| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005901968306430194, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00011803936612860389, | |
| "eval_loss": NaN, | |
| "eval_runtime": 544.0765, | |
| "eval_samples_per_second": 6.558, | |
| "eval_steps_per_second": 3.279, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005901968306430194, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0011803936612860388, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0011803936612860388, | |
| "eval_loss": NaN, | |
| "eval_runtime": 253.0764, | |
| "eval_samples_per_second": 14.099, | |
| "eval_steps_per_second": 7.049, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0017705904919290583, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0023607873225720776, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0023607873225720776, | |
| "eval_loss": NaN, | |
| "eval_runtime": 315.3678, | |
| "eval_samples_per_second": 11.314, | |
| "eval_steps_per_second": 5.657, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002950984153215097, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0035411809838581166, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0035411809838581166, | |
| "eval_loss": NaN, | |
| "eval_runtime": 411.0857, | |
| "eval_samples_per_second": 8.679, | |
| "eval_steps_per_second": 4.34, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004131377814501136, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.004721574645144155, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.004721574645144155, | |
| "eval_loss": NaN, | |
| "eval_runtime": 670.1374, | |
| "eval_samples_per_second": 5.324, | |
| "eval_steps_per_second": 2.662, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005311771475787175, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.005901968306430194, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.005901968306430194, | |
| "eval_loss": NaN, | |
| "eval_runtime": 910.9339, | |
| "eval_samples_per_second": 3.917, | |
| "eval_steps_per_second": 1.958, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8931009736212480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |