| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.015194489465153971, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002025931928687196, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002025931928687196, | |
| "eval_loss": NaN, | |
| "eval_runtime": 71.975, | |
| "eval_samples_per_second": 28.885, | |
| "eval_steps_per_second": 14.449, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004051863857374392, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006077795786061589, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008103727714748784, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.997620553954645e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001012965964343598, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.990486745229364e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0012155591572123178, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9786121534345265e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0014181523500810373, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.962019382530521e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0016207455429497568, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.940740017799833e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0018233387358184765, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.914814565722671e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002025931928687196, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.884292376870567e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002228525121555916, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.849231551964771e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0024311183144246355, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8096988312782174e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002633711507293355, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.765769467591625e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0028363047001620746, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.717527082945554e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0030388978930307943, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.665063509461097e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0032414910858995136, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.608478614532215e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0034440842787682334, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.54788011072248e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.003646677471636953, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4833833507280884e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0038492706645056724, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.415111107797445e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.004051863857374392, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.34319334202531e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0042544570502431114, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004457050243111832, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.188975519039151e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.004659643435980551, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.1069690242163484e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004862236628849271, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.021903572521802e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00506482982171799, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.933941090877615e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00506482982171799, | |
| "eval_loss": NaN, | |
| "eval_runtime": 71.6128, | |
| "eval_samples_per_second": 29.031, | |
| "eval_steps_per_second": 14.523, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00526742301458671, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.84324902086706e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.00547001620745543, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.005672609400324149, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.654371533087586e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0058752025931928685, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.556545654351749e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.006077795786061589, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.456708580912725e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006280388978930308, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.355050358314172e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.006482982171799027, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.251764498760683e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.006685575364667747, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.147047612756302e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.006888168557536467, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0410990348452573e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.007090761750405186, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9341204441673266e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.007293354943273906, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8263154805501297e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0074959481361426255, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.717889356869146e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.007698541329011345, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6090484684133404e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.007901134521880064, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.008103727714748784, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3909515315866605e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008306320907617504, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2821106431308544e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.008508914100486223, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.173684519449872e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.008711507293354943, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0658795558326743e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.008914100486223663, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.958900965154743e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.009116693679092382, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.852952387243698e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.009319286871961102, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7482355012393177e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.009521880064829822, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6449496416858284e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.009724473257698542, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5432914190872757e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.00992706645056726, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.443454345648252e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.01012965964343598, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3456284669124158e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01012965964343598, | |
| "eval_loss": NaN, | |
| "eval_runtime": 71.5185, | |
| "eval_samples_per_second": 29.069, | |
| "eval_steps_per_second": 14.542, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.010332252836304701, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2500000000000006e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.01053484602917342, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1567509791329401e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.01073743922204214, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0660589091223855e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.01094003241491086, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.780964274781984e-06, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.011142625607779578, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.930309757836517e-06, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.011345218800648298, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.110244809608495e-06, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.011547811993517018, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.3223304703363135e-06, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.011750405186385737, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.568066579746901e-06, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.011952998379254457, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.848888922025553e-06, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.012155591572123177, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.166166492719124e-06, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.012358184764991896, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.521198892775203e-06, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.012560777957860616, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9152138546778625e-06, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.012763371150729336, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3493649053890326e-06, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.012965964343598054, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8247291705444575e-06, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.013168557536466775, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3423053240837515e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.013371150729335495, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9030116872178316e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.013573743922204213, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5076844803522922e-06, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.013776337115072933, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1570762312943295e-06, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.013978930307941654, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.51854342773295e-07, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.014181523500810372, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.925998220016659e-07, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.014384116693679092, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7980617469479953e-07, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.014586709886547812, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1387846565474045e-07, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.01478930307941653, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.513254770636137e-08, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.014991896272285251, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3794460453555047e-08, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.015194489465153971, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.015194489465153971, | |
| "eval_loss": NaN, | |
| "eval_runtime": 71.4978, | |
| "eval_samples_per_second": 29.078, | |
| "eval_steps_per_second": 14.546, | |
| "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": 7865367200268288.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |