| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.012854571942754306, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001713942925700574, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001713942925700574, | |
| "eval_loss": NaN, | |
| "eval_runtime": 469.2906, | |
| "eval_samples_per_second": 5.236, | |
| "eval_steps_per_second": 2.619, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003427885851401148, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005141828777101723, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006855771702802296, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.997620553954645e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008569714628502871, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.990486745229364e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0010283657554203446, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9786121534345265e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011997600479904018, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.962019382530521e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013711543405604593, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.940740017799833e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0015425486331305167, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.914814565722671e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0017139429257005741, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.884292376870567e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0018853372182706316, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.849231551964771e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.002056731510840689, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8096988312782174e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0022281258034107464, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.765769467591625e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0023995200959808036, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.717527082945554e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0025709143885508613, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.665063509461097e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0027423086811209185, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.608478614532215e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002913702973690976, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.54788011072248e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0030850972662610334, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4833833507280884e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003256491558831091, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.415111107797445e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0034278858514011482, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.34319334202531e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003599280143971206, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003770674436541263, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.188975519039151e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.003942068729111321, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.1069690242163484e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004113463021681378, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.021903572521802e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004284857314251435, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.933941090877615e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004284857314251435, | |
| "eval_loss": NaN, | |
| "eval_runtime": 468.6798, | |
| "eval_samples_per_second": 5.242, | |
| "eval_steps_per_second": 2.622, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004456251606821493, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.84324902086706e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0046276458993915505, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004799040191961607, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.654371533087586e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.004970434484531665, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.556545654351749e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.005141828777101723, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.456708580912725e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00531322306967178, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.355050358314172e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.005484617362241837, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.251764498760683e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.005656011654811895, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.147047612756302e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.005827405947381952, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0410990348452573e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.00599880023995201, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9341204441673266e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006170194532522067, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8263154805501297e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.006341588825092124, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.717889356869146e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.006512983117662182, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6090484684133404e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.00668437741023224, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0068557717028022965, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3909515315866605e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007027165995372354, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2821106431308544e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.007198560287942412, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.173684519449872e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0073699545805124686, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0658795558326743e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.007541348873082526, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.958900965154743e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.007712743165652584, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.852952387243698e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.007884137458222642, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7482355012393177e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.008055531750792698, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6449496416858284e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.008226926043362757, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5432914190872757e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.008398320335932814, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.443454345648252e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.00856971462850287, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3456284669124158e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00856971462850287, | |
| "eval_loss": NaN, | |
| "eval_runtime": 468.5593, | |
| "eval_samples_per_second": 5.244, | |
| "eval_steps_per_second": 2.623, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008741108921072929, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2500000000000006e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.008912503213642986, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1567509791329401e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.009083897506213042, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0660589091223855e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.009255291798783101, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.780964274781984e-06, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.009426686091353158, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.930309757836517e-06, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.009598080383923215, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.110244809608495e-06, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.009769474676493273, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.3223304703363135e-06, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.00994086896906333, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.568066579746901e-06, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.010112263261633388, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.848888922025553e-06, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.010283657554203445, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.166166492719124e-06, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.010455051846773502, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.521198892775203e-06, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.01062644613934356, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9152138546778625e-06, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.010797840431913617, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3493649053890326e-06, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.010969234724483674, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8247291705444575e-06, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.011140629017053733, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3423053240837515e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.01131202330962379, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9030116872178316e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.011483417602193846, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5076844803522922e-06, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.011654811894763905, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1570762312943295e-06, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.011826206187333961, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.51854342773295e-07, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.01199760047990402, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.925998220016659e-07, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.012168994772474077, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7980617469479953e-07, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.012340389065044133, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1387846565474045e-07, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.012511783357614192, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.513254770636137e-08, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.012683177650184249, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3794460453555047e-08, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.012854571942754306, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.012854571942754306, | |
| "eval_loss": NaN, | |
| "eval_runtime": 468.897, | |
| "eval_samples_per_second": 5.24, | |
| "eval_steps_per_second": 2.621, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.041709664305152e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |