| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 1.2121212121212122, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.024242424242424242, | |
| "grad_norm": 27.580669403076172, | |
| "learning_rate": 0.0001, | |
| "loss": 7.2765, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.024242424242424242, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.228, | |
| "eval_samples_per_second": 8.079, | |
| "eval_steps_per_second": 4.04, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.048484848484848485, | |
| "grad_norm": 23.396574020385742, | |
| "learning_rate": 0.0002, | |
| "loss": 7.3094, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07272727272727272, | |
| "grad_norm": 27.01788902282715, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 9.0047, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.09696969696969697, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.12121212121212122, | |
| "grad_norm": 35.79210662841797, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 5.509, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.14545454545454545, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1696969696969697, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.19393939393939394, | |
| "grad_norm": 25.79961395263672, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 5.2964, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.21818181818181817, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.24242424242424243, | |
| "grad_norm": 29.951295852661133, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 2.8452, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 32.658363342285156, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 3.1162, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2909090909090909, | |
| "grad_norm": 17.688011169433594, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 2.3919, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3151515151515151, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.3393939393939394, | |
| "grad_norm": 7.906186580657959, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.345, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 7.411261081695557, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 0.9667, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3878787878787879, | |
| "grad_norm": 7.091380596160889, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.6503, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.4121212121212121, | |
| "grad_norm": 9.68917465209961, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.956, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.43636363636363634, | |
| "grad_norm": 8.627195358276367, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.7758, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.46060606060606063, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.48484848484848486, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.509090909090909, | |
| "grad_norm": 10.164412498474121, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 0.9879, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5575757575757576, | |
| "grad_norm": 8.16072940826416, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.4841, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5818181818181818, | |
| "grad_norm": 13.351353645324707, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.9616, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6060606060606061, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6060606060606061, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2355, | |
| "eval_samples_per_second": 8.052, | |
| "eval_steps_per_second": 4.026, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6303030303030303, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.6545454545454545, | |
| "grad_norm": 13.499174118041992, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 1.0393, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6787878787878788, | |
| "grad_norm": 6.368555068969727, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 0.3086, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.703030303030303, | |
| "grad_norm": 13.0841064453125, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 0.9051, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 13.383321762084961, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 1.1452, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7515151515151515, | |
| "grad_norm": 0.0, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.7757575757575758, | |
| "grad_norm": 0.0, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 8.7849702835083, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 0.8124, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.8242424242424242, | |
| "grad_norm": 16.79686737060547, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.5349, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.8484848484848485, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.8727272727272727, | |
| "grad_norm": 14.058218002319336, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 0.8506, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.896969696969697, | |
| "grad_norm": 11.131260871887207, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 1.0009, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.9212121212121213, | |
| "grad_norm": 16.038894653320312, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.6914, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.9454545454545454, | |
| "grad_norm": 15.095179557800293, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 0.6247, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.9696969696969697, | |
| "grad_norm": 11.539749145507812, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 0.8336, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9939393939393939, | |
| "grad_norm": 13.128904342651367, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 1.1426, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.018181818181818, | |
| "grad_norm": 10.853378295898438, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 6.4015, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.0424242424242425, | |
| "grad_norm": 9.659259796142578, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 0.4573, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.0, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.0909090909090908, | |
| "grad_norm": 0.0, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.1151515151515152, | |
| "grad_norm": 4.810526371002197, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 1.6521, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.1393939393939394, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.1636363636363636, | |
| "grad_norm": 13.763459205627441, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 0.7686, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.187878787878788, | |
| "grad_norm": 10.437994003295898, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 0.7031, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.2121212121212122, | |
| "grad_norm": 7.7976579666137695, | |
| "learning_rate": 0.0, | |
| "loss": 0.4385, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.2121212121212122, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.2391, | |
| "eval_samples_per_second": 8.039, | |
| "eval_steps_per_second": 4.019, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.30626883682304e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |