| { | |
| "best_metric": 2.3962597846984863, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.009206407659731172, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003682563063892469, | |
| "grad_norm": 1.91280996799469, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1982, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003682563063892469, | |
| "eval_loss": 3.6061596870422363, | |
| "eval_runtime": 1.5161, | |
| "eval_samples_per_second": 32.978, | |
| "eval_steps_per_second": 8.574, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007365126127784938, | |
| "grad_norm": 2.0957469940185547, | |
| "learning_rate": 0.0001, | |
| "loss": 2.4763, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011047689191677407, | |
| "grad_norm": 1.9613713026046753, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.5186, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014730252255569876, | |
| "grad_norm": 1.4553881883621216, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.4343, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0018412815319462346, | |
| "grad_norm": 1.5710747241973877, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.3533, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0022095378383354815, | |
| "grad_norm": 1.426024317741394, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.2975, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0025777941447247283, | |
| "grad_norm": 1.3779783248901367, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.4956, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002946050451113975, | |
| "grad_norm": 1.282586693763733, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.5275, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0033143067575032224, | |
| "grad_norm": 1.0497735738754272, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.6698, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0036825630638924692, | |
| "grad_norm": 1.044584035873413, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.7479, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004050819370281716, | |
| "grad_norm": 1.3881807327270508, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.9648, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004419075676670963, | |
| "grad_norm": 2.0393691062927246, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 3.2128, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00478733198306021, | |
| "grad_norm": 0.870771050453186, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.7127, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005155588289449457, | |
| "grad_norm": 0.8859942555427551, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.8588, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005523844595838704, | |
| "grad_norm": 0.8486651182174683, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.0634, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00589210090222795, | |
| "grad_norm": 0.7893238663673401, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 2.0783, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0062603572086171975, | |
| "grad_norm": 0.6707751154899597, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 2.106, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006628613515006445, | |
| "grad_norm": 0.6826125979423523, | |
| "learning_rate": 7.75e-05, | |
| "loss": 2.2365, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006996869821395691, | |
| "grad_norm": 0.6989638209342957, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 2.1631, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0073651261277849385, | |
| "grad_norm": 0.7944750785827637, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 2.2346, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007733382434174185, | |
| "grad_norm": 0.7866911292076111, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 2.1823, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.008101638740563431, | |
| "grad_norm": 0.8714109659194946, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 2.3636, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.00846989504695268, | |
| "grad_norm": 1.1833001375198364, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 2.7353, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.008838151353341926, | |
| "grad_norm": 1.4409525394439697, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 3.0607, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.009206407659731172, | |
| "grad_norm": 2.9500479698181152, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 3.1293, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.009206407659731172, | |
| "eval_loss": 2.3962597846984863, | |
| "eval_runtime": 1.475, | |
| "eval_samples_per_second": 33.898, | |
| "eval_steps_per_second": 8.813, | |
| "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": 7.952285976808653e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |