| { | |
| "best_metric": 0.537278950214386, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.24737167594310452, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009894867037724181, | |
| "grad_norm": 1.1154512166976929, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5745, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009894867037724181, | |
| "eval_loss": 0.8256334662437439, | |
| "eval_runtime": 6.5178, | |
| "eval_samples_per_second": 7.671, | |
| "eval_steps_per_second": 7.671, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.019789734075448363, | |
| "grad_norm": 0.9112982153892517, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6089, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.029684601113172542, | |
| "grad_norm": 0.7618346810340881, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 0.6075, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.039579468150896725, | |
| "grad_norm": 0.5135230422019958, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 0.5738, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.049474335188620905, | |
| "grad_norm": 0.6625581383705139, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 0.655, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.059369202226345084, | |
| "grad_norm": 0.6755515336990356, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 0.6549, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06926406926406926, | |
| "grad_norm": 0.6802213191986084, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 0.6454, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07915893630179345, | |
| "grad_norm": 0.5502082109451294, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 0.5799, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08905380333951762, | |
| "grad_norm": 0.5589600801467896, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 0.6364, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09894867037724181, | |
| "grad_norm": 0.509834349155426, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 0.5921, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10884353741496598, | |
| "grad_norm": 0.4775814414024353, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 0.5942, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.11873840445269017, | |
| "grad_norm": 0.45048290491104126, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 0.5359, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.12863327149041434, | |
| "grad_norm": 0.4422420561313629, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 0.5369, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.13852813852813853, | |
| "grad_norm": 0.5037291049957275, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 0.5707, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.14842300556586271, | |
| "grad_norm": 0.4767208695411682, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 0.6039, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1583178726035869, | |
| "grad_norm": 0.4372898042201996, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 0.569, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.16821273964131106, | |
| "grad_norm": 0.5202221870422363, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 0.5685, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.17810760667903525, | |
| "grad_norm": 0.4551151692867279, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 0.5613, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.18800247371675943, | |
| "grad_norm": 0.44439488649368286, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 0.5903, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.19789734075448362, | |
| "grad_norm": 0.4228428304195404, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 0.5221, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2077922077922078, | |
| "grad_norm": 0.47059401869773865, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 0.5994, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.21768707482993196, | |
| "grad_norm": 0.4544641971588135, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 0.5831, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.22758194186765615, | |
| "grad_norm": 0.4875115156173706, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 0.6481, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.23747680890538034, | |
| "grad_norm": 0.4927768111228943, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 0.6625, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.24737167594310452, | |
| "grad_norm": 0.5276088118553162, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6882, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24737167594310452, | |
| "eval_loss": 0.537278950214386, | |
| "eval_runtime": 6.5835, | |
| "eval_samples_per_second": 7.595, | |
| "eval_steps_per_second": 7.595, | |
| "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": 2.03101109747712e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |