| { | |
| "best_metric": 1.5172053575515747, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.003500940877860925, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00017504704389304627, | |
| "grad_norm": 1.4835988283157349, | |
| "learning_rate": 2e-05, | |
| "loss": 5.6312, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00017504704389304627, | |
| "eval_loss": 1.7600253820419312, | |
| "eval_runtime": 403.7285, | |
| "eval_samples_per_second": 5.959, | |
| "eval_steps_per_second": 2.98, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00035009408778609254, | |
| "grad_norm": 1.494039535522461, | |
| "learning_rate": 4e-05, | |
| "loss": 6.5696, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005251411316791387, | |
| "grad_norm": 1.2590696811676025, | |
| "learning_rate": 6e-05, | |
| "loss": 8.6124, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007001881755721851, | |
| "grad_norm": 2.2208402156829834, | |
| "learning_rate": 8e-05, | |
| "loss": 7.8411, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008752352194652313, | |
| "grad_norm": 1.6514173746109009, | |
| "learning_rate": 0.0001, | |
| "loss": 6.1182, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008752352194652313, | |
| "eval_loss": 1.7442522048950195, | |
| "eval_runtime": 406.5838, | |
| "eval_samples_per_second": 5.918, | |
| "eval_steps_per_second": 2.959, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0010502822633582775, | |
| "grad_norm": 1.3935221433639526, | |
| "learning_rate": 0.00012, | |
| "loss": 6.7917, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0012253293072513238, | |
| "grad_norm": 1.7046202421188354, | |
| "learning_rate": 0.00014, | |
| "loss": 7.4533, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0014003763511443701, | |
| "grad_norm": 1.6477290391921997, | |
| "learning_rate": 0.00016, | |
| "loss": 6.6885, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0015754233950374162, | |
| "grad_norm": 1.411340594291687, | |
| "learning_rate": 0.00018, | |
| "loss": 5.5161, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0017504704389304626, | |
| "grad_norm": 1.3269705772399902, | |
| "learning_rate": 0.0002, | |
| "loss": 7.1847, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0017504704389304626, | |
| "eval_loss": 1.6344908475875854, | |
| "eval_runtime": 407.2233, | |
| "eval_samples_per_second": 5.908, | |
| "eval_steps_per_second": 2.954, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001925517482823509, | |
| "grad_norm": 1.3951776027679443, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 5.2835, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.002100564526716555, | |
| "grad_norm": 1.2195020914077759, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 5.6981, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0022756115706096015, | |
| "grad_norm": 1.0527544021606445, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 6.3586, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0024506586145026476, | |
| "grad_norm": 1.6312555074691772, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 6.1024, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0026257056583956937, | |
| "grad_norm": 0.9510515928268433, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 5.9786, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0026257056583956937, | |
| "eval_loss": 1.5309654474258423, | |
| "eval_runtime": 409.8829, | |
| "eval_samples_per_second": 5.87, | |
| "eval_steps_per_second": 2.935, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0028007527022887403, | |
| "grad_norm": 1.1782293319702148, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 6.5324, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0029757997461817864, | |
| "grad_norm": 1.6559582948684692, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 6.5493, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0031508467900748325, | |
| "grad_norm": 1.4915060997009277, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 6.1002, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003325893833967879, | |
| "grad_norm": 1.6910254955291748, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 6.0799, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.003500940877860925, | |
| "grad_norm": 1.761253833770752, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 7.1205, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003500940877860925, | |
| "eval_loss": 1.5172053575515747, | |
| "eval_runtime": 405.8316, | |
| "eval_samples_per_second": 5.929, | |
| "eval_steps_per_second": 2.964, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 4967685188222976.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |