| { | |
| "best_metric": 0.10174055397510529, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.04113322021697774, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016453288086791095, | |
| "grad_norm": 2.9340085983276367, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9811, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016453288086791095, | |
| "eval_loss": 0.5447852611541748, | |
| "eval_runtime": 8.3061, | |
| "eval_samples_per_second": 6.02, | |
| "eval_steps_per_second": 1.565, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003290657617358219, | |
| "grad_norm": 2.7483158111572266, | |
| "learning_rate": 0.0001, | |
| "loss": 3.0801, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0049359864260373285, | |
| "grad_norm": 3.0211894512176514, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.2171, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006581315234716438, | |
| "grad_norm": 3.101088523864746, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.2919, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008226644043395548, | |
| "grad_norm": 3.177380084991455, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 3.3945, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009871972852074657, | |
| "grad_norm": 3.1485860347747803, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 3.3476, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011517301660753767, | |
| "grad_norm": 3.2044968605041504, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 3.5363, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013162630469432876, | |
| "grad_norm": 4.661653518676758, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 4.4327, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.014807959278111986, | |
| "grad_norm": 8.384300231933594, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 7.6822, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.016453288086791095, | |
| "grad_norm": 15.747698783874512, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 12.8179, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018098616895470203, | |
| "grad_norm": 36.05744552612305, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 21.0175, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.019743945704149314, | |
| "grad_norm": 47.37175750732422, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 24.7845, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.021389274512828422, | |
| "grad_norm": 32.3269157409668, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 16.2157, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.023034603321507533, | |
| "grad_norm": 6.595750331878662, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.6754, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02467993213018664, | |
| "grad_norm": 4.476025581359863, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.4852, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.026325260938865752, | |
| "grad_norm": 3.3909082412719727, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.2812, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02797058974754486, | |
| "grad_norm": 3.04364275932312, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.224, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02961591855622397, | |
| "grad_norm": 2.1135096549987793, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.2866, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03126124736490308, | |
| "grad_norm": 1.528654932975769, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.3186, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03290657617358219, | |
| "grad_norm": 7.454995632171631, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.7653, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0345519049822613, | |
| "grad_norm": 2.611647844314575, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 2.2766, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.036197233790940406, | |
| "grad_norm": 5.667532444000244, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 4.3051, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03784256259961952, | |
| "grad_norm": 14.412378311157227, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 8.8846, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03948789140829863, | |
| "grad_norm": 33.06006622314453, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 14.0859, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04113322021697774, | |
| "grad_norm": 29.786027908325195, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 16.3331, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04113322021697774, | |
| "eval_loss": 0.10174055397510529, | |
| "eval_runtime": 8.2589, | |
| "eval_samples_per_second": 6.054, | |
| "eval_steps_per_second": 1.574, | |
| "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": 3.2845074557147546e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |