| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 820, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.024390243902439025, | |
| "grad_norm": 0.13146615028381348, | |
| "learning_rate": 0.00019631901840490797, | |
| "loss": 2.6062, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04878048780487805, | |
| "grad_norm": 0.11177688837051392, | |
| "learning_rate": 0.0001914110429447853, | |
| "loss": 2.3258, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07317073170731707, | |
| "grad_norm": 0.1093992292881012, | |
| "learning_rate": 0.00018650306748466258, | |
| "loss": 2.327, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0975609756097561, | |
| "grad_norm": 0.1171504482626915, | |
| "learning_rate": 0.00018159509202453987, | |
| "loss": 2.2707, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.12195121951219512, | |
| "grad_norm": 0.10171514004468918, | |
| "learning_rate": 0.0001766871165644172, | |
| "loss": 2.2441, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14634146341463414, | |
| "grad_norm": 0.12730270624160767, | |
| "learning_rate": 0.0001717791411042945, | |
| "loss": 2.1971, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.17073170731707318, | |
| "grad_norm": 0.15077818930149078, | |
| "learning_rate": 0.00016687116564417177, | |
| "loss": 2.2968, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1951219512195122, | |
| "grad_norm": 0.10773204267024994, | |
| "learning_rate": 0.00016196319018404909, | |
| "loss": 2.188, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.21951219512195122, | |
| "grad_norm": 0.16448411345481873, | |
| "learning_rate": 0.0001570552147239264, | |
| "loss": 2.1903, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.24390243902439024, | |
| "grad_norm": 0.1230635941028595, | |
| "learning_rate": 0.0001521472392638037, | |
| "loss": 2.2464, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2682926829268293, | |
| "grad_norm": 0.11764346063137054, | |
| "learning_rate": 0.00014723926380368098, | |
| "loss": 2.2082, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.2926829268292683, | |
| "grad_norm": 0.1021975502371788, | |
| "learning_rate": 0.00014233128834355828, | |
| "loss": 2.1972, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.3170731707317073, | |
| "grad_norm": 0.12520350515842438, | |
| "learning_rate": 0.0001374233128834356, | |
| "loss": 2.1768, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.34146341463414637, | |
| "grad_norm": 0.10592948645353317, | |
| "learning_rate": 0.00013251533742331288, | |
| "loss": 2.1624, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.36585365853658536, | |
| "grad_norm": 0.11086229979991913, | |
| "learning_rate": 0.00012760736196319017, | |
| "loss": 2.1809, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.3902439024390244, | |
| "grad_norm": 0.1199096217751503, | |
| "learning_rate": 0.0001226993865030675, | |
| "loss": 2.1735, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.4146341463414634, | |
| "grad_norm": 0.11156365275382996, | |
| "learning_rate": 0.0001177914110429448, | |
| "loss": 2.2331, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.43902439024390244, | |
| "grad_norm": 0.10787837207317352, | |
| "learning_rate": 0.00011288343558282209, | |
| "loss": 2.1008, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.4634146341463415, | |
| "grad_norm": 0.1065380647778511, | |
| "learning_rate": 0.00010797546012269939, | |
| "loss": 2.228, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.4878048780487805, | |
| "grad_norm": 0.13571393489837646, | |
| "learning_rate": 0.0001030674846625767, | |
| "loss": 2.2502, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.5121951219512195, | |
| "grad_norm": 0.12763665616512299, | |
| "learning_rate": 9.815950920245399e-05, | |
| "loss": 2.2069, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.5365853658536586, | |
| "grad_norm": 0.12322117388248444, | |
| "learning_rate": 9.325153374233129e-05, | |
| "loss": 2.1653, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.5609756097560976, | |
| "grad_norm": 0.11602451652288437, | |
| "learning_rate": 8.83435582822086e-05, | |
| "loss": 2.204, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.5853658536585366, | |
| "grad_norm": 0.13550212979316711, | |
| "learning_rate": 8.343558282208588e-05, | |
| "loss": 2.1583, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.6097560975609756, | |
| "grad_norm": 0.09856979548931122, | |
| "learning_rate": 7.85276073619632e-05, | |
| "loss": 2.1924, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.6341463414634146, | |
| "grad_norm": 0.1261129528284073, | |
| "learning_rate": 7.361963190184049e-05, | |
| "loss": 2.1347, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.6585365853658537, | |
| "grad_norm": 0.1323924958705902, | |
| "learning_rate": 6.87116564417178e-05, | |
| "loss": 2.1493, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.6829268292682927, | |
| "grad_norm": 0.12028100341558456, | |
| "learning_rate": 6.380368098159509e-05, | |
| "loss": 2.1703, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.7073170731707317, | |
| "grad_norm": 0.11706235259771347, | |
| "learning_rate": 5.88957055214724e-05, | |
| "loss": 2.1665, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.7317073170731707, | |
| "grad_norm": 0.12799355387687683, | |
| "learning_rate": 5.3987730061349695e-05, | |
| "loss": 2.1631, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.7560975609756098, | |
| "grad_norm": 0.10057336091995239, | |
| "learning_rate": 4.907975460122699e-05, | |
| "loss": 2.2172, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.7804878048780488, | |
| "grad_norm": 0.15589593350887299, | |
| "learning_rate": 4.41717791411043e-05, | |
| "loss": 2.1731, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.8048780487804879, | |
| "grad_norm": 0.11708714812994003, | |
| "learning_rate": 3.92638036809816e-05, | |
| "loss": 2.1731, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.8292682926829268, | |
| "grad_norm": 0.11283290386199951, | |
| "learning_rate": 3.43558282208589e-05, | |
| "loss": 2.1074, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.8536585365853658, | |
| "grad_norm": 0.11966817826032639, | |
| "learning_rate": 2.94478527607362e-05, | |
| "loss": 2.1979, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.8780487804878049, | |
| "grad_norm": 0.15318670868873596, | |
| "learning_rate": 2.4539877300613496e-05, | |
| "loss": 2.1476, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.9024390243902439, | |
| "grad_norm": 0.12104146927595139, | |
| "learning_rate": 1.96319018404908e-05, | |
| "loss": 2.2062, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.926829268292683, | |
| "grad_norm": 0.14861464500427246, | |
| "learning_rate": 1.47239263803681e-05, | |
| "loss": 2.1754, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.9512195121951219, | |
| "grad_norm": 0.11242931336164474, | |
| "learning_rate": 9.8159509202454e-06, | |
| "loss": 2.172, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.975609756097561, | |
| "grad_norm": 0.1298566460609436, | |
| "learning_rate": 4.9079754601227e-06, | |
| "loss": 2.1327, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.14202716946601868, | |
| "learning_rate": 0.0, | |
| "loss": 2.1028, | |
| "step": 820 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 820, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.1324741394592563e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |