| { | |
| "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": 1.5155491828918457, | |
| "learning_rate": 1.267605633802817e-05, | |
| "loss": 1.8226, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.8172667026519775, | |
| "eval_runtime": 73.1932, | |
| "eval_samples_per_second": 3.074, | |
| "eval_steps_per_second": 0.779, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 1.649418830871582, | |
| "learning_rate": 2.535211267605634e-05, | |
| "loss": 1.6744, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.5906846523284912, | |
| "eval_runtime": 73.1988, | |
| "eval_samples_per_second": 3.074, | |
| "eval_steps_per_second": 0.779, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 2.1592600345611572, | |
| "learning_rate": 3.802816901408451e-05, | |
| "loss": 1.5273, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 1.526986002922058, | |
| "eval_runtime": 73.174, | |
| "eval_samples_per_second": 3.075, | |
| "eval_steps_per_second": 0.779, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 2.3729259967803955, | |
| "learning_rate": 4.992175273865415e-05, | |
| "loss": 1.4981, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 1.5036466121673584, | |
| "eval_runtime": 73.1899, | |
| "eval_samples_per_second": 3.074, | |
| "eval_steps_per_second": 0.779, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 2.0879106521606445, | |
| "learning_rate": 4.85133020344288e-05, | |
| "loss": 1.4484, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_loss": 1.4860492944717407, | |
| "eval_runtime": 73.1845, | |
| "eval_samples_per_second": 3.074, | |
| "eval_steps_per_second": 0.779, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 2.163222074508667, | |
| "learning_rate": 4.710485133020345e-05, | |
| "loss": 1.4242, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 1.4793643951416016, | |
| "eval_runtime": 73.1805, | |
| "eval_samples_per_second": 3.075, | |
| "eval_steps_per_second": 0.779, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 2.0721864700317383, | |
| "learning_rate": 4.569640062597809e-05, | |
| "loss": 1.4706, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_loss": 1.473569631576538, | |
| "eval_runtime": 73.2169, | |
| "eval_samples_per_second": 3.073, | |
| "eval_steps_per_second": 0.779, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "grad_norm": 2.9931325912475586, | |
| "learning_rate": 4.428794992175274e-05, | |
| "loss": 1.4157, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_loss": 1.4716590642929077, | |
| "eval_runtime": 73.218, | |
| "eval_samples_per_second": 3.073, | |
| "eval_steps_per_second": 0.778, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "grad_norm": 2.3123691082000732, | |
| "learning_rate": 4.287949921752739e-05, | |
| "loss": 1.3791, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_loss": 1.473205804824829, | |
| "eval_runtime": 73.1999, | |
| "eval_samples_per_second": 3.074, | |
| "eval_steps_per_second": 0.779, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "grad_norm": 2.8663740158081055, | |
| "learning_rate": 4.1471048513302035e-05, | |
| "loss": 1.3836, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "eval_loss": 1.4686306715011597, | |
| "eval_runtime": 73.1902, | |
| "eval_samples_per_second": 3.074, | |
| "eval_steps_per_second": 0.779, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "grad_norm": 2.138514757156372, | |
| "learning_rate": 4.0062597809076686e-05, | |
| "loss": 1.3963, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "eval_loss": 1.4640343189239502, | |
| "eval_runtime": 73.1446, | |
| "eval_samples_per_second": 3.076, | |
| "eval_steps_per_second": 0.779, | |
| "step": 594 | |
| } | |
| ], | |
| "logging_steps": 54, | |
| "max_steps": 2130, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 54, | |
| "total_flos": 6.008456641536e+16, | |
| "train_batch_size": 6, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |