| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.21499596882558453, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010749798441279225, | |
| "eval_loss": 2.633302688598633, | |
| "eval_runtime": 31.7207, | |
| "eval_samples_per_second": 12.358, | |
| "eval_steps_per_second": 6.179, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005374899220639613, | |
| "grad_norm": 1.0801095962524414, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1635, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010749798441279226, | |
| "grad_norm": 1.8692516088485718, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4162, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01612469766191884, | |
| "grad_norm": 2.035304069519043, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 0.9354, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.021499596882558453, | |
| "grad_norm": 2.7511253356933594, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 0.8112, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.026874496103198066, | |
| "grad_norm": 2.422313928604126, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 0.7849, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03224939532383768, | |
| "grad_norm": 2.5819692611694336, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 0.6657, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03762429454447729, | |
| "grad_norm": 2.4328465461730957, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 0.6872, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.042999193765116905, | |
| "grad_norm": 2.129849433898926, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 0.7661, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04837409298575652, | |
| "grad_norm": 3.1652305126190186, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 0.7971, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05374899220639613, | |
| "grad_norm": 2.1810810565948486, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 0.6101, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05374899220639613, | |
| "eval_loss": 0.7575846910476685, | |
| "eval_runtime": 32.089, | |
| "eval_samples_per_second": 12.216, | |
| "eval_steps_per_second": 6.108, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.059123891427035745, | |
| "grad_norm": 1.179375171661377, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 0.628, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.06449879064767536, | |
| "grad_norm": 1.4318596124649048, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 0.6071, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.06987368986831496, | |
| "grad_norm": 0.842193067073822, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 0.4833, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.07524858908895458, | |
| "grad_norm": 1.4781662225723267, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 0.6483, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.08062348830959419, | |
| "grad_norm": 1.721100926399231, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 0.6261, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.08599838753023381, | |
| "grad_norm": 1.579014539718628, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 0.6904, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.09137328675087342, | |
| "grad_norm": 2.411149740219116, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 0.5852, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.09674818597151304, | |
| "grad_norm": 2.7585904598236084, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 0.6734, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.10212308519215264, | |
| "grad_norm": 1.8563114404678345, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 0.6365, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.10749798441279226, | |
| "grad_norm": 3.247232437133789, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 0.7104, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.10749798441279226, | |
| "eval_loss": 0.6235585808753967, | |
| "eval_runtime": 32.1467, | |
| "eval_samples_per_second": 12.194, | |
| "eval_steps_per_second": 6.097, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11287288363343187, | |
| "grad_norm": 1.1242468357086182, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5403, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.11824778285407149, | |
| "grad_norm": 1.0179481506347656, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 0.5151, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.1236226820747111, | |
| "grad_norm": 1.5832953453063965, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 0.5154, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.12899758129535072, | |
| "grad_norm": 0.951425313949585, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 0.4058, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.13437248051599032, | |
| "grad_norm": 1.8775848150253296, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 0.5965, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.13974737973662993, | |
| "grad_norm": 1.5794333219528198, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 0.5362, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.14512227895726956, | |
| "grad_norm": 1.7076222896575928, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 0.5668, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.15049717817790917, | |
| "grad_norm": 1.849480390548706, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 0.5461, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.15587207739854878, | |
| "grad_norm": 1.9041430950164795, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 0.5302, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.16124697661918838, | |
| "grad_norm": 2.6399660110473633, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 0.6175, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.16124697661918838, | |
| "eval_loss": 0.5478774309158325, | |
| "eval_runtime": 32.2037, | |
| "eval_samples_per_second": 12.173, | |
| "eval_steps_per_second": 6.086, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.16662187583982802, | |
| "grad_norm": 0.9312940835952759, | |
| "learning_rate": 1.3213804466343421e-05, | |
| "loss": 0.411, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.17199677506046762, | |
| "grad_norm": 1.047676920890808, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 0.4869, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.17737167428110723, | |
| "grad_norm": 1.1791578531265259, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 0.4584, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.18274657350174683, | |
| "grad_norm": 1.4493966102600098, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 0.4337, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.18812147272238647, | |
| "grad_norm": 1.671579122543335, | |
| "learning_rate": 4.2113336672471245e-06, | |
| "loss": 0.4747, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.19349637194302607, | |
| "grad_norm": 2.335181474685669, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 0.592, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.19887127116366568, | |
| "grad_norm": 1.7437834739685059, | |
| "learning_rate": 1.5299867030334814e-06, | |
| "loss": 0.5927, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.2042461703843053, | |
| "grad_norm": 1.8436033725738525, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 0.5768, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.20962106960494492, | |
| "grad_norm": 3.186182737350464, | |
| "learning_rate": 1.7077534966650766e-07, | |
| "loss": 0.7015, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.21499596882558453, | |
| "grad_norm": 1.6149808168411255, | |
| "learning_rate": 0.0, | |
| "loss": 0.5627, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.21499596882558453, | |
| "eval_loss": 0.5310530662536621, | |
| "eval_runtime": 32.1744, | |
| "eval_samples_per_second": 12.184, | |
| "eval_steps_per_second": 6.092, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 7.39825699258368e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |