| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 4.9728, |
| "eval_steps": 500, |
| "global_step": 780, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.064, |
| "grad_norm": 115.26007653843197, |
| "learning_rate": 1.153846153846154e-06, |
| "loss": 1.8013, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.128, |
| "grad_norm": 10.569494321215535, |
| "learning_rate": 2.435897435897436e-06, |
| "loss": 0.9178, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.192, |
| "grad_norm": 4.124932595911465, |
| "learning_rate": 3.7179487179487184e-06, |
| "loss": 0.0701, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.256, |
| "grad_norm": 2.159300862803656, |
| "learning_rate": 5e-06, |
| "loss": 0.063, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 1.9071472971676064, |
| "learning_rate": 6.282051282051282e-06, |
| "loss": 0.0551, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.384, |
| "grad_norm": 1.77751831177194, |
| "learning_rate": 7.564102564102564e-06, |
| "loss": 0.1684, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.448, |
| "grad_norm": 2.8846747837228044, |
| "learning_rate": 8.846153846153847e-06, |
| "loss": 0.0594, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.512, |
| "grad_norm": 2.2232099871457214, |
| "learning_rate": 9.985754985754987e-06, |
| "loss": 0.0701, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.576, |
| "grad_norm": 0.17533270856659205, |
| "learning_rate": 9.843304843304844e-06, |
| "loss": 0.0472, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 4.6946861778266005, |
| "learning_rate": 9.700854700854701e-06, |
| "loss": 0.0884, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.704, |
| "grad_norm": 1.5944295283894352, |
| "learning_rate": 9.558404558404559e-06, |
| "loss": 0.0524, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.768, |
| "grad_norm": 12.143478923229893, |
| "learning_rate": 9.415954415954418e-06, |
| "loss": 0.0751, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.832, |
| "grad_norm": 1.928902876563226, |
| "learning_rate": 9.273504273504275e-06, |
| "loss": 0.0468, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.896, |
| "grad_norm": 6.170092925228969, |
| "learning_rate": 9.131054131054132e-06, |
| "loss": 0.0599, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 2.597167689806361, |
| "learning_rate": 8.988603988603988e-06, |
| "loss": 0.0391, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.0192, |
| "grad_norm": 1.6009822144938042, |
| "learning_rate": 8.846153846153847e-06, |
| "loss": 0.0651, |
| "step": 160 |
| }, |
| { |
| "epoch": 1.0832, |
| "grad_norm": 1.95329743835081, |
| "learning_rate": 8.703703703703705e-06, |
| "loss": 0.0458, |
| "step": 170 |
| }, |
| { |
| "epoch": 1.1472, |
| "grad_norm": 3.5182962689108472, |
| "learning_rate": 8.561253561253562e-06, |
| "loss": 0.042, |
| "step": 180 |
| }, |
| { |
| "epoch": 1.2112, |
| "grad_norm": 0.6280194803283852, |
| "learning_rate": 8.41880341880342e-06, |
| "loss": 0.0486, |
| "step": 190 |
| }, |
| { |
| "epoch": 1.2752, |
| "grad_norm": 2.005435993786338, |
| "learning_rate": 8.276353276353277e-06, |
| "loss": 0.044, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.3392, |
| "grad_norm": 3.625729078804922, |
| "learning_rate": 8.133903133903136e-06, |
| "loss": 0.0496, |
| "step": 210 |
| }, |
| { |
| "epoch": 1.4032, |
| "grad_norm": 5.776880834282877, |
| "learning_rate": 7.991452991452993e-06, |
| "loss": 0.0598, |
| "step": 220 |
| }, |
| { |
| "epoch": 1.4672, |
| "grad_norm": 1.6783013007732481, |
| "learning_rate": 7.849002849002849e-06, |
| "loss": 0.048, |
| "step": 230 |
| }, |
| { |
| "epoch": 1.5312000000000001, |
| "grad_norm": 1.663831218977686, |
| "learning_rate": 7.706552706552706e-06, |
| "loss": 0.0423, |
| "step": 240 |
| }, |
| { |
| "epoch": 1.5952, |
| "grad_norm": 1.9513045254560206, |
| "learning_rate": 7.564102564102564e-06, |
| "loss": 0.0481, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.6592, |
| "grad_norm": 2.2562075660922165, |
| "learning_rate": 7.421652421652423e-06, |
| "loss": 0.0498, |
| "step": 260 |
| }, |
| { |
| "epoch": 1.7231999999999998, |
| "grad_norm": 3.2420166505807773, |
| "learning_rate": 7.27920227920228e-06, |
| "loss": 0.029, |
| "step": 270 |
| }, |
| { |
| "epoch": 1.7872, |
| "grad_norm": 2.0275028822982852, |
| "learning_rate": 7.136752136752137e-06, |
| "loss": 0.0393, |
| "step": 280 |
| }, |
| { |
| "epoch": 1.8512, |
| "grad_norm": 1.8500231759762549, |
| "learning_rate": 6.9943019943019955e-06, |
| "loss": 0.037, |
| "step": 290 |
| }, |
| { |
| "epoch": 1.9152, |
| "grad_norm": 3.7282930807176604, |
| "learning_rate": 6.851851851851853e-06, |
| "loss": 0.0373, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.9792, |
| "grad_norm": 3.42282088810128, |
| "learning_rate": 6.7094017094017094e-06, |
| "loss": 0.0352, |
| "step": 310 |
| }, |
| { |
| "epoch": 2.0384, |
| "grad_norm": 0.9105851467194691, |
| "learning_rate": 6.566951566951567e-06, |
| "loss": 0.0292, |
| "step": 320 |
| }, |
| { |
| "epoch": 2.1024, |
| "grad_norm": 1.244830667076524, |
| "learning_rate": 6.424501424501425e-06, |
| "loss": 0.0405, |
| "step": 330 |
| }, |
| { |
| "epoch": 2.1664, |
| "grad_norm": 1.0510058128223077, |
| "learning_rate": 6.282051282051282e-06, |
| "loss": 0.0282, |
| "step": 340 |
| }, |
| { |
| "epoch": 2.2304, |
| "grad_norm": 1.5807447986200327, |
| "learning_rate": 6.13960113960114e-06, |
| "loss": 0.0379, |
| "step": 350 |
| }, |
| { |
| "epoch": 2.2944, |
| "grad_norm": 2.9923562143253855, |
| "learning_rate": 5.997150997150998e-06, |
| "loss": 0.0362, |
| "step": 360 |
| }, |
| { |
| "epoch": 2.3584, |
| "grad_norm": 1.1768976103669906, |
| "learning_rate": 5.854700854700855e-06, |
| "loss": 0.0304, |
| "step": 370 |
| }, |
| { |
| "epoch": 2.4224, |
| "grad_norm": 1.0469384723844881, |
| "learning_rate": 5.7122507122507136e-06, |
| "loss": 0.0341, |
| "step": 380 |
| }, |
| { |
| "epoch": 2.4864, |
| "grad_norm": 3.0634909414310805, |
| "learning_rate": 5.56980056980057e-06, |
| "loss": 0.0455, |
| "step": 390 |
| }, |
| { |
| "epoch": 2.5504, |
| "grad_norm": 5.409022806393993, |
| "learning_rate": 5.4273504273504275e-06, |
| "loss": 0.0391, |
| "step": 400 |
| }, |
| { |
| "epoch": 2.6144, |
| "grad_norm": 2.341956839425436, |
| "learning_rate": 5.284900284900285e-06, |
| "loss": 0.0354, |
| "step": 410 |
| }, |
| { |
| "epoch": 2.6784, |
| "grad_norm": 2.511241308504355, |
| "learning_rate": 5.142450142450143e-06, |
| "loss": 0.0253, |
| "step": 420 |
| }, |
| { |
| "epoch": 2.7424, |
| "grad_norm": 0.690018698433535, |
| "learning_rate": 5e-06, |
| "loss": 0.0342, |
| "step": 430 |
| }, |
| { |
| "epoch": 2.8064, |
| "grad_norm": 1.4836436664927006, |
| "learning_rate": 4.857549857549858e-06, |
| "loss": 0.0289, |
| "step": 440 |
| }, |
| { |
| "epoch": 2.8704, |
| "grad_norm": 3.3287631024455555, |
| "learning_rate": 4.715099715099716e-06, |
| "loss": 0.034, |
| "step": 450 |
| }, |
| { |
| "epoch": 2.9344, |
| "grad_norm": 1.9028860466386455, |
| "learning_rate": 4.5726495726495725e-06, |
| "loss": 0.0394, |
| "step": 460 |
| }, |
| { |
| "epoch": 2.9984, |
| "grad_norm": 1.5644909433575458, |
| "learning_rate": 4.430199430199431e-06, |
| "loss": 0.0316, |
| "step": 470 |
| }, |
| { |
| "epoch": 3.0576, |
| "grad_norm": 0.5702118410044564, |
| "learning_rate": 4.287749287749288e-06, |
| "loss": 0.0271, |
| "step": 480 |
| }, |
| { |
| "epoch": 3.1216, |
| "grad_norm": 0.7240226489581562, |
| "learning_rate": 4.145299145299146e-06, |
| "loss": 0.0257, |
| "step": 490 |
| }, |
| { |
| "epoch": 3.1856, |
| "grad_norm": 1.3730314778183395, |
| "learning_rate": 4.002849002849003e-06, |
| "loss": 0.0242, |
| "step": 500 |
| }, |
| { |
| "epoch": 3.2496, |
| "grad_norm": 1.409286440913811, |
| "learning_rate": 3.860398860398861e-06, |
| "loss": 0.0176, |
| "step": 510 |
| }, |
| { |
| "epoch": 3.3136, |
| "grad_norm": 0.353728945819478, |
| "learning_rate": 3.7179487179487184e-06, |
| "loss": 0.0214, |
| "step": 520 |
| }, |
| { |
| "epoch": 3.3776, |
| "grad_norm": 0.6615032954587686, |
| "learning_rate": 3.5754985754985762e-06, |
| "loss": 0.0283, |
| "step": 530 |
| }, |
| { |
| "epoch": 3.4416, |
| "grad_norm": 1.047780597662055, |
| "learning_rate": 3.433048433048433e-06, |
| "loss": 0.0272, |
| "step": 540 |
| }, |
| { |
| "epoch": 3.5056000000000003, |
| "grad_norm": 1.0880693279764668, |
| "learning_rate": 3.290598290598291e-06, |
| "loss": 0.0191, |
| "step": 550 |
| }, |
| { |
| "epoch": 3.5696, |
| "grad_norm": 0.593950500649586, |
| "learning_rate": 3.1481481481481483e-06, |
| "loss": 0.0267, |
| "step": 560 |
| }, |
| { |
| "epoch": 3.6336, |
| "grad_norm": 1.4894282812370825, |
| "learning_rate": 3.005698005698006e-06, |
| "loss": 0.0397, |
| "step": 570 |
| }, |
| { |
| "epoch": 3.6976, |
| "grad_norm": 2.6737604623174818, |
| "learning_rate": 2.8632478632478635e-06, |
| "loss": 0.0271, |
| "step": 580 |
| }, |
| { |
| "epoch": 3.7616, |
| "grad_norm": 0.7247629374871387, |
| "learning_rate": 2.720797720797721e-06, |
| "loss": 0.0243, |
| "step": 590 |
| }, |
| { |
| "epoch": 3.8256, |
| "grad_norm": 2.025099186148271, |
| "learning_rate": 2.5783475783475787e-06, |
| "loss": 0.0235, |
| "step": 600 |
| }, |
| { |
| "epoch": 3.8895999999999997, |
| "grad_norm": 0.2161434673903271, |
| "learning_rate": 2.435897435897436e-06, |
| "loss": 0.0249, |
| "step": 610 |
| }, |
| { |
| "epoch": 3.9536, |
| "grad_norm": 0.9482360067668893, |
| "learning_rate": 2.293447293447294e-06, |
| "loss": 0.0186, |
| "step": 620 |
| }, |
| { |
| "epoch": 4.0128, |
| "grad_norm": 0.3787496021708608, |
| "learning_rate": 2.150997150997151e-06, |
| "loss": 0.0167, |
| "step": 630 |
| }, |
| { |
| "epoch": 4.0768, |
| "grad_norm": 1.306024706029847, |
| "learning_rate": 2.008547008547009e-06, |
| "loss": 0.0159, |
| "step": 640 |
| }, |
| { |
| "epoch": 4.1408, |
| "grad_norm": 3.6816675792077183, |
| "learning_rate": 1.8660968660968661e-06, |
| "loss": 0.0183, |
| "step": 650 |
| }, |
| { |
| "epoch": 4.2048, |
| "grad_norm": 0.9437993473728703, |
| "learning_rate": 1.723646723646724e-06, |
| "loss": 0.0137, |
| "step": 660 |
| }, |
| { |
| "epoch": 4.2688, |
| "grad_norm": 1.1491393759333486, |
| "learning_rate": 1.5811965811965813e-06, |
| "loss": 0.0176, |
| "step": 670 |
| }, |
| { |
| "epoch": 4.3328, |
| "grad_norm": 0.7015793398100599, |
| "learning_rate": 1.4387464387464389e-06, |
| "loss": 0.0142, |
| "step": 680 |
| }, |
| { |
| "epoch": 4.3968, |
| "grad_norm": 1.154214916933845, |
| "learning_rate": 1.2962962962962962e-06, |
| "loss": 0.0185, |
| "step": 690 |
| }, |
| { |
| "epoch": 4.4608, |
| "grad_norm": 0.1581403197209941, |
| "learning_rate": 1.153846153846154e-06, |
| "loss": 0.0097, |
| "step": 700 |
| }, |
| { |
| "epoch": 4.5248, |
| "grad_norm": 0.944788394994583, |
| "learning_rate": 1.0113960113960116e-06, |
| "loss": 0.0104, |
| "step": 710 |
| }, |
| { |
| "epoch": 4.5888, |
| "grad_norm": 1.399396791060691, |
| "learning_rate": 8.689458689458691e-07, |
| "loss": 0.0163, |
| "step": 720 |
| }, |
| { |
| "epoch": 4.6528, |
| "grad_norm": 1.1267866164560314, |
| "learning_rate": 7.264957264957266e-07, |
| "loss": 0.0151, |
| "step": 730 |
| }, |
| { |
| "epoch": 4.7168, |
| "grad_norm": 0.5615964881104024, |
| "learning_rate": 5.84045584045584e-07, |
| "loss": 0.0132, |
| "step": 740 |
| }, |
| { |
| "epoch": 4.7808, |
| "grad_norm": 1.0241538807872168, |
| "learning_rate": 4.415954415954416e-07, |
| "loss": 0.012, |
| "step": 750 |
| }, |
| { |
| "epoch": 4.8448, |
| "grad_norm": 1.9733087302730272, |
| "learning_rate": 2.991452991452992e-07, |
| "loss": 0.0152, |
| "step": 760 |
| }, |
| { |
| "epoch": 4.9088, |
| "grad_norm": 0.8383865793115187, |
| "learning_rate": 1.566951566951567e-07, |
| "loss": 0.0109, |
| "step": 770 |
| }, |
| { |
| "epoch": 4.9728, |
| "grad_norm": 0.5899609475557703, |
| "learning_rate": 1.4245014245014247e-08, |
| "loss": 0.0113, |
| "step": 780 |
| }, |
| { |
| "epoch": 4.9728, |
| "step": 780, |
| "total_flos": 544113163239424.0, |
| "train_loss": 0.0703721432827222, |
| "train_runtime": 36514.9195, |
| "train_samples_per_second": 2.739, |
| "train_steps_per_second": 0.021 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 780, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 544113163239424.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
