| { | |
| "best_metric": 10.363873481750488, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.059497248252268334, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002379889930090733, | |
| "grad_norm": 0.0426366962492466, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3782, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002379889930090733, | |
| "eval_loss": 10.375080108642578, | |
| "eval_runtime": 0.0848, | |
| "eval_samples_per_second": 589.444, | |
| "eval_steps_per_second": 153.255, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004759779860181466, | |
| "grad_norm": 0.05311519652605057, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3748, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0071396697902722, | |
| "grad_norm": 0.074241042137146, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 10.3696, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009519559720362933, | |
| "grad_norm": 0.07961831986904144, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 10.3689, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011899449650453666, | |
| "grad_norm": 0.08965161442756653, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 10.3738, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0142793395805444, | |
| "grad_norm": 0.09700139611959457, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 10.3708, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.016659229510635132, | |
| "grad_norm": 0.10126373171806335, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 10.3701, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.019039119440725866, | |
| "grad_norm": 0.10692870616912842, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 10.3723, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0214190093708166, | |
| "grad_norm": 0.10815344750881195, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 10.3693, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.023798899300907332, | |
| "grad_norm": 0.10395736992359161, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 10.3701, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.026178789230998065, | |
| "grad_norm": 0.118967704474926, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 10.3687, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0285586791610888, | |
| "grad_norm": 0.12255120277404785, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 10.3699, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.030938569091179532, | |
| "grad_norm": 0.058280669152736664, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 10.3746, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.033318459021270265, | |
| "grad_norm": 0.04936497285962105, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 10.3754, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.035698348951361, | |
| "grad_norm": 0.07907063513994217, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 10.3692, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03807823888145173, | |
| "grad_norm": 0.0914483442902565, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 10.3659, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04045812881154247, | |
| "grad_norm": 0.1104273870587349, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 10.3646, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0428380187416332, | |
| "grad_norm": 0.116667240858078, | |
| "learning_rate": 7.75e-05, | |
| "loss": 10.365, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.045217908671723935, | |
| "grad_norm": 0.1322374939918518, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 10.3665, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.047597798601814664, | |
| "grad_norm": 0.13855485618114471, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 10.3659, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0499776885319054, | |
| "grad_norm": 0.12768369913101196, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 10.3616, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05235757846199613, | |
| "grad_norm": 0.1414341926574707, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 10.3626, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05473746839208687, | |
| "grad_norm": 0.1361013501882553, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 10.3631, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0571173583221776, | |
| "grad_norm": 0.13812997937202454, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 10.3627, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.059497248252268334, | |
| "grad_norm": 0.13790108263492584, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 10.3618, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.059497248252268334, | |
| "eval_loss": 10.363873481750488, | |
| "eval_runtime": 0.0816, | |
| "eval_samples_per_second": 612.812, | |
| "eval_steps_per_second": 159.331, | |
| "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": 21384029798400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |