| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.011099805753399316, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00014799741004532422, | |
| "grad_norm": 25.31769561767578, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 8.1636, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014799741004532422, | |
| "eval_loss": 8.671719551086426, | |
| "eval_runtime": 262.1288, | |
| "eval_samples_per_second": 21.707, | |
| "eval_steps_per_second": 10.853, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00029599482009064844, | |
| "grad_norm": 28.9766902923584, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 8.3506, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0004439922301359726, | |
| "grad_norm": 37.51851272583008, | |
| "learning_rate": 0.0002, | |
| "loss": 7.7496, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005919896401812969, | |
| "grad_norm": 17.686782836914062, | |
| "learning_rate": 0.0001999048221581858, | |
| "loss": 6.2181, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.000739987050226621, | |
| "grad_norm": 19.165815353393555, | |
| "learning_rate": 0.00019961946980917456, | |
| "loss": 5.9745, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008879844602719452, | |
| "grad_norm": 9.92040729522705, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 4.5077, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0010359818703172695, | |
| "grad_norm": 10.178970336914062, | |
| "learning_rate": 0.00019848077530122083, | |
| "loss": 3.2111, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0011839792803625938, | |
| "grad_norm": 13.662432670593262, | |
| "learning_rate": 0.00019762960071199333, | |
| "loss": 3.2317, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0013319766904079178, | |
| "grad_norm": 10.111414909362793, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 3.1016, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001479974100453242, | |
| "grad_norm": 6.914839744567871, | |
| "learning_rate": 0.0001953716950748227, | |
| "loss": 2.0293, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0016279715104985664, | |
| "grad_norm": 11.782793998718262, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 2.6581, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0017759689205438904, | |
| "grad_norm": 7.749815464019775, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 2.3704, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0019239663305892147, | |
| "grad_norm": 31.856861114501953, | |
| "learning_rate": 0.000190630778703665, | |
| "loss": 2.5376, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002071963740634539, | |
| "grad_norm": 10.559371948242188, | |
| "learning_rate": 0.00018870108331782217, | |
| "loss": 2.3736, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.002219961150679863, | |
| "grad_norm": 5.9514665603637695, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 2.4374, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0023679585607251875, | |
| "grad_norm": 6.814925193786621, | |
| "learning_rate": 0.0001843391445812886, | |
| "loss": 2.1366, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0025159559707705116, | |
| "grad_norm": 10.532800674438477, | |
| "learning_rate": 0.0001819152044288992, | |
| "loss": 2.6406, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0026639533808158356, | |
| "grad_norm": 6.617628574371338, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 2.0348, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00281195079086116, | |
| "grad_norm": 5.439142227172852, | |
| "learning_rate": 0.0001766044443118978, | |
| "loss": 1.9106, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.002959948200906484, | |
| "grad_norm": 4.196650505065918, | |
| "learning_rate": 0.0001737277336810124, | |
| "loss": 1.7394, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0031079456109518082, | |
| "grad_norm": 6.421461582183838, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.0149, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0032559430209971327, | |
| "grad_norm": 4.891075134277344, | |
| "learning_rate": 0.00016755902076156604, | |
| "loss": 1.8183, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0034039404310424568, | |
| "grad_norm": 3.9953277111053467, | |
| "learning_rate": 0.00016427876096865394, | |
| "loss": 1.8134, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.003551937841087781, | |
| "grad_norm": 4.448080539703369, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 1.8657, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0036999352511331053, | |
| "grad_norm": 4.5448079109191895, | |
| "learning_rate": 0.0001573576436351046, | |
| "loss": 2.1479, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0036999352511331053, | |
| "eval_loss": 2.039273262023926, | |
| "eval_runtime": 262.3396, | |
| "eval_samples_per_second": 21.689, | |
| "eval_steps_per_second": 10.845, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0038479326611784294, | |
| "grad_norm": 6.708371639251709, | |
| "learning_rate": 0.0001537299608346824, | |
| "loss": 2.0388, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.003995930071223753, | |
| "grad_norm": 5.384842395782471, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.7815, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004143927481269078, | |
| "grad_norm": 5.319408416748047, | |
| "learning_rate": 0.00014617486132350343, | |
| "loss": 1.769, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.004291924891314402, | |
| "grad_norm": 5.727357387542725, | |
| "learning_rate": 0.00014226182617406996, | |
| "loss": 2.3294, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.004439922301359726, | |
| "grad_norm": 4.128015518188477, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 2.114, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0045879197114050505, | |
| "grad_norm": 4.526007175445557, | |
| "learning_rate": 0.00013420201433256689, | |
| "loss": 1.9098, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.004735917121450375, | |
| "grad_norm": 4.137485504150391, | |
| "learning_rate": 0.00013007057995042732, | |
| "loss": 1.9011, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.004883914531495699, | |
| "grad_norm": 3.771566390991211, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 1.6609, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.005031911941541023, | |
| "grad_norm": 3.3007614612579346, | |
| "learning_rate": 0.00012164396139381029, | |
| "loss": 1.6353, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.005179909351586348, | |
| "grad_norm": 4.597551345825195, | |
| "learning_rate": 0.00011736481776669306, | |
| "loss": 2.11, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.005327906761631671, | |
| "grad_norm": 3.7648379802703857, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 1.7404, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.005475904171676996, | |
| "grad_norm": 5.169516086578369, | |
| "learning_rate": 0.00010871557427476583, | |
| "loss": 1.9993, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.00562390158172232, | |
| "grad_norm": 3.914263963699341, | |
| "learning_rate": 0.00010436193873653361, | |
| "loss": 1.9136, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.005771898991767644, | |
| "grad_norm": 3.3549132347106934, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9494, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.005919896401812968, | |
| "grad_norm": 3.380098342895508, | |
| "learning_rate": 9.563806126346642e-05, | |
| "loss": 1.4687, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006067893811858293, | |
| "grad_norm": 3.6071436405181885, | |
| "learning_rate": 9.128442572523417e-05, | |
| "loss": 1.7524, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0062158912219036164, | |
| "grad_norm": 3.8395206928253174, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 1.7826, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.006363888631948941, | |
| "grad_norm": 3.7298543453216553, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 1.5537, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.006511886041994265, | |
| "grad_norm": 2.709172248840332, | |
| "learning_rate": 7.835603860618972e-05, | |
| "loss": 1.4122, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.006659883452039589, | |
| "grad_norm": 3.5382652282714844, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 1.849, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0068078808620849135, | |
| "grad_norm": 3.254901170730591, | |
| "learning_rate": 6.992942004957271e-05, | |
| "loss": 1.6019, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.006955878272130238, | |
| "grad_norm": 5.000037670135498, | |
| "learning_rate": 6.579798566743314e-05, | |
| "loss": 1.996, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.007103875682175562, | |
| "grad_norm": 4.309709548950195, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 1.955, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.007251873092220886, | |
| "grad_norm": 4.277580261230469, | |
| "learning_rate": 5.773817382593008e-05, | |
| "loss": 1.7035, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.007399870502266211, | |
| "grad_norm": 2.9081766605377197, | |
| "learning_rate": 5.382513867649663e-05, | |
| "loss": 1.6438, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007399870502266211, | |
| "eval_loss": 1.7859166860580444, | |
| "eval_runtime": 262.3802, | |
| "eval_samples_per_second": 21.686, | |
| "eval_steps_per_second": 10.843, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007547867912311534, | |
| "grad_norm": 3.295409917831421, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.53, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.007695865322356859, | |
| "grad_norm": 3.640821933746338, | |
| "learning_rate": 4.6270039165317605e-05, | |
| "loss": 1.5741, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.007843862732402182, | |
| "grad_norm": 3.3498494625091553, | |
| "learning_rate": 4.264235636489542e-05, | |
| "loss": 1.8344, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.007991860142447507, | |
| "grad_norm": 3.336550712585449, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 1.7062, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.008139857552492831, | |
| "grad_norm": 3.63503360748291, | |
| "learning_rate": 3.5721239031346066e-05, | |
| "loss": 1.9349, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.008287854962538156, | |
| "grad_norm": 5.259622573852539, | |
| "learning_rate": 3.244097923843398e-05, | |
| "loss": 1.9626, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.00843585237258348, | |
| "grad_norm": 3.1736204624176025, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 1.5769, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.008583849782628805, | |
| "grad_norm": 4.028581142425537, | |
| "learning_rate": 2.6272266318987603e-05, | |
| "loss": 1.5609, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.008731847192674128, | |
| "grad_norm": 3.3158867359161377, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 1.5602, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.008879844602719452, | |
| "grad_norm": 3.735447883605957, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 1.6289, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.009027842012764777, | |
| "grad_norm": 3.006415843963623, | |
| "learning_rate": 1.808479557110081e-05, | |
| "loss": 1.5157, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.009175839422810101, | |
| "grad_norm": 4.4025163650512695, | |
| "learning_rate": 1.566085541871145e-05, | |
| "loss": 1.8182, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.009323836832855426, | |
| "grad_norm": 3.871246337890625, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 1.6006, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.00947183424290075, | |
| "grad_norm": 4.13185453414917, | |
| "learning_rate": 1.129891668217783e-05, | |
| "loss": 1.8801, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.009619831652946073, | |
| "grad_norm": 3.3973031044006348, | |
| "learning_rate": 9.369221296335006e-06, | |
| "loss": 1.608, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.009767829062991397, | |
| "grad_norm": 3.1978251934051514, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 1.4367, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.009915826473036722, | |
| "grad_norm": 3.893763780593872, | |
| "learning_rate": 6.030737921409169e-06, | |
| "loss": 1.7755, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.010063823883082046, | |
| "grad_norm": 3.148879289627075, | |
| "learning_rate": 4.628304925177318e-06, | |
| "loss": 1.6701, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.01021182129312737, | |
| "grad_norm": 3.3002231121063232, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 1.6809, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.010359818703172695, | |
| "grad_norm": 3.7661850452423096, | |
| "learning_rate": 2.3703992880066638e-06, | |
| "loss": 1.6621, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.010507816113218018, | |
| "grad_norm": 4.00441312789917, | |
| "learning_rate": 1.5192246987791981e-06, | |
| "loss": 1.595, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.010655813523263342, | |
| "grad_norm": 3.0560474395751953, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 1.546, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.010803810933308667, | |
| "grad_norm": 4.167281627655029, | |
| "learning_rate": 3.805301908254455e-07, | |
| "loss": 1.8541, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.010951808343353991, | |
| "grad_norm": 3.4628982543945312, | |
| "learning_rate": 9.517784181422019e-08, | |
| "loss": 1.48, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.011099805753399316, | |
| "grad_norm": 3.617460012435913, | |
| "learning_rate": 0.0, | |
| "loss": 1.5994, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.011099805753399316, | |
| "eval_loss": 1.7009334564208984, | |
| "eval_runtime": 262.4084, | |
| "eval_samples_per_second": 21.684, | |
| "eval_steps_per_second": 10.842, | |
| "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": 1.54405315805184e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |