| { | |
| "best_metric": 2.4257006645202637, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.005509641873278, | |
| "eval_steps": 25, | |
| "global_step": 34, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0881542699724518, | |
| "grad_norm": 2.2832279205322266, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8182, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0881542699724518, | |
| "eval_loss": 3.1459929943084717, | |
| "eval_runtime": 5.1666, | |
| "eval_samples_per_second": 9.678, | |
| "eval_steps_per_second": 2.516, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1763085399449036, | |
| "grad_norm": 2.4270896911621094, | |
| "learning_rate": 0.0001, | |
| "loss": 2.9394, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2644628099173554, | |
| "grad_norm": 1.7247925996780396, | |
| "learning_rate": 9.978331270024886e-05, | |
| "loss": 2.8249, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.3526170798898072, | |
| "grad_norm": 0.517701268196106, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.5043, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.44077134986225897, | |
| "grad_norm": 1.2870688438415527, | |
| "learning_rate": 9.80623151079494e-05, | |
| "loss": 2.675, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5289256198347108, | |
| "grad_norm": 1.1491432189941406, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.46, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6170798898071626, | |
| "grad_norm": 0.7123168110847473, | |
| "learning_rate": 9.468645689567598e-05, | |
| "loss": 2.476, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.7052341597796143, | |
| "grad_norm": 0.540136992931366, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.4515, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.7933884297520661, | |
| "grad_norm": 0.3604734539985657, | |
| "learning_rate": 8.978547040132317e-05, | |
| "loss": 2.3541, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.8815426997245179, | |
| "grad_norm": 0.41715145111083984, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.3314, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9696969696969697, | |
| "grad_norm": 0.5570409297943115, | |
| "learning_rate": 8.354769778736406e-05, | |
| "loss": 2.4239, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.0606060606060606, | |
| "grad_norm": 0.9138440489768982, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 3.9875, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.1487603305785123, | |
| "grad_norm": 0.4669186770915985, | |
| "learning_rate": 7.62128531571699e-05, | |
| "loss": 2.3004, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.2369146005509641, | |
| "grad_norm": 0.29149070382118225, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.5514, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.325068870523416, | |
| "grad_norm": 0.4434710741043091, | |
| "learning_rate": 6.80628104764508e-05, | |
| "loss": 3.0328, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.4132231404958677, | |
| "grad_norm": 0.34659796953201294, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 2.2989, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.5013774104683195, | |
| "grad_norm": 0.29691722989082336, | |
| "learning_rate": 5.941077131483025e-05, | |
| "loss": 1.7226, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.5895316804407713, | |
| "grad_norm": 0.318291038274765, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.7114, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.677685950413223, | |
| "grad_norm": 0.4363364279270172, | |
| "learning_rate": 5.058922868516978e-05, | |
| "loss": 2.3956, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.765840220385675, | |
| "grad_norm": 0.31696414947509766, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.9789, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.8539944903581267, | |
| "grad_norm": 0.31689485907554626, | |
| "learning_rate": 4.19371895235492e-05, | |
| "loss": 2.3921, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.9421487603305785, | |
| "grad_norm": 0.4861513376235962, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 2.5216, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.0330578512396693, | |
| "grad_norm": 0.6045956015586853, | |
| "learning_rate": 3.378714684283011e-05, | |
| "loss": 3.5434, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.121212121212121, | |
| "grad_norm": 0.3145506680011749, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 2.1778, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.209366391184573, | |
| "grad_norm": 0.3042181432247162, | |
| "learning_rate": 2.645230221263596e-05, | |
| "loss": 1.7248, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.209366391184573, | |
| "eval_loss": 2.4257006645202637, | |
| "eval_runtime": 5.1557, | |
| "eval_samples_per_second": 9.698, | |
| "eval_steps_per_second": 2.521, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.2975206611570247, | |
| "grad_norm": 0.41272634267807007, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 2.5983, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.3856749311294765, | |
| "grad_norm": 0.36301037669181824, | |
| "learning_rate": 2.0214529598676836e-05, | |
| "loss": 2.2062, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.4738292011019283, | |
| "grad_norm": 0.3128720819950104, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.4659, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.56198347107438, | |
| "grad_norm": 0.4098537266254425, | |
| "learning_rate": 1.531354310432403e-05, | |
| "loss": 2.8288, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.650137741046832, | |
| "grad_norm": 0.3570498824119568, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 2.247, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.7382920110192837, | |
| "grad_norm": 0.33370527625083923, | |
| "learning_rate": 1.1937684892050604e-05, | |
| "loss": 1.6995, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.8264462809917354, | |
| "grad_norm": 0.3551836907863617, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 2.5734, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.9146005509641872, | |
| "grad_norm": 0.43611598014831543, | |
| "learning_rate": 1.0216687299751144e-05, | |
| "loss": 2.4137, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 3.005509641873278, | |
| "grad_norm": 0.7053166627883911, | |
| "learning_rate": 1e-05, | |
| "loss": 3.3946, | |
| "step": 34 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 34, | |
| "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": 4.509339571988726e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |