| { | |
| "best_metric": 0.3024834394454956, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.2147074610842727, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008588298443370907, | |
| "grad_norm": 7.55905294418335, | |
| "learning_rate": 5e-05, | |
| "loss": 9.1199, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008588298443370907, | |
| "eval_loss": 9.081170082092285, | |
| "eval_runtime": 2.5395, | |
| "eval_samples_per_second": 19.689, | |
| "eval_steps_per_second": 5.119, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017176596886741814, | |
| "grad_norm": 7.514353275299072, | |
| "learning_rate": 0.0001, | |
| "loss": 8.8054, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02576489533011272, | |
| "grad_norm": 7.8171467781066895, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 8.7824, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03435319377348363, | |
| "grad_norm": 7.417876243591309, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 6.9901, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04294149221685454, | |
| "grad_norm": 6.940496444702148, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 5.0434, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05152979066022544, | |
| "grad_norm": 5.353168487548828, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 4.0804, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06011808910359635, | |
| "grad_norm": 4.561730861663818, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 3.0291, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06870638754696726, | |
| "grad_norm": 4.618034362792969, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.4864, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07729468599033816, | |
| "grad_norm": 3.445601463317871, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.7061, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08588298443370908, | |
| "grad_norm": 2.718672752380371, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.0334, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09447128287707998, | |
| "grad_norm": 2.2221052646636963, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.87, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10305958132045089, | |
| "grad_norm": 2.8456015586853027, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.8587, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11164787976382179, | |
| "grad_norm": 3.1550638675689697, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.7196, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1202361782071927, | |
| "grad_norm": 2.76228928565979, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.4587, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1288244766505636, | |
| "grad_norm": 2.384809732437134, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.3835, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1374127750939345, | |
| "grad_norm": 2.198056936264038, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.3717, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.14600107353730543, | |
| "grad_norm": 3.1217353343963623, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.3326, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.15458937198067632, | |
| "grad_norm": 1.242319941520691, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.2944, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.16317767042404724, | |
| "grad_norm": 4.2636613845825195, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.3544, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.17176596886741816, | |
| "grad_norm": 2.7467615604400635, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.3021, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18035426731078905, | |
| "grad_norm": 1.0115433931350708, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.3188, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.18894256575415996, | |
| "grad_norm": 1.282575249671936, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.3169, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": 0.8947703242301941, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.3382, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.20611916264090177, | |
| "grad_norm": 0.7449538111686707, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.3761, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2147074610842727, | |
| "grad_norm": 1.1275854110717773, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.3411, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2147074610842727, | |
| "eval_loss": 0.3024834394454956, | |
| "eval_runtime": 1.9145, | |
| "eval_samples_per_second": 26.116, | |
| "eval_steps_per_second": 6.79, | |
| "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": 2.66009604784128e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |