| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 256, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00390625, | |
| "grad_norm": 1.1706680059432983, | |
| "learning_rate": 1.1538461538461538e-05, | |
| "loss": 1.9646, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01953125, | |
| "grad_norm": 1.8140126466751099, | |
| "learning_rate": 5.769230769230769e-05, | |
| "loss": 1.9391, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0390625, | |
| "grad_norm": 0.9559171795845032, | |
| "learning_rate": 0.00011538461538461538, | |
| "loss": 1.8731, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05859375, | |
| "grad_norm": 1.280180811882019, | |
| "learning_rate": 0.00017307692307692304, | |
| "loss": 1.663, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.078125, | |
| "grad_norm": 1.2522212266921997, | |
| "learning_rate": 0.00023076923076923076, | |
| "loss": 1.2646, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09765625, | |
| "grad_norm": 0.3725765645503998, | |
| "learning_rate": 0.00028846153846153843, | |
| "loss": 1.1492, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1171875, | |
| "grad_norm": 0.4075080156326294, | |
| "learning_rate": 0.00029977617052242417, | |
| "loss": 1.0681, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13671875, | |
| "grad_norm": 0.572589635848999, | |
| "learning_rate": 0.0002988680080036802, | |
| "loss": 1.0165, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.15625, | |
| "grad_norm": 0.30389469861984253, | |
| "learning_rate": 0.00029726575411133377, | |
| "loss": 0.9663, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.17578125, | |
| "grad_norm": 0.24198134243488312, | |
| "learning_rate": 0.0002949768792926617, | |
| "loss": 0.9329, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1953125, | |
| "grad_norm": 0.19795848429203033, | |
| "learning_rate": 0.00029201205533865653, | |
| "loss": 0.9227, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.21484375, | |
| "grad_norm": 0.19215987622737885, | |
| "learning_rate": 0.00028838510562721075, | |
| "loss": 0.9304, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.234375, | |
| "grad_norm": 0.18681851029396057, | |
| "learning_rate": 0.00028411294067214764, | |
| "loss": 0.9045, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.25390625, | |
| "grad_norm": 0.17366646230220795, | |
| "learning_rate": 0.00027921547927859996, | |
| "loss": 0.8884, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.2734375, | |
| "grad_norm": 0.1574220508337021, | |
| "learning_rate": 0.0002737155556723452, | |
| "loss": 0.8777, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.29296875, | |
| "grad_norm": 0.17448483407497406, | |
| "learning_rate": 0.0002676388130361047, | |
| "loss": 0.8948, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.3125, | |
| "grad_norm": 0.15831591188907623, | |
| "learning_rate": 0.00026101358394918777, | |
| "loss": 0.8762, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.33203125, | |
| "grad_norm": 0.1556362807750702, | |
| "learning_rate": 0.0002538707582879288, | |
| "loss": 0.8668, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.3515625, | |
| "grad_norm": 0.1763574779033661, | |
| "learning_rate": 0.00024624363920282413, | |
| "loss": 0.8855, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.37109375, | |
| "grad_norm": 0.18880251049995422, | |
| "learning_rate": 0.00023816778784387094, | |
| "loss": 0.8553, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.390625, | |
| "grad_norm": 0.1806374490261078, | |
| "learning_rate": 0.0002296808575580705, | |
| "loss": 0.8632, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.41015625, | |
| "grad_norm": 0.15463082492351532, | |
| "learning_rate": 0.0002208224183321428, | |
| "loss": 0.8585, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.4296875, | |
| "grad_norm": 0.16831685602664948, | |
| "learning_rate": 0.00021163377229898225, | |
| "loss": 0.8478, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.44921875, | |
| "grad_norm": 0.18693634867668152, | |
| "learning_rate": 0.00020215776116804833, | |
| "loss": 0.8508, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.46875, | |
| "grad_norm": 0.17928317189216614, | |
| "learning_rate": 0.00019243856647753948, | |
| "loss": 0.8551, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.48828125, | |
| "grad_norm": 0.16863255202770233, | |
| "learning_rate": 0.00018252150359966712, | |
| "loss": 0.8521, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.5078125, | |
| "grad_norm": 0.16852350533008575, | |
| "learning_rate": 0.00017245281045947164, | |
| "loss": 0.849, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.52734375, | |
| "grad_norm": 0.182328999042511, | |
| "learning_rate": 0.00016227943195227197, | |
| "loss": 0.8521, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.546875, | |
| "grad_norm": 0.18237030506134033, | |
| "learning_rate": 0.00015204880106489262, | |
| "loss": 0.8487, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.56640625, | |
| "grad_norm": 0.20504002273082733, | |
| "learning_rate": 0.0001418086177211835, | |
| "loss": 0.8422, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.5859375, | |
| "grad_norm": 0.21228522062301636, | |
| "learning_rate": 0.00013160662638295526, | |
| "loss": 0.8317, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.60546875, | |
| "grad_norm": 0.20387493073940277, | |
| "learning_rate": 0.00012149039344325893, | |
| "loss": 0.8359, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.625, | |
| "grad_norm": 0.22508500516414642, | |
| "learning_rate": 0.00011150708544990398, | |
| "loss": 0.8432, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.64453125, | |
| "grad_norm": 0.1838555485010147, | |
| "learning_rate": 0.00010170324919323928, | |
| "loss": 0.8395, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.6640625, | |
| "grad_norm": 0.17921607196331024, | |
| "learning_rate": 9.212459468352966e-05, | |
| "loss": 0.8267, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.68359375, | |
| "grad_norm": 0.1911832094192505, | |
| "learning_rate": 8.281578202978773e-05, | |
| "loss": 0.8271, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.703125, | |
| "grad_norm": 0.17375214397907257, | |
| "learning_rate": 7.382021321372908e-05, | |
| "loss": 0.833, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.72265625, | |
| "grad_norm": 0.204771026968956, | |
| "learning_rate": 6.517982972969911e-05, | |
| "loss": 0.8364, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.7421875, | |
| "grad_norm": 0.20459486544132233, | |
| "learning_rate": 5.693491703406478e-05, | |
| "loss": 0.8256, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.76171875, | |
| "grad_norm": 0.1818506121635437, | |
| "learning_rate": 4.912391671582092e-05, | |
| "loss": 0.8423, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.78125, | |
| "grad_norm": 0.1734897941350937, | |
| "learning_rate": 4.178324726415664e-05, | |
| "loss": 0.8291, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.80078125, | |
| "grad_norm": 0.18124301731586456, | |
| "learning_rate": 3.494713426864761e-05, | |
| "loss": 0.8296, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.8203125, | |
| "grad_norm": 0.1811358779668808, | |
| "learning_rate": 2.8647450843757897e-05, | |
| "loss": 0.8402, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.83984375, | |
| "grad_norm": 0.20237997174263, | |
| "learning_rate": 2.291356902166746e-05, | |
| "loss": 0.8219, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.859375, | |
| "grad_norm": 0.17338159680366516, | |
| "learning_rate": 1.7772222806299264e-05, | |
| "loss": 0.8263, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.87890625, | |
| "grad_norm": 0.17720431089401245, | |
| "learning_rate": 1.3247383527051985e-05, | |
| "loss": 0.8302, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.8984375, | |
| "grad_norm": 0.1745912879705429, | |
| "learning_rate": 9.360148073396962e-06, | |
| "loss": 0.8252, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.91796875, | |
| "grad_norm": 0.1862880140542984, | |
| "learning_rate": 6.128640531440515e-06, | |
| "loss": 0.8411, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.9375, | |
| "grad_norm": 0.17852172255516052, | |
| "learning_rate": 3.5679276810683167e-06, | |
| "loss": 0.8201, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.95703125, | |
| "grad_norm": 0.19089260697364807, | |
| "learning_rate": 1.6899487476622898e-06, | |
| "loss": 0.8322, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.9765625, | |
| "grad_norm": 0.1653287410736084, | |
| "learning_rate": 5.034597359205639e-07, | |
| "loss": 0.832, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.99609375, | |
| "grad_norm": 0.17792922258377075, | |
| "learning_rate": 1.3992605321688776e-08, | |
| "loss": 0.8284, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 256, | |
| "total_flos": 7.558147382936863e+17, | |
| "train_loss": 0.0, | |
| "train_runtime": 1.5255, | |
| "train_samples_per_second": 10721.267, | |
| "train_steps_per_second": 167.817 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 256, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.558147382936863e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |