| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04595236271731638, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006126981695642184, | |
| "grad_norm": 17.287343978881836, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 6.7338, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006126981695642184, | |
| "eval_loss": 7.338890075683594, | |
| "eval_runtime": 102.2997, | |
| "eval_samples_per_second": 13.441, | |
| "eval_steps_per_second": 6.725, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012253963391284368, | |
| "grad_norm": 19.69684600830078, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 6.6071, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0018380945086926552, | |
| "grad_norm": 15.072196960449219, | |
| "learning_rate": 0.0002, | |
| "loss": 5.4661, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0024507926782568737, | |
| "grad_norm": 13.428487777709961, | |
| "learning_rate": 0.0001999048221581858, | |
| "loss": 4.7479, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0030634908478210923, | |
| "grad_norm": 11.567410469055176, | |
| "learning_rate": 0.00019961946980917456, | |
| "loss": 3.0655, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0036761890173853105, | |
| "grad_norm": 9.213797569274902, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 2.3632, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004288887186949529, | |
| "grad_norm": 7.1370110511779785, | |
| "learning_rate": 0.00019848077530122083, | |
| "loss": 2.0916, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004901585356513747, | |
| "grad_norm": 6.3253607749938965, | |
| "learning_rate": 0.00019762960071199333, | |
| "loss": 2.1295, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005514283526077966, | |
| "grad_norm": 7.013556957244873, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 2.4501, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006126981695642185, | |
| "grad_norm": 5.644176483154297, | |
| "learning_rate": 0.0001953716950748227, | |
| "loss": 1.9675, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006739679865206402, | |
| "grad_norm": 5.919342994689941, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 2.3086, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.007352378034770621, | |
| "grad_norm": 5.985039234161377, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 2.0753, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007965076204334839, | |
| "grad_norm": 4.99806022644043, | |
| "learning_rate": 0.000190630778703665, | |
| "loss": 2.3884, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.008577774373899057, | |
| "grad_norm": 4.707241535186768, | |
| "learning_rate": 0.00018870108331782217, | |
| "loss": 2.3303, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.009190472543463276, | |
| "grad_norm": 5.004825592041016, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 1.8894, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009803170713027495, | |
| "grad_norm": 4.547674179077148, | |
| "learning_rate": 0.0001843391445812886, | |
| "loss": 1.8635, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.010415868882591713, | |
| "grad_norm": 3.931337833404541, | |
| "learning_rate": 0.0001819152044288992, | |
| "loss": 1.7631, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.011028567052155932, | |
| "grad_norm": 4.3983025550842285, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 1.5144, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01164126522172015, | |
| "grad_norm": 4.176623821258545, | |
| "learning_rate": 0.0001766044443118978, | |
| "loss": 1.6272, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01225396339128437, | |
| "grad_norm": 4.463096618652344, | |
| "learning_rate": 0.0001737277336810124, | |
| "loss": 1.778, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.012866661560848588, | |
| "grad_norm": 3.474909543991089, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.1662, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.013479359730412805, | |
| "grad_norm": 5.438625812530518, | |
| "learning_rate": 0.00016755902076156604, | |
| "loss": 2.1278, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.014092057899977023, | |
| "grad_norm": 3.6824615001678467, | |
| "learning_rate": 0.00016427876096865394, | |
| "loss": 1.9374, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.014704756069541242, | |
| "grad_norm": 3.76320481300354, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 1.3381, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01531745423910546, | |
| "grad_norm": 4.320566177368164, | |
| "learning_rate": 0.0001573576436351046, | |
| "loss": 1.987, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01531745423910546, | |
| "eval_loss": 1.7541515827178955, | |
| "eval_runtime": 103.2143, | |
| "eval_samples_per_second": 13.322, | |
| "eval_steps_per_second": 6.666, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.015930152408669677, | |
| "grad_norm": 4.183315277099609, | |
| "learning_rate": 0.0001537299608346824, | |
| "loss": 1.7487, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.016542850578233896, | |
| "grad_norm": 3.80495285987854, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.5895, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.017155548747798115, | |
| "grad_norm": 4.383512496948242, | |
| "learning_rate": 0.00014617486132350343, | |
| "loss": 1.7426, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.017768246917362333, | |
| "grad_norm": 3.543182134628296, | |
| "learning_rate": 0.00014226182617406996, | |
| "loss": 1.3334, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.018380945086926552, | |
| "grad_norm": 5.36271858215332, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 2.0307, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01899364325649077, | |
| "grad_norm": 4.558619022369385, | |
| "learning_rate": 0.00013420201433256689, | |
| "loss": 1.5612, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.01960634142605499, | |
| "grad_norm": 4.2172393798828125, | |
| "learning_rate": 0.00013007057995042732, | |
| "loss": 1.6558, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.020219039595619208, | |
| "grad_norm": 3.8163092136383057, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 1.2329, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.020831737765183427, | |
| "grad_norm": 4.494469165802002, | |
| "learning_rate": 0.00012164396139381029, | |
| "loss": 1.6348, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.021444435934747645, | |
| "grad_norm": 4.1140031814575195, | |
| "learning_rate": 0.00011736481776669306, | |
| "loss": 1.7624, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.022057134104311864, | |
| "grad_norm": 5.299776554107666, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 2.5285, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.022669832273876082, | |
| "grad_norm": 3.846937656402588, | |
| "learning_rate": 0.00010871557427476583, | |
| "loss": 1.5106, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0232825304434403, | |
| "grad_norm": 4.549310207366943, | |
| "learning_rate": 0.00010436193873653361, | |
| "loss": 1.9129, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02389522861300452, | |
| "grad_norm": 5.004308700561523, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7608, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02450792678256874, | |
| "grad_norm": 3.4253933429718018, | |
| "learning_rate": 9.563806126346642e-05, | |
| "loss": 1.4814, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.025120624952132957, | |
| "grad_norm": 4.386419773101807, | |
| "learning_rate": 9.128442572523417e-05, | |
| "loss": 1.3271, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.025733323121697176, | |
| "grad_norm": 4.444244861602783, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 1.7585, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.02634602129126139, | |
| "grad_norm": 3.8281044960021973, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 1.4, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.02695871946082561, | |
| "grad_norm": 4.207068920135498, | |
| "learning_rate": 7.835603860618972e-05, | |
| "loss": 1.7096, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.027571417630389828, | |
| "grad_norm": 4.072748184204102, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 1.5046, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.028184115799954047, | |
| "grad_norm": 4.015542030334473, | |
| "learning_rate": 6.992942004957271e-05, | |
| "loss": 1.1774, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.028796813969518265, | |
| "grad_norm": 3.9917783737182617, | |
| "learning_rate": 6.579798566743314e-05, | |
| "loss": 1.5171, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.029409512139082484, | |
| "grad_norm": 4.313107013702393, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 1.7398, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.030022210308646703, | |
| "grad_norm": 4.4379448890686035, | |
| "learning_rate": 5.773817382593008e-05, | |
| "loss": 1.2932, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03063490847821092, | |
| "grad_norm": 4.202969551086426, | |
| "learning_rate": 5.382513867649663e-05, | |
| "loss": 1.8661, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03063490847821092, | |
| "eval_loss": 1.6266911029815674, | |
| "eval_runtime": 103.2244, | |
| "eval_samples_per_second": 13.32, | |
| "eval_steps_per_second": 6.665, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03124760664777514, | |
| "grad_norm": 4.884973049163818, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.72, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.031860304817339355, | |
| "grad_norm": 3.4544296264648438, | |
| "learning_rate": 4.6270039165317605e-05, | |
| "loss": 1.2158, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.032473002986903574, | |
| "grad_norm": 4.243190288543701, | |
| "learning_rate": 4.264235636489542e-05, | |
| "loss": 1.6973, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.03308570115646779, | |
| "grad_norm": 4.426884174346924, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 1.7983, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.03369839932603201, | |
| "grad_norm": 4.506540298461914, | |
| "learning_rate": 3.5721239031346066e-05, | |
| "loss": 1.811, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.03431109749559623, | |
| "grad_norm": 3.716324806213379, | |
| "learning_rate": 3.244097923843398e-05, | |
| "loss": 1.5807, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.03492379566516045, | |
| "grad_norm": 3.674492597579956, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 1.7437, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.03553649383472467, | |
| "grad_norm": 4.3944196701049805, | |
| "learning_rate": 2.6272266318987603e-05, | |
| "loss": 1.8616, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.036149192004288885, | |
| "grad_norm": 3.621537685394287, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 1.6906, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.036761890173853104, | |
| "grad_norm": 4.570217609405518, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 1.9371, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.03737458834341732, | |
| "grad_norm": 5.0197978019714355, | |
| "learning_rate": 1.808479557110081e-05, | |
| "loss": 1.9263, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.03798728651298154, | |
| "grad_norm": 3.4639062881469727, | |
| "learning_rate": 1.566085541871145e-05, | |
| "loss": 1.4091, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.03859998468254576, | |
| "grad_norm": 3.4522595405578613, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 1.2912, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.03921268285210998, | |
| "grad_norm": 3.5978481769561768, | |
| "learning_rate": 1.129891668217783e-05, | |
| "loss": 1.2895, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.0398253810216742, | |
| "grad_norm": 3.4568052291870117, | |
| "learning_rate": 9.369221296335006e-06, | |
| "loss": 1.2123, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.040438079191238416, | |
| "grad_norm": 3.386666774749756, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 1.4917, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.041050777360802634, | |
| "grad_norm": 4.11414098739624, | |
| "learning_rate": 6.030737921409169e-06, | |
| "loss": 1.8244, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.04166347553036685, | |
| "grad_norm": 4.072088241577148, | |
| "learning_rate": 4.628304925177318e-06, | |
| "loss": 1.7772, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.04227617369993107, | |
| "grad_norm": 2.989717721939087, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 1.3807, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.04288887186949529, | |
| "grad_norm": 3.5867974758148193, | |
| "learning_rate": 2.3703992880066638e-06, | |
| "loss": 1.6627, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.04350157003905951, | |
| "grad_norm": 3.1271986961364746, | |
| "learning_rate": 1.5192246987791981e-06, | |
| "loss": 1.164, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.04411426820862373, | |
| "grad_norm": 3.63596248626709, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 1.4727, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.044726966378187946, | |
| "grad_norm": 3.8074846267700195, | |
| "learning_rate": 3.805301908254455e-07, | |
| "loss": 1.3727, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.045339664547752165, | |
| "grad_norm": 3.8898539543151855, | |
| "learning_rate": 9.517784181422019e-08, | |
| "loss": 1.2908, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.04595236271731638, | |
| "grad_norm": 3.450756311416626, | |
| "learning_rate": 0.0, | |
| "loss": 1.4413, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.04595236271731638, | |
| "eval_loss": 1.600237250328064, | |
| "eval_runtime": 103.267, | |
| "eval_samples_per_second": 13.315, | |
| "eval_steps_per_second": 6.662, | |
| "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": 2.95132603613184e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |