| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.11286681715575621, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002257336343115124, | |
| "eval_loss": 10.37696647644043, | |
| "eval_runtime": 1.3605, | |
| "eval_samples_per_second": 549.072, | |
| "eval_steps_per_second": 69.093, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006772009029345372, | |
| "grad_norm": 0.5311530232429504, | |
| "learning_rate": 3e-05, | |
| "loss": 10.3708, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.011286681715575621, | |
| "eval_loss": 10.375223159790039, | |
| "eval_runtime": 1.3445, | |
| "eval_samples_per_second": 555.583, | |
| "eval_steps_per_second": 69.913, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013544018058690745, | |
| "grad_norm": 0.4600737690925598, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3742, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.020316027088036117, | |
| "grad_norm": 0.4388561248779297, | |
| "learning_rate": 9e-05, | |
| "loss": 10.3715, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.022573363431151242, | |
| "eval_loss": 10.36904525756836, | |
| "eval_runtime": 1.3711, | |
| "eval_samples_per_second": 544.833, | |
| "eval_steps_per_second": 68.56, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02708803611738149, | |
| "grad_norm": 0.39423269033432007, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 10.3707, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.033860045146726865, | |
| "grad_norm": 0.45872196555137634, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3518, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.033860045146726865, | |
| "eval_loss": 10.359448432922363, | |
| "eval_runtime": 1.4011, | |
| "eval_samples_per_second": 533.148, | |
| "eval_steps_per_second": 67.09, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.040632054176072234, | |
| "grad_norm": 0.5480523705482483, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 10.3586, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.045146726862302484, | |
| "eval_loss": 10.348822593688965, | |
| "eval_runtime": 1.4092, | |
| "eval_samples_per_second": 530.083, | |
| "eval_steps_per_second": 66.704, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04740406320541761, | |
| "grad_norm": 0.481340229511261, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 10.3482, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05417607223476298, | |
| "grad_norm": 0.6495785713195801, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 10.3488, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.056433408577878104, | |
| "eval_loss": 10.337669372558594, | |
| "eval_runtime": 1.3982, | |
| "eval_samples_per_second": 534.277, | |
| "eval_steps_per_second": 67.232, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.060948081264108354, | |
| "grad_norm": 0.7056164145469666, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 10.3473, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06772009029345373, | |
| "grad_norm": 0.7669053673744202, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3337, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06772009029345373, | |
| "eval_loss": 10.328136444091797, | |
| "eval_runtime": 1.3693, | |
| "eval_samples_per_second": 545.526, | |
| "eval_steps_per_second": 68.647, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0744920993227991, | |
| "grad_norm": 0.6908026337623596, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 10.338, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.07900677200902935, | |
| "eval_loss": 10.320672035217285, | |
| "eval_runtime": 1.3491, | |
| "eval_samples_per_second": 553.69, | |
| "eval_steps_per_second": 69.675, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08126410835214447, | |
| "grad_norm": 0.54636549949646, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 10.3207, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.08803611738148984, | |
| "grad_norm": 0.703861653804779, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 10.3198, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09029345372460497, | |
| "eval_loss": 10.316521644592285, | |
| "eval_runtime": 1.3669, | |
| "eval_samples_per_second": 546.511, | |
| "eval_steps_per_second": 68.771, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09480812641083522, | |
| "grad_norm": 0.5754713416099548, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 10.3213, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.10158013544018059, | |
| "grad_norm": 0.7273910641670227, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.3121, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.10158013544018059, | |
| "eval_loss": 10.314825057983398, | |
| "eval_runtime": 1.405, | |
| "eval_samples_per_second": 531.663, | |
| "eval_steps_per_second": 66.903, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.10835214446952596, | |
| "grad_norm": 0.7388740181922913, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 10.3121, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.11286681715575621, | |
| "eval_loss": 10.314505577087402, | |
| "eval_runtime": 1.3781, | |
| "eval_samples_per_second": 542.057, | |
| "eval_steps_per_second": 68.211, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5577533030400.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |