| { | |
| "best_metric": 3.7517294883728027, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.0009194641363013636, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.677856545205454e-05, | |
| "grad_norm": 2.1201064586639404, | |
| "learning_rate": 1e-05, | |
| "loss": 14.0814, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.677856545205454e-05, | |
| "eval_loss": 3.8606455326080322, | |
| "eval_runtime": 739.1058, | |
| "eval_samples_per_second": 15.49, | |
| "eval_steps_per_second": 7.746, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.355713090410909e-05, | |
| "grad_norm": 3.3264341354370117, | |
| "learning_rate": 2e-05, | |
| "loss": 16.4635, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00011033569635616363, | |
| "grad_norm": 2.497408866882324, | |
| "learning_rate": 3e-05, | |
| "loss": 15.8726, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00014711426180821817, | |
| "grad_norm": 3.2194437980651855, | |
| "learning_rate": 4e-05, | |
| "loss": 14.8162, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00018389282726027272, | |
| "grad_norm": 3.457934617996216, | |
| "learning_rate": 5e-05, | |
| "loss": 15.1606, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00018389282726027272, | |
| "eval_loss": 3.8564059734344482, | |
| "eval_runtime": 738.9862, | |
| "eval_samples_per_second": 15.493, | |
| "eval_steps_per_second": 7.747, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00022067139271232726, | |
| "grad_norm": 2.7731423377990723, | |
| "learning_rate": 6e-05, | |
| "loss": 14.1681, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002574499581643818, | |
| "grad_norm": 2.2123680114746094, | |
| "learning_rate": 7e-05, | |
| "loss": 14.4528, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00029422852361643635, | |
| "grad_norm": 2.2788443565368652, | |
| "learning_rate": 8e-05, | |
| "loss": 15.9437, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0003310070890684909, | |
| "grad_norm": 6.673981666564941, | |
| "learning_rate": 9e-05, | |
| "loss": 15.1776, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00036778565452054543, | |
| "grad_norm": 2.5079147815704346, | |
| "learning_rate": 0.0001, | |
| "loss": 15.3765, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00036778565452054543, | |
| "eval_loss": 3.8233513832092285, | |
| "eval_runtime": 741.3845, | |
| "eval_samples_per_second": 15.443, | |
| "eval_steps_per_second": 7.722, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004045642199726, | |
| "grad_norm": 2.8351001739501953, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 16.4796, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0004413427854246545, | |
| "grad_norm": 3.332181453704834, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 15.6604, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00047812135087670906, | |
| "grad_norm": 4.804444313049316, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 15.2079, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0005148999163287636, | |
| "grad_norm": 2.3618407249450684, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 14.6311, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0005516784817808181, | |
| "grad_norm": 3.831026792526245, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 15.2172, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0005516784817808181, | |
| "eval_loss": 3.776841878890991, | |
| "eval_runtime": 743.7441, | |
| "eval_samples_per_second": 15.394, | |
| "eval_steps_per_second": 7.698, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0005884570472328727, | |
| "grad_norm": 3.0379860401153564, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 15.2776, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0006252356126849272, | |
| "grad_norm": 3.142021417617798, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 14.6165, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0006620141781369818, | |
| "grad_norm": 3.2710373401641846, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 16.1777, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0006987927435890363, | |
| "grad_norm": 4.714978218078613, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 15.0562, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0007355713090410909, | |
| "grad_norm": 3.9726500511169434, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 15.9209, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0007355713090410909, | |
| "eval_loss": 3.755293130874634, | |
| "eval_runtime": 739.3398, | |
| "eval_samples_per_second": 15.485, | |
| "eval_steps_per_second": 7.743, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0007723498744931454, | |
| "grad_norm": 4.634418487548828, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 15.9765, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0008091284399452, | |
| "grad_norm": 3.4980578422546387, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 15.835, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0008459070053972545, | |
| "grad_norm": 3.5311439037323, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 15.0439, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.000882685570849309, | |
| "grad_norm": 3.130390167236328, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 14.4918, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0009194641363013636, | |
| "grad_norm": 2.921156644821167, | |
| "learning_rate": 0.0, | |
| "loss": 15.3883, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0009194641363013636, | |
| "eval_loss": 3.7517294883728027, | |
| "eval_runtime": 745.0938, | |
| "eval_samples_per_second": 15.366, | |
| "eval_steps_per_second": 7.684, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 375348264960000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |