| { | |
| "best_metric": 0.7120001316070557, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.036603221083455345, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014641288433382138, | |
| "grad_norm": 0.9750430583953857, | |
| "learning_rate": 4e-05, | |
| "loss": 1.0625, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014641288433382138, | |
| "eval_loss": 1.124760389328003, | |
| "eval_runtime": 76.9259, | |
| "eval_samples_per_second": 3.744, | |
| "eval_steps_per_second": 1.872, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0029282576866764276, | |
| "grad_norm": 1.0913565158843994, | |
| "learning_rate": 8e-05, | |
| "loss": 1.0917, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004392386530014641, | |
| "grad_norm": 1.0702697038650513, | |
| "learning_rate": 0.00012, | |
| "loss": 1.0758, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005856515373352855, | |
| "grad_norm": 1.0503638982772827, | |
| "learning_rate": 0.00016, | |
| "loss": 1.0126, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007320644216691069, | |
| "grad_norm": 1.3807379007339478, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9423, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008784773060029283, | |
| "grad_norm": 1.5241297483444214, | |
| "learning_rate": 0.00019994532573409262, | |
| "loss": 0.9538, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010248901903367497, | |
| "grad_norm": 1.7318557500839233, | |
| "learning_rate": 0.00019978136272187747, | |
| "loss": 0.8408, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01171303074670571, | |
| "grad_norm": 1.2110615968704224, | |
| "learning_rate": 0.00019950829025450114, | |
| "loss": 0.8412, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.013177159590043924, | |
| "grad_norm": 0.9903315901756287, | |
| "learning_rate": 0.00019912640693269752, | |
| "loss": 0.8473, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.014641288433382138, | |
| "grad_norm": 0.8798181414604187, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 0.8267, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.016105417276720352, | |
| "grad_norm": 0.9941743016242981, | |
| "learning_rate": 0.00019803799658748094, | |
| "loss": 0.8427, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.017569546120058566, | |
| "grad_norm": 0.9219509959220886, | |
| "learning_rate": 0.0001973326597248006, | |
| "loss": 0.7463, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01903367496339678, | |
| "grad_norm": 0.8963194489479065, | |
| "learning_rate": 0.00019652089102773488, | |
| "loss": 0.8373, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.020497803806734993, | |
| "grad_norm": 0.9019066691398621, | |
| "learning_rate": 0.00019560357815343577, | |
| "loss": 0.754, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.021961932650073207, | |
| "grad_norm": 1.0534106492996216, | |
| "learning_rate": 0.00019458172417006347, | |
| "loss": 0.7813, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02342606149341142, | |
| "grad_norm": 0.8860576152801514, | |
| "learning_rate": 0.0001934564464599461, | |
| "loss": 0.7497, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.024890190336749635, | |
| "grad_norm": 0.9496033191680908, | |
| "learning_rate": 0.00019222897549773848, | |
| "loss": 0.6888, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02635431918008785, | |
| "grad_norm": 0.9020019173622131, | |
| "learning_rate": 0.00019090065350491626, | |
| "loss": 0.7641, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.027818448023426062, | |
| "grad_norm": 0.8967961668968201, | |
| "learning_rate": 0.00018947293298207635, | |
| "loss": 0.75, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.029282576866764276, | |
| "grad_norm": 0.8483291268348694, | |
| "learning_rate": 0.0001879473751206489, | |
| "loss": 0.6926, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03074670571010249, | |
| "grad_norm": 0.9041450023651123, | |
| "learning_rate": 0.00018632564809575742, | |
| "loss": 0.7076, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.032210834553440704, | |
| "grad_norm": 0.8793591260910034, | |
| "learning_rate": 0.00018460952524209355, | |
| "loss": 0.6334, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03367496339677892, | |
| "grad_norm": 0.9118833541870117, | |
| "learning_rate": 0.00018280088311480201, | |
| "loss": 0.7029, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03513909224011713, | |
| "grad_norm": 0.9427176117897034, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.7891, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.036603221083455345, | |
| "grad_norm": 0.9533204436302185, | |
| "learning_rate": 0.00017891405093963938, | |
| "loss": 0.8176, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.036603221083455345, | |
| "eval_loss": 0.7120001316070557, | |
| "eval_runtime": 77.4992, | |
| "eval_samples_per_second": 3.716, | |
| "eval_steps_per_second": 1.858, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "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": 1.00529829052416e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |