| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9968847352024922, | |
| "eval_steps": 500, | |
| "global_step": 60, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.016614745586708203, | |
| "grad_norm": 0.061364494264125824, | |
| "learning_rate": 4.999991432639962e-05, | |
| "loss": 0.5857, | |
| "num_input_tokens_seen": 70408, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.033229491173416406, | |
| "grad_norm": 0.0613991804420948, | |
| "learning_rate": 4.999965730618567e-05, | |
| "loss": 0.5331, | |
| "num_input_tokens_seen": 139640, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04984423676012461, | |
| "grad_norm": 0.06351307034492493, | |
| "learning_rate": 4.9999228941119745e-05, | |
| "loss": 0.5852, | |
| "num_input_tokens_seen": 223656, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06645898234683281, | |
| "grad_norm": 0.05762802064418793, | |
| "learning_rate": 4.999862923413781e-05, | |
| "loss": 0.5384, | |
| "num_input_tokens_seen": 300688, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.08307372793354102, | |
| "grad_norm": 0.0632179006934166, | |
| "learning_rate": 4.999785818935018e-05, | |
| "loss": 0.5273, | |
| "num_input_tokens_seen": 366368, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09968847352024922, | |
| "grad_norm": 0.056689903140068054, | |
| "learning_rate": 4.999691581204152e-05, | |
| "loss": 0.5145, | |
| "num_input_tokens_seen": 445808, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11630321910695743, | |
| "grad_norm": 0.06574171781539917, | |
| "learning_rate": 4.9995802108670775e-05, | |
| "loss": 0.5301, | |
| "num_input_tokens_seen": 522800, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.13291796469366562, | |
| "grad_norm": 0.06367070972919464, | |
| "learning_rate": 4.999451708687114e-05, | |
| "loss": 0.5552, | |
| "num_input_tokens_seen": 599608, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.14953271028037382, | |
| "grad_norm": 0.0585966520011425, | |
| "learning_rate": 4.9993060755450015e-05, | |
| "loss": 0.5999, | |
| "num_input_tokens_seen": 681424, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.16614745586708204, | |
| "grad_norm": 0.05650574713945389, | |
| "learning_rate": 4.999143312438893e-05, | |
| "loss": 0.4535, | |
| "num_input_tokens_seen": 756744, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.18276220145379024, | |
| "grad_norm": 0.05954223498702049, | |
| "learning_rate": 4.998963420484349e-05, | |
| "loss": 0.4674, | |
| "num_input_tokens_seen": 842576, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.19937694704049844, | |
| "grad_norm": 0.0663776770234108, | |
| "learning_rate": 4.998766400914329e-05, | |
| "loss": 0.4703, | |
| "num_input_tokens_seen": 917232, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.21599169262720663, | |
| "grad_norm": 0.056374579668045044, | |
| "learning_rate": 4.9985522550791825e-05, | |
| "loss": 0.3725, | |
| "num_input_tokens_seen": 1006800, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.23260643821391486, | |
| "grad_norm": 0.06437493115663528, | |
| "learning_rate": 4.998320984446641e-05, | |
| "loss": 0.4653, | |
| "num_input_tokens_seen": 1085824, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.24922118380062305, | |
| "grad_norm": 0.06560757756233215, | |
| "learning_rate": 4.9980725906018074e-05, | |
| "loss": 0.5026, | |
| "num_input_tokens_seen": 1164160, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.26583592938733125, | |
| "grad_norm": 0.06942517310380936, | |
| "learning_rate": 4.997807075247146e-05, | |
| "loss": 0.5401, | |
| "num_input_tokens_seen": 1242264, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2824506749740395, | |
| "grad_norm": 0.06349828094244003, | |
| "learning_rate": 4.997524440202469e-05, | |
| "loss": 0.4713, | |
| "num_input_tokens_seen": 1325904, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.29906542056074764, | |
| "grad_norm": 0.08846385776996613, | |
| "learning_rate": 4.9972246874049254e-05, | |
| "loss": 0.5834, | |
| "num_input_tokens_seen": 1385632, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.31568016614745587, | |
| "grad_norm": 0.062130190432071686, | |
| "learning_rate": 4.996907818908987e-05, | |
| "loss": 0.4045, | |
| "num_input_tokens_seen": 1470632, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3322949117341641, | |
| "grad_norm": 0.07743565738201141, | |
| "learning_rate": 4.996573836886435e-05, | |
| "loss": 0.5283, | |
| "num_input_tokens_seen": 1547536, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.34890965732087226, | |
| "grad_norm": 0.06756695359945297, | |
| "learning_rate": 4.9962227436263453e-05, | |
| "loss": 0.4199, | |
| "num_input_tokens_seen": 1615528, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3655244029075805, | |
| "grad_norm": 0.08662309497594833, | |
| "learning_rate": 4.995854541535071e-05, | |
| "loss": 0.4775, | |
| "num_input_tokens_seen": 1694352, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3821391484942887, | |
| "grad_norm": 0.08380820602178574, | |
| "learning_rate": 4.9954692331362294e-05, | |
| "loss": 0.4871, | |
| "num_input_tokens_seen": 1753776, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3987538940809969, | |
| "grad_norm": 0.09967435896396637, | |
| "learning_rate": 4.995066821070679e-05, | |
| "loss": 0.4871, | |
| "num_input_tokens_seen": 1809048, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.4153686396677051, | |
| "grad_norm": 0.0871267095208168, | |
| "learning_rate": 4.994647308096509e-05, | |
| "loss": 0.5461, | |
| "num_input_tokens_seen": 1884264, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.43198338525441327, | |
| "grad_norm": 0.065020851790905, | |
| "learning_rate": 4.994210697089014e-05, | |
| "loss": 0.405, | |
| "num_input_tokens_seen": 1981704, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.4485981308411215, | |
| "grad_norm": 0.09853450953960419, | |
| "learning_rate": 4.9937569910406756e-05, | |
| "loss": 0.4487, | |
| "num_input_tokens_seen": 2044144, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4652128764278297, | |
| "grad_norm": 0.08763110637664795, | |
| "learning_rate": 4.9932861930611454e-05, | |
| "loss": 0.3946, | |
| "num_input_tokens_seen": 2107584, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4818276220145379, | |
| "grad_norm": 0.08950547873973846, | |
| "learning_rate": 4.9927983063772196e-05, | |
| "loss": 0.4257, | |
| "num_input_tokens_seen": 2169248, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.4984423676012461, | |
| "grad_norm": 0.09980211406946182, | |
| "learning_rate": 4.99229333433282e-05, | |
| "loss": 0.3911, | |
| "num_input_tokens_seen": 2230344, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5150571131879543, | |
| "grad_norm": 0.092055544257164, | |
| "learning_rate": 4.9917712803889674e-05, | |
| "loss": 0.3749, | |
| "num_input_tokens_seen": 2302368, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5316718587746625, | |
| "grad_norm": 0.10067818313837051, | |
| "learning_rate": 4.991232148123761e-05, | |
| "loss": 0.4761, | |
| "num_input_tokens_seen": 2369984, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5482866043613707, | |
| "grad_norm": 0.0717971920967102, | |
| "learning_rate": 4.990675941232353e-05, | |
| "loss": 0.4328, | |
| "num_input_tokens_seen": 2453032, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.564901349948079, | |
| "grad_norm": 0.07436250895261765, | |
| "learning_rate": 4.990102663526924e-05, | |
| "loss": 0.417, | |
| "num_input_tokens_seen": 2527464, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5815160955347871, | |
| "grad_norm": 0.09256689995527267, | |
| "learning_rate": 4.989512318936655e-05, | |
| "loss": 0.4097, | |
| "num_input_tokens_seen": 2597032, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5981308411214953, | |
| "grad_norm": 0.09964177012443542, | |
| "learning_rate": 4.9889049115077005e-05, | |
| "loss": 0.4065, | |
| "num_input_tokens_seen": 2671704, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6147455867082036, | |
| "grad_norm": 0.06627887487411499, | |
| "learning_rate": 4.988280445403164e-05, | |
| "loss": 0.4136, | |
| "num_input_tokens_seen": 2767640, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6313603322949117, | |
| "grad_norm": 0.0746045857667923, | |
| "learning_rate": 4.987638924903067e-05, | |
| "loss": 0.4125, | |
| "num_input_tokens_seen": 2843720, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6479750778816199, | |
| "grad_norm": 0.0795741006731987, | |
| "learning_rate": 4.9869803544043166e-05, | |
| "loss": 0.3135, | |
| "num_input_tokens_seen": 2921472, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6645898234683282, | |
| "grad_norm": 0.08914181590080261, | |
| "learning_rate": 4.9863047384206835e-05, | |
| "loss": 0.4549, | |
| "num_input_tokens_seen": 2998400, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6812045690550363, | |
| "grad_norm": 0.11220043897628784, | |
| "learning_rate": 4.985612081582764e-05, | |
| "loss": 0.4135, | |
| "num_input_tokens_seen": 3059648, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6978193146417445, | |
| "grad_norm": 0.08390027284622192, | |
| "learning_rate": 4.98490238863795e-05, | |
| "loss": 0.3538, | |
| "num_input_tokens_seen": 3140184, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7144340602284528, | |
| "grad_norm": 0.08858532458543777, | |
| "learning_rate": 4.984175664450397e-05, | |
| "loss": 0.3644, | |
| "num_input_tokens_seen": 3207184, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.731048805815161, | |
| "grad_norm": 0.07439564168453217, | |
| "learning_rate": 4.983431914000991e-05, | |
| "loss": 0.4019, | |
| "num_input_tokens_seen": 3292344, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7476635514018691, | |
| "grad_norm": 0.08694300055503845, | |
| "learning_rate": 4.982671142387316e-05, | |
| "loss": 0.4238, | |
| "num_input_tokens_seen": 3365384, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7642782969885774, | |
| "grad_norm": 0.0867784395813942, | |
| "learning_rate": 4.981893354823614e-05, | |
| "loss": 0.3702, | |
| "num_input_tokens_seen": 3440720, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7808930425752856, | |
| "grad_norm": 0.06278439611196518, | |
| "learning_rate": 4.9810985566407544e-05, | |
| "loss": 0.3354, | |
| "num_input_tokens_seen": 3533576, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.7975077881619937, | |
| "grad_norm": 0.08999717980623245, | |
| "learning_rate": 4.980286753286195e-05, | |
| "loss": 0.4981, | |
| "num_input_tokens_seen": 3599744, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.814122533748702, | |
| "grad_norm": 0.07938859611749649, | |
| "learning_rate": 4.979457950323945e-05, | |
| "loss": 0.4016, | |
| "num_input_tokens_seen": 3689520, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.8307372793354102, | |
| "grad_norm": 0.1045590192079544, | |
| "learning_rate": 4.9786121534345265e-05, | |
| "loss": 0.388, | |
| "num_input_tokens_seen": 3751808, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8473520249221184, | |
| "grad_norm": 0.07890618592500687, | |
| "learning_rate": 4.9777493684149375e-05, | |
| "loss": 0.3674, | |
| "num_input_tokens_seen": 3839096, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.8639667705088265, | |
| "grad_norm": 0.07802557945251465, | |
| "learning_rate": 4.976869601178609e-05, | |
| "loss": 0.4147, | |
| "num_input_tokens_seen": 3919824, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.8805815160955348, | |
| "grad_norm": 0.0913538783788681, | |
| "learning_rate": 4.975972857755369e-05, | |
| "loss": 0.2978, | |
| "num_input_tokens_seen": 3989312, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.897196261682243, | |
| "grad_norm": 0.08525951951742172, | |
| "learning_rate": 4.975059144291394e-05, | |
| "loss": 0.3923, | |
| "num_input_tokens_seen": 4060528, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.9138110072689511, | |
| "grad_norm": 0.08649709820747375, | |
| "learning_rate": 4.974128467049176e-05, | |
| "loss": 0.3282, | |
| "num_input_tokens_seen": 4129368, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.9304257528556594, | |
| "grad_norm": 0.11635593324899673, | |
| "learning_rate": 4.9731808324074717e-05, | |
| "loss": 0.3403, | |
| "num_input_tokens_seen": 4175208, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.9470404984423676, | |
| "grad_norm": 0.1115177720785141, | |
| "learning_rate": 4.972216246861262e-05, | |
| "loss": 0.3191, | |
| "num_input_tokens_seen": 4218096, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.9636552440290758, | |
| "grad_norm": 0.0986371859908104, | |
| "learning_rate": 4.971234717021709e-05, | |
| "loss": 0.3745, | |
| "num_input_tokens_seen": 4275968, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.980269989615784, | |
| "grad_norm": 0.07860780507326126, | |
| "learning_rate": 4.9702362496161085e-05, | |
| "loss": 0.3129, | |
| "num_input_tokens_seen": 4346616, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.9968847352024922, | |
| "grad_norm": 0.08581527322530746, | |
| "learning_rate": 4.9692208514878444e-05, | |
| "loss": 0.3324, | |
| "num_input_tokens_seen": 4425064, | |
| "step": 60 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 1200, | |
| "num_input_tokens_seen": 4425064, | |
| "num_train_epochs": 20, | |
| "save_steps": 60, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.8879949658967245e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |