| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.11672016340822877, | |
| "eval_steps": 500, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0023344032681645753, | |
| "grad_norm": 0.9251645803451538, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0118, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0046688065363291505, | |
| "grad_norm": 0.8869811296463013, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0693, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007003209804493727, | |
| "grad_norm": 0.7835819721221924, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 1.0136, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009337613072658301, | |
| "grad_norm": 0.7174569964408875, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 0.9456, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011672016340822877, | |
| "grad_norm": 0.6670809388160706, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 0.9231, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014006419608987453, | |
| "grad_norm": 0.4366455078125, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 0.8884, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01634082287715203, | |
| "grad_norm": 0.3974485993385315, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 0.797, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.018675226145316602, | |
| "grad_norm": 0.3396911323070526, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.8978, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02100962941348118, | |
| "grad_norm": 0.3323412239551544, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 0.8268, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.023344032681645754, | |
| "grad_norm": 0.35627806186676025, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.8035, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02567843594981033, | |
| "grad_norm": 0.2914733588695526, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 0.7306, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.028012839217974907, | |
| "grad_norm": 0.37003418803215027, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 0.8839, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03034724248613948, | |
| "grad_norm": 0.312983900308609, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 0.7196, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03268164575430406, | |
| "grad_norm": 0.30982452630996704, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.7025, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03501604902246863, | |
| "grad_norm": 0.3327038884162903, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 0.8131, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.037350452290633204, | |
| "grad_norm": 0.29588159918785095, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.7766, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.039684855558797784, | |
| "grad_norm": 0.28512606024742126, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.7497, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04201925882696236, | |
| "grad_norm": 0.32307806611061096, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.8001, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.044353662095126936, | |
| "grad_norm": 0.2647784352302551, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 0.7829, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04668806536329151, | |
| "grad_norm": 0.27985048294067383, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.7745, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04902246863145608, | |
| "grad_norm": 0.2878023087978363, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 0.8015, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05135687189962066, | |
| "grad_norm": 0.29202720522880554, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.7511, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.053691275167785234, | |
| "grad_norm": 0.2617012560367584, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.7916, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05602567843594981, | |
| "grad_norm": 0.28169676661491394, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.7677, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.058360081704114386, | |
| "grad_norm": 0.3874562978744507, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 0.7009, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06069448497227896, | |
| "grad_norm": 0.2985963523387909, | |
| "learning_rate": 0.0001, | |
| "loss": 0.714, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06302888824044353, | |
| "grad_norm": 0.2679181694984436, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 0.6831, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06536329150860812, | |
| "grad_norm": 0.254097044467926, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 0.9036, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06769769477677269, | |
| "grad_norm": 0.25508198142051697, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 0.7911, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07003209804493726, | |
| "grad_norm": 0.25058841705322266, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 0.7423, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07236650131310184, | |
| "grad_norm": 0.25600212812423706, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 0.8124, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07470090458126641, | |
| "grad_norm": 0.24672138690948486, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.7959, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.077035307849431, | |
| "grad_norm": 0.23841053247451782, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 0.7236, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.07936971111759557, | |
| "grad_norm": 0.2680072486400604, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.7722, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08170411438576014, | |
| "grad_norm": 0.2535754144191742, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.7169, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08403851765392471, | |
| "grad_norm": 0.31870993971824646, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 0.7683, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.08637292092208929, | |
| "grad_norm": 0.2390068918466568, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 0.9436, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.08870732419025387, | |
| "grad_norm": 0.24789878726005554, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.8016, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09104172745841844, | |
| "grad_norm": 0.2508408725261688, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 0.7239, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09337613072658302, | |
| "grad_norm": 0.2461533099412918, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 0.6868, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09571053399474759, | |
| "grad_norm": 0.23145893216133118, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 0.7022, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.09804493726291216, | |
| "grad_norm": 0.27093321084976196, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.7102, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.10037934053107675, | |
| "grad_norm": 0.2575005292892456, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 0.8102, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.10271374379924132, | |
| "grad_norm": 0.2539258599281311, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.7719, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1050481470674059, | |
| "grad_norm": 0.2590281069278717, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 0.7796, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.10738255033557047, | |
| "grad_norm": 0.2578396201133728, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.8162, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.10971695360373504, | |
| "grad_norm": 0.23866446316242218, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 0.7376, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.11205135687189963, | |
| "grad_norm": 0.23026113212108612, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 0.7812, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1143857601400642, | |
| "grad_norm": 0.27130571007728577, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 0.7669, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.11672016340822877, | |
| "grad_norm": 0.2607179284095764, | |
| "learning_rate": 0.0, | |
| "loss": 0.7356, | |
| "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": 2.9842415890622054e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |