| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 1320, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11363636363636363, | |
| "grad_norm": 3.6305034160614014, | |
| "learning_rate": 1.925757575757576e-05, | |
| "loss": 3.2806, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.22727272727272727, | |
| "grad_norm": 2.281816244125366, | |
| "learning_rate": 1.8500000000000002e-05, | |
| "loss": 2.4506, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3409090909090909, | |
| "grad_norm": 2.2095892429351807, | |
| "learning_rate": 1.7742424242424242e-05, | |
| "loss": 2.1299, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.45454545454545453, | |
| "grad_norm": 2.5947232246398926, | |
| "learning_rate": 1.6984848484848488e-05, | |
| "loss": 1.9122, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5681818181818182, | |
| "grad_norm": 2.4549477100372314, | |
| "learning_rate": 1.622727272727273e-05, | |
| "loss": 1.7845, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6818181818181818, | |
| "grad_norm": 2.7835488319396973, | |
| "learning_rate": 1.546969696969697e-05, | |
| "loss": 1.72, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7954545454545454, | |
| "grad_norm": 2.144644260406494, | |
| "learning_rate": 1.4712121212121213e-05, | |
| "loss": 1.6272, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 3.0163283348083496, | |
| "learning_rate": 1.3954545454545457e-05, | |
| "loss": 1.5849, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.0227272727272727, | |
| "grad_norm": 2.3680009841918945, | |
| "learning_rate": 1.3196969696969696e-05, | |
| "loss": 1.4882, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.1363636363636362, | |
| "grad_norm": 4.114340305328369, | |
| "learning_rate": 1.243939393939394e-05, | |
| "loss": 1.4369, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 2.8105506896972656, | |
| "learning_rate": 1.1681818181818183e-05, | |
| "loss": 1.4074, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.3636363636363638, | |
| "grad_norm": 2.8310678005218506, | |
| "learning_rate": 1.0924242424242426e-05, | |
| "loss": 1.3947, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.4772727272727273, | |
| "grad_norm": 2.5817012786865234, | |
| "learning_rate": 1.0166666666666667e-05, | |
| "loss": 1.3374, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.5909090909090908, | |
| "grad_norm": 2.7582809925079346, | |
| "learning_rate": 9.40909090909091e-06, | |
| "loss": 1.3187, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.7045454545454546, | |
| "grad_norm": 2.8198204040527344, | |
| "learning_rate": 8.651515151515152e-06, | |
| "loss": 1.3353, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.8181818181818183, | |
| "grad_norm": 2.636787176132202, | |
| "learning_rate": 7.893939393939395e-06, | |
| "loss": 1.3196, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.9318181818181817, | |
| "grad_norm": 2.5723042488098145, | |
| "learning_rate": 7.136363636363637e-06, | |
| "loss": 1.3137, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.0454545454545454, | |
| "grad_norm": 2.4720075130462646, | |
| "learning_rate": 6.37878787878788e-06, | |
| "loss": 1.3009, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.159090909090909, | |
| "grad_norm": 3.039733648300171, | |
| "learning_rate": 5.6212121212121215e-06, | |
| "loss": 1.2022, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.2727272727272725, | |
| "grad_norm": 2.657588243484497, | |
| "learning_rate": 4.863636363636364e-06, | |
| "loss": 1.2119, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.3863636363636362, | |
| "grad_norm": 2.3504629135131836, | |
| "learning_rate": 4.106060606060606e-06, | |
| "loss": 1.2174, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 2.6929402351379395, | |
| "learning_rate": 3.3484848484848487e-06, | |
| "loss": 1.2055, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.6136363636363638, | |
| "grad_norm": 2.170069932937622, | |
| "learning_rate": 2.590909090909091e-06, | |
| "loss": 1.2235, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.7272727272727275, | |
| "grad_norm": 2.4112389087677, | |
| "learning_rate": 1.8333333333333333e-06, | |
| "loss": 1.1969, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.840909090909091, | |
| "grad_norm": 2.7049269676208496, | |
| "learning_rate": 1.0757575757575758e-06, | |
| "loss": 1.2136, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.9545454545454546, | |
| "grad_norm": 2.719223976135254, | |
| "learning_rate": 3.181818181818182e-07, | |
| "loss": 1.202, | |
| "step": 1300 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 1320, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2692954290166848.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |