| { | |
| "best_metric": 9.151042938232422, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.06575702778234424, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0026302811112937697, | |
| "grad_norm": 4.166772365570068, | |
| "learning_rate": 5e-05, | |
| "loss": 10.4191, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0026302811112937697, | |
| "eval_loss": 10.206449508666992, | |
| "eval_runtime": 0.2492, | |
| "eval_samples_per_second": 200.666, | |
| "eval_steps_per_second": 52.173, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005260562222587539, | |
| "grad_norm": 3.9618587493896484, | |
| "learning_rate": 0.0001, | |
| "loss": 10.2675, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007890843333881308, | |
| "grad_norm": 4.077890872955322, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 10.2374, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010521124445175079, | |
| "grad_norm": 4.005270957946777, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 10.141, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013151405556468848, | |
| "grad_norm": 3.936140775680542, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 10.0376, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015781686667762616, | |
| "grad_norm": 3.7704663276672363, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 9.9487, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.018411967779056387, | |
| "grad_norm": 3.607231855392456, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 9.8131, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.021042248890350158, | |
| "grad_norm": 3.440260648727417, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 9.8168, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.023672530001643925, | |
| "grad_norm": 3.4772696495056152, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 9.6004, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.026302811112937696, | |
| "grad_norm": 3.6518537998199463, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 9.4994, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.028933092224231464, | |
| "grad_norm": 4.118347644805908, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 9.3983, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03156337333552523, | |
| "grad_norm": 4.641587257385254, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 9.2531, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.034193654446819, | |
| "grad_norm": 3.165553092956543, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 9.49, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03682393555811277, | |
| "grad_norm": 3.1877760887145996, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 9.4558, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.039454216669406544, | |
| "grad_norm": 3.2752976417541504, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 9.4161, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.042084497780700315, | |
| "grad_norm": 3.2027299404144287, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 9.3854, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04471477889199408, | |
| "grad_norm": 3.0393407344818115, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 9.421, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04734506000328785, | |
| "grad_norm": 2.993825674057007, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 9.3122, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04997534111458162, | |
| "grad_norm": 3.0169641971588135, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 9.2748, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05260562222587539, | |
| "grad_norm": 3.0002386569976807, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 9.2551, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05523590333716916, | |
| "grad_norm": 3.03594708442688, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 9.1614, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05786618444846293, | |
| "grad_norm": 3.229689836502075, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 9.0535, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0604964655597567, | |
| "grad_norm": 3.7371973991394043, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 9.0129, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06312674667105046, | |
| "grad_norm": 4.012978553771973, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 8.9554, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06575702778234424, | |
| "grad_norm": 5.139892101287842, | |
| "learning_rate": 1e-05, | |
| "loss": 8.7045, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06575702778234424, | |
| "eval_loss": 9.151042938232422, | |
| "eval_runtime": 0.2436, | |
| "eval_samples_per_second": 205.267, | |
| "eval_steps_per_second": 53.37, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 116006898892800.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |