| { | |
| "best_metric": 0.1271306425333023, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 1.352159468438538, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.053156146179401995, | |
| "grad_norm": 16.144733428955078, | |
| "learning_rate": 5e-05, | |
| "loss": 4.8852, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.053156146179401995, | |
| "eval_loss": 4.792490005493164, | |
| "eval_runtime": 1.2864, | |
| "eval_samples_per_second": 38.869, | |
| "eval_steps_per_second": 10.106, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.10631229235880399, | |
| "grad_norm": 15.608192443847656, | |
| "learning_rate": 0.0001, | |
| "loss": 4.6739, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.15946843853820597, | |
| "grad_norm": 14.042940139770508, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 4.3826, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.21262458471760798, | |
| "grad_norm": 16.18175506591797, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.236, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.26578073089701, | |
| "grad_norm": 9.477006912231445, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.051, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.31893687707641194, | |
| "grad_norm": 6.747547149658203, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.0292, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.37209302325581395, | |
| "grad_norm": 3.7970376014709473, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.6351, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.42524916943521596, | |
| "grad_norm": 3.995140314102173, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.5011, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.47840531561461797, | |
| "grad_norm": 3.99289608001709, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.4304, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.53156146179402, | |
| "grad_norm": 2.5063412189483643, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.2656, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.584717607973422, | |
| "grad_norm": 1.6351100206375122, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.235, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6378737541528239, | |
| "grad_norm": 1.896690845489502, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.1664, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6910299003322259, | |
| "grad_norm": 1.7002002000808716, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.1649, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7441860465116279, | |
| "grad_norm": 3.440533399581909, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.2211, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.7973421926910299, | |
| "grad_norm": 2.0268311500549316, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.1784, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.8504983388704319, | |
| "grad_norm": 2.489518404006958, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.1835, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.9036544850498339, | |
| "grad_norm": 2.5720105171203613, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.2256, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.9568106312292359, | |
| "grad_norm": 2.0609378814697266, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.1873, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.0332225913621262, | |
| "grad_norm": 5.151944637298584, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.3486, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.0863787375415281, | |
| "grad_norm": 1.6826090812683105, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.1144, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.1395348837209303, | |
| "grad_norm": 1.0322390794754028, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.0483, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.1926910299003322, | |
| "grad_norm": 0.5722368955612183, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0898, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.2458471760797343, | |
| "grad_norm": 1.1440904140472412, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.1622, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.2990033222591362, | |
| "grad_norm": 0.8407073616981506, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.0988, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.352159468438538, | |
| "grad_norm": 1.039757251739502, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.1143, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.352159468438538, | |
| "eval_loss": 0.1271306425333023, | |
| "eval_runtime": 0.7183, | |
| "eval_samples_per_second": 69.606, | |
| "eval_steps_per_second": 18.098, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 1.27222702669824e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |