| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.028169014084507, | |
| "eval_steps": 54, | |
| "global_step": 432, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 2.3513402938842773, | |
| "learning_rate": 1.267605633802817e-05, | |
| "loss": 0.762, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 0.7501299381256104, | |
| "eval_runtime": 52.392, | |
| "eval_samples_per_second": 4.295, | |
| "eval_steps_per_second": 1.088, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 2.591146230697632, | |
| "learning_rate": 2.535211267605634e-05, | |
| "loss": 0.6669, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 0.6195361614227295, | |
| "eval_runtime": 52.4012, | |
| "eval_samples_per_second": 4.294, | |
| "eval_steps_per_second": 1.088, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 1.591381311416626, | |
| "learning_rate": 3.802816901408451e-05, | |
| "loss": 0.5832, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 0.5714844465255737, | |
| "eval_runtime": 52.3923, | |
| "eval_samples_per_second": 4.295, | |
| "eval_steps_per_second": 1.088, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 1.6814194917678833, | |
| "learning_rate": 4.992175273865415e-05, | |
| "loss": 0.5585, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 0.5567753911018372, | |
| "eval_runtime": 52.4015, | |
| "eval_samples_per_second": 4.294, | |
| "eval_steps_per_second": 1.088, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 1.8983561992645264, | |
| "learning_rate": 4.85133020344288e-05, | |
| "loss": 0.5008, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_loss": 0.5528200268745422, | |
| "eval_runtime": 52.3944, | |
| "eval_samples_per_second": 4.294, | |
| "eval_steps_per_second": 1.088, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 2.4356637001037598, | |
| "learning_rate": 4.710485133020345e-05, | |
| "loss": 0.5118, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 0.5451384782791138, | |
| "eval_runtime": 52.391, | |
| "eval_samples_per_second": 4.295, | |
| "eval_steps_per_second": 1.088, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 2.4634923934936523, | |
| "learning_rate": 4.569640062597809e-05, | |
| "loss": 0.545, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_loss": 0.5402218699455261, | |
| "eval_runtime": 52.3935, | |
| "eval_samples_per_second": 4.294, | |
| "eval_steps_per_second": 1.088, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "grad_norm": 1.9934064149856567, | |
| "learning_rate": 4.428794992175274e-05, | |
| "loss": 0.4951, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_loss": 0.538709282875061, | |
| "eval_runtime": 52.3838, | |
| "eval_samples_per_second": 4.295, | |
| "eval_steps_per_second": 1.088, | |
| "step": 432 | |
| } | |
| ], | |
| "logging_steps": 54, | |
| "max_steps": 2130, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 54, | |
| "total_flos": 3.006466069458125e+16, | |
| "train_batch_size": 6, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |