| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.050697084917617236, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016899028305872412, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.3853, | |
| "eval_samples_per_second": 180.471, | |
| "eval_steps_per_second": 90.236, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005069708491761723, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008449514152936205, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.4012, | |
| "eval_samples_per_second": 178.423, | |
| "eval_steps_per_second": 89.211, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010139416983523447, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015209125475285171, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01689902830587241, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.3907, | |
| "eval_samples_per_second": 179.761, | |
| "eval_steps_per_second": 89.881, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.020278833967046894, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.025348542458808618, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.025348542458808618, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.4611, | |
| "eval_samples_per_second": 171.105, | |
| "eval_steps_per_second": 85.553, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.030418250950570342, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03379805661174482, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.4023, | |
| "eval_samples_per_second": 178.275, | |
| "eval_steps_per_second": 89.138, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.035487959442332066, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04055766793409379, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04224757076468103, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.4304, | |
| "eval_samples_per_second": 174.778, | |
| "eval_steps_per_second": 87.389, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.045627376425855515, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.050697084917617236, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.050697084917617236, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.408, | |
| "eval_samples_per_second": 177.555, | |
| "eval_steps_per_second": 88.777, | |
| "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": 64909329039360.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |