| { | |
| "best_metric": 2.515887498855591, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.24875621890547264, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004975124378109453, | |
| "grad_norm": 3.0430262088775635, | |
| "learning_rate": 0.0001, | |
| "loss": 3.2635, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004975124378109453, | |
| "eval_loss": 3.682396650314331, | |
| "eval_runtime": 6.5408, | |
| "eval_samples_per_second": 12.995, | |
| "eval_steps_per_second": 6.574, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009950248756218905, | |
| "grad_norm": 3.611407518386841, | |
| "learning_rate": 0.0002, | |
| "loss": 3.1135, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.014925373134328358, | |
| "grad_norm": 3.713569402694702, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 3.2019, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01990049751243781, | |
| "grad_norm": 3.7321176528930664, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 2.8382, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.024875621890547265, | |
| "grad_norm": 3.764651298522949, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 2.8298, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.029850746268656716, | |
| "grad_norm": 3.621135950088501, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 3.1415, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03482587064676617, | |
| "grad_norm": 8.381474494934082, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 2.8867, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03980099502487562, | |
| "grad_norm": 3.6087472438812256, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 2.6187, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04477611940298507, | |
| "grad_norm": 4.97490119934082, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 2.7751, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04975124378109453, | |
| "grad_norm": 3.8109967708587646, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 2.9982, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05472636815920398, | |
| "grad_norm": 3.904412269592285, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 2.9809, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05970149253731343, | |
| "grad_norm": 3.4200658798217773, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 2.5012, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06467661691542288, | |
| "grad_norm": 4.79351806640625, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 3.2791, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06965174129353234, | |
| "grad_norm": 4.197938919067383, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.7394, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07462686567164178, | |
| "grad_norm": 3.96777081489563, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 2.3632, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07960199004975124, | |
| "grad_norm": 3.868743658065796, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 2.6906, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0845771144278607, | |
| "grad_norm": 4.248363018035889, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 2.4091, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08955223880597014, | |
| "grad_norm": 4.386332035064697, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 3.0164, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0945273631840796, | |
| "grad_norm": 4.483827114105225, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 2.6212, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.09950248756218906, | |
| "grad_norm": 3.482344627380371, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 2.5468, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1044776119402985, | |
| "grad_norm": 3.7087607383728027, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 2.5328, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.10945273631840796, | |
| "grad_norm": 4.2484049797058105, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 2.0708, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.11442786069651742, | |
| "grad_norm": 4.827538967132568, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 2.785, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.11940298507462686, | |
| "grad_norm": 3.7040979862213135, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 2.342, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.12437810945273632, | |
| "grad_norm": 4.959524631500244, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 2.704, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12437810945273632, | |
| "eval_loss": 2.594191312789917, | |
| "eval_runtime": 6.1599, | |
| "eval_samples_per_second": 13.799, | |
| "eval_steps_per_second": 6.981, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12935323383084577, | |
| "grad_norm": 3.9420931339263916, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5456, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.13432835820895522, | |
| "grad_norm": 5.832747936248779, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 2.1194, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.13930348258706468, | |
| "grad_norm": 5.003444194793701, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 2.3539, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.14427860696517414, | |
| "grad_norm": 3.70873761177063, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 2.5001, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.14925373134328357, | |
| "grad_norm": 3.857776403427124, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 2.3172, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.15422885572139303, | |
| "grad_norm": 3.669508934020996, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 2.1357, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.15920398009950248, | |
| "grad_norm": 7.074223518371582, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 3.0023, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.16417910447761194, | |
| "grad_norm": 4.587769508361816, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 2.2561, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1691542288557214, | |
| "grad_norm": 4.273606777191162, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 2.448, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.17412935323383086, | |
| "grad_norm": 4.296418190002441, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 2.3099, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1791044776119403, | |
| "grad_norm": 3.6311933994293213, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 2.3837, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.18407960199004975, | |
| "grad_norm": 4.1932902336120605, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 2.6655, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.1890547263681592, | |
| "grad_norm": 4.752549171447754, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 2.6488, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.19402985074626866, | |
| "grad_norm": 4.613941669464111, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 2.5856, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.19900497512437812, | |
| "grad_norm": 4.24809455871582, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 2.2621, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.20398009950248755, | |
| "grad_norm": 4.745845794677734, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 2.2354, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.208955223880597, | |
| "grad_norm": 5.25393009185791, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 2.6063, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.21393034825870647, | |
| "grad_norm": 4.762695789337158, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 2.3609, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.21890547263681592, | |
| "grad_norm": 4.703743934631348, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 2.2418, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.22388059701492538, | |
| "grad_norm": 5.409986972808838, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 2.1651, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.22885572139303484, | |
| "grad_norm": 4.685298442840576, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 2.1631, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.23383084577114427, | |
| "grad_norm": 6.100794315338135, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 2.3216, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.23880597014925373, | |
| "grad_norm": 4.347185134887695, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 2.1609, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.24378109452736318, | |
| "grad_norm": 5.658843040466309, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 2.4468, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.24875621890547264, | |
| "grad_norm": 5.9395833015441895, | |
| "learning_rate": 0.0, | |
| "loss": 2.4286, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.24875621890547264, | |
| "eval_loss": 2.515887498855591, | |
| "eval_runtime": 6.187, | |
| "eval_samples_per_second": 13.739, | |
| "eval_steps_per_second": 6.95, | |
| "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": 3604771504128000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |