| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9990205680705191, | |
| "eval_steps": 500, | |
| "global_step": 510, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.039177277179236046, | |
| "grad_norm": 0.5212510228157043, | |
| "learning_rate": 0.00098, | |
| "loss": 1.6695, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07835455435847209, | |
| "grad_norm": 0.46687546372413635, | |
| "learning_rate": 0.00094, | |
| "loss": 1.4897, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11753183153770813, | |
| "grad_norm": 0.3956817388534546, | |
| "learning_rate": 0.0009000000000000001, | |
| "loss": 1.1361, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15670910871694418, | |
| "grad_norm": 0.6187575459480286, | |
| "learning_rate": 0.00086, | |
| "loss": 1.1006, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.1958863858961802, | |
| "grad_norm": 0.5952175259590149, | |
| "learning_rate": 0.00082, | |
| "loss": 1.1829, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.23506366307541626, | |
| "grad_norm": 0.5533424019813538, | |
| "learning_rate": 0.0007800000000000001, | |
| "loss": 1.1187, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2742409402546523, | |
| "grad_norm": 0.49875837564468384, | |
| "learning_rate": 0.00074, | |
| "loss": 1.1533, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.31341821743388837, | |
| "grad_norm": 0.3221249580383301, | |
| "learning_rate": 0.0007, | |
| "loss": 1.0684, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3525954946131244, | |
| "grad_norm": 0.4444270730018616, | |
| "learning_rate": 0.00066, | |
| "loss": 0.9958, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.3917727717923604, | |
| "grad_norm": 0.3522554337978363, | |
| "learning_rate": 0.00062, | |
| "loss": 1.0248, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4309500489715965, | |
| "grad_norm": 0.5420783162117004, | |
| "learning_rate": 0.00058, | |
| "loss": 0.8882, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.4701273261508325, | |
| "grad_norm": 0.390200674533844, | |
| "learning_rate": 0.00054, | |
| "loss": 1.057, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5093046033300686, | |
| "grad_norm": 0.29798322916030884, | |
| "learning_rate": 0.0005, | |
| "loss": 0.9993, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.5484818805093046, | |
| "grad_norm": 0.32027778029441833, | |
| "learning_rate": 0.00046, | |
| "loss": 31543.7594, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.5876591576885406, | |
| "grad_norm": 0.3356141746044159, | |
| "learning_rate": 0.00042, | |
| "loss": 1.0387, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6268364348677767, | |
| "grad_norm": 0.4466319680213928, | |
| "learning_rate": 0.00038, | |
| "loss": 1.0035, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.6660137120470128, | |
| "grad_norm": 0.34509071707725525, | |
| "learning_rate": 0.00034, | |
| "loss": 1.079, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7051909892262488, | |
| "grad_norm": 0.3388811945915222, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8813, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.7443682664054848, | |
| "grad_norm": 0.42653968930244446, | |
| "learning_rate": 0.00026000000000000003, | |
| "loss": 0.9738, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.7835455435847208, | |
| "grad_norm": 0.41174277663230896, | |
| "learning_rate": 0.00022, | |
| "loss": 1.0102, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.8227228207639569, | |
| "grad_norm": 0.2753573954105377, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.9923, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.861900097943193, | |
| "grad_norm": 0.4338860809803009, | |
| "learning_rate": 0.00014000000000000001, | |
| "loss": 0.9225, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.901077375122429, | |
| "grad_norm": 0.3668128252029419, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0012, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.940254652301665, | |
| "grad_norm": 0.20731355249881744, | |
| "learning_rate": 6e-05, | |
| "loss": 0.9247, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.9794319294809011, | |
| "grad_norm": 0.2774331867694855, | |
| "learning_rate": 2e-05, | |
| "loss": 1.0422, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.9990205680705191, | |
| "step": 510, | |
| "total_flos": 468651156894720.0, | |
| "train_loss": 1238.0412948421404, | |
| "train_runtime": 10118.6641, | |
| "train_samples_per_second": 0.101, | |
| "train_steps_per_second": 0.05 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 510, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 468651156894720.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |