| { | |
| "best_metric": 0.03165920078754425, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.03276003276003276, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006552006552006552, | |
| "grad_norm": 25.569299697875977, | |
| "learning_rate": 0.0001, | |
| "loss": 3.8904, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006552006552006552, | |
| "eval_loss": 4.842487335205078, | |
| "eval_runtime": 47.8134, | |
| "eval_samples_per_second": 13.448, | |
| "eval_steps_per_second": 6.735, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013104013104013104, | |
| "grad_norm": 26.99811553955078, | |
| "learning_rate": 0.0002, | |
| "loss": 3.7983, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0019656019656019656, | |
| "grad_norm": 18.86760902404785, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 3.2163, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002620802620802621, | |
| "grad_norm": 8.032041549682617, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 1.312, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003276003276003276, | |
| "grad_norm": 12.221858024597168, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 1.5404, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003931203931203931, | |
| "grad_norm": 6.73016357421875, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 0.7534, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004586404586404586, | |
| "grad_norm": 5.138332366943359, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 0.5106, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005241605241605242, | |
| "grad_norm": 3.2426226139068604, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.2306, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005896805896805897, | |
| "grad_norm": 2.5002543926239014, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 0.2208, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006552006552006552, | |
| "grad_norm": 3.1149609088897705, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.1595, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007207207207207207, | |
| "grad_norm": 5.99144983291626, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 0.2541, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.007862407862407862, | |
| "grad_norm": 2.8587491512298584, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 0.0591, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008517608517608518, | |
| "grad_norm": 7.1438446044921875, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 0.1592, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009172809172809172, | |
| "grad_norm": 6.31621789932251, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0789, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.009828009828009828, | |
| "grad_norm": 0.5160434246063232, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 0.0066, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010483210483210484, | |
| "grad_norm": 0.10023625195026398, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.001, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.011138411138411138, | |
| "grad_norm": 10.3001127243042, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.1524, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.011793611793611793, | |
| "grad_norm": 3.8258275985717773, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0286, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.012448812448812449, | |
| "grad_norm": 5.547224044799805, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 0.0208, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.013104013104013105, | |
| "grad_norm": 0.06522075831890106, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.0004, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013759213759213759, | |
| "grad_norm": 0.010205689817667007, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 0.0001, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.014414414414414415, | |
| "grad_norm": 0.13218703866004944, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.0004, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01506961506961507, | |
| "grad_norm": 0.078118696808815, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.0005, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.015724815724815724, | |
| "grad_norm": 11.428861618041992, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.3499, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01638001638001638, | |
| "grad_norm": 0.003702717600390315, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01638001638001638, | |
| "eval_loss": 0.1716570109128952, | |
| "eval_runtime": 47.4703, | |
| "eval_samples_per_second": 13.545, | |
| "eval_steps_per_second": 6.783, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.017035217035217036, | |
| "grad_norm": 0.06484061479568481, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0006, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.01769041769041769, | |
| "grad_norm": 0.9557607769966125, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 0.0036, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.018345618345618344, | |
| "grad_norm": 0.2809895873069763, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 0.0008, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.019000819000819, | |
| "grad_norm": 0.05950084701180458, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 0.0004, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.019656019656019656, | |
| "grad_norm": 8.605826377868652, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 0.1053, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02031122031122031, | |
| "grad_norm": 4.249216556549072, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 0.0207, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.020966420966420967, | |
| "grad_norm": 0.7386406064033508, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.0041, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.021621621621621623, | |
| "grad_norm": 0.3371402621269226, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 0.0048, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.022276822276822275, | |
| "grad_norm": 10.98389720916748, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0363, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.02293202293202293, | |
| "grad_norm": 15.460600852966309, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.2665, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.023587223587223587, | |
| "grad_norm": 0.05989992246031761, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 0.0004, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.024242424242424242, | |
| "grad_norm": 0.5496867299079895, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 0.0037, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.024897624897624898, | |
| "grad_norm": 23.222116470336914, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.2077, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.025552825552825554, | |
| "grad_norm": 4.982071876525879, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 0.0356, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02620802620802621, | |
| "grad_norm": 2.1850380897521973, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 0.007, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.026863226863226862, | |
| "grad_norm": 0.0053272852674126625, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.027518427518427518, | |
| "grad_norm": 32.137962341308594, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 1.2831, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.028173628173628174, | |
| "grad_norm": 0.3219406306743622, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 0.002, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.02882882882882883, | |
| "grad_norm": 0.6160392761230469, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.0045, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.029484029484029485, | |
| "grad_norm": 0.635273814201355, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 0.0045, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03013923013923014, | |
| "grad_norm": 1.5323097705841064, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.0096, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.030794430794430793, | |
| "grad_norm": 1.9046576023101807, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 0.0121, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.03144963144963145, | |
| "grad_norm": 0.9863927364349365, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 0.0071, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03210483210483211, | |
| "grad_norm": 1.4912574291229248, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 0.01, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03276003276003276, | |
| "grad_norm": 0.752311646938324, | |
| "learning_rate": 0.0, | |
| "loss": 0.0066, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03276003276003276, | |
| "eval_loss": 0.03165920078754425, | |
| "eval_runtime": 47.498, | |
| "eval_samples_per_second": 13.537, | |
| "eval_steps_per_second": 6.779, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3106157258342400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |