| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04992511233150274, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006656681644200366, | |
| "grad_norm": 4.565742492675781, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 5.2699, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006656681644200366, | |
| "eval_loss": 5.414046287536621, | |
| "eval_runtime": 292.7399, | |
| "eval_samples_per_second": 4.321, | |
| "eval_steps_per_second": 2.162, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013313363288400732, | |
| "grad_norm": 5.261593818664551, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 5.5603, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00199700449326011, | |
| "grad_norm": 5.0060577392578125, | |
| "learning_rate": 0.0002, | |
| "loss": 5.3154, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0026626726576801465, | |
| "grad_norm": 4.290820121765137, | |
| "learning_rate": 0.0001999048221581858, | |
| "loss": 4.7453, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003328340822100183, | |
| "grad_norm": 4.488643169403076, | |
| "learning_rate": 0.00019961946980917456, | |
| "loss": 4.0802, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00399400898652022, | |
| "grad_norm": 4.862600803375244, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 3.7522, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004659677150940256, | |
| "grad_norm": 5.443639278411865, | |
| "learning_rate": 0.00019848077530122083, | |
| "loss": 2.7179, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005325345315360293, | |
| "grad_norm": 3.63372540473938, | |
| "learning_rate": 0.00019762960071199333, | |
| "loss": 2.3048, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005991013479780329, | |
| "grad_norm": 2.9024391174316406, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 1.6602, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006656681644200366, | |
| "grad_norm": 4.694620132446289, | |
| "learning_rate": 0.0001953716950748227, | |
| "loss": 2.0155, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007322349808620403, | |
| "grad_norm": 4.4970855712890625, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 1.8371, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00798801797304044, | |
| "grad_norm": 3.8255815505981445, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 1.7279, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008653686137460476, | |
| "grad_norm": 3.8512322902679443, | |
| "learning_rate": 0.000190630778703665, | |
| "loss": 1.3884, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009319354301880512, | |
| "grad_norm": 4.351423263549805, | |
| "learning_rate": 0.00018870108331782217, | |
| "loss": 1.5076, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00998502246630055, | |
| "grad_norm": 4.972479820251465, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 1.3592, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010650690630720586, | |
| "grad_norm": 4.12640905380249, | |
| "learning_rate": 0.0001843391445812886, | |
| "loss": 1.2625, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.011316358795140622, | |
| "grad_norm": 4.288045883178711, | |
| "learning_rate": 0.0001819152044288992, | |
| "loss": 1.2336, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.011982026959560658, | |
| "grad_norm": 4.866492748260498, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 1.4185, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.012647695123980696, | |
| "grad_norm": 3.893460512161255, | |
| "learning_rate": 0.0001766044443118978, | |
| "loss": 1.2172, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.013313363288400732, | |
| "grad_norm": 3.1255502700805664, | |
| "learning_rate": 0.0001737277336810124, | |
| "loss": 0.9529, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013979031452820768, | |
| "grad_norm": 2.7771689891815186, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.014644699617240806, | |
| "grad_norm": 2.2438104152679443, | |
| "learning_rate": 0.00016755902076156604, | |
| "loss": 0.7369, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.015310367781660842, | |
| "grad_norm": 3.5781610012054443, | |
| "learning_rate": 0.00016427876096865394, | |
| "loss": 1.108, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01597603594608088, | |
| "grad_norm": 2.71801495552063, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.7519, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.016641704110500914, | |
| "grad_norm": 2.9104671478271484, | |
| "learning_rate": 0.0001573576436351046, | |
| "loss": 0.6761, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.016641704110500914, | |
| "eval_loss": 0.7497785687446594, | |
| "eval_runtime": 294.9753, | |
| "eval_samples_per_second": 4.288, | |
| "eval_steps_per_second": 2.146, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.017307372274920952, | |
| "grad_norm": 4.477328300476074, | |
| "learning_rate": 0.0001537299608346824, | |
| "loss": 0.8882, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.01797304043934099, | |
| "grad_norm": 2.8925857543945312, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.6097, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.018638708603761024, | |
| "grad_norm": 2.060027837753296, | |
| "learning_rate": 0.00014617486132350343, | |
| "loss": 0.3883, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.019304376768181062, | |
| "grad_norm": 3.449633836746216, | |
| "learning_rate": 0.00014226182617406996, | |
| "loss": 0.5409, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0199700449326011, | |
| "grad_norm": 5.332679748535156, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.8763, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.020635713097021134, | |
| "grad_norm": 3.696377754211426, | |
| "learning_rate": 0.00013420201433256689, | |
| "loss": 0.4409, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.021301381261441172, | |
| "grad_norm": 3.181502103805542, | |
| "learning_rate": 0.00013007057995042732, | |
| "loss": 0.4034, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02196704942586121, | |
| "grad_norm": 3.712878704071045, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.4278, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.022632717590281244, | |
| "grad_norm": 4.807991981506348, | |
| "learning_rate": 0.00012164396139381029, | |
| "loss": 0.5724, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.023298385754701282, | |
| "grad_norm": 4.910369873046875, | |
| "learning_rate": 0.00011736481776669306, | |
| "loss": 0.6912, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.023964053919121316, | |
| "grad_norm": 4.7990193367004395, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.611, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.024629722083541354, | |
| "grad_norm": 5.814478397369385, | |
| "learning_rate": 0.00010871557427476583, | |
| "loss": 0.5512, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.025295390247961392, | |
| "grad_norm": 3.2857327461242676, | |
| "learning_rate": 0.00010436193873653361, | |
| "loss": 0.4976, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.025961058412381426, | |
| "grad_norm": 2.919463872909546, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3717, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.026626726576801464, | |
| "grad_norm": 2.6156516075134277, | |
| "learning_rate": 9.563806126346642e-05, | |
| "loss": 0.3615, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.027292394741221502, | |
| "grad_norm": 2.868933916091919, | |
| "learning_rate": 9.128442572523417e-05, | |
| "loss": 0.3111, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.027958062905641536, | |
| "grad_norm": 2.936983823776245, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 0.2645, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.028623731070061574, | |
| "grad_norm": 1.8019835948944092, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 0.1452, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.029289399234481612, | |
| "grad_norm": 4.0728983879089355, | |
| "learning_rate": 7.835603860618972e-05, | |
| "loss": 0.3946, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.029955067398901646, | |
| "grad_norm": 1.7865502834320068, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 0.1265, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.030620735563321684, | |
| "grad_norm": 2.652951240539551, | |
| "learning_rate": 6.992942004957271e-05, | |
| "loss": 0.1366, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.03128640372774172, | |
| "grad_norm": 4.144972801208496, | |
| "learning_rate": 6.579798566743314e-05, | |
| "loss": 0.4658, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.03195207189216176, | |
| "grad_norm": 2.2921547889709473, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.1661, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.032617740056581794, | |
| "grad_norm": 2.8767738342285156, | |
| "learning_rate": 5.773817382593008e-05, | |
| "loss": 0.2198, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03328340822100183, | |
| "grad_norm": 5.364581108093262, | |
| "learning_rate": 5.382513867649663e-05, | |
| "loss": 0.3999, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03328340822100183, | |
| "eval_loss": 0.2637653350830078, | |
| "eval_runtime": 294.8304, | |
| "eval_samples_per_second": 4.291, | |
| "eval_steps_per_second": 2.147, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03394907638542187, | |
| "grad_norm": 2.3751840591430664, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0587, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.034614744549841904, | |
| "grad_norm": 3.929506778717041, | |
| "learning_rate": 4.6270039165317605e-05, | |
| "loss": 0.243, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.03528041271426194, | |
| "grad_norm": 4.9729132652282715, | |
| "learning_rate": 4.264235636489542e-05, | |
| "loss": 0.3327, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.03594608087868198, | |
| "grad_norm": 4.64143180847168, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 0.3707, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.036611749043102014, | |
| "grad_norm": 3.2200844287872314, | |
| "learning_rate": 3.5721239031346066e-05, | |
| "loss": 0.2981, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.03727741720752205, | |
| "grad_norm": 2.6393558979034424, | |
| "learning_rate": 3.244097923843398e-05, | |
| "loss": 0.1529, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.03794308537194209, | |
| "grad_norm": 4.790804862976074, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.2654, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.038608753536362124, | |
| "grad_norm": 1.2065534591674805, | |
| "learning_rate": 2.6272266318987603e-05, | |
| "loss": 0.0551, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.03927442170078216, | |
| "grad_norm": 3.567166328430176, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 0.3295, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.0399400898652022, | |
| "grad_norm": 1.8716219663619995, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 0.1449, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.040605758029622234, | |
| "grad_norm": 2.8182613849639893, | |
| "learning_rate": 1.808479557110081e-05, | |
| "loss": 0.1724, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.04127142619404227, | |
| "grad_norm": 4.6796112060546875, | |
| "learning_rate": 1.566085541871145e-05, | |
| "loss": 0.2599, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.04193709435846231, | |
| "grad_norm": 3.623056411743164, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.0858, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.042602762522882344, | |
| "grad_norm": 1.3320046663284302, | |
| "learning_rate": 1.129891668217783e-05, | |
| "loss": 0.0667, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.04326843068730238, | |
| "grad_norm": 2.166306495666504, | |
| "learning_rate": 9.369221296335006e-06, | |
| "loss": 0.1206, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.04393409885172242, | |
| "grad_norm": 2.2918238639831543, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.0988, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.044599767016142454, | |
| "grad_norm": 3.8302066326141357, | |
| "learning_rate": 6.030737921409169e-06, | |
| "loss": 0.3119, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.04526543518056249, | |
| "grad_norm": 3.98258638381958, | |
| "learning_rate": 4.628304925177318e-06, | |
| "loss": 0.2715, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.04593110334498253, | |
| "grad_norm": 4.596426010131836, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.5579, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.046596771509402564, | |
| "grad_norm": 2.9032671451568604, | |
| "learning_rate": 2.3703992880066638e-06, | |
| "loss": 0.1493, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0472624396738226, | |
| "grad_norm": 7.22641134262085, | |
| "learning_rate": 1.5192246987791981e-06, | |
| "loss": 0.4988, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.04792810783824263, | |
| "grad_norm": 5.318079948425293, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 0.3443, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.048593776002662674, | |
| "grad_norm": 2.0902915000915527, | |
| "learning_rate": 3.805301908254455e-07, | |
| "loss": 0.1034, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.04925944416708271, | |
| "grad_norm": 3.0144219398498535, | |
| "learning_rate": 9.517784181422019e-08, | |
| "loss": 0.3192, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.04992511233150274, | |
| "grad_norm": 4.522768974304199, | |
| "learning_rate": 0.0, | |
| "loss": 0.0828, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.04992511233150274, | |
| "eval_loss": 0.2045978456735611, | |
| "eval_runtime": 294.7269, | |
| "eval_samples_per_second": 4.292, | |
| "eval_steps_per_second": 2.148, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "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": 9.9164117532672e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |