| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.32674399607907206, | |
| "global_step": 10000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 3.729578500245058e-05, | |
| "loss": 6.3916, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 3.7091570004901157e-05, | |
| "loss": 5.0294, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 3.6887355007351737e-05, | |
| "loss": 4.6716, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3.6683140009802316e-05, | |
| "loss": 4.4325, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 3.6478925012252896e-05, | |
| "loss": 4.2343, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 3.6274710014703476e-05, | |
| "loss": 4.1306, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 3.6070495017154056e-05, | |
| "loss": 4.056, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 3.5866280019604636e-05, | |
| "loss": 3.9515, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 3.5662065022055216e-05, | |
| "loss": 3.8561, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 3.5457850024505796e-05, | |
| "loss": 3.8194, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 3.5253635026956376e-05, | |
| "loss": 3.7632, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.5049420029406956e-05, | |
| "loss": 3.7016, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.4845205031857536e-05, | |
| "loss": 3.6589, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.4640990034308116e-05, | |
| "loss": 3.645, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 3.4436775036758696e-05, | |
| "loss": 3.5688, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.4232560039209276e-05, | |
| "loss": 3.558, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.4028345041659856e-05, | |
| "loss": 3.5789, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 3.3824130044110436e-05, | |
| "loss": 3.5275, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.3619915046561016e-05, | |
| "loss": 3.4434, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.3415700049011596e-05, | |
| "loss": 3.4455, | |
| "step": 10000 | |
| } | |
| ], | |
| "max_steps": 91815, | |
| "num_train_epochs": 3, | |
| "total_flos": 4657287913271424.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |