| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03407735559720566, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006815471119441132, | |
| "eval_loss": 14.195473670959473, | |
| "eval_runtime": 48.1068, | |
| "eval_samples_per_second": 12.846, | |
| "eval_steps_per_second": 6.423, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0034077355597205657, | |
| "grad_norm": 15.207267761230469, | |
| "learning_rate": 5e-05, | |
| "loss": 14.1778, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0068154711194411315, | |
| "grad_norm": 27.689302444458008, | |
| "learning_rate": 0.0001, | |
| "loss": 11.2951, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0068154711194411315, | |
| "eval_loss": 6.358828067779541, | |
| "eval_runtime": 50.8889, | |
| "eval_samples_per_second": 12.144, | |
| "eval_steps_per_second": 6.072, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010223206679161698, | |
| "grad_norm": 15.382610321044922, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.6507, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013630942238882263, | |
| "grad_norm": 10.985650062561035, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.7042, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013630942238882263, | |
| "eval_loss": 0.767593264579773, | |
| "eval_runtime": 51.6642, | |
| "eval_samples_per_second": 11.962, | |
| "eval_steps_per_second": 5.981, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01703867779860283, | |
| "grad_norm": 15.141491889953613, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.7003, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.020446413358323395, | |
| "grad_norm": 17.040071487426758, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0002, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.020446413358323395, | |
| "eval_loss": 0.9968551993370056, | |
| "eval_runtime": 51.8197, | |
| "eval_samples_per_second": 11.926, | |
| "eval_steps_per_second": 5.963, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02385414891804396, | |
| "grad_norm": 9.234129905700684, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.7241, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.027261884477764526, | |
| "grad_norm": 10.225706100463867, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5404, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.027261884477764526, | |
| "eval_loss": 0.7299230098724365, | |
| "eval_runtime": 51.8588, | |
| "eval_samples_per_second": 11.917, | |
| "eval_steps_per_second": 5.958, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03066962003748509, | |
| "grad_norm": 7.497749328613281, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.7514, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03407735559720566, | |
| "grad_norm": 5.096440315246582, | |
| "learning_rate": 0.0, | |
| "loss": 0.3999, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03407735559720566, | |
| "eval_loss": 0.5272278785705566, | |
| "eval_runtime": 51.9113, | |
| "eval_samples_per_second": 11.905, | |
| "eval_steps_per_second": 5.952, | |
| "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": 9247982302003200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |