| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.30143180105501133, | |
| "eval_steps": 500, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006028636021100226, | |
| "grad_norm": 0.486471027135849, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3471, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012057272042200452, | |
| "grad_norm": 0.5119717121124268, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3925, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01808590806330068, | |
| "grad_norm": 0.4457521140575409, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 0.3398, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.024114544084400905, | |
| "grad_norm": 0.409963995218277, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 0.2609, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03014318010550113, | |
| "grad_norm": 0.5352571606636047, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 0.2358, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03617181612660136, | |
| "grad_norm": 0.495702862739563, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 0.3512, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04220045214770158, | |
| "grad_norm": 0.4354080855846405, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 0.2329, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04822908816880181, | |
| "grad_norm": 0.3071988523006439, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.1409, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05425772418990203, | |
| "grad_norm": 0.25767603516578674, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 0.1745, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06028636021100226, | |
| "grad_norm": 0.24111005663871765, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.1417, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06631499623210249, | |
| "grad_norm": 0.3556184470653534, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 0.1783, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07234363225320271, | |
| "grad_norm": 0.2842593789100647, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 0.1272, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07837226827430294, | |
| "grad_norm": 0.2948729693889618, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 0.1524, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08440090429540316, | |
| "grad_norm": 0.2625027298927307, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.2062, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0904295403165034, | |
| "grad_norm": 0.2535743713378906, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 0.1715, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09645817633760362, | |
| "grad_norm": 0.22839832305908203, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.1143, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.10248681235870384, | |
| "grad_norm": 0.23887796700000763, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.1447, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.10851544837980406, | |
| "grad_norm": 0.2899695932865143, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.2285, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1145440844009043, | |
| "grad_norm": 0.2376154214143753, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 0.137, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.12057272042200452, | |
| "grad_norm": 0.35903647541999817, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.1455, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12660135644310475, | |
| "grad_norm": 0.29238924384117126, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 0.1189, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.13262999246420498, | |
| "grad_norm": 0.23753075301647186, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.1442, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1386586284853052, | |
| "grad_norm": 0.24815434217453003, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.1317, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.14468726450640543, | |
| "grad_norm": 0.2568942606449127, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.1653, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.15071590052750566, | |
| "grad_norm": 0.20504365861415863, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 0.1585, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.15674453654860587, | |
| "grad_norm": 0.2357844114303589, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1181, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1627731725697061, | |
| "grad_norm": 0.32542815804481506, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 0.2239, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.16880180859080632, | |
| "grad_norm": 0.27462485432624817, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 0.1411, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.17483044461190655, | |
| "grad_norm": 0.3306806683540344, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 0.1945, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.1808590806330068, | |
| "grad_norm": 0.20712682604789734, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 0.108, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.186887716654107, | |
| "grad_norm": 0.25769761204719543, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 0.1467, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.19291635267520724, | |
| "grad_norm": 0.22794191539287567, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.1393, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.19894498869630747, | |
| "grad_norm": 0.22670631110668182, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 0.1157, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.20497362471740768, | |
| "grad_norm": 0.21888034045696259, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.1228, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.21100226073850792, | |
| "grad_norm": 0.21215690672397614, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.1263, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.21703089675960813, | |
| "grad_norm": 0.2192404419183731, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 0.133, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.22305953278070836, | |
| "grad_norm": 0.25261539220809937, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 0.1651, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2290881688018086, | |
| "grad_norm": 0.2244417369365692, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.1253, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2351168048229088, | |
| "grad_norm": 0.22674843668937683, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 0.1354, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.24114544084400905, | |
| "grad_norm": 0.1793588250875473, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 0.0989, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.24717407686510928, | |
| "grad_norm": 0.20526793599128723, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 0.1263, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2532027128862095, | |
| "grad_norm": 0.2529662847518921, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.1717, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2592313489073097, | |
| "grad_norm": 0.2361597716808319, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 0.1353, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.26525998492840996, | |
| "grad_norm": 0.25286707282066345, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.1714, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2712886209495102, | |
| "grad_norm": 0.1881972849369049, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 0.0928, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2773172569706104, | |
| "grad_norm": 0.16801650822162628, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.0906, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.28334589299171065, | |
| "grad_norm": 0.2937343120574951, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 0.2129, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.28937452901281085, | |
| "grad_norm": 0.18096446990966797, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 0.1005, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.29540316503391106, | |
| "grad_norm": 0.2875116467475891, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 0.1927, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.30143180105501133, | |
| "grad_norm": 0.21270711719989777, | |
| "learning_rate": 0.0, | |
| "loss": 0.136, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.6797609962530406e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |