| { | |
| "best_metric": 1.2017804384231567, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.5818181818181818, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02327272727272727, | |
| "grad_norm": 1.7745463848114014, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5999, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02327272727272727, | |
| "eval_loss": 1.773289442062378, | |
| "eval_runtime": 3.9571, | |
| "eval_samples_per_second": 12.635, | |
| "eval_steps_per_second": 3.285, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04654545454545454, | |
| "grad_norm": 1.9175318479537964, | |
| "learning_rate": 0.0001, | |
| "loss": 1.773, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06981818181818182, | |
| "grad_norm": 1.262076735496521, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.6515, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.09309090909090909, | |
| "grad_norm": 0.9791045188903809, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.4618, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.11636363636363636, | |
| "grad_norm": 0.8115462064743042, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.4479, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.13963636363636364, | |
| "grad_norm": 0.7214769721031189, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.3714, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.16290909090909092, | |
| "grad_norm": 0.5080850720405579, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.328, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.18618181818181817, | |
| "grad_norm": 0.8564537167549133, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.346, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.20945454545454545, | |
| "grad_norm": 0.5081934928894043, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.3867, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.23272727272727273, | |
| "grad_norm": 0.5730867981910706, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.4286, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.256, | |
| "grad_norm": 0.6481610536575317, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.3303, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2792727272727273, | |
| "grad_norm": 0.5679121017456055, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.363, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.30254545454545456, | |
| "grad_norm": 0.4099390208721161, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.3366, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.32581818181818184, | |
| "grad_norm": 0.3924468159675598, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.2421, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3490909090909091, | |
| "grad_norm": 0.42564189434051514, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.2091, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.37236363636363634, | |
| "grad_norm": 0.39355647563934326, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.1623, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3956363636363636, | |
| "grad_norm": 0.36167147755622864, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.1963, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4189090909090909, | |
| "grad_norm": 0.3511923849582672, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.1963, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.4421818181818182, | |
| "grad_norm": 0.37287771701812744, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.2414, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.46545454545454545, | |
| "grad_norm": 0.3826206922531128, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.3273, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.48872727272727273, | |
| "grad_norm": 0.5573943853378296, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.4127, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.512, | |
| "grad_norm": 0.5266674160957336, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.2144, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5352727272727272, | |
| "grad_norm": 0.48996224999427795, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.2944, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5585454545454546, | |
| "grad_norm": 0.41946741938591003, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.2175, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5818181818181818, | |
| "grad_norm": 0.3697955310344696, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.1384, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5818181818181818, | |
| "eval_loss": 1.2017804384231567, | |
| "eval_runtime": 4.0484, | |
| "eval_samples_per_second": 12.351, | |
| "eval_steps_per_second": 3.211, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 1.62480894509056e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |