| { | |
| "best_metric": 1.4338550567626953, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.009140767824497258, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00036563071297989033, | |
| "grad_norm": 0.263685405254364, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7146, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00036563071297989033, | |
| "eval_loss": 1.621423363685608, | |
| "eval_runtime": 68.7234, | |
| "eval_samples_per_second": 67.037, | |
| "eval_steps_per_second": 8.381, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007312614259597807, | |
| "grad_norm": 0.23099811375141144, | |
| "learning_rate": 4e-05, | |
| "loss": 1.5916, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0010968921389396709, | |
| "grad_norm": 0.2454378455877304, | |
| "learning_rate": 6e-05, | |
| "loss": 1.5647, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014625228519195613, | |
| "grad_norm": 0.23810383677482605, | |
| "learning_rate": 8e-05, | |
| "loss": 1.5945, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0018281535648994515, | |
| "grad_norm": 0.23558178544044495, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5168, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0021937842778793418, | |
| "grad_norm": 0.22106045484542847, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.6018, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002559414990859232, | |
| "grad_norm": 0.1976412981748581, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.5256, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0029250457038391227, | |
| "grad_norm": 0.18290100991725922, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.5062, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0032906764168190127, | |
| "grad_norm": 0.18400928378105164, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.487, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003656307129798903, | |
| "grad_norm": 0.1838669329881668, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.4553, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0040219378427787935, | |
| "grad_norm": 0.19167158007621765, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.4515, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0043875685557586835, | |
| "grad_norm": 0.18224981427192688, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.4875, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004753199268738574, | |
| "grad_norm": 0.17719820141792297, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 1.4564, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005118829981718464, | |
| "grad_norm": 0.17880447208881378, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.4321, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005484460694698354, | |
| "grad_norm": 0.16925093531608582, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.3777, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005850091407678245, | |
| "grad_norm": 0.16614092886447906, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 1.4482, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.006215722120658135, | |
| "grad_norm": 0.1792985200881958, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.3997, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006581352833638025, | |
| "grad_norm": 0.16103695333003998, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 1.4049, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006946983546617916, | |
| "grad_norm": 0.15694041550159454, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 1.3884, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.007312614259597806, | |
| "grad_norm": 0.1585288643836975, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.3791, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007678244972577696, | |
| "grad_norm": 0.15279190242290497, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.414, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.008043875685557587, | |
| "grad_norm": 0.1613546460866928, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 1.3907, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.008409506398537478, | |
| "grad_norm": 0.1541416198015213, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.3546, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.008775137111517367, | |
| "grad_norm": 0.16708770394325256, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 1.449, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.009140767824497258, | |
| "grad_norm": 0.1675138622522354, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.5012, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.009140767824497258, | |
| "eval_loss": 1.4338550567626953, | |
| "eval_runtime": 68.6236, | |
| "eval_samples_per_second": 67.134, | |
| "eval_steps_per_second": 8.394, | |
| "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": 5, | |
| "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": 1717219885056000.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |