| { | |
| "best_metric": 0.2869703769683838, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.24721878862793573, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009888751545117428, | |
| "grad_norm": 0.9529975652694702, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0219, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009888751545117428, | |
| "eval_loss": 1.3110345602035522, | |
| "eval_runtime": 7.7724, | |
| "eval_samples_per_second": 87.617, | |
| "eval_steps_per_second": 11.065, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.019777503090234856, | |
| "grad_norm": 1.0081549882888794, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1021, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.029666254635352288, | |
| "grad_norm": 0.9224106669425964, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.086, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03955500618046971, | |
| "grad_norm": 0.7995649576187134, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.9693, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.049443757725587144, | |
| "grad_norm": 0.7404234409332275, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.9118, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.059332509270704575, | |
| "grad_norm": 0.7574806213378906, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.8586, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.069221260815822, | |
| "grad_norm": 0.821106493473053, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.7926, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07911001236093942, | |
| "grad_norm": 0.8635395169258118, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.783, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08899876390605686, | |
| "grad_norm": 1.0159235000610352, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.7064, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09888751545117429, | |
| "grad_norm": 1.0130189657211304, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.589, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10877626699629171, | |
| "grad_norm": 1.2768349647521973, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.5688, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.11866501854140915, | |
| "grad_norm": 2.3141722679138184, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.7207, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.12855377008652658, | |
| "grad_norm": 1.249726414680481, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.6056, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.138442521631644, | |
| "grad_norm": 0.7423824071884155, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.3629, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.14833127317676142, | |
| "grad_norm": 0.679111897945404, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.3774, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.15822002472187885, | |
| "grad_norm": 0.9115525484085083, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.3451, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1681087762669963, | |
| "grad_norm": 0.712714672088623, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.3456, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.17799752781211373, | |
| "grad_norm": 0.4200282394886017, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.308, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.18788627935723115, | |
| "grad_norm": 0.3945173919200897, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.3046, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.19777503090234858, | |
| "grad_norm": 0.46987950801849365, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.3372, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.207663782447466, | |
| "grad_norm": 0.47412583231925964, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.305, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.21755253399258342, | |
| "grad_norm": 0.4029322862625122, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.3065, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.22744128553770088, | |
| "grad_norm": 0.4010602533817291, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.2876, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2373300370828183, | |
| "grad_norm": 0.4016035795211792, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.2817, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.24721878862793573, | |
| "grad_norm": 0.6217444539070129, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.4688, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24721878862793573, | |
| "eval_loss": 0.2869703769683838, | |
| "eval_runtime": 7.8213, | |
| "eval_samples_per_second": 87.07, | |
| "eval_steps_per_second": 10.996, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "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": 5.29768176943104e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |