| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.015304170386430302, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005101390128810101, | |
| "eval_loss": 1.255810260772705, | |
| "eval_runtime": 58.2412, | |
| "eval_samples_per_second": 14.182, | |
| "eval_steps_per_second": 7.091, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015304170386430302, | |
| "grad_norm": 0.4550890326499939, | |
| "learning_rate": 6e-05, | |
| "loss": 1.256, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0030608340772860605, | |
| "grad_norm": 0.3050088584423065, | |
| "learning_rate": 0.00012, | |
| "loss": 1.1877, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004081112103048081, | |
| "eval_loss": 1.181563377380371, | |
| "eval_runtime": 57.0637, | |
| "eval_samples_per_second": 14.475, | |
| "eval_steps_per_second": 7.238, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00459125111592909, | |
| "grad_norm": 0.34536296129226685, | |
| "learning_rate": 0.00018, | |
| "loss": 1.2362, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006121668154572121, | |
| "grad_norm": 0.3734286427497864, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.1759, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007652085193215151, | |
| "grad_norm": 0.31507617235183716, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.1013, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008162224206096162, | |
| "eval_loss": 1.0907156467437744, | |
| "eval_runtime": 57.1, | |
| "eval_samples_per_second": 14.466, | |
| "eval_steps_per_second": 7.233, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00918250223185818, | |
| "grad_norm": 0.2881808876991272, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.9326, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.010712919270501211, | |
| "grad_norm": 0.37691137194633484, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.9449, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.012243336309144242, | |
| "grad_norm": 0.45833703875541687, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.092, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.012243336309144242, | |
| "eval_loss": 1.0757582187652588, | |
| "eval_runtime": 57.1584, | |
| "eval_samples_per_second": 14.451, | |
| "eval_steps_per_second": 7.226, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.013773753347787273, | |
| "grad_norm": 0.23235857486724854, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.0106, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.015304170386430302, | |
| "grad_norm": 0.26949524879455566, | |
| "learning_rate": 0.0, | |
| "loss": 0.9973, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.181705733931008e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |