| { | |
| "best_metric": 1.7624279260635376, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.0066751775180021195, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00026700710072008477, | |
| "grad_norm": 1.3567132949829102, | |
| "learning_rate": 5e-05, | |
| "loss": 2.687, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00026700710072008477, | |
| "eval_loss": 3.6886894702911377, | |
| "eval_runtime": 1.1537, | |
| "eval_samples_per_second": 43.34, | |
| "eval_steps_per_second": 11.268, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005340142014401695, | |
| "grad_norm": 1.3082774877548218, | |
| "learning_rate": 0.0001, | |
| "loss": 2.6167, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008010213021602544, | |
| "grad_norm": 1.4745134115219116, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 2.7026, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001068028402880339, | |
| "grad_norm": 2.810551643371582, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 2.9056, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0013350355036004238, | |
| "grad_norm": 3.3739430904388428, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 2.66, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016020426043205087, | |
| "grad_norm": 2.617138147354126, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 2.5437, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0018690497050405934, | |
| "grad_norm": 2.838907480239868, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 2.5536, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002136056805760678, | |
| "grad_norm": 2.6245129108428955, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 2.5274, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002403063906480763, | |
| "grad_norm": 2.5215673446655273, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 2.3462, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0026700710072008475, | |
| "grad_norm": 2.0649657249450684, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 2.9629, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0029370781079209327, | |
| "grad_norm": 2.771552324295044, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 3.4145, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0032040852086410174, | |
| "grad_norm": 4.581740379333496, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 4.0181, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003471092309361102, | |
| "grad_norm": 3.7180395126342773, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 2.4237, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003738099410081187, | |
| "grad_norm": 5.509239196777344, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 1.6143, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0040051065108012715, | |
| "grad_norm": 5.437826156616211, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 1.6484, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004272113611521356, | |
| "grad_norm": 4.950212478637695, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 1.7074, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004539120712241441, | |
| "grad_norm": 4.100536346435547, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 1.6609, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004806127812961526, | |
| "grad_norm": 4.357456684112549, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 1.7817, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00507313491368161, | |
| "grad_norm": 3.1520206928253174, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 1.7028, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.005340142014401695, | |
| "grad_norm": 2.7379584312438965, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 1.6811, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005607149115121781, | |
| "grad_norm": 2.1581881046295166, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 1.7694, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005874156215841865, | |
| "grad_norm": 1.9265141487121582, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 1.9304, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.00614116331656195, | |
| "grad_norm": 2.518392324447632, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 2.7913, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006408170417282035, | |
| "grad_norm": 3.212178945541382, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 3.0619, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0066751775180021195, | |
| "grad_norm": 5.334901332855225, | |
| "learning_rate": 1e-05, | |
| "loss": 3.7039, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0066751775180021195, | |
| "eval_loss": 1.7624279260635376, | |
| "eval_runtime": 1.176, | |
| "eval_samples_per_second": 42.515, | |
| "eval_steps_per_second": 11.054, | |
| "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": 5.299337291418829e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |