| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9989594172736732, | |
| "eval_steps": 500, | |
| "global_step": 240, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04162330905306972, | |
| "grad_norm": 0.7745468616485596, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7706, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08324661810613944, | |
| "grad_norm": 0.5561801791191101, | |
| "learning_rate": 4e-05, | |
| "loss": 1.6448, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12486992715920915, | |
| "grad_norm": 0.23404787480831146, | |
| "learning_rate": 6e-05, | |
| "loss": 1.4716, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.16649323621227888, | |
| "grad_norm": 0.18818368017673492, | |
| "learning_rate": 8e-05, | |
| "loss": 1.3672, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2081165452653486, | |
| "grad_norm": 0.18688304722309113, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2657, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2497398543184183, | |
| "grad_norm": 0.1951465606689453, | |
| "learning_rate": 0.00012, | |
| "loss": 1.125, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.29136316337148804, | |
| "grad_norm": 0.1746235191822052, | |
| "learning_rate": 0.00014, | |
| "loss": 1.1003, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.33298647242455776, | |
| "grad_norm": 0.20920881628990173, | |
| "learning_rate": 0.00016, | |
| "loss": 1.0207, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.37460978147762747, | |
| "grad_norm": 0.22199565172195435, | |
| "learning_rate": 0.00018, | |
| "loss": 0.9757, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.4162330905306972, | |
| "grad_norm": 0.18666373193264008, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9414, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4578563995837669, | |
| "grad_norm": 0.2139161080121994, | |
| "learning_rate": 0.000199658449300667, | |
| "loss": 0.9025, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.4994797086368366, | |
| "grad_norm": 0.19018647074699402, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 0.904, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5411030176899063, | |
| "grad_norm": 0.28649064898490906, | |
| "learning_rate": 0.00019694002659393305, | |
| "loss": 0.9177, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5827263267429761, | |
| "grad_norm": 0.21059155464172363, | |
| "learning_rate": 0.00019458172417006347, | |
| "loss": 0.8929, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.6243496357960457, | |
| "grad_norm": 0.21605370938777924, | |
| "learning_rate": 0.00019157733266550575, | |
| "loss": 0.8692, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6659729448491155, | |
| "grad_norm": 0.204218327999115, | |
| "learning_rate": 0.0001879473751206489, | |
| "loss": 0.8661, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.7075962539021852, | |
| "grad_norm": 0.20825326442718506, | |
| "learning_rate": 0.00018371664782625287, | |
| "loss": 0.8508, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.7492195629552549, | |
| "grad_norm": 0.21748915314674377, | |
| "learning_rate": 0.00017891405093963938, | |
| "loss": 0.8912, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.7908428720083247, | |
| "grad_norm": 0.21721281111240387, | |
| "learning_rate": 0.00017357239106731317, | |
| "loss": 0.8368, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.8324661810613944, | |
| "grad_norm": 0.2268160879611969, | |
| "learning_rate": 0.00016772815716257412, | |
| "loss": 0.8407, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8740894901144641, | |
| "grad_norm": 0.25088444352149963, | |
| "learning_rate": 0.0001614212712689668, | |
| "loss": 0.8206, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.9157127991675338, | |
| "grad_norm": 0.2083650529384613, | |
| "learning_rate": 0.00015469481581224272, | |
| "loss": 0.8191, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.9573361082206036, | |
| "grad_norm": 0.20936889946460724, | |
| "learning_rate": 0.00014759473930370736, | |
| "loss": 0.8103, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.9989594172736732, | |
| "grad_norm": 0.2282739132642746, | |
| "learning_rate": 0.00014016954246529696, | |
| "loss": 0.7974, | |
| "step": 240 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 480, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 3.3445792601604096e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |