss": 1.4029, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_loss": 1.431531548500061, | |
| "eval_runtime": 71.0955, | |
| "eval_samples_per_second": 3.165, | |
| "eval_steps_per_second": 0.802, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "grad_norm": 2.5842223167419434, | |
| "learning_rate": 4.287949921752739e-05, | |
| "loss": 1.35, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_loss": 1.430802583694458, | |
| "eval_runtime": 71.0806, | |
| "eval_samples_per_second": 3.165, | |
| "eval_steps_per_second": 0.802, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "grad_norm": 2.942049980163574, | |
| "learning_rate": 4.1471048513302035e-05, | |
| "loss": 1.3749, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "eval_loss": 1.4312644004821777, | |
| "eval_runtime": 71.1092, | |
| "eval_samples_per_second": 3.164, | |
| "eval_steps_per_second": 0.802, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "grad_norm": 2.2633845806121826, | |
| "learning_rate": 4.0062597809076686e-05, | |
| "loss": 1.3596, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "eval_loss": 1.4272420406341553, | |
| "eval_runtime": 71.1027, | |
| "eval_samples_per_second": 3.164, | |
| "eval_steps_per_second": 0.802, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "grad_norm": 2.9916341304779053, | |
| "learning_rate": 3.865414710485133e-05, | |
| "loss": 1.3655, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "eval_loss": 1.429884433746338, | |
| "eval_runtime": 71.0733, | |
| "eval_samples_per_second": 3.166, | |
| "eval_steps_per_second": 0.802, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "grad_norm": 3.2689390182495117, | |
| "learning_rate": 3.724569640062598e-05, | |
| "loss": 1.3184, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "eval_loss": 1.4284456968307495, | |
| "eval_runtime": 71.0941, | |
| "eval_samples_per_second": 3.165, | |
| "eval_steps_per_second": 0.802, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "grad_norm": 2.7613720893859863, | |
| "learning_rate": 3.5837245696400626e-05, | |
| "loss": 1.3084, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "eval_loss": 1.4279944896697998, | |
| "eval_runtime": 71.0944, | |
| "eval_samples_per_second": 3.165, | |
| "eval_steps_per_second": 0.802, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "grad_norm": 2.9932751655578613, | |
| "learning_rate": 3.442879499217527e-05, | |
| "loss": 1.3247, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "eval_loss": 1.4245632886886597, | |
| "eval_runtime": 71.0816, | |
| "eval_samples_per_second": 3.165, | |
| "eval_steps_per_second": 0.802, | |
| "step": 810 | |
| } | |
| ], | |
| "logging_steps": 54, | |
| "max_steps": 2130, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 54, | |
| "total_flos": 7.901132314617446e+16, | |
| "train_batch_size": 6, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |