| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.021193924408336277, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00028258565877781704, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00028258565877781704, | |
| "eval_loss": NaN, | |
| "eval_runtime": 91.2489, | |
| "eval_samples_per_second": 16.329, | |
| "eval_steps_per_second": 8.164, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005651713175556341, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008477569763334511, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011303426351112682, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.997620553954645e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001412928293889085, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.990486745229364e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016955139526669022, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9786121534345265e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001978099611444719, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.962019382530521e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0022606852702225363, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.940740017799833e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002543270929000353, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.914814565722671e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00282585658777817, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.884292376870567e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0031084422465559873, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.849231551964771e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0033910279053338045, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8096988312782174e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003673613564111621, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.765769467591625e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003956199222889438, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.717527082945554e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0042387848816672555, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.665063509461097e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004521370540445073, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.608478614532215e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00480395619922289, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.54788011072248e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.005086541858000706, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4833833507280884e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005369127516778523, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.415111107797445e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00565171317555634, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.34319334202531e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0059342988343341575, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006216884493111975, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.188975519039151e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006499470151889792, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.1069690242163484e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006782055810667609, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.021903572521802e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.007064641469445425, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.933941090877615e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007064641469445425, | |
| "eval_loss": NaN, | |
| "eval_runtime": 90.8959, | |
| "eval_samples_per_second": 16.392, | |
| "eval_steps_per_second": 8.196, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007347227128223242, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.84324902086706e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0076298127870010595, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007912398445778877, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.654371533087586e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.008194984104556694, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.556545654351749e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.008477569763334511, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.456708580912725e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008760155422112328, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.355050358314172e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.009042741080890145, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.251764498760683e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.009325326739667962, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.147047612756302e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.00960791239844578, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0410990348452573e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.009890498057223597, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9341204441673266e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.010173083716001412, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8263154805501297e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01045566937477923, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.717889356869146e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.010738255033557046, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6090484684133404e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.011020840692334864, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.01130342635111268, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3909515315866605e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011586012009890498, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2821106431308544e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.011868597668668315, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.173684519449872e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.012151183327446132, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0658795558326743e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.01243376898622395, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.958900965154743e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.012716354645001766, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.852952387243698e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.012998940303779584, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7482355012393177e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0132815259625574, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6449496416858284e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.013564111621335218, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5432914190872757e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.013846697280113035, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.443454345648252e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.01412928293889085, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3456284669124158e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01412928293889085, | |
| "eval_loss": NaN, | |
| "eval_runtime": 90.3579, | |
| "eval_samples_per_second": 16.49, | |
| "eval_steps_per_second": 8.245, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.014411868597668668, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2500000000000006e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.014694454256446485, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1567509791329401e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.014977039915224302, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0660589091223855e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.015259625574002119, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.780964274781984e-06, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.015542211232779936, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.930309757836517e-06, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.015824796891557753, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.110244809608495e-06, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.016107382550335572, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.3223304703363135e-06, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.016389968209113388, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.568066579746901e-06, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.016672553867891203, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.848888922025553e-06, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.016955139526669022, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.166166492719124e-06, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.017237725185446837, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.521198892775203e-06, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.017520310844224656, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9152138546778625e-06, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.01780289650300247, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3493649053890326e-06, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.01808548216178029, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8247291705444575e-06, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.018368067820558106, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3423053240837515e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.018650653479335925, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9030116872178316e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.01893323913811374, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5076844803522922e-06, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.01921582479689156, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1570762312943295e-06, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.019498410455669375, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.51854342773295e-07, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.019780996114447193, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.925998220016659e-07, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.02006358177322501, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7980617469479953e-07, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.020346167432002824, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1387846565474045e-07, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.020628753090780643, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.513254770636137e-08, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.02091133874955846, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3794460453555047e-08, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.021193924408336277, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.021193924408336277, | |
| "eval_loss": NaN, | |
| "eval_runtime": 90.4859, | |
| "eval_samples_per_second": 16.467, | |
| "eval_steps_per_second": 8.233, | |
| "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": 1.4667956399112192e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |