| { | |
| "best_metric": 11.761922836303711, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.1505740636175419, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006022962544701675, | |
| "grad_norm": 0.01612170971930027, | |
| "learning_rate": 5e-05, | |
| "loss": 11.7634, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006022962544701675, | |
| "eval_loss": 11.763358116149902, | |
| "eval_runtime": 0.1602, | |
| "eval_samples_per_second": 312.115, | |
| "eval_steps_per_second": 81.15, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01204592508940335, | |
| "grad_norm": 0.017310731112957, | |
| "learning_rate": 0.0001, | |
| "loss": 11.7641, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.018068887634105024, | |
| "grad_norm": 0.017811642959713936, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 11.7633, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0240918501788067, | |
| "grad_norm": 0.017435574904084206, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 11.7639, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.030114812723508376, | |
| "grad_norm": 0.01878247782588005, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 11.764, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03613777526821005, | |
| "grad_norm": 0.020671362057328224, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 11.764, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04216073781291173, | |
| "grad_norm": 0.020911457017064095, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 11.7628, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0481837003576134, | |
| "grad_norm": 0.023352282121777534, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 11.7639, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05420666290231508, | |
| "grad_norm": 0.027156133204698563, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 11.7645, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06022962544701675, | |
| "grad_norm": 0.03595906123518944, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 11.7645, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06625258799171843, | |
| "grad_norm": 0.03207791969180107, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 11.7657, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0722755505364201, | |
| "grad_norm": 0.024177242070436478, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 11.7622, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07829851308112178, | |
| "grad_norm": 0.020650768652558327, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 11.7629, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08432147562582346, | |
| "grad_norm": 0.023741766810417175, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 11.7627, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09034443817052512, | |
| "grad_norm": 0.02351335994899273, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 11.762, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0963674007152268, | |
| "grad_norm": 0.025068705901503563, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 11.7628, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.10239036325992848, | |
| "grad_norm": 0.02813185192644596, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 11.7617, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.10841332580463016, | |
| "grad_norm": 0.027025412768125534, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 11.7626, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.11443628834933182, | |
| "grad_norm": 0.026679476723074913, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 11.7635, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1204592508940335, | |
| "grad_norm": 0.028635568916797638, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 11.7631, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12648221343873517, | |
| "grad_norm": 0.03578168898820877, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 11.7632, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.13250517598343686, | |
| "grad_norm": 0.03557748720049858, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 11.7632, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.13852813852813853, | |
| "grad_norm": 0.040470145642757416, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 11.7638, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1445511010728402, | |
| "grad_norm": 0.03568543121218681, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 11.7636, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1505740636175419, | |
| "grad_norm": 0.034206315875053406, | |
| "learning_rate": 1e-05, | |
| "loss": 11.7606, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1505740636175419, | |
| "eval_loss": 11.761922836303711, | |
| "eval_runtime": 0.1607, | |
| "eval_samples_per_second": 311.181, | |
| "eval_steps_per_second": 80.907, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 81994283220992.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |