| { | |
| "best_metric": 2.0614235401153564, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.18181818181818182, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0036363636363636364, | |
| "grad_norm": 5.301558971405029, | |
| "learning_rate": 2e-05, | |
| "loss": 4.6837, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0036363636363636364, | |
| "eval_loss": 4.996428966522217, | |
| "eval_runtime": 16.332, | |
| "eval_samples_per_second": 28.349, | |
| "eval_steps_per_second": 3.551, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007272727272727273, | |
| "grad_norm": 4.122321128845215, | |
| "learning_rate": 4e-05, | |
| "loss": 4.0658, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01090909090909091, | |
| "grad_norm": 4.729526996612549, | |
| "learning_rate": 6e-05, | |
| "loss": 4.4412, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.014545454545454545, | |
| "grad_norm": 5.44406795501709, | |
| "learning_rate": 8e-05, | |
| "loss": 4.9525, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01818181818181818, | |
| "grad_norm": 4.86469841003418, | |
| "learning_rate": 0.0001, | |
| "loss": 4.9367, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02181818181818182, | |
| "grad_norm": 5.874657154083252, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 4.7384, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.025454545454545455, | |
| "grad_norm": 5.480888366699219, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 4.2604, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02909090909090909, | |
| "grad_norm": 2.321042537689209, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 2.3919, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03272727272727273, | |
| "grad_norm": 2.5301353931427, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 2.6209, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03636363636363636, | |
| "grad_norm": 2.511705160140991, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 2.5702, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 2.504190444946289, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 2.6799, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04363636363636364, | |
| "grad_norm": 2.3854761123657227, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 2.496, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04727272727272727, | |
| "grad_norm": 2.252695083618164, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 2.5682, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.05090909090909091, | |
| "grad_norm": 2.9842593669891357, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 2.5234, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05454545454545454, | |
| "grad_norm": 2.452545404434204, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 2.5165, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05818181818181818, | |
| "grad_norm": 1.9901292324066162, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 2.2514, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06181818181818182, | |
| "grad_norm": 1.9319262504577637, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 2.115, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06545454545454546, | |
| "grad_norm": 2.623239755630493, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 2.3468, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06909090909090909, | |
| "grad_norm": 2.582571506500244, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 2.3558, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.07272727272727272, | |
| "grad_norm": 2.57682466506958, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.4353, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07636363636363637, | |
| "grad_norm": 2.5038254261016846, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 2.5775, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 1.9422601461410522, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 1.9987, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.08363636363636363, | |
| "grad_norm": 2.397315740585327, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 2.1462, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.08727272727272728, | |
| "grad_norm": 2.152684450149536, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 2.3077, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09090909090909091, | |
| "grad_norm": 2.3351070880889893, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 2.4673, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09090909090909091, | |
| "eval_loss": 2.2046091556549072, | |
| "eval_runtime": 16.6106, | |
| "eval_samples_per_second": 27.874, | |
| "eval_steps_per_second": 3.492, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09454545454545454, | |
| "grad_norm": 2.232198476791382, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 2.3027, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.09818181818181818, | |
| "grad_norm": 2.7883410453796387, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 2.443, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.10181818181818182, | |
| "grad_norm": 2.533133029937744, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 2.4495, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.10545454545454545, | |
| "grad_norm": 2.0543668270111084, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 1.9154, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.10909090909090909, | |
| "grad_norm": 2.120340585708618, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 1.9321, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11272727272727273, | |
| "grad_norm": 2.3573496341705322, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 2.2358, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.11636363636363636, | |
| "grad_norm": 2.295992851257324, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 2.1238, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 2.4279768466949463, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 2.3682, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.12363636363636364, | |
| "grad_norm": 2.529550313949585, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 2.209, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.12727272727272726, | |
| "grad_norm": 2.266796350479126, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.1055, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.13090909090909092, | |
| "grad_norm": 2.4525721073150635, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 2.1957, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.13454545454545455, | |
| "grad_norm": 1.8528436422348022, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 1.8631, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.13818181818181818, | |
| "grad_norm": 1.8262501955032349, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 2.0233, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.14181818181818182, | |
| "grad_norm": 2.080160617828369, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 1.884, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.14545454545454545, | |
| "grad_norm": 2.064708709716797, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 2.0776, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14909090909090908, | |
| "grad_norm": 2.0797815322875977, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 2.0999, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.15272727272727274, | |
| "grad_norm": 2.636698007583618, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 2.0736, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.15636363636363637, | |
| "grad_norm": 3.001413345336914, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 2.1067, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 2.8234450817108154, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 2.7408, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.16363636363636364, | |
| "grad_norm": 2.3741395473480225, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 2.0327, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.16727272727272727, | |
| "grad_norm": 2.951899290084839, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 2.312, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1709090909090909, | |
| "grad_norm": 3.7195920944213867, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 1.9652, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.17454545454545456, | |
| "grad_norm": 3.5826423168182373, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 2.4803, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1781818181818182, | |
| "grad_norm": 3.770677328109741, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 2.265, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": 5.106058120727539, | |
| "learning_rate": 0.0, | |
| "loss": 2.3384, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "eval_loss": 2.0614235401153564, | |
| "eval_runtime": 16.6414, | |
| "eval_samples_per_second": 27.822, | |
| "eval_steps_per_second": 3.485, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.5547217133568e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |