| { | |
| "best_metric": 0.09947963058948517, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.01533918779000652, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006135675116002607, | |
| "grad_norm": 0.7583703994750977, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7206, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006135675116002607, | |
| "eval_loss": 1.1403805017471313, | |
| "eval_runtime": 4.3679, | |
| "eval_samples_per_second": 11.447, | |
| "eval_steps_per_second": 2.976, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012271350232005214, | |
| "grad_norm": 0.8787322640419006, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8522, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0018407025348007823, | |
| "grad_norm": 0.8613839745521545, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.8327, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002454270046401043, | |
| "grad_norm": 0.821357250213623, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.6956, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003067837558001304, | |
| "grad_norm": 0.695791482925415, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.6351, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0036814050696015645, | |
| "grad_norm": 0.6424224972724915, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.4879, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004294972581201826, | |
| "grad_norm": 0.7815857529640198, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.4486, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004908540092802086, | |
| "grad_norm": 0.8228691816329956, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.4152, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005522107604402347, | |
| "grad_norm": 0.6749762892723083, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.3557, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006135675116002608, | |
| "grad_norm": 0.5336638689041138, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.3013, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006749242627602868, | |
| "grad_norm": 0.5431511402130127, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.297, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.007362810139203129, | |
| "grad_norm": 0.5695570111274719, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.2957, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00797637765080339, | |
| "grad_norm": 0.647546112537384, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.2095, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.008589945162403651, | |
| "grad_norm": 0.502677857875824, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.1585, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.009203512674003912, | |
| "grad_norm": 0.4411288797855377, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.1422, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009817080185604172, | |
| "grad_norm": 0.35536736249923706, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.1201, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.010430647697204433, | |
| "grad_norm": 0.28933218121528625, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.1229, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.011044215208804694, | |
| "grad_norm": 0.30381715297698975, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.125, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.011657782720404955, | |
| "grad_norm": 0.31191951036453247, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.1141, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.012271350232005216, | |
| "grad_norm": 0.31290727853775024, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.112, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.012884917743605477, | |
| "grad_norm": 0.3080437481403351, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.1185, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.013498485255205736, | |
| "grad_norm": 0.26505807042121887, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.1071, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.014112052766805997, | |
| "grad_norm": 0.3317841589450836, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.1331, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.014725620278406258, | |
| "grad_norm": 0.29665809869766235, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.1352, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01533918779000652, | |
| "grad_norm": 0.4122360646724701, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.1553, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01533918779000652, | |
| "eval_loss": 0.09947963058948517, | |
| "eval_runtime": 4.407, | |
| "eval_samples_per_second": 11.346, | |
| "eval_steps_per_second": 2.95, | |
| "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": 1.327074698592256e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |