| { | |
| "best_metric": 1.7455496788024902, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.0797872340425534, | |
| "eval_steps": 25, | |
| "global_step": 36, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0851063829787234, | |
| "grad_norm": 0.337377667427063, | |
| "learning_rate": 5e-05, | |
| "loss": 1.543, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0851063829787234, | |
| "eval_loss": 2.8193228244781494, | |
| "eval_runtime": 1.9155, | |
| "eval_samples_per_second": 26.103, | |
| "eval_steps_per_second": 6.787, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1702127659574468, | |
| "grad_norm": 1.0103968381881714, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3898, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2553191489361702, | |
| "grad_norm": 0.40538832545280457, | |
| "learning_rate": 9.980803793327656e-05, | |
| "loss": 1.3125, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.3404255319148936, | |
| "grad_norm": 0.30337655544281006, | |
| "learning_rate": 9.923378948577559e-05, | |
| "loss": 1.6227, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.425531914893617, | |
| "grad_norm": 2.6769063472747803, | |
| "learning_rate": 9.828215394277687e-05, | |
| "loss": 2.5671, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5106382978723404, | |
| "grad_norm": 0.2441849261522293, | |
| "learning_rate": 9.6961250323196e-05, | |
| "loss": 1.1992, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5957446808510638, | |
| "grad_norm": 0.3681361973285675, | |
| "learning_rate": 9.528234811097782e-05, | |
| "loss": 1.7804, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.6808510638297872, | |
| "grad_norm": 1.3270093202590942, | |
| "learning_rate": 9.325977110783264e-05, | |
| "loss": 2.2679, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.7659574468085106, | |
| "grad_norm": 0.2342531681060791, | |
| "learning_rate": 9.091077522761079e-05, | |
| "loss": 1.1517, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.851063829787234, | |
| "grad_norm": 1.1225703954696655, | |
| "learning_rate": 8.825540127492967e-05, | |
| "loss": 1.8651, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9361702127659575, | |
| "grad_norm": 1.0222384929656982, | |
| "learning_rate": 8.531630396409507e-05, | |
| "loss": 2.0007, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.0265957446808511, | |
| "grad_norm": 0.36375167965888977, | |
| "learning_rate": 8.211855863706654e-05, | |
| "loss": 1.9288, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.1117021276595744, | |
| "grad_norm": 0.33239567279815674, | |
| "learning_rate": 7.868944732948101e-05, | |
| "loss": 1.6168, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.196808510638298, | |
| "grad_norm": 0.26805180311203003, | |
| "learning_rate": 7.505822600994424e-05, | |
| "loss": 1.0579, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.2819148936170213, | |
| "grad_norm": 0.3009487986564636, | |
| "learning_rate": 7.12558749784219e-05, | |
| "loss": 1.5312, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.3670212765957448, | |
| "grad_norm": 0.39399126172065735, | |
| "learning_rate": 6.731483455324374e-05, | |
| "loss": 1.8618, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.452127659574468, | |
| "grad_norm": 0.34218811988830566, | |
| "learning_rate": 6.326872830174567e-05, | |
| "loss": 0.9687, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.5372340425531914, | |
| "grad_norm": 0.3016256093978882, | |
| "learning_rate": 5.9152076175848594e-05, | |
| "loss": 1.8985, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.622340425531915, | |
| "grad_norm": 0.38652870059013367, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.827, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.7074468085106385, | |
| "grad_norm": 0.4191890060901642, | |
| "learning_rate": 5.0847923824151424e-05, | |
| "loss": 1.2199, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.7925531914893615, | |
| "grad_norm": 0.278137743473053, | |
| "learning_rate": 4.673127169825433e-05, | |
| "loss": 1.7785, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.877659574468085, | |
| "grad_norm": 0.4404103755950928, | |
| "learning_rate": 4.268516544675628e-05, | |
| "loss": 2.0553, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.9627659574468086, | |
| "grad_norm": 0.537523627281189, | |
| "learning_rate": 3.8744125021578126e-05, | |
| "loss": 2.2151, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.0531914893617023, | |
| "grad_norm": 0.16800740361213684, | |
| "learning_rate": 3.494177399005578e-05, | |
| "loss": 1.1205, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.1382978723404253, | |
| "grad_norm": 0.34991270303726196, | |
| "learning_rate": 3.1310552670518986e-05, | |
| "loss": 1.9167, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.1382978723404253, | |
| "eval_loss": 1.7455496788024902, | |
| "eval_runtime": 0.9406, | |
| "eval_samples_per_second": 53.157, | |
| "eval_steps_per_second": 13.821, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.223404255319149, | |
| "grad_norm": 0.18386214971542358, | |
| "learning_rate": 2.7881441362933468e-05, | |
| "loss": 0.4926, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.3085106382978724, | |
| "grad_norm": 0.2846694588661194, | |
| "learning_rate": 2.4683696035904928e-05, | |
| "loss": 1.9249, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.393617021276596, | |
| "grad_norm": 0.40197649598121643, | |
| "learning_rate": 2.1744598725070347e-05, | |
| "loss": 2.0293, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.478723404255319, | |
| "grad_norm": 0.21188139915466309, | |
| "learning_rate": 1.9089224772389225e-05, | |
| "loss": 0.7225, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.5638297872340425, | |
| "grad_norm": 0.25818443298339844, | |
| "learning_rate": 1.674022889216737e-05, | |
| "loss": 1.9215, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.648936170212766, | |
| "grad_norm": 0.4542253315448761, | |
| "learning_rate": 1.4717651889022202e-05, | |
| "loss": 1.9208, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.7340425531914896, | |
| "grad_norm": 0.29611721634864807, | |
| "learning_rate": 1.3038749676803994e-05, | |
| "loss": 1.176, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.8191489361702127, | |
| "grad_norm": 0.27275022864341736, | |
| "learning_rate": 1.1717846057223144e-05, | |
| "loss": 1.8955, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.904255319148936, | |
| "grad_norm": 0.6470306515693665, | |
| "learning_rate": 1.076621051422442e-05, | |
| "loss": 2.0274, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.9893617021276597, | |
| "grad_norm": 0.5650705695152283, | |
| "learning_rate": 1.019196206672345e-05, | |
| "loss": 1.638, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 3.0797872340425534, | |
| "grad_norm": 0.15843090415000916, | |
| "learning_rate": 1e-05, | |
| "loss": 1.2924, | |
| "step": 36 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 36, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 5.637908650681958e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |