| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.576, | |
| "eval_steps": 9, | |
| "global_step": 90, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0064, | |
| "eval_loss": 2.962462902069092, | |
| "eval_runtime": 14.3886, | |
| "eval_samples_per_second": 73.113, | |
| "eval_steps_per_second": 2.293, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0192, | |
| "grad_norm": 2.497889995574951, | |
| "learning_rate": 3e-05, | |
| "loss": 2.9509, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0384, | |
| "grad_norm": 1.9927830696105957, | |
| "learning_rate": 6e-05, | |
| "loss": 2.9487, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0576, | |
| "grad_norm": 1.110428810119629, | |
| "learning_rate": 9e-05, | |
| "loss": 2.6523, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0576, | |
| "eval_loss": 2.410982847213745, | |
| "eval_runtime": 4.6211, | |
| "eval_samples_per_second": 227.65, | |
| "eval_steps_per_second": 7.141, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0768, | |
| "grad_norm": 1.4526073932647705, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 2.378, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.096, | |
| "grad_norm": 1.4305192232131958, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 2.3302, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1152, | |
| "grad_norm": 1.1190311908721924, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 2.2509, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1152, | |
| "eval_loss": 2.1677029132843018, | |
| "eval_runtime": 4.5951, | |
| "eval_samples_per_second": 228.939, | |
| "eval_steps_per_second": 7.182, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1344, | |
| "grad_norm": 1.0180203914642334, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 2.1507, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1536, | |
| "grad_norm": 0.8608107566833496, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 2.0623, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1728, | |
| "grad_norm": 0.8825973272323608, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 2.1129, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1728, | |
| "eval_loss": 2.0721230506896973, | |
| "eval_runtime": 4.6294, | |
| "eval_samples_per_second": 227.245, | |
| "eval_steps_per_second": 7.128, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.192, | |
| "grad_norm": 0.8532243371009827, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 2.0382, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2112, | |
| "grad_norm": 0.7470282912254333, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 2.0626, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2304, | |
| "grad_norm": 0.885766327381134, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 2.0687, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2304, | |
| "eval_loss": 2.036273717880249, | |
| "eval_runtime": 4.5994, | |
| "eval_samples_per_second": 228.727, | |
| "eval_steps_per_second": 7.175, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2496, | |
| "grad_norm": 0.8446648716926575, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 2.0859, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.2688, | |
| "grad_norm": 0.8682901859283447, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 2.0376, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.288, | |
| "grad_norm": 0.7690749168395996, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 2.0631, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.288, | |
| "eval_loss": 2.0197086334228516, | |
| "eval_runtime": 4.6016, | |
| "eval_samples_per_second": 228.616, | |
| "eval_steps_per_second": 7.171, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3072, | |
| "grad_norm": 0.7606220841407776, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 2.0648, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3264, | |
| "grad_norm": 0.9449107646942139, | |
| "learning_rate": 5.695865504800327e-05, | |
| "loss": 1.9471, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.3456, | |
| "grad_norm": 0.7188290953636169, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 2.011, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.3456, | |
| "eval_loss": 2.008131504058838, | |
| "eval_runtime": 4.5949, | |
| "eval_samples_per_second": 228.948, | |
| "eval_steps_per_second": 7.182, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.3648, | |
| "grad_norm": 0.898175060749054, | |
| "learning_rate": 4.6512176312793736e-05, | |
| "loss": 2.0437, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.384, | |
| "grad_norm": 0.8860452175140381, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 2.0314, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4032, | |
| "grad_norm": 0.7955260872840881, | |
| "learning_rate": 3.6218132209150045e-05, | |
| "loss": 2.0663, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.4032, | |
| "eval_loss": 2.0011115074157715, | |
| "eval_runtime": 4.6261, | |
| "eval_samples_per_second": 227.405, | |
| "eval_steps_per_second": 7.133, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.4224, | |
| "grad_norm": 0.7795498371124268, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 1.9806, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.4416, | |
| "grad_norm": 0.8645098209381104, | |
| "learning_rate": 2.6526421860705473e-05, | |
| "loss": 2.0406, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.4608, | |
| "grad_norm": 0.9535412192344666, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 2.026, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.4608, | |
| "eval_loss": 1.9973247051239014, | |
| "eval_runtime": 4.6137, | |
| "eval_samples_per_second": 228.018, | |
| "eval_steps_per_second": 7.153, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.6900295615196228, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 2.0248, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.4992, | |
| "grad_norm": 0.9134931564331055, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 2.0247, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.5184, | |
| "grad_norm": 0.7832142114639282, | |
| "learning_rate": 1.0599462319663905e-05, | |
| "loss": 2.0234, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.5184, | |
| "eval_loss": 1.9945977926254272, | |
| "eval_runtime": 4.596, | |
| "eval_samples_per_second": 228.897, | |
| "eval_steps_per_second": 7.18, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.5376, | |
| "grad_norm": 0.740906834602356, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 2.0243, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.5568, | |
| "grad_norm": 0.8714410066604614, | |
| "learning_rate": 5.060297685041659e-06, | |
| "loss": 1.9928, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.576, | |
| "grad_norm": 0.8628079891204834, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.998, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.576, | |
| "eval_loss": 1.993507981300354, | |
| "eval_runtime": 4.6158, | |
| "eval_samples_per_second": 227.913, | |
| "eval_steps_per_second": 7.149, | |
| "step": 90 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.4526559989792768e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |