| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.8741258741258742, | |
| "eval_steps": 500, | |
| "global_step": 5500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01589319771137953, | |
| "grad_norm": 0.9081700444221497, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3142, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03178639542275906, | |
| "grad_norm": 0.8463758826255798, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0015, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04767959313413859, | |
| "grad_norm": 1.0305041074752808, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9429, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.06357279084551812, | |
| "grad_norm": 0.48407527804374695, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9406, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.07946598855689765, | |
| "grad_norm": 0.9855284690856934, | |
| "learning_rate": 0.0002, | |
| "loss": 1.79, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.09535918626827718, | |
| "grad_norm": 0.8263546228408813, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7586, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.11125238397965671, | |
| "grad_norm": 1.258915901184082, | |
| "learning_rate": 0.0002, | |
| "loss": 1.628, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.12714558169103624, | |
| "grad_norm": 0.7160557508468628, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4786, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.14303877940241577, | |
| "grad_norm": 2.1789512634277344, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4301, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.1589319771137953, | |
| "grad_norm": 0.34466424584388733, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5137, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.17482517482517482, | |
| "grad_norm": 1.9239227771759033, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4945, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.19071837253655435, | |
| "grad_norm": 1.7776683568954468, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3702, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.2066115702479339, | |
| "grad_norm": 1.5118937492370605, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4384, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.22250476795931343, | |
| "grad_norm": 1.504011869430542, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3728, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.23839796567069294, | |
| "grad_norm": 0.8850716352462769, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4082, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.25429116338207247, | |
| "grad_norm": 0.7327104210853577, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3342, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.270184361093452, | |
| "grad_norm": 0.9595212936401367, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3882, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.28607755880483154, | |
| "grad_norm": 2.5830607414245605, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2326, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.3019707565162111, | |
| "grad_norm": 1.852844476699829, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3595, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.3178639542275906, | |
| "grad_norm": 1.6929068565368652, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0967, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.3337571519389701, | |
| "grad_norm": 1.2370538711547852, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3132, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.34965034965034963, | |
| "grad_norm": 1.0512717962265015, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2205, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.36554354736172917, | |
| "grad_norm": 2.0815775394439697, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2684, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.3814367450731087, | |
| "grad_norm": 1.7328189611434937, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0058, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.39732994278448824, | |
| "grad_norm": 1.8121742010116577, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1701, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.4132231404958678, | |
| "grad_norm": 1.3292349576950073, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1467, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.4291163382072473, | |
| "grad_norm": 1.1031920909881592, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2143, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.44500953591862685, | |
| "grad_norm": 1.3371531963348389, | |
| "learning_rate": 0.0002, | |
| "loss": 0.996, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.46090273363000633, | |
| "grad_norm": 0.6710326671600342, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9845, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.47679593134138587, | |
| "grad_norm": 0.930266797542572, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0894, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.4926891290527654, | |
| "grad_norm": 1.5724022388458252, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0488, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.5085823267641449, | |
| "grad_norm": 1.4082521200180054, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1167, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.5244755244755245, | |
| "grad_norm": 1.9330273866653442, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9845, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.540368722186904, | |
| "grad_norm": 2.368753433227539, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0145, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.5562619198982836, | |
| "grad_norm": 0.16658253967761993, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9638, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.5721551176096631, | |
| "grad_norm": 1.6113061904907227, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0362, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.5880483153210426, | |
| "grad_norm": 1.9637274742126465, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9143, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.6039415130324222, | |
| "grad_norm": 1.396763801574707, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7685, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.6198347107438017, | |
| "grad_norm": 2.6856513023376465, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9068, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.6357279084551812, | |
| "grad_norm": 0.7980265617370605, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9764, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.6516211061665607, | |
| "grad_norm": 3.0948915481567383, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0757, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.6675143038779402, | |
| "grad_norm": 0.8271145820617676, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8772, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.6834075015893197, | |
| "grad_norm": 1.1177769899368286, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8533, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.6993006993006993, | |
| "grad_norm": 1.5585882663726807, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7309, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.7151938970120788, | |
| "grad_norm": 0.3275369107723236, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8906, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.7310870947234583, | |
| "grad_norm": 0.05096842721104622, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9252, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.7469802924348379, | |
| "grad_norm": 1.699520230293274, | |
| "learning_rate": 0.0002, | |
| "loss": 0.816, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.7628734901462174, | |
| "grad_norm": 1.1933566331863403, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9015, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.778766687857597, | |
| "grad_norm": 2.1289737224578857, | |
| "learning_rate": 0.0002, | |
| "loss": 0.659, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.7946598855689765, | |
| "grad_norm": 0.6902903318405151, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6742, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.810553083280356, | |
| "grad_norm": 2.0536046028137207, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7554, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.8264462809917356, | |
| "grad_norm": 0.2782207429409027, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7318, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.8423394787031151, | |
| "grad_norm": 0.13541792333126068, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7749, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.8582326764144946, | |
| "grad_norm": 2.2065443992614746, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7728, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.8741258741258742, | |
| "grad_norm": 1.3952250480651855, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8359, | |
| "step": 5500 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 6292, | |
| "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": 2.8051153354752e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |