| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9118125313435558, | |
| "eval_steps": 100, | |
| "global_step": 7500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012157500417914077, | |
| "eval_accuracy": 0.9982292163897571, | |
| "eval_f1": 0.5714285714285715, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5992217898832685, | |
| "eval_recall": 0.5460992907801419, | |
| "eval_runtime": 4.2246, | |
| "eval_samples_per_second": 12.072, | |
| "eval_steps_per_second": 12.072, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.024315000835828153, | |
| "eval_accuracy": 0.9979520502594583, | |
| "eval_f1": 0.561128526645768, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5028089887640449, | |
| "eval_recall": 0.6347517730496454, | |
| "eval_runtime": 4.0691, | |
| "eval_samples_per_second": 12.534, | |
| "eval_steps_per_second": 12.534, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03647250125374223, | |
| "eval_accuracy": 0.9982908088631569, | |
| "eval_f1": 0.6003401360544217, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.576797385620915, | |
| "eval_recall": 0.625886524822695, | |
| "eval_runtime": 3.8202, | |
| "eval_samples_per_second": 13.35, | |
| "eval_steps_per_second": 13.35, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.048630001671656306, | |
| "eval_accuracy": 0.9983370032182067, | |
| "eval_f1": 0.5949579831932772, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5654952076677316, | |
| "eval_recall": 0.6276595744680851, | |
| "eval_runtime": 3.892, | |
| "eval_samples_per_second": 13.104, | |
| "eval_steps_per_second": 13.104, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.060787502089570386, | |
| "grad_norm": 0.56640625, | |
| "learning_rate": 9.39209726443769e-05, | |
| "loss": 0.0667, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.060787502089570386, | |
| "eval_accuracy": 0.9980906333246077, | |
| "eval_f1": 0.5690789473684211, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5306748466257669, | |
| "eval_recall": 0.6134751773049646, | |
| "eval_runtime": 3.9741, | |
| "eval_samples_per_second": 12.833, | |
| "eval_steps_per_second": 12.833, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.07294500250748447, | |
| "eval_accuracy": 0.9981522257980074, | |
| "eval_f1": 0.5753646677471637, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5298507462686567, | |
| "eval_recall": 0.6294326241134752, | |
| "eval_runtime": 3.9469, | |
| "eval_samples_per_second": 12.922, | |
| "eval_steps_per_second": 12.922, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.08510250292539853, | |
| "eval_accuracy": 0.9983524013365567, | |
| "eval_f1": 0.608108108108108, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5806451612903226, | |
| "eval_recall": 0.6382978723404256, | |
| "eval_runtime": 4.9419, | |
| "eval_samples_per_second": 10.32, | |
| "eval_steps_per_second": 10.32, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.09726000334331261, | |
| "eval_accuracy": 0.9978904577860586, | |
| "eval_f1": 0.5460317460317461, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.4942528735632184, | |
| "eval_recall": 0.6099290780141844, | |
| "eval_runtime": 3.9464, | |
| "eval_samples_per_second": 12.923, | |
| "eval_steps_per_second": 12.923, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.10941750376122669, | |
| "eval_accuracy": 0.9981984201530573, | |
| "eval_f1": 0.5831960461285007, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5446153846153846, | |
| "eval_recall": 0.6276595744680851, | |
| "eval_runtime": 3.9207, | |
| "eval_samples_per_second": 13.008, | |
| "eval_steps_per_second": 13.008, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.12157500417914077, | |
| "grad_norm": 0.49609375, | |
| "learning_rate": 8.78419452887538e-05, | |
| "loss": 0.0273, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.12157500417914077, | |
| "eval_accuracy": 0.9981368276796575, | |
| "eval_f1": 0.5692821368948245, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5378548895899053, | |
| "eval_recall": 0.6046099290780141, | |
| "eval_runtime": 3.9151, | |
| "eval_samples_per_second": 13.026, | |
| "eval_steps_per_second": 13.026, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.13373250459705485, | |
| "eval_accuracy": 0.9985679749934558, | |
| "eval_f1": 0.6378091872791519, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.6355633802816901, | |
| "eval_recall": 0.6400709219858156, | |
| "eval_runtime": 3.9167, | |
| "eval_samples_per_second": 13.021, | |
| "eval_steps_per_second": 13.021, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.14589000501496893, | |
| "eval_accuracy": 0.9982446145081071, | |
| "eval_f1": 0.5888324873096447, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5631067961165048, | |
| "eval_recall": 0.6170212765957447, | |
| "eval_runtime": 3.9347, | |
| "eval_samples_per_second": 12.962, | |
| "eval_steps_per_second": 12.962, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.158047505432883, | |
| "eval_accuracy": 0.9982908088631569, | |
| "eval_f1": 0.6126418152350082, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.564179104477612, | |
| "eval_recall": 0.6702127659574468, | |
| "eval_runtime": 3.9694, | |
| "eval_samples_per_second": 12.848, | |
| "eval_steps_per_second": 12.848, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.17020500585079706, | |
| "eval_accuracy": 0.9983524013365567, | |
| "eval_f1": 0.6128500823723229, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5723076923076923, | |
| "eval_recall": 0.6595744680851063, | |
| "eval_runtime": 3.9587, | |
| "eval_samples_per_second": 12.883, | |
| "eval_steps_per_second": 12.883, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.18236250626871114, | |
| "grad_norm": 1.453125, | |
| "learning_rate": 8.17629179331307e-05, | |
| "loss": 0.0198, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.18236250626871114, | |
| "eval_accuracy": 0.9984139938099564, | |
| "eval_f1": 0.6216216216216217, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5935483870967742, | |
| "eval_recall": 0.6524822695035462, | |
| "eval_runtime": 3.9699, | |
| "eval_samples_per_second": 12.847, | |
| "eval_steps_per_second": 12.847, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.19452000668662522, | |
| "eval_accuracy": 0.9983985956916065, | |
| "eval_f1": 0.6113013698630136, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5910596026490066, | |
| "eval_recall": 0.6329787234042553, | |
| "eval_runtime": 3.9634, | |
| "eval_samples_per_second": 12.868, | |
| "eval_steps_per_second": 12.868, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.2066775071045393, | |
| "eval_accuracy": 0.998537178756756, | |
| "eval_f1": 0.6450511945392491, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.6217105263157895, | |
| "eval_recall": 0.6702127659574468, | |
| "eval_runtime": 3.9348, | |
| "eval_samples_per_second": 12.961, | |
| "eval_steps_per_second": 12.961, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.21883500752245338, | |
| "eval_accuracy": 0.9985063825200561, | |
| "eval_f1": 0.61101243339254, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.6120996441281139, | |
| "eval_recall": 0.6099290780141844, | |
| "eval_runtime": 3.9403, | |
| "eval_samples_per_second": 12.943, | |
| "eval_steps_per_second": 12.943, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.23099250794036746, | |
| "eval_accuracy": 0.9985987712301557, | |
| "eval_f1": 0.638888888888889, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.6258503401360545, | |
| "eval_recall": 0.6524822695035462, | |
| "eval_runtime": 3.8792, | |
| "eval_samples_per_second": 13.147, | |
| "eval_steps_per_second": 13.147, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.24315000835828154, | |
| "grad_norm": 0.337890625, | |
| "learning_rate": 7.56838905775076e-05, | |
| "loss": 0.015, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.24315000835828154, | |
| "eval_accuracy": 0.9983677994549066, | |
| "eval_f1": 0.6179966044142615, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5928338762214984, | |
| "eval_recall": 0.6453900709219859, | |
| "eval_runtime": 3.8941, | |
| "eval_samples_per_second": 13.097, | |
| "eval_steps_per_second": 13.097, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.2553075087761956, | |
| "eval_accuracy": 0.998521780638406, | |
| "eval_f1": 0.6296928327645053, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.6069078947368421, | |
| "eval_recall": 0.6542553191489362, | |
| "eval_runtime": 3.8421, | |
| "eval_samples_per_second": 13.274, | |
| "eval_steps_per_second": 13.274, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.2674650091941097, | |
| "eval_accuracy": 0.9984755862833562, | |
| "eval_f1": 0.6352739726027398, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.6142384105960265, | |
| "eval_recall": 0.6578014184397163, | |
| "eval_runtime": 3.8929, | |
| "eval_samples_per_second": 13.101, | |
| "eval_steps_per_second": 13.101, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.2796225096120238, | |
| "eval_accuracy": 0.9985679749934558, | |
| "eval_f1": 0.6507666098807496, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.6262295081967213, | |
| "eval_recall": 0.6773049645390071, | |
| "eval_runtime": 4.0354, | |
| "eval_samples_per_second": 12.638, | |
| "eval_steps_per_second": 12.638, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.29178001002993786, | |
| "eval_accuracy": 0.998275410744807, | |
| "eval_f1": 0.5949152542372882, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5698051948051948, | |
| "eval_recall": 0.6223404255319149, | |
| "eval_runtime": 3.9548, | |
| "eval_samples_per_second": 12.896, | |
| "eval_steps_per_second": 12.896, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.30393751044785194, | |
| "grad_norm": 0.5, | |
| "learning_rate": 6.96048632218845e-05, | |
| "loss": 0.0122, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.30393751044785194, | |
| "eval_accuracy": 0.9983677994549066, | |
| "eval_f1": 0.6200657894736843, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5782208588957055, | |
| "eval_recall": 0.6684397163120568, | |
| "eval_runtime": 3.9191, | |
| "eval_samples_per_second": 13.013, | |
| "eval_steps_per_second": 13.013, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.316095010865766, | |
| "eval_accuracy": 0.998537178756756, | |
| "eval_f1": 0.6379310344827586, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.6208053691275168, | |
| "eval_recall": 0.6560283687943262, | |
| "eval_runtime": 3.9133, | |
| "eval_samples_per_second": 13.033, | |
| "eval_steps_per_second": 13.033, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.32825251128368005, | |
| "eval_accuracy": 0.9984293919283064, | |
| "eval_f1": 0.6284722222222222, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.6156462585034014, | |
| "eval_recall": 0.6418439716312057, | |
| "eval_runtime": 3.9458, | |
| "eval_samples_per_second": 12.925, | |
| "eval_steps_per_second": 12.925, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.34041001170159413, | |
| "eval_accuracy": 0.9984293919283064, | |
| "eval_f1": 0.6254295532646049, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.6066666666666667, | |
| "eval_recall": 0.6453900709219859, | |
| "eval_runtime": 5.0134, | |
| "eval_samples_per_second": 10.173, | |
| "eval_steps_per_second": 10.173, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.3525675121195082, | |
| "eval_accuracy": 0.9984601881650063, | |
| "eval_f1": 0.6185567010309279, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.6, | |
| "eval_recall": 0.6382978723404256, | |
| "eval_runtime": 3.9121, | |
| "eval_samples_per_second": 13.037, | |
| "eval_steps_per_second": 13.037, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.3647250125374223, | |
| "grad_norm": 0.47265625, | |
| "learning_rate": 6.352583586626139e-05, | |
| "loss": 0.0102, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.3647250125374223, | |
| "eval_accuracy": 0.9984601881650063, | |
| "eval_f1": 0.6175438596491228, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.6111111111111112, | |
| "eval_recall": 0.624113475177305, | |
| "eval_runtime": 3.9032, | |
| "eval_samples_per_second": 13.066, | |
| "eval_steps_per_second": 13.066, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.37688251295533637, | |
| "eval_accuracy": 0.9983985956916065, | |
| "eval_f1": 0.6067615658362988, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.6089285714285714, | |
| "eval_recall": 0.6046099290780141, | |
| "eval_runtime": 3.9167, | |
| "eval_samples_per_second": 13.021, | |
| "eval_steps_per_second": 13.021, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.38904001337325045, | |
| "eval_accuracy": 0.9981984201530573, | |
| "eval_f1": 0.5792163543441226, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5573770491803278, | |
| "eval_recall": 0.6028368794326241, | |
| "eval_runtime": 3.9349, | |
| "eval_samples_per_second": 12.961, | |
| "eval_steps_per_second": 12.961, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.40119751379116453, | |
| "eval_accuracy": 0.998275410744807, | |
| "eval_f1": 0.6016528925619835, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5634674922600619, | |
| "eval_recall": 0.6453900709219859, | |
| "eval_runtime": 5.1154, | |
| "eval_samples_per_second": 9.97, | |
| "eval_steps_per_second": 9.97, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.4133550142090786, | |
| "eval_accuracy": 0.9983985956916065, | |
| "eval_f1": 0.6064735945485519, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5836065573770491, | |
| "eval_recall": 0.6312056737588653, | |
| "eval_runtime": 3.9386, | |
| "eval_samples_per_second": 12.949, | |
| "eval_steps_per_second": 12.949, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.4255125146269927, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 5.744680851063831e-05, | |
| "loss": 0.0087, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.4255125146269927, | |
| "eval_accuracy": 0.9984601881650063, | |
| "eval_f1": 0.6166950596252129, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5934426229508196, | |
| "eval_recall": 0.6418439716312057, | |
| "eval_runtime": 3.9507, | |
| "eval_samples_per_second": 12.909, | |
| "eval_steps_per_second": 12.909, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.43767001504490677, | |
| "eval_accuracy": 0.9985525768751059, | |
| "eval_f1": 0.6412859560067682, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.6132686084142395, | |
| "eval_recall": 0.6719858156028369, | |
| "eval_runtime": 3.9696, | |
| "eval_samples_per_second": 12.848, | |
| "eval_steps_per_second": 12.848, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.44982751546282085, | |
| "eval_accuracy": 0.998521780638406, | |
| "eval_f1": 0.638655462184874, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.6070287539936102, | |
| "eval_recall": 0.6737588652482269, | |
| "eval_runtime": 3.9563, | |
| "eval_samples_per_second": 12.891, | |
| "eval_steps_per_second": 12.891, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.46198501588073493, | |
| "eval_accuracy": 0.9984909844017061, | |
| "eval_f1": 0.6237288135593221, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5974025974025974, | |
| "eval_recall": 0.6524822695035462, | |
| "eval_runtime": 3.9225, | |
| "eval_samples_per_second": 13.002, | |
| "eval_steps_per_second": 13.002, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.474142516298649, | |
| "eval_accuracy": 0.9984601881650063, | |
| "eval_f1": 0.6193656093489149, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5851735015772871, | |
| "eval_recall": 0.6578014184397163, | |
| "eval_runtime": 3.8167, | |
| "eval_samples_per_second": 13.362, | |
| "eval_steps_per_second": 13.362, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.4863000167165631, | |
| "grad_norm": 0.2578125, | |
| "learning_rate": 5.13677811550152e-05, | |
| "loss": 0.0074, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.4863000167165631, | |
| "eval_accuracy": 0.9984293919283064, | |
| "eval_f1": 0.6102564102564102, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5891089108910891, | |
| "eval_recall": 0.6329787234042553, | |
| "eval_runtime": 3.9064, | |
| "eval_samples_per_second": 13.055, | |
| "eval_steps_per_second": 13.055, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.49845751713447717, | |
| "eval_accuracy": 0.9983677994549066, | |
| "eval_f1": 0.5982905982905984, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5775577557755776, | |
| "eval_recall": 0.6205673758865248, | |
| "eval_runtime": 3.8733, | |
| "eval_samples_per_second": 13.167, | |
| "eval_steps_per_second": 13.167, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.5106150175523912, | |
| "eval_accuracy": 0.9985525768751059, | |
| "eval_f1": 0.6456558773424191, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.6213114754098361, | |
| "eval_recall": 0.6719858156028369, | |
| "eval_runtime": 3.9945, | |
| "eval_samples_per_second": 12.767, | |
| "eval_steps_per_second": 12.767, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.5227725179703053, | |
| "eval_accuracy": 0.9984755862833562, | |
| "eval_f1": 0.6348408710217756, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.6015873015873016, | |
| "eval_recall": 0.6719858156028369, | |
| "eval_runtime": 3.9449, | |
| "eval_samples_per_second": 12.928, | |
| "eval_steps_per_second": 12.928, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.5349300183882194, | |
| "eval_accuracy": 0.9984447900466563, | |
| "eval_f1": 0.6231155778894472, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5904761904761905, | |
| "eval_recall": 0.6595744680851063, | |
| "eval_runtime": 3.9223, | |
| "eval_samples_per_second": 13.003, | |
| "eval_steps_per_second": 13.003, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.5470875188061335, | |
| "grad_norm": 0.796875, | |
| "learning_rate": 4.52887537993921e-05, | |
| "loss": 0.0069, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.5470875188061335, | |
| "eval_accuracy": 0.9983985956916065, | |
| "eval_f1": 0.6139767054908487, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5783699059561128, | |
| "eval_recall": 0.6542553191489362, | |
| "eval_runtime": 3.8802, | |
| "eval_samples_per_second": 13.144, | |
| "eval_steps_per_second": 13.144, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.5592450192240476, | |
| "eval_accuracy": 0.9983216050998568, | |
| "eval_f1": 0.5902192242833052, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5627009646302251, | |
| "eval_recall": 0.6205673758865248, | |
| "eval_runtime": 3.8007, | |
| "eval_samples_per_second": 13.418, | |
| "eval_steps_per_second": 13.418, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.5714025196419616, | |
| "eval_accuracy": 0.9984755862833562, | |
| "eval_f1": 0.6243739565943239, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5899053627760252, | |
| "eval_recall": 0.6631205673758865, | |
| "eval_runtime": 5.2589, | |
| "eval_samples_per_second": 9.698, | |
| "eval_steps_per_second": 9.698, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.5835600200598757, | |
| "eval_accuracy": 0.9984755862833562, | |
| "eval_f1": 0.6231155778894472, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5904761904761905, | |
| "eval_recall": 0.6595744680851063, | |
| "eval_runtime": 3.9226, | |
| "eval_samples_per_second": 13.001, | |
| "eval_steps_per_second": 13.001, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.5957175204777898, | |
| "eval_accuracy": 0.9984755862833562, | |
| "eval_f1": 0.6298157453936348, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5968253968253968, | |
| "eval_recall": 0.6666666666666666, | |
| "eval_runtime": 3.9435, | |
| "eval_samples_per_second": 12.933, | |
| "eval_steps_per_second": 12.933, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.6078750208957039, | |
| "grad_norm": 0.298828125, | |
| "learning_rate": 3.9209726443769e-05, | |
| "loss": 0.0065, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.6078750208957039, | |
| "eval_accuracy": 0.9984293919283064, | |
| "eval_f1": 0.6074450084602369, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.580906148867314, | |
| "eval_recall": 0.6365248226950354, | |
| "eval_runtime": 3.9158, | |
| "eval_samples_per_second": 13.024, | |
| "eval_steps_per_second": 13.024, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.620032521313618, | |
| "eval_accuracy": 0.9984909844017061, | |
| "eval_f1": 0.6282271944922547, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.6103678929765887, | |
| "eval_recall": 0.6471631205673759, | |
| "eval_runtime": 3.9051, | |
| "eval_samples_per_second": 13.06, | |
| "eval_steps_per_second": 13.06, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.632190021731532, | |
| "eval_accuracy": 0.9984139938099564, | |
| "eval_f1": 0.6184873949579831, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5878594249201278, | |
| "eval_recall": 0.6524822695035462, | |
| "eval_runtime": 3.9165, | |
| "eval_samples_per_second": 13.022, | |
| "eval_steps_per_second": 13.022, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.6443475221494461, | |
| "eval_accuracy": 0.9984139938099564, | |
| "eval_f1": 0.6115843270868824, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5885245901639344, | |
| "eval_recall": 0.6365248226950354, | |
| "eval_runtime": 3.9234, | |
| "eval_samples_per_second": 12.999, | |
| "eval_steps_per_second": 12.999, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.6565050225673601, | |
| "eval_accuracy": 0.9985063825200561, | |
| "eval_f1": 0.6408094435075886, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.6109324758842444, | |
| "eval_recall": 0.6737588652482269, | |
| "eval_runtime": 3.9194, | |
| "eval_samples_per_second": 13.012, | |
| "eval_steps_per_second": 13.012, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.6686625229852742, | |
| "grad_norm": 0.40625, | |
| "learning_rate": 3.31306990881459e-05, | |
| "loss": 0.0059, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.6686625229852742, | |
| "eval_accuracy": 0.998537178756756, | |
| "eval_f1": 0.6480541455160745, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.6197411003236246, | |
| "eval_recall": 0.6790780141843972, | |
| "eval_runtime": 3.9129, | |
| "eval_samples_per_second": 13.034, | |
| "eval_steps_per_second": 13.034, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.6808200234031883, | |
| "eval_accuracy": 0.9984601881650063, | |
| "eval_f1": 0.6254295532646049, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.6066666666666667, | |
| "eval_recall": 0.6453900709219859, | |
| "eval_runtime": 5.213, | |
| "eval_samples_per_second": 9.783, | |
| "eval_steps_per_second": 9.783, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.6929775238211023, | |
| "eval_accuracy": 0.9984909844017061, | |
| "eval_f1": 0.626465661641541, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5936507936507937, | |
| "eval_recall": 0.6631205673758865, | |
| "eval_runtime": 3.9034, | |
| "eval_samples_per_second": 13.066, | |
| "eval_steps_per_second": 13.066, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.7051350242390164, | |
| "eval_accuracy": 0.9984601881650063, | |
| "eval_f1": 0.6192893401015229, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5922330097087378, | |
| "eval_recall": 0.648936170212766, | |
| "eval_runtime": 3.9098, | |
| "eval_samples_per_second": 13.044, | |
| "eval_steps_per_second": 13.044, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.7172925246569305, | |
| "eval_accuracy": 0.9984909844017061, | |
| "eval_f1": 0.6323777403035413, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.6028938906752411, | |
| "eval_recall": 0.6648936170212766, | |
| "eval_runtime": 3.9284, | |
| "eval_samples_per_second": 12.982, | |
| "eval_steps_per_second": 12.982, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.7294500250748446, | |
| "grad_norm": 0.41796875, | |
| "learning_rate": 2.7051671732522798e-05, | |
| "loss": 0.0058, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.7294500250748446, | |
| "eval_accuracy": 0.9984293919283064, | |
| "eval_f1": 0.6126279863481229, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5904605263157895, | |
| "eval_recall": 0.6365248226950354, | |
| "eval_runtime": 5.2952, | |
| "eval_samples_per_second": 9.631, | |
| "eval_steps_per_second": 9.631, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.7416075254927587, | |
| "eval_accuracy": 0.9984755862833562, | |
| "eval_f1": 0.6201022146507666, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5967213114754099, | |
| "eval_recall": 0.6453900709219859, | |
| "eval_runtime": 5.2342, | |
| "eval_samples_per_second": 9.744, | |
| "eval_steps_per_second": 9.744, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.7537650259106727, | |
| "eval_accuracy": 0.9984909844017061, | |
| "eval_f1": 0.6306913996627319, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.6012861736334405, | |
| "eval_recall": 0.6631205673758865, | |
| "eval_runtime": 3.8769, | |
| "eval_samples_per_second": 13.155, | |
| "eval_steps_per_second": 13.155, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.7659225263285868, | |
| "eval_accuracy": 0.9984909844017061, | |
| "eval_f1": 0.6281833616298812, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.6026058631921825, | |
| "eval_recall": 0.6560283687943262, | |
| "eval_runtime": 3.8104, | |
| "eval_samples_per_second": 13.384, | |
| "eval_steps_per_second": 13.384, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.7780800267465009, | |
| "eval_accuracy": 0.9984601881650063, | |
| "eval_f1": 0.6302521008403361, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5990415335463258, | |
| "eval_recall": 0.6648936170212766, | |
| "eval_runtime": 3.9796, | |
| "eval_samples_per_second": 12.815, | |
| "eval_steps_per_second": 12.815, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.790237527164415, | |
| "grad_norm": 0.5390625, | |
| "learning_rate": 2.0972644376899697e-05, | |
| "loss": 0.0055, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.790237527164415, | |
| "eval_accuracy": 0.9984601881650063, | |
| "eval_f1": 0.6302521008403361, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5990415335463258, | |
| "eval_recall": 0.6648936170212766, | |
| "eval_runtime": 3.9236, | |
| "eval_samples_per_second": 12.998, | |
| "eval_steps_per_second": 12.998, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.8023950275823291, | |
| "eval_accuracy": 0.9985063825200561, | |
| "eval_f1": 0.6256410256410256, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.6039603960396039, | |
| "eval_recall": 0.648936170212766, | |
| "eval_runtime": 3.9065, | |
| "eval_samples_per_second": 13.055, | |
| "eval_steps_per_second": 13.055, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 0.8145525280002431, | |
| "eval_accuracy": 0.9984755862833562, | |
| "eval_f1": 0.6209262435677531, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.6013289036544851, | |
| "eval_recall": 0.6418439716312057, | |
| "eval_runtime": 3.883, | |
| "eval_samples_per_second": 13.134, | |
| "eval_steps_per_second": 13.134, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 0.8267100284181572, | |
| "eval_accuracy": 0.9984293919283064, | |
| "eval_f1": 0.6214405360134003, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5888888888888889, | |
| "eval_recall": 0.6578014184397163, | |
| "eval_runtime": 3.8972, | |
| "eval_samples_per_second": 13.086, | |
| "eval_steps_per_second": 13.086, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.8388675288360713, | |
| "eval_accuracy": 0.9984293919283064, | |
| "eval_f1": 0.6121416526138279, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5836012861736335, | |
| "eval_recall": 0.6436170212765957, | |
| "eval_runtime": 3.9065, | |
| "eval_samples_per_second": 13.055, | |
| "eval_steps_per_second": 13.055, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 0.8510250292539854, | |
| "grad_norm": 0.5234375, | |
| "learning_rate": 1.4893617021276596e-05, | |
| "loss": 0.0052, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.8510250292539854, | |
| "eval_accuracy": 0.9984601881650063, | |
| "eval_f1": 0.6235294117647059, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5926517571884984, | |
| "eval_recall": 0.6578014184397163, | |
| "eval_runtime": 4.6336, | |
| "eval_samples_per_second": 11.007, | |
| "eval_steps_per_second": 11.007, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.8631825296718995, | |
| "eval_accuracy": 0.9984601881650063, | |
| "eval_f1": 0.6302521008403361, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5990415335463258, | |
| "eval_recall": 0.6648936170212766, | |
| "eval_runtime": 3.9703, | |
| "eval_samples_per_second": 12.845, | |
| "eval_steps_per_second": 12.845, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 0.8753400300898135, | |
| "eval_accuracy": 0.9984293919283064, | |
| "eval_f1": 0.6214405360134003, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.5888888888888889, | |
| "eval_recall": 0.6578014184397163, | |
| "eval_runtime": 3.9965, | |
| "eval_samples_per_second": 12.761, | |
| "eval_steps_per_second": 12.761, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 0.8874975305077276, | |
| "eval_accuracy": 0.998537178756756, | |
| "eval_f1": 0.637137989778535, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.6131147540983607, | |
| "eval_recall": 0.6631205673758865, | |
| "eval_runtime": 4.0553, | |
| "eval_samples_per_second": 12.576, | |
| "eval_steps_per_second": 12.576, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 0.8996550309256417, | |
| "eval_accuracy": 0.9985525768751059, | |
| "eval_f1": 0.6417657045840408, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.6156351791530945, | |
| "eval_recall": 0.6702127659574468, | |
| "eval_runtime": 4.0275, | |
| "eval_samples_per_second": 12.663, | |
| "eval_steps_per_second": 12.663, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 0.9118125313435558, | |
| "grad_norm": 0.2412109375, | |
| "learning_rate": 8.814589665653496e-06, | |
| "loss": 0.0052, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.9118125313435558, | |
| "eval_accuracy": 0.9985525768751059, | |
| "eval_f1": 0.6417657045840408, | |
| "eval_loss": NaN, | |
| "eval_precision": 0.6156351791530945, | |
| "eval_recall": 0.6702127659574468, | |
| "eval_runtime": 4.1063, | |
| "eval_samples_per_second": 12.42, | |
| "eval_steps_per_second": 12.42, | |
| "step": 7500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 8225, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.941757589813818e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |