|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.9952941176470587, |
|
"eval_steps": 500, |
|
"global_step": 212, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.047058823529411764, |
|
"grad_norm": 0.5000221729278564, |
|
"learning_rate": 4.9931407070965254e-05, |
|
"loss": 0.841, |
|
"num_input_tokens_seen": 114256, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.09411764705882353, |
|
"grad_norm": 0.38539719581604004, |
|
"learning_rate": 4.97260046830541e-05, |
|
"loss": 0.692, |
|
"num_input_tokens_seen": 225200, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.1411764705882353, |
|
"grad_norm": 0.275894433259964, |
|
"learning_rate": 4.9384919968379945e-05, |
|
"loss": 0.5684, |
|
"num_input_tokens_seen": 338592, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.18823529411764706, |
|
"grad_norm": 0.22247478365898132, |
|
"learning_rate": 4.891002460691306e-05, |
|
"loss": 0.5256, |
|
"num_input_tokens_seen": 455856, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.23529411764705882, |
|
"grad_norm": 0.20748302340507507, |
|
"learning_rate": 4.83039245557597e-05, |
|
"loss": 0.483, |
|
"num_input_tokens_seen": 569056, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.2823529411764706, |
|
"grad_norm": 0.207512766122818, |
|
"learning_rate": 4.756994574914359e-05, |
|
"loss": 0.4401, |
|
"num_input_tokens_seen": 683408, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.32941176470588235, |
|
"grad_norm": 0.18322080373764038, |
|
"learning_rate": 4.6712115847560355e-05, |
|
"loss": 0.4162, |
|
"num_input_tokens_seen": 802032, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.3764705882352941, |
|
"grad_norm": 0.16893012821674347, |
|
"learning_rate": 4.573514213625505e-05, |
|
"loss": 0.3951, |
|
"num_input_tokens_seen": 917808, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.4235294117647059, |
|
"grad_norm": 0.17897149920463562, |
|
"learning_rate": 4.464438569430354e-05, |
|
"loss": 0.4007, |
|
"num_input_tokens_seen": 1037840, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.47058823529411764, |
|
"grad_norm": 0.14339417219161987, |
|
"learning_rate": 4.344583197604318e-05, |
|
"loss": 0.3672, |
|
"num_input_tokens_seen": 1154864, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.5176470588235295, |
|
"grad_norm": 0.1722479611635208, |
|
"learning_rate": 4.214605796628527e-05, |
|
"loss": 0.3764, |
|
"num_input_tokens_seen": 1273984, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.5647058823529412, |
|
"grad_norm": 0.15474933385849, |
|
"learning_rate": 4.075219608954278e-05, |
|
"loss": 0.361, |
|
"num_input_tokens_seen": 1391904, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.611764705882353, |
|
"grad_norm": 0.14795532822608948, |
|
"learning_rate": 3.927189507131938e-05, |
|
"loss": 0.3472, |
|
"num_input_tokens_seen": 1506640, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.6588235294117647, |
|
"grad_norm": 0.1496661901473999, |
|
"learning_rate": 3.7713277966230514e-05, |
|
"loss": 0.3497, |
|
"num_input_tokens_seen": 1619120, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.7058823529411765, |
|
"grad_norm": 0.15912510454654694, |
|
"learning_rate": 3.608489758327472e-05, |
|
"loss": 0.3552, |
|
"num_input_tokens_seen": 1739248, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.7529411764705882, |
|
"grad_norm": 0.17292849719524384, |
|
"learning_rate": 3.4395689552855955e-05, |
|
"loss": 0.3369, |
|
"num_input_tokens_seen": 1854336, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"grad_norm": 0.1803598403930664, |
|
"learning_rate": 3.265492329309867e-05, |
|
"loss": 0.3302, |
|
"num_input_tokens_seen": 1971904, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.8470588235294118, |
|
"grad_norm": 0.171905979514122, |
|
"learning_rate": 3.0872151144524595e-05, |
|
"loss": 0.3305, |
|
"num_input_tokens_seen": 2080496, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.8941176470588236, |
|
"grad_norm": 0.17595848441123962, |
|
"learning_rate": 2.9057155952211502e-05, |
|
"loss": 0.3239, |
|
"num_input_tokens_seen": 2191968, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.9411764705882353, |
|
"grad_norm": 0.16902042925357819, |
|
"learning_rate": 2.7219897383073373e-05, |
|
"loss": 0.3111, |
|
"num_input_tokens_seen": 2306544, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.9882352941176471, |
|
"grad_norm": 0.17742857336997986, |
|
"learning_rate": 2.537045727284232e-05, |
|
"loss": 0.2959, |
|
"num_input_tokens_seen": 2418400, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 1.035294117647059, |
|
"grad_norm": 0.16856059432029724, |
|
"learning_rate": 2.3518984302657146e-05, |
|
"loss": 0.306, |
|
"num_input_tokens_seen": 2537984, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 1.0823529411764705, |
|
"grad_norm": 0.19464781880378723, |
|
"learning_rate": 2.1675638308842145e-05, |
|
"loss": 0.3206, |
|
"num_input_tokens_seen": 2656416, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 1.1294117647058823, |
|
"grad_norm": 0.17075157165527344, |
|
"learning_rate": 1.9850534531472546e-05, |
|
"loss": 0.3053, |
|
"num_input_tokens_seen": 2773280, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 1.1764705882352942, |
|
"grad_norm": 0.173744335770607, |
|
"learning_rate": 1.8053688107658908e-05, |
|
"loss": 0.3176, |
|
"num_input_tokens_seen": 2889024, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 1.223529411764706, |
|
"grad_norm": 0.18248489499092102, |
|
"learning_rate": 1.6294959114140034e-05, |
|
"loss": 0.2997, |
|
"num_input_tokens_seen": 3004880, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 1.2705882352941176, |
|
"grad_norm": 0.1806834191083908, |
|
"learning_rate": 1.4583998460759424e-05, |
|
"loss": 0.2954, |
|
"num_input_tokens_seen": 3117936, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 1.3176470588235294, |
|
"grad_norm": 0.1907871961593628, |
|
"learning_rate": 1.2930194931731382e-05, |
|
"loss": 0.3048, |
|
"num_input_tokens_seen": 3231712, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 1.3647058823529412, |
|
"grad_norm": 0.20322641730308533, |
|
"learning_rate": 1.1342623665304209e-05, |
|
"loss": 0.3208, |
|
"num_input_tokens_seen": 3350528, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 1.4117647058823528, |
|
"grad_norm": 0.16647660732269287, |
|
"learning_rate": 9.829996354535172e-06, |
|
"loss": 0.3015, |
|
"num_input_tokens_seen": 3464144, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 1.4588235294117646, |
|
"grad_norm": 0.18004418909549713, |
|
"learning_rate": 8.400613442446948e-06, |
|
"loss": 0.3106, |
|
"num_input_tokens_seen": 3580464, |
|
"step": 155 |
|
}, |
|
{ |
|
"epoch": 1.5058823529411764, |
|
"grad_norm": 0.1924523115158081, |
|
"learning_rate": 7.062318573891716e-06, |
|
"loss": 0.3055, |
|
"num_input_tokens_seen": 3695040, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 1.5529411764705883, |
|
"grad_norm": 0.19149142503738403, |
|
"learning_rate": 5.822455554065217e-06, |
|
"loss": 0.3069, |
|
"num_input_tokens_seen": 3812512, |
|
"step": 165 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"grad_norm": 0.19474638998508453, |
|
"learning_rate": 4.687828049857967e-06, |
|
"loss": 0.2806, |
|
"num_input_tokens_seen": 3922976, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 1.6470588235294117, |
|
"grad_norm": 0.19301049411296844, |
|
"learning_rate": 3.6646622551801345e-06, |
|
"loss": 0.2782, |
|
"num_input_tokens_seen": 4038656, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 1.6941176470588235, |
|
"grad_norm": 0.20220619440078735, |
|
"learning_rate": 2.75857272513132e-06, |
|
"loss": 0.3066, |
|
"num_input_tokens_seen": 4154032, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 1.7411764705882353, |
|
"grad_norm": 0.19466643035411835, |
|
"learning_rate": 1.9745315664982276e-06, |
|
"loss": 0.2908, |
|
"num_input_tokens_seen": 4267600, |
|
"step": 185 |
|
}, |
|
{ |
|
"epoch": 1.788235294117647, |
|
"grad_norm": 0.17281493544578552, |
|
"learning_rate": 1.3168411536452152e-06, |
|
"loss": 0.2829, |
|
"num_input_tokens_seen": 4382640, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 1.835294117647059, |
|
"grad_norm": 0.19972845911979675, |
|
"learning_rate": 7.891105195175358e-07, |
|
"loss": 0.2968, |
|
"num_input_tokens_seen": 4503040, |
|
"step": 195 |
|
}, |
|
{ |
|
"epoch": 1.8823529411764706, |
|
"grad_norm": 0.17375272512435913, |
|
"learning_rate": 3.9423555131007925e-07, |
|
"loss": 0.2968, |
|
"num_input_tokens_seen": 4618144, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.9294117647058824, |
|
"grad_norm": 0.17855483293533325, |
|
"learning_rate": 1.343830994765982e-07, |
|
"loss": 0.2879, |
|
"num_input_tokens_seen": 4731744, |
|
"step": 205 |
|
}, |
|
{ |
|
"epoch": 1.9764705882352942, |
|
"grad_norm": 0.20227883756160736, |
|
"learning_rate": 1.0979087280141298e-08, |
|
"loss": 0.3026, |
|
"num_input_tokens_seen": 4844416, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 1.9952941176470587, |
|
"num_input_tokens_seen": 4890624, |
|
"step": 212, |
|
"total_flos": 1.0960363294870733e+17, |
|
"train_loss": 0.36075482390961555, |
|
"train_runtime": 1824.8202, |
|
"train_samples_per_second": 3.726, |
|
"train_steps_per_second": 0.116 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 212, |
|
"num_input_tokens_seen": 4890624, |
|
"num_train_epochs": 2, |
|
"save_steps": 100, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1.0960363294870733e+17, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|