| { | |
| "best_metric": 1.7508697509765625, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.02689437235258522, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010757748941034088, | |
| "grad_norm": 1.6709057092666626, | |
| "learning_rate": 5e-05, | |
| "loss": 1.707, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010757748941034088, | |
| "eval_loss": 2.019153356552124, | |
| "eval_runtime": 186.2275, | |
| "eval_samples_per_second": 33.631, | |
| "eval_steps_per_second": 4.205, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0021515497882068175, | |
| "grad_norm": 1.8899304866790771, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8408, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0032273246823102267, | |
| "grad_norm": 1.4666272401809692, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.7696, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004303099576413635, | |
| "grad_norm": 0.9372745752334595, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.7414, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005378874470517044, | |
| "grad_norm": 0.8082295656204224, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.7415, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006454649364620453, | |
| "grad_norm": 0.9279489517211914, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.7757, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007530424258723862, | |
| "grad_norm": 0.701418936252594, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.8196, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00860619915282727, | |
| "grad_norm": 0.688548743724823, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.7341, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00968197404693068, | |
| "grad_norm": 0.6612863540649414, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.7848, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010757748941034088, | |
| "grad_norm": 0.6995035409927368, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.8447, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011833523835137498, | |
| "grad_norm": 0.7706447243690491, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.8312, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.012909298729240907, | |
| "grad_norm": 0.9608161449432373, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.0029, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.013985073623344316, | |
| "grad_norm": 1.8199213743209839, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.6517, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.015060848517447724, | |
| "grad_norm": 1.3464016914367676, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.6332, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.016136623411551133, | |
| "grad_norm": 0.96041339635849, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.6261, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01721239830565454, | |
| "grad_norm": 0.7431668043136597, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.6273, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01828817319975795, | |
| "grad_norm": 0.560585618019104, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.6822, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01936394809386136, | |
| "grad_norm": 0.5964136123657227, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.7219, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02043972298796477, | |
| "grad_norm": 0.6002236604690552, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.7398, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.021515497882068177, | |
| "grad_norm": 0.6054794788360596, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.778, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.022591272776171584, | |
| "grad_norm": 0.6320491433143616, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.7474, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.023667047670274995, | |
| "grad_norm": 0.6241698265075684, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.8189, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.024742822564378403, | |
| "grad_norm": 0.7055386304855347, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.7957, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.025818597458481814, | |
| "grad_norm": 0.8027210235595703, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.9507, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02689437235258522, | |
| "grad_norm": 1.0420467853546143, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.1519, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02689437235258522, | |
| "eval_loss": 1.7508697509765625, | |
| "eval_runtime": 186.2853, | |
| "eval_samples_per_second": 33.62, | |
| "eval_steps_per_second": 4.203, | |
| "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": 2.829012279754752e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |