| { | |
| "best_metric": 11.734221458435059, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.017699115044248, | |
| "eval_steps": 25, | |
| "global_step": 57, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.035398230088495575, | |
| "grad_norm": 0.031247906386852264, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 11.7618, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.035398230088495575, | |
| "eval_loss": 11.758525848388672, | |
| "eval_runtime": 0.0557, | |
| "eval_samples_per_second": 897.074, | |
| "eval_steps_per_second": 35.883, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07079646017699115, | |
| "grad_norm": 0.033341653645038605, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 11.7604, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.10619469026548672, | |
| "grad_norm": 0.03511160612106323, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 11.7606, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1415929203539823, | |
| "grad_norm": 0.04077626019716263, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 11.7602, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.17699115044247787, | |
| "grad_norm": 0.04330646991729736, | |
| "learning_rate": 0.00015, | |
| "loss": 11.7584, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.21238938053097345, | |
| "grad_norm": 0.043747056275606155, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 11.7597, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.24778761061946902, | |
| "grad_norm": 0.06513168662786484, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 11.7631, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2831858407079646, | |
| "grad_norm": 0.02857106737792492, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 11.7625, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3185840707964602, | |
| "grad_norm": 0.0340174175798893, | |
| "learning_rate": 0.00027, | |
| "loss": 11.758, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.35398230088495575, | |
| "grad_norm": 0.03516850247979164, | |
| "learning_rate": 0.0003, | |
| "loss": 11.7586, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3893805309734513, | |
| "grad_norm": 0.04234551265835762, | |
| "learning_rate": 0.000299665031793473, | |
| "loss": 11.7581, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4247787610619469, | |
| "grad_norm": 0.043856628239154816, | |
| "learning_rate": 0.000298661623223217, | |
| "loss": 11.7554, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.46017699115044247, | |
| "grad_norm": 0.055923618376255035, | |
| "learning_rate": 0.000296994255755488, | |
| "loss": 11.7555, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.49557522123893805, | |
| "grad_norm": 0.07664037495851517, | |
| "learning_rate": 0.00029467037625815644, | |
| "loss": 11.7647, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5309734513274337, | |
| "grad_norm": 0.04599139839410782, | |
| "learning_rate": 0.00029170036374118777, | |
| "loss": 11.7596, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5663716814159292, | |
| "grad_norm": 0.04845264554023743, | |
| "learning_rate": 0.0002880974830014643, | |
| "loss": 11.7567, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6017699115044248, | |
| "grad_norm": 0.04592902958393097, | |
| "learning_rate": 0.00028387782537898215, | |
| "loss": 11.7575, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6371681415929203, | |
| "grad_norm": 0.06315469741821289, | |
| "learning_rate": 0.0002790602368890209, | |
| "loss": 11.7521, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.672566371681416, | |
| "grad_norm": 0.07420399785041809, | |
| "learning_rate": 0.00027366623405126404, | |
| "loss": 11.7532, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7079646017699115, | |
| "grad_norm": 0.07503742724657059, | |
| "learning_rate": 0.0002677199077917991, | |
| "loss": 11.7526, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7433628318584071, | |
| "grad_norm": 0.09958707541227341, | |
| "learning_rate": 0.0002612478158471936, | |
| "loss": 11.7529, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7787610619469026, | |
| "grad_norm": 0.06647299975156784, | |
| "learning_rate": 0.0002542788641511963, | |
| "loss": 11.7575, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8141592920353983, | |
| "grad_norm": 0.07075267285108566, | |
| "learning_rate": 0.0002468441777338203, | |
| "loss": 11.7543, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8495575221238938, | |
| "grad_norm": 0.0799153745174408, | |
| "learning_rate": 0.00023897696170940326, | |
| "loss": 11.7512, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.8849557522123894, | |
| "grad_norm": 0.0752144306898117, | |
| "learning_rate": 0.00023071235297450588, | |
| "loss": 11.752, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8849557522123894, | |
| "eval_loss": 11.748730659484863, | |
| "eval_runtime": 0.0544, | |
| "eval_samples_per_second": 918.418, | |
| "eval_steps_per_second": 36.737, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9203539823008849, | |
| "grad_norm": 0.09072871506214142, | |
| "learning_rate": 0.00022208726327800255, | |
| "loss": 11.7499, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9557522123893806, | |
| "grad_norm": 0.10960599780082703, | |
| "learning_rate": 0.00021314021436425024, | |
| "loss": 11.7441, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.9911504424778761, | |
| "grad_norm": 0.12274184077978134, | |
| "learning_rate": 0.0002039111659256269, | |
| "loss": 11.7448, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.0265486725663717, | |
| "grad_norm": 0.1580979973077774, | |
| "learning_rate": 0.0001944413371328451, | |
| "loss": 20.9127, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.0619469026548674, | |
| "grad_norm": 0.0814850702881813, | |
| "learning_rate": 0.00018477302254012924, | |
| "loss": 11.5984, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0973451327433628, | |
| "grad_norm": 0.0942695289850235, | |
| "learning_rate": 0.0001749494031874695, | |
| "loss": 11.8138, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.1327433628318584, | |
| "grad_norm": 0.09790118783712387, | |
| "learning_rate": 0.00016501435374361475, | |
| "loss": 11.7438, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.168141592920354, | |
| "grad_norm": 0.1221451684832573, | |
| "learning_rate": 0.00015501224655115118, | |
| "loss": 11.5821, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.2035398230088497, | |
| "grad_norm": 0.10308799147605896, | |
| "learning_rate": 0.00014498775344884884, | |
| "loss": 11.9058, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.238938053097345, | |
| "grad_norm": 0.1409374475479126, | |
| "learning_rate": 0.00013498564625638522, | |
| "loss": 12.3076, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.2743362831858407, | |
| "grad_norm": 0.10012196749448776, | |
| "learning_rate": 0.0001250505968125305, | |
| "loss": 11.4403, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.3097345132743363, | |
| "grad_norm": 0.10341328382492065, | |
| "learning_rate": 0.00011522697745987075, | |
| "loss": 11.4606, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.3451327433628317, | |
| "grad_norm": 0.0907343178987503, | |
| "learning_rate": 0.0001055586628671549, | |
| "loss": 11.6055, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.3805309734513274, | |
| "grad_norm": 0.08441987633705139, | |
| "learning_rate": 9.608883407437309e-05, | |
| "loss": 11.7105, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.415929203539823, | |
| "grad_norm": 0.10750183463096619, | |
| "learning_rate": 8.685978563574976e-05, | |
| "loss": 12.0368, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.4513274336283186, | |
| "grad_norm": 0.1244698315858841, | |
| "learning_rate": 7.791273672199742e-05, | |
| "loss": 11.7444, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.4867256637168142, | |
| "grad_norm": 0.17445337772369385, | |
| "learning_rate": 6.92876470254941e-05, | |
| "loss": 12.5033, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.5221238938053099, | |
| "grad_norm": 0.10217167437076569, | |
| "learning_rate": 6.1023038290596715e-05, | |
| "loss": 11.0555, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.5575221238938053, | |
| "grad_norm": 0.09945648908615112, | |
| "learning_rate": 5.315582226617963e-05, | |
| "loss": 11.5445, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.592920353982301, | |
| "grad_norm": 0.08290676027536392, | |
| "learning_rate": 4.5721135848803653e-05, | |
| "loss": 11.5874, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.6283185840707963, | |
| "grad_norm": 0.10276991873979568, | |
| "learning_rate": 3.875218415280636e-05, | |
| "loss": 11.7448, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.663716814159292, | |
| "grad_norm": 0.10032013803720474, | |
| "learning_rate": 3.228009220820085e-05, | |
| "loss": 11.8132, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.6991150442477876, | |
| "grad_norm": 0.10768602788448334, | |
| "learning_rate": 2.6333765948735986e-05, | |
| "loss": 11.9151, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.7345132743362832, | |
| "grad_norm": 0.14142917096614838, | |
| "learning_rate": 2.0939763110979125e-05, | |
| "loss": 12.6256, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.7699115044247788, | |
| "grad_norm": 0.08887699246406555, | |
| "learning_rate": 1.612217462101783e-05, | |
| "loss": 10.8969, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.7699115044247788, | |
| "eval_loss": 11.734221458435059, | |
| "eval_runtime": 0.0543, | |
| "eval_samples_per_second": 920.765, | |
| "eval_steps_per_second": 36.831, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.8053097345132745, | |
| "grad_norm": 0.10223124921321869, | |
| "learning_rate": 1.1902516998535666e-05, | |
| "loss": 11.5613, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.8407079646017699, | |
| "grad_norm": 0.08183666318655014, | |
| "learning_rate": 8.299636258812197e-06, | |
| "loss": 11.7158, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.8761061946902655, | |
| "grad_norm": 0.09326402842998505, | |
| "learning_rate": 5.329623741843531e-06, | |
| "loss": 11.7962, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.911504424778761, | |
| "grad_norm": 0.10565122961997986, | |
| "learning_rate": 3.0057442445119872e-06, | |
| "loss": 11.7664, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.9469026548672566, | |
| "grad_norm": 0.11125579476356506, | |
| "learning_rate": 1.3383767767829956e-06, | |
| "loss": 11.8781, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.9823008849557522, | |
| "grad_norm": 0.13728636503219604, | |
| "learning_rate": 3.349682065270254e-07, | |
| "loss": 12.3971, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.017699115044248, | |
| "grad_norm": 0.16288495063781738, | |
| "learning_rate": 0.0, | |
| "loss": 20.1629, | |
| "step": 57 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 57, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 98692671209472.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |