|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.04962455109369899, |
|
"eval_steps": 76, |
|
"global_step": 76, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.000652954619653934, |
|
"grad_norm": 4.757781028747559, |
|
"learning_rate": 4.000000000000001e-06, |
|
"loss": 4.2047, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.000652954619653934, |
|
"eval_loss": NaN, |
|
"eval_runtime": 704.7675, |
|
"eval_samples_per_second": 3.661, |
|
"eval_steps_per_second": 0.915, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.001305909239307868, |
|
"grad_norm": 4.874630928039551, |
|
"learning_rate": 8.000000000000001e-06, |
|
"loss": 4.1653, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0019588638589618022, |
|
"grad_norm": 5.5883331298828125, |
|
"learning_rate": 1.2e-05, |
|
"loss": 4.1635, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.002611818478615736, |
|
"grad_norm": 5.3879313468933105, |
|
"learning_rate": 1.6000000000000003e-05, |
|
"loss": 3.8569, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.00326477309826967, |
|
"grad_norm": 4.848824501037598, |
|
"learning_rate": 2e-05, |
|
"loss": 4.0147, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.0039177277179236044, |
|
"grad_norm": 5.3052978515625, |
|
"learning_rate": 2.4e-05, |
|
"loss": 3.7956, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.004570682337577538, |
|
"grad_norm": 6.782866954803467, |
|
"learning_rate": 2.8000000000000003e-05, |
|
"loss": 4.6771, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.005223636957231472, |
|
"grad_norm": 6.1247735023498535, |
|
"learning_rate": 3.2000000000000005e-05, |
|
"loss": 3.8201, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.005876591576885406, |
|
"grad_norm": 5.305412769317627, |
|
"learning_rate": 3.6e-05, |
|
"loss": 3.2011, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.00652954619653934, |
|
"grad_norm": 4.974228858947754, |
|
"learning_rate": 4e-05, |
|
"loss": 3.2488, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.007182500816193275, |
|
"grad_norm": 4.17997407913208, |
|
"learning_rate": 4.4000000000000006e-05, |
|
"loss": 2.8667, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.007835455435847209, |
|
"grad_norm": 5.494494915008545, |
|
"learning_rate": 4.8e-05, |
|
"loss": 3.0199, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.008488410055501142, |
|
"grad_norm": 3.663966178894043, |
|
"learning_rate": 5.2000000000000004e-05, |
|
"loss": 2.5652, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.009141364675155077, |
|
"grad_norm": 3.196805477142334, |
|
"learning_rate": 5.6000000000000006e-05, |
|
"loss": 2.6467, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.009794319294809012, |
|
"grad_norm": 3.161735773086548, |
|
"learning_rate": 6e-05, |
|
"loss": 2.4477, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.010447273914462945, |
|
"grad_norm": 4.473456859588623, |
|
"learning_rate": 6.400000000000001e-05, |
|
"loss": 2.4943, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.01110022853411688, |
|
"grad_norm": 5.138904094696045, |
|
"learning_rate": 6.800000000000001e-05, |
|
"loss": 2.51, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.011753183153770812, |
|
"grad_norm": 5.232083320617676, |
|
"learning_rate": 7.2e-05, |
|
"loss": 2.3384, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.012406137773424747, |
|
"grad_norm": 5.67042875289917, |
|
"learning_rate": 7.6e-05, |
|
"loss": 2.3158, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.01305909239307868, |
|
"grad_norm": 6.414549350738525, |
|
"learning_rate": 8e-05, |
|
"loss": 2.2479, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.013712047012732615, |
|
"grad_norm": 6.064276218414307, |
|
"learning_rate": 8.4e-05, |
|
"loss": 2.689, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.01436500163238655, |
|
"grad_norm": 4.989445686340332, |
|
"learning_rate": 8.800000000000001e-05, |
|
"loss": 1.9927, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.015017956252040483, |
|
"grad_norm": 6.970681667327881, |
|
"learning_rate": 9.200000000000001e-05, |
|
"loss": 2.0652, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.015670910871694418, |
|
"grad_norm": 5.712936878204346, |
|
"learning_rate": 9.6e-05, |
|
"loss": 1.7749, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.01632386549134835, |
|
"grad_norm": 6.509803771972656, |
|
"learning_rate": 0.0001, |
|
"loss": 1.6381, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.016976820111002284, |
|
"grad_norm": 9.46315860748291, |
|
"learning_rate": 0.00010400000000000001, |
|
"loss": 2.9097, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.01762977473065622, |
|
"grad_norm": 7.60649299621582, |
|
"learning_rate": 0.00010800000000000001, |
|
"loss": 2.3185, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.018282729350310153, |
|
"grad_norm": 4.304985046386719, |
|
"learning_rate": 0.00011200000000000001, |
|
"loss": 1.8866, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.018935683969964087, |
|
"grad_norm": 4.42153787612915, |
|
"learning_rate": 0.000116, |
|
"loss": 1.9317, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.019588638589618023, |
|
"grad_norm": 4.993203163146973, |
|
"learning_rate": 0.00012, |
|
"loss": 1.963, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.020241593209271956, |
|
"grad_norm": 5.630634784698486, |
|
"learning_rate": 0.000124, |
|
"loss": 2.0134, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.02089454782892589, |
|
"grad_norm": 4.011257648468018, |
|
"learning_rate": 0.00012800000000000002, |
|
"loss": 1.5838, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.021547502448579822, |
|
"grad_norm": 4.430102348327637, |
|
"learning_rate": 0.000132, |
|
"loss": 1.567, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.02220045706823376, |
|
"grad_norm": 4.285562038421631, |
|
"learning_rate": 0.00013600000000000003, |
|
"loss": 1.5668, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.022853411687887692, |
|
"grad_norm": 4.76671028137207, |
|
"learning_rate": 0.00014, |
|
"loss": 1.4504, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.023506366307541625, |
|
"grad_norm": 3.6335926055908203, |
|
"learning_rate": 0.000144, |
|
"loss": 1.7653, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.02415932092719556, |
|
"grad_norm": 3.863640546798706, |
|
"learning_rate": 0.000148, |
|
"loss": 1.7619, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.024812275546849494, |
|
"grad_norm": 3.339837074279785, |
|
"learning_rate": 0.000152, |
|
"loss": 1.9767, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.025465230166503428, |
|
"grad_norm": 3.004544734954834, |
|
"learning_rate": 0.00015600000000000002, |
|
"loss": 1.954, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.02611818478615736, |
|
"grad_norm": 3.1160991191864014, |
|
"learning_rate": 0.00016, |
|
"loss": 2.2944, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.026771139405811297, |
|
"grad_norm": 2.9257686138153076, |
|
"learning_rate": 0.000164, |
|
"loss": 2.1756, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.02742409402546523, |
|
"grad_norm": 3.0116686820983887, |
|
"learning_rate": 0.000168, |
|
"loss": 2.2031, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.028077048645119163, |
|
"grad_norm": 3.1789779663085938, |
|
"learning_rate": 0.000172, |
|
"loss": 1.71, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.0287300032647731, |
|
"grad_norm": 3.2652573585510254, |
|
"learning_rate": 0.00017600000000000002, |
|
"loss": 2.108, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.029382957884427033, |
|
"grad_norm": 3.3591766357421875, |
|
"learning_rate": 0.00018, |
|
"loss": 2.252, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.030035912504080966, |
|
"grad_norm": 4.020256519317627, |
|
"learning_rate": 0.00018400000000000003, |
|
"loss": 2.0209, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.0306888671237349, |
|
"grad_norm": 3.1844100952148438, |
|
"learning_rate": 0.000188, |
|
"loss": 1.7205, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.031341821743388835, |
|
"grad_norm": 4.041150093078613, |
|
"learning_rate": 0.000192, |
|
"loss": 2.0322, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.031994776363042765, |
|
"grad_norm": 3.976959228515625, |
|
"learning_rate": 0.000196, |
|
"loss": 1.5729, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.0326477309826967, |
|
"grad_norm": 3.8643813133239746, |
|
"learning_rate": 0.0002, |
|
"loss": 1.3921, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.03330068560235064, |
|
"grad_norm": 4.523630142211914, |
|
"learning_rate": 0.0001999922905547776, |
|
"loss": 2.0141, |
|
"step": 51 |
|
}, |
|
{ |
|
"epoch": 0.03395364022200457, |
|
"grad_norm": 3.308136463165283, |
|
"learning_rate": 0.0001999691634078213, |
|
"loss": 1.6375, |
|
"step": 52 |
|
}, |
|
{ |
|
"epoch": 0.034606594841658504, |
|
"grad_norm": 3.70528244972229, |
|
"learning_rate": 0.00019993062212508053, |
|
"loss": 2.1218, |
|
"step": 53 |
|
}, |
|
{ |
|
"epoch": 0.03525954946131244, |
|
"grad_norm": 3.909076690673828, |
|
"learning_rate": 0.0001998766726491935, |
|
"loss": 1.7935, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 0.03591250408096637, |
|
"grad_norm": 3.2719497680664062, |
|
"learning_rate": 0.00019980732329857076, |
|
"loss": 1.4998, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.03656545870062031, |
|
"grad_norm": 4.357359886169434, |
|
"learning_rate": 0.0001997225847661127, |
|
"loss": 1.7119, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 0.03721841332027424, |
|
"grad_norm": 3.111414909362793, |
|
"learning_rate": 0.00019962247011756081, |
|
"loss": 1.3332, |
|
"step": 57 |
|
}, |
|
{ |
|
"epoch": 0.03787136793992817, |
|
"grad_norm": 3.3698601722717285, |
|
"learning_rate": 0.00019950699478948309, |
|
"loss": 1.3576, |
|
"step": 58 |
|
}, |
|
{ |
|
"epoch": 0.03852432255958211, |
|
"grad_norm": 4.0696024894714355, |
|
"learning_rate": 0.00019937617658689384, |
|
"loss": 1.2196, |
|
"step": 59 |
|
}, |
|
{ |
|
"epoch": 0.039177277179236046, |
|
"grad_norm": 3.984119176864624, |
|
"learning_rate": 0.00019923003568050844, |
|
"loss": 1.4652, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.039830231798889976, |
|
"grad_norm": 3.909024238586426, |
|
"learning_rate": 0.00019906859460363307, |
|
"loss": 1.2951, |
|
"step": 61 |
|
}, |
|
{ |
|
"epoch": 0.04048318641854391, |
|
"grad_norm": 3.550440788269043, |
|
"learning_rate": 0.0001988918782486906, |
|
"loss": 1.4699, |
|
"step": 62 |
|
}, |
|
{ |
|
"epoch": 0.04113614103819784, |
|
"grad_norm": 3.341071367263794, |
|
"learning_rate": 0.0001986999138633821, |
|
"loss": 2.1781, |
|
"step": 63 |
|
}, |
|
{ |
|
"epoch": 0.04178909565785178, |
|
"grad_norm": 2.938025951385498, |
|
"learning_rate": 0.00019849273104648592, |
|
"loss": 1.7088, |
|
"step": 64 |
|
}, |
|
{ |
|
"epoch": 0.042442050277505715, |
|
"grad_norm": 2.956080913543701, |
|
"learning_rate": 0.00019827036174329353, |
|
"loss": 2.0676, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.043095004897159644, |
|
"grad_norm": 2.349592924118042, |
|
"learning_rate": 0.00019803284024068427, |
|
"loss": 1.7783, |
|
"step": 66 |
|
}, |
|
{ |
|
"epoch": 0.04374795951681358, |
|
"grad_norm": 2.7854583263397217, |
|
"learning_rate": 0.0001977802031618383, |
|
"loss": 2.222, |
|
"step": 67 |
|
}, |
|
{ |
|
"epoch": 0.04440091413646752, |
|
"grad_norm": 3.6111695766448975, |
|
"learning_rate": 0.00019751248946059014, |
|
"loss": 2.0701, |
|
"step": 68 |
|
}, |
|
{ |
|
"epoch": 0.04505386875612145, |
|
"grad_norm": 3.226724863052368, |
|
"learning_rate": 0.00019722974041542203, |
|
"loss": 2.2502, |
|
"step": 69 |
|
}, |
|
{ |
|
"epoch": 0.045706823375775384, |
|
"grad_norm": 3.4755945205688477, |
|
"learning_rate": 0.0001969319996230995, |
|
"loss": 2.0837, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.04635977799542932, |
|
"grad_norm": 3.1673951148986816, |
|
"learning_rate": 0.0001966193129919491, |
|
"loss": 1.8692, |
|
"step": 71 |
|
}, |
|
{ |
|
"epoch": 0.04701273261508325, |
|
"grad_norm": 3.5966238975524902, |
|
"learning_rate": 0.00019629172873477995, |
|
"loss": 2.0036, |
|
"step": 72 |
|
}, |
|
{ |
|
"epoch": 0.047665687234737186, |
|
"grad_norm": 4.344339370727539, |
|
"learning_rate": 0.00019594929736144976, |
|
"loss": 1.963, |
|
"step": 73 |
|
}, |
|
{ |
|
"epoch": 0.04831864185439112, |
|
"grad_norm": 3.6855549812316895, |
|
"learning_rate": 0.00019559207167107684, |
|
"loss": 1.5932, |
|
"step": 74 |
|
}, |
|
{ |
|
"epoch": 0.04897159647404505, |
|
"grad_norm": 3.7931909561157227, |
|
"learning_rate": 0.000195220106743899, |
|
"loss": 1.272, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.04962455109369899, |
|
"grad_norm": 3.422001361846924, |
|
"learning_rate": 0.00019483345993278093, |
|
"loss": 1.8281, |
|
"step": 76 |
|
}, |
|
{ |
|
"epoch": 0.04962455109369899, |
|
"eval_loss": NaN, |
|
"eval_runtime": 704.1079, |
|
"eval_samples_per_second": 3.664, |
|
"eval_steps_per_second": 0.916, |
|
"step": 76 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 303, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 76, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 2.331358757084201e+17, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|