| { | |
| "best_metric": 2.25999116897583, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.2385211687537269, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009540846750149075, | |
| "grad_norm": 1.8301076889038086, | |
| "learning_rate": 5e-05, | |
| "loss": 4.322, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009540846750149075, | |
| "eval_loss": 4.8114399909973145, | |
| "eval_runtime": 18.1126, | |
| "eval_samples_per_second": 38.978, | |
| "eval_steps_per_second": 4.914, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01908169350029815, | |
| "grad_norm": 1.8661367893218994, | |
| "learning_rate": 0.0001, | |
| "loss": 4.4709, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.028622540250447227, | |
| "grad_norm": 1.7598766088485718, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.3484, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0381633870005963, | |
| "grad_norm": 1.779036521911621, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.3718, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04770423375074538, | |
| "grad_norm": 1.6287198066711426, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 4.3085, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.057245080500894455, | |
| "grad_norm": 1.5695362091064453, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 4.1665, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06678592725104353, | |
| "grad_norm": 1.5657461881637573, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 4.1333, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0763267740011926, | |
| "grad_norm": 1.6495347023010254, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.035, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08586762075134168, | |
| "grad_norm": 1.7429325580596924, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 3.935, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09540846750149076, | |
| "grad_norm": 1.949917197227478, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.8395, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10494931425163984, | |
| "grad_norm": 1.8356688022613525, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 3.7738, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.11449016100178891, | |
| "grad_norm": 1.7465165853500366, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.6787, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.12403100775193798, | |
| "grad_norm": 1.9388281106948853, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 3.3392, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.13357185450208706, | |
| "grad_norm": 1.9967145919799805, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.9606, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.14311270125223613, | |
| "grad_norm": 1.7755789756774902, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.8587, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1526535480023852, | |
| "grad_norm": 1.6878576278686523, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.7728, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.16219439475253428, | |
| "grad_norm": 1.6326628923416138, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.7704, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.17173524150268335, | |
| "grad_norm": 1.579866886138916, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.6041, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.18127608825283245, | |
| "grad_norm": 1.4619033336639404, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.6488, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.19081693500298152, | |
| "grad_norm": 1.3311792612075806, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.4769, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2003577817531306, | |
| "grad_norm": 1.508536696434021, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.5221, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.20989862850327967, | |
| "grad_norm": 1.3549234867095947, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.5081, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.21943947525342875, | |
| "grad_norm": 1.482054352760315, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.501, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.22898032200357782, | |
| "grad_norm": 1.4199994802474976, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.448, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2385211687537269, | |
| "grad_norm": 1.699617862701416, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.7868, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2385211687537269, | |
| "eval_loss": 2.25999116897583, | |
| "eval_runtime": 17.9847, | |
| "eval_samples_per_second": 39.256, | |
| "eval_steps_per_second": 4.949, | |
| "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 | |
| } | |