| { | |
| "best_metric": 5.01399564743042, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.007040766035344645, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002816306414137858, | |
| "grad_norm": 48.62163543701172, | |
| "learning_rate": 0.0001, | |
| "loss": 23.4818, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002816306414137858, | |
| "eval_loss": 7.5018486976623535, | |
| "eval_runtime": 400.4908, | |
| "eval_samples_per_second": 3.733, | |
| "eval_steps_per_second": 1.868, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005632612828275716, | |
| "grad_norm": 50.03125762939453, | |
| "learning_rate": 0.0002, | |
| "loss": 25.3606, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008448919242413575, | |
| "grad_norm": 36.288734436035156, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 24.6152, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011265225656551432, | |
| "grad_norm": 35.620784759521484, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 21.223, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0014081532070689292, | |
| "grad_norm": 38.215370178222656, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 18.8518, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001689783848482715, | |
| "grad_norm": 24.101730346679688, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 18.2537, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001971414489896501, | |
| "grad_norm": 23.53477668762207, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 18.4047, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0022530451313102864, | |
| "grad_norm": 22.56336212158203, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 17.9984, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0025346757727240724, | |
| "grad_norm": 25.97075080871582, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 18.8505, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0028163064141378583, | |
| "grad_norm": 29.8724365234375, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 19.6848, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003097937055551644, | |
| "grad_norm": 73.4782943725586, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 19.3712, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00337956769696543, | |
| "grad_norm": 52.7482795715332, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 18.7228, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0036611983383792158, | |
| "grad_norm": 26.27608299255371, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 19.0088, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003942828979793002, | |
| "grad_norm": 28.202800750732422, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 18.9887, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004224459621206787, | |
| "grad_norm": 50.869102478027344, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 20.59, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004506090262620573, | |
| "grad_norm": 32.090274810791016, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 18.3551, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004787720904034359, | |
| "grad_norm": 29.982337951660156, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 18.6836, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.005069351545448145, | |
| "grad_norm": 35.667816162109375, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 19.2915, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00535098218686193, | |
| "grad_norm": 26.442718505859375, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 20.3658, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.005632612828275717, | |
| "grad_norm": 33.17983627319336, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 20.531, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005914243469689502, | |
| "grad_norm": 24.06730842590332, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 19.4856, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006195874111103288, | |
| "grad_norm": 22.876537322998047, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 20.0974, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006477504752517074, | |
| "grad_norm": 23.80173683166504, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 19.9339, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.00675913539393086, | |
| "grad_norm": 23.31247329711914, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 20.3456, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.007040766035344645, | |
| "grad_norm": 21.842885971069336, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 19.6822, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007040766035344645, | |
| "eval_loss": 5.01399564743042, | |
| "eval_runtime": 403.6754, | |
| "eval_samples_per_second": 3.703, | |
| "eval_steps_per_second": 1.853, | |
| "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": 3.51564749340672e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |