| { | |
| "best_metric": 0.6996614336967468, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.39408866995073893, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.015763546798029555, | |
| "grad_norm": 29.17995262145996, | |
| "learning_rate": 2e-05, | |
| "loss": 13.3509, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.015763546798029555, | |
| "eval_loss": 13.427430152893066, | |
| "eval_runtime": 0.7017, | |
| "eval_samples_per_second": 71.258, | |
| "eval_steps_per_second": 18.527, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03152709359605911, | |
| "grad_norm": 28.460174560546875, | |
| "learning_rate": 4e-05, | |
| "loss": 12.8886, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04729064039408867, | |
| "grad_norm": 27.8137264251709, | |
| "learning_rate": 6e-05, | |
| "loss": 12.7057, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06305418719211822, | |
| "grad_norm": 26.662076950073242, | |
| "learning_rate": 8e-05, | |
| "loss": 11.5203, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07881773399014778, | |
| "grad_norm": 28.166336059570312, | |
| "learning_rate": 0.0001, | |
| "loss": 8.9608, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09458128078817735, | |
| "grad_norm": 27.162477493286133, | |
| "learning_rate": 9.997539658034168e-05, | |
| "loss": 6.8103, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1103448275862069, | |
| "grad_norm": 22.779897689819336, | |
| "learning_rate": 9.990161322484486e-05, | |
| "loss": 4.7953, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.12610837438423644, | |
| "grad_norm": 31.25025749206543, | |
| "learning_rate": 9.977873061452552e-05, | |
| "loss": 3.5934, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.14187192118226602, | |
| "grad_norm": 32.73939895629883, | |
| "learning_rate": 9.96068831197139e-05, | |
| "loss": 2.0744, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.15763546798029557, | |
| "grad_norm": 22.30132293701172, | |
| "learning_rate": 9.938625865312251e-05, | |
| "loss": 0.9963, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17339901477832512, | |
| "grad_norm": 23.55769920349121, | |
| "learning_rate": 9.911709846436641e-05, | |
| "loss": 0.7853, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1891625615763547, | |
| "grad_norm": 12.216867446899414, | |
| "learning_rate": 9.879969687616027e-05, | |
| "loss": 0.6935, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.20492610837438424, | |
| "grad_norm": 13.3597993850708, | |
| "learning_rate": 9.84344009624807e-05, | |
| "loss": 0.7613, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2206896551724138, | |
| "grad_norm": 9.345667839050293, | |
| "learning_rate": 9.80216101690461e-05, | |
| "loss": 0.5759, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.23645320197044334, | |
| "grad_norm": 11.192370414733887, | |
| "learning_rate": 9.756177587652856e-05, | |
| "loss": 0.6503, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2522167487684729, | |
| "grad_norm": 11.622135162353516, | |
| "learning_rate": 9.705540090697575e-05, | |
| "loss": 0.6265, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.26798029556650244, | |
| "grad_norm": 13.78838062286377, | |
| "learning_rate": 9.650303897398232e-05, | |
| "loss": 0.5981, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.28374384236453204, | |
| "grad_norm": 7.175749778747559, | |
| "learning_rate": 9.590529407721231e-05, | |
| "loss": 0.5388, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2995073891625616, | |
| "grad_norm": 12.73121452331543, | |
| "learning_rate": 9.526281984193436e-05, | |
| "loss": 0.6199, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.31527093596059114, | |
| "grad_norm": 13.318937301635742, | |
| "learning_rate": 9.4576318804292e-05, | |
| "loss": 0.561, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3310344827586207, | |
| "grad_norm": 1.523805022239685, | |
| "learning_rate": 9.384654164309083e-05, | |
| "loss": 0.5285, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.34679802955665023, | |
| "grad_norm": 27.318439483642578, | |
| "learning_rate": 9.30742863589421e-05, | |
| "loss": 0.7602, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3625615763546798, | |
| "grad_norm": 27.310163497924805, | |
| "learning_rate": 9.226039740166091e-05, | |
| "loss": 0.8761, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3783251231527094, | |
| "grad_norm": 19.47849464416504, | |
| "learning_rate": 9.140576474687264e-05, | |
| "loss": 0.6216, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.39408866995073893, | |
| "grad_norm": 2.0372307300567627, | |
| "learning_rate": 9.051132292283771e-05, | |
| "loss": 0.4954, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.39408866995073893, | |
| "eval_loss": 0.6996614336967468, | |
| "eval_runtime": 0.7017, | |
| "eval_samples_per_second": 71.253, | |
| "eval_steps_per_second": 18.526, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 7.94731890081792e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |