| { | |
| "best_metric": 0.6939069628715515, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.08029709926728897, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003211883970691559, | |
| "grad_norm": 20.16118621826172, | |
| "learning_rate": 2e-05, | |
| "loss": 10.5874, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003211883970691559, | |
| "eval_loss": 10.961771011352539, | |
| "eval_runtime": 0.5041, | |
| "eval_samples_per_second": 99.189, | |
| "eval_steps_per_second": 25.789, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006423767941383118, | |
| "grad_norm": 19.579418182373047, | |
| "learning_rate": 4e-05, | |
| "loss": 11.2853, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009635651912074676, | |
| "grad_norm": 19.505998611450195, | |
| "learning_rate": 6e-05, | |
| "loss": 11.473, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012847535882766235, | |
| "grad_norm": 19.151931762695312, | |
| "learning_rate": 8e-05, | |
| "loss": 10.7664, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.016059419853457792, | |
| "grad_norm": 15.65612506866455, | |
| "learning_rate": 0.0001, | |
| "loss": 9.6991, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.019271303824149353, | |
| "grad_norm": 15.794941902160645, | |
| "learning_rate": 9.997539658034168e-05, | |
| "loss": 8.4858, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02248318779484091, | |
| "grad_norm": 24.663986206054688, | |
| "learning_rate": 9.990161322484486e-05, | |
| "loss": 7.7278, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02569507176553247, | |
| "grad_norm": 32.05091857910156, | |
| "learning_rate": 9.977873061452552e-05, | |
| "loss": 5.7351, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.028906955736224028, | |
| "grad_norm": 20.47426986694336, | |
| "learning_rate": 9.96068831197139e-05, | |
| "loss": 3.6171, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.032118839706915585, | |
| "grad_norm": 16.713817596435547, | |
| "learning_rate": 9.938625865312251e-05, | |
| "loss": 2.2651, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.035330723677607145, | |
| "grad_norm": 15.718864440917969, | |
| "learning_rate": 9.911709846436641e-05, | |
| "loss": 1.6319, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.038542607648298706, | |
| "grad_norm": 8.562857627868652, | |
| "learning_rate": 9.879969687616027e-05, | |
| "loss": 1.043, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.041754491618990267, | |
| "grad_norm": 7.533064842224121, | |
| "learning_rate": 9.84344009624807e-05, | |
| "loss": 1.4191, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04496637558968182, | |
| "grad_norm": 9.270398139953613, | |
| "learning_rate": 9.80216101690461e-05, | |
| "loss": 1.9694, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04817825956037338, | |
| "grad_norm": 6.436896324157715, | |
| "learning_rate": 9.756177587652856e-05, | |
| "loss": 1.4584, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05139014353106494, | |
| "grad_norm": 9.544507026672363, | |
| "learning_rate": 9.705540090697575e-05, | |
| "loss": 1.0719, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0546020275017565, | |
| "grad_norm": 12.543577194213867, | |
| "learning_rate": 9.650303897398232e-05, | |
| "loss": 1.2843, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.057813911472448055, | |
| "grad_norm": 5.713746070861816, | |
| "learning_rate": 9.590529407721231e-05, | |
| "loss": 0.9745, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.061025795443139616, | |
| "grad_norm": 3.9435653686523438, | |
| "learning_rate": 9.526281984193436e-05, | |
| "loss": 0.7748, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06423767941383117, | |
| "grad_norm": 12.931794166564941, | |
| "learning_rate": 9.4576318804292e-05, | |
| "loss": 2.0045, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06744956338452274, | |
| "grad_norm": 9.132307052612305, | |
| "learning_rate": 9.384654164309083e-05, | |
| "loss": 1.4456, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07066144735521429, | |
| "grad_norm": 4.245421886444092, | |
| "learning_rate": 9.30742863589421e-05, | |
| "loss": 0.8106, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07387333132590586, | |
| "grad_norm": 6.020063400268555, | |
| "learning_rate": 9.226039740166091e-05, | |
| "loss": 0.5633, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07708521529659741, | |
| "grad_norm": 5.152550220489502, | |
| "learning_rate": 9.140576474687264e-05, | |
| "loss": 0.6608, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08029709926728897, | |
| "grad_norm": 4.782017707824707, | |
| "learning_rate": 9.051132292283771e-05, | |
| "loss": 0.6502, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08029709926728897, | |
| "eval_loss": 0.6939069628715515, | |
| "eval_runtime": 0.5032, | |
| "eval_samples_per_second": 99.361, | |
| "eval_steps_per_second": 25.834, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.16708196040704e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |