| { | |
| "best_metric": 0.0005636036512441933, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.003663070752211579, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00014652283008846317, | |
| "grad_norm": 67.46258544921875, | |
| "learning_rate": 5e-05, | |
| "loss": 7.3346, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014652283008846317, | |
| "eval_loss": 7.334836959838867, | |
| "eval_runtime": 2450.429, | |
| "eval_samples_per_second": 18.763, | |
| "eval_steps_per_second": 2.346, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00029304566017692633, | |
| "grad_norm": 67.42963409423828, | |
| "learning_rate": 0.0001, | |
| "loss": 7.3346, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0004395684902653895, | |
| "grad_norm": 17.986305236816406, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.2234, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005860913203538527, | |
| "grad_norm": 10.093182563781738, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.9459, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0007326141504423158, | |
| "grad_norm": 4.0528645515441895, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.2877, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000879136980530779, | |
| "grad_norm": 1.00792396068573, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.0218, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001025659810619242, | |
| "grad_norm": 0.8242140412330627, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.0026, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0011721826407077053, | |
| "grad_norm": 0.01713043637573719, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0002, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0013187054707961684, | |
| "grad_norm": 0.0027765310369431973, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0014652283008846315, | |
| "grad_norm": 0.005665022414177656, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0016117511309730948, | |
| "grad_norm": 0.017976634204387665, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.001758273961061558, | |
| "grad_norm": 0.006979241501539946, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.001904796791150021, | |
| "grad_norm": 0.0015923851169645786, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002051319621238484, | |
| "grad_norm": 0.0010537989437580109, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0021978424513269474, | |
| "grad_norm": 0.0012975798454135656, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0023443652814154107, | |
| "grad_norm": 0.0013601743848994374, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0024908881115038735, | |
| "grad_norm": 0.0014510821783915162, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.002637410941592337, | |
| "grad_norm": 0.0015000648563727736, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0027839337716808, | |
| "grad_norm": 0.0012648840202018619, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.002930456601769263, | |
| "grad_norm": 0.0009284365805797279, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0030769794318577263, | |
| "grad_norm": 0.0007029483676888049, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0032235022619461896, | |
| "grad_norm": 0.0004989892477169633, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0033700250920346525, | |
| "grad_norm": 0.0003535033611115068, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.003516547922123116, | |
| "grad_norm": 0.0002854061604011804, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003663070752211579, | |
| "grad_norm": 0.0002517289249226451, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.003663070752211579, | |
| "eval_loss": 0.0005636036512441933, | |
| "eval_runtime": 2444.0569, | |
| "eval_samples_per_second": 18.812, | |
| "eval_steps_per_second": 2.352, | |
| "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": 3.315690861756416e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |