| { | |
| "best_metric": 11.756360054016113, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.060753341433778855, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002430133657351154, | |
| "grad_norm": 0.03307952731847763, | |
| "learning_rate": 5e-05, | |
| "loss": 11.763, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002430133657351154, | |
| "eval_loss": 11.758548736572266, | |
| "eval_runtime": 0.5847, | |
| "eval_samples_per_second": 85.507, | |
| "eval_steps_per_second": 85.507, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004860267314702308, | |
| "grad_norm": 0.030670348554849625, | |
| "learning_rate": 0.0001, | |
| "loss": 11.7633, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007290400972053463, | |
| "grad_norm": 0.038815468549728394, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 11.763, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009720534629404616, | |
| "grad_norm": 0.03586955368518829, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 11.7661, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012150668286755772, | |
| "grad_norm": 0.037899650633335114, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 11.7641, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014580801944106925, | |
| "grad_norm": 0.040155936032533646, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 11.763, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01701093560145808, | |
| "grad_norm": 0.04388712719082832, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 11.7645, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.019441069258809233, | |
| "grad_norm": 0.03561596944928169, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 11.7641, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02187120291616039, | |
| "grad_norm": 0.038865040987730026, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 11.7602, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.024301336573511544, | |
| "grad_norm": 0.04436539113521576, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 11.7581, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.026731470230862697, | |
| "grad_norm": 0.045174892991781235, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 11.7601, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02916160388821385, | |
| "grad_norm": 0.053117893636226654, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 11.7618, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.031591737545565005, | |
| "grad_norm": 0.045657284557819366, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 11.7633, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03402187120291616, | |
| "grad_norm": 0.04333147779107094, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 11.7582, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03645200486026731, | |
| "grad_norm": 0.05519665777683258, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 11.7594, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.038882138517618466, | |
| "grad_norm": 0.051656998693943024, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 11.7622, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.041312272174969626, | |
| "grad_norm": 0.05169561877846718, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 11.758, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04374240583232078, | |
| "grad_norm": 0.05096937716007233, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 11.7611, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.046172539489671933, | |
| "grad_norm": 0.051274389028549194, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 11.7606, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04860267314702309, | |
| "grad_norm": 0.05126600340008736, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 11.758, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05103280680437424, | |
| "grad_norm": 0.05662069469690323, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 11.7601, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.053462940461725394, | |
| "grad_norm": 0.05599432811141014, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 11.7576, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05589307411907655, | |
| "grad_norm": 0.067054383456707, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 11.7589, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0583232077764277, | |
| "grad_norm": 0.060488082468509674, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 11.7603, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.060753341433778855, | |
| "grad_norm": 0.07440540939569473, | |
| "learning_rate": 1e-05, | |
| "loss": 11.7541, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.060753341433778855, | |
| "eval_loss": 11.756360054016113, | |
| "eval_runtime": 0.5745, | |
| "eval_samples_per_second": 87.028, | |
| "eval_steps_per_second": 87.028, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 20485767168000.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |