| { | |
| "best_metric": 2.814382314682007, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.0617283950617282, | |
| "eval_steps": 25, | |
| "global_step": 31, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09876543209876543, | |
| "grad_norm": 6.233891010284424, | |
| "learning_rate": 5e-05, | |
| "loss": 5.1325, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.09876543209876543, | |
| "eval_loss": 6.649930000305176, | |
| "eval_runtime": 0.4865, | |
| "eval_samples_per_second": 139.77, | |
| "eval_steps_per_second": 18.499, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": 12.484169960021973, | |
| "learning_rate": 0.0001, | |
| "loss": 6.673, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": 5.378587245941162, | |
| "learning_rate": 9.970689785771798e-05, | |
| "loss": 5.1172, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "grad_norm": 6.7046661376953125, | |
| "learning_rate": 9.883102778550434e-05, | |
| "loss": 4.9902, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.49382716049382713, | |
| "grad_norm": 14.028969764709473, | |
| "learning_rate": 9.738265855914013e-05, | |
| "loss": 5.5544, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 4.125074863433838, | |
| "learning_rate": 9.537877098354786e-05, | |
| "loss": 4.0607, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.691358024691358, | |
| "grad_norm": 6.239777565002441, | |
| "learning_rate": 9.284285880837946e-05, | |
| "loss": 4.1057, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "grad_norm": 4.690567970275879, | |
| "learning_rate": 8.980465328528219e-05, | |
| "loss": 3.8628, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 5.21114444732666, | |
| "learning_rate": 8.629977459615655e-05, | |
| "loss": 3.5969, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.9876543209876543, | |
| "grad_norm": 9.486303329467773, | |
| "learning_rate": 8.236931423909138e-05, | |
| "loss": 3.5655, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0864197530864197, | |
| "grad_norm": 7.3250861167907715, | |
| "learning_rate": 7.805935326811912e-05, | |
| "loss": 6.019, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "grad_norm": 6.11453914642334, | |
| "learning_rate": 7.342042203498951e-05, | |
| "loss": 3.0734, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.2839506172839505, | |
| "grad_norm": 4.089361190795898, | |
| "learning_rate": 6.850690776699573e-05, | |
| "loss": 3.147, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.382716049382716, | |
| "grad_norm": 4.826321125030518, | |
| "learning_rate": 6.337641692646106e-05, | |
| "loss": 3.099, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.4814814814814814, | |
| "grad_norm": 9.735791206359863, | |
| "learning_rate": 5.808909982763825e-05, | |
| "loss": 3.2368, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "grad_norm": 3.000741481781006, | |
| "learning_rate": 5.270694542927088e-05, | |
| "loss": 2.879, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.6790123456790123, | |
| "grad_norm": 5.924734115600586, | |
| "learning_rate": 4.729305457072913e-05, | |
| "loss": 2.8802, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 3.4073195457458496, | |
| "learning_rate": 4.1910900172361764e-05, | |
| "loss": 2.6786, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.876543209876543, | |
| "grad_norm": 5.1113362312316895, | |
| "learning_rate": 3.6623583073538966e-05, | |
| "loss": 2.9771, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "grad_norm": 9.201824188232422, | |
| "learning_rate": 3.149309223300428e-05, | |
| "loss": 2.9374, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.074074074074074, | |
| "grad_norm": 5.898633003234863, | |
| "learning_rate": 2.65795779650105e-05, | |
| "loss": 4.9788, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.1728395061728394, | |
| "grad_norm": 5.2269511222839355, | |
| "learning_rate": 2.194064673188089e-05, | |
| "loss": 2.5893, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.271604938271605, | |
| "grad_norm": 2.710216760635376, | |
| "learning_rate": 1.7630685760908622e-05, | |
| "loss": 2.1731, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "grad_norm": 5.270141124725342, | |
| "learning_rate": 1.3700225403843469e-05, | |
| "loss": 2.9662, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.4691358024691357, | |
| "grad_norm": 6.2401933670043945, | |
| "learning_rate": 1.0195346714717813e-05, | |
| "loss": 2.7014, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.4691358024691357, | |
| "eval_loss": 2.814382314682007, | |
| "eval_runtime": 0.4823, | |
| "eval_samples_per_second": 140.979, | |
| "eval_steps_per_second": 18.659, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.567901234567901, | |
| "grad_norm": 3.632655143737793, | |
| "learning_rate": 7.157141191620548e-06, | |
| "loss": 2.9517, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 5.402245998382568, | |
| "learning_rate": 4.621229016452156e-06, | |
| "loss": 2.4943, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "grad_norm": 2.5133705139160156, | |
| "learning_rate": 2.6173414408598827e-06, | |
| "loss": 2.0811, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.8641975308641974, | |
| "grad_norm": 5.495011329650879, | |
| "learning_rate": 1.1689722144956671e-06, | |
| "loss": 3.0137, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 6.708992004394531, | |
| "learning_rate": 2.9310214228202013e-07, | |
| "loss": 2.7247, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 3.0617283950617282, | |
| "grad_norm": 5.700857162475586, | |
| "learning_rate": 0.0, | |
| "loss": 5.0588, | |
| "step": 31 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 31, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.5775615131058176e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |