| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02796420581655481, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003728560775540641, | |
| "grad_norm": 14.098886489868164, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 14.0719, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003728560775540641, | |
| "eval_loss": 1.8703862428665161, | |
| "eval_runtime": 509.0913, | |
| "eval_samples_per_second": 4.437, | |
| "eval_steps_per_second": 2.22, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007457121551081282, | |
| "grad_norm": 17.57554054260254, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 16.0438, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011185682326621924, | |
| "grad_norm": 14.289568901062012, | |
| "learning_rate": 0.0002, | |
| "loss": 14.013, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014914243102162564, | |
| "grad_norm": 16.104290008544922, | |
| "learning_rate": 0.0001999048221581858, | |
| "loss": 12.8257, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0018642803877703207, | |
| "grad_norm": 21.064966201782227, | |
| "learning_rate": 0.00019961946980917456, | |
| "loss": 10.156, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0022371364653243847, | |
| "grad_norm": 15.340848922729492, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 7.2449, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002609992542878449, | |
| "grad_norm": 18.457630157470703, | |
| "learning_rate": 0.00019848077530122083, | |
| "loss": 6.17, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002982848620432513, | |
| "grad_norm": 13.35014820098877, | |
| "learning_rate": 0.00019762960071199333, | |
| "loss": 5.0583, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003355704697986577, | |
| "grad_norm": 32.16826629638672, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 5.1311, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0037285607755406414, | |
| "grad_norm": 19.90258026123047, | |
| "learning_rate": 0.0001953716950748227, | |
| "loss": 4.7855, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004101416853094705, | |
| "grad_norm": 19.41876792907715, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 4.0821, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0044742729306487695, | |
| "grad_norm": 32.109249114990234, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 4.0448, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004847129008202834, | |
| "grad_norm": 33.09053421020508, | |
| "learning_rate": 0.000190630778703665, | |
| "loss": 5.074, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005219985085756898, | |
| "grad_norm": 12.651711463928223, | |
| "learning_rate": 0.00018870108331782217, | |
| "loss": 3.5618, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005592841163310962, | |
| "grad_norm": 10.729059219360352, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 2.2738, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005965697240865026, | |
| "grad_norm": 17.2890567779541, | |
| "learning_rate": 0.0001843391445812886, | |
| "loss": 2.7353, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00633855331841909, | |
| "grad_norm": 23.347806930541992, | |
| "learning_rate": 0.0001819152044288992, | |
| "loss": 2.7702, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006711409395973154, | |
| "grad_norm": 22.53374481201172, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 3.9281, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0070842654735272185, | |
| "grad_norm": 7.728074550628662, | |
| "learning_rate": 0.0001766044443118978, | |
| "loss": 2.3155, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.007457121551081283, | |
| "grad_norm": 11.007797241210938, | |
| "learning_rate": 0.0001737277336810124, | |
| "loss": 2.4846, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007829977628635347, | |
| "grad_norm": 7.158455848693848, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.9451, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00820283370618941, | |
| "grad_norm": 7.924790382385254, | |
| "learning_rate": 0.00016755902076156604, | |
| "loss": 1.974, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.008575689783743476, | |
| "grad_norm": 10.626357078552246, | |
| "learning_rate": 0.00016427876096865394, | |
| "loss": 2.9784, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.008948545861297539, | |
| "grad_norm": 8.380443572998047, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 1.9285, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.009321401938851604, | |
| "grad_norm": 8.995612144470215, | |
| "learning_rate": 0.0001573576436351046, | |
| "loss": 2.5047, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.009321401938851604, | |
| "eval_loss": 0.322700172662735, | |
| "eval_runtime": 512.0454, | |
| "eval_samples_per_second": 4.412, | |
| "eval_steps_per_second": 2.207, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.009694258016405667, | |
| "grad_norm": 18.933256149291992, | |
| "learning_rate": 0.0001537299608346824, | |
| "loss": 3.038, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.010067114093959731, | |
| "grad_norm": 8.585943222045898, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 2.5117, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.010439970171513796, | |
| "grad_norm": 10.232223510742188, | |
| "learning_rate": 0.00014617486132350343, | |
| "loss": 2.5074, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.01081282624906786, | |
| "grad_norm": 8.64398193359375, | |
| "learning_rate": 0.00014226182617406996, | |
| "loss": 2.9964, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.011185682326621925, | |
| "grad_norm": 11.656851768493652, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 2.8767, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.011558538404175988, | |
| "grad_norm": 7.217341423034668, | |
| "learning_rate": 0.00013420201433256689, | |
| "loss": 1.8044, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.011931394481730051, | |
| "grad_norm": 8.281699180603027, | |
| "learning_rate": 0.00013007057995042732, | |
| "loss": 2.0798, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.012304250559284116, | |
| "grad_norm": 12.387796401977539, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 3.5874, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.01267710663683818, | |
| "grad_norm": 9.76694107055664, | |
| "learning_rate": 0.00012164396139381029, | |
| "loss": 2.8491, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.013049962714392245, | |
| "grad_norm": 7.733439922332764, | |
| "learning_rate": 0.00011736481776669306, | |
| "loss": 2.16, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.013422818791946308, | |
| "grad_norm": 6.12880277633667, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 2.0449, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.013795674869500374, | |
| "grad_norm": 6.441651821136475, | |
| "learning_rate": 0.00010871557427476583, | |
| "loss": 1.8501, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.014168530947054437, | |
| "grad_norm": 15.817225456237793, | |
| "learning_rate": 0.00010436193873653361, | |
| "loss": 2.776, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0145413870246085, | |
| "grad_norm": 8.889180183410645, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1201, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.014914243102162566, | |
| "grad_norm": 4.129387855529785, | |
| "learning_rate": 9.563806126346642e-05, | |
| "loss": 1.448, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.015287099179716629, | |
| "grad_norm": 9.360006332397461, | |
| "learning_rate": 9.128442572523417e-05, | |
| "loss": 2.4102, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.015659955257270694, | |
| "grad_norm": 11.799320220947266, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 2.9307, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.01603281133482476, | |
| "grad_norm": 6.900726318359375, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 1.3355, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.01640566741237882, | |
| "grad_norm": 6.313440322875977, | |
| "learning_rate": 7.835603860618972e-05, | |
| "loss": 1.6515, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.016778523489932886, | |
| "grad_norm": 8.934613227844238, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 2.0291, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01715137956748695, | |
| "grad_norm": 9.353364944458008, | |
| "learning_rate": 6.992942004957271e-05, | |
| "loss": 1.9863, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.017524235645041013, | |
| "grad_norm": 8.81008243560791, | |
| "learning_rate": 6.579798566743314e-05, | |
| "loss": 1.7731, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.017897091722595078, | |
| "grad_norm": 11.235795974731445, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 1.6917, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.018269947800149143, | |
| "grad_norm": 8.671363830566406, | |
| "learning_rate": 5.773817382593008e-05, | |
| "loss": 2.321, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.018642803877703208, | |
| "grad_norm": 6.4699578285217285, | |
| "learning_rate": 5.382513867649663e-05, | |
| "loss": 1.7027, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.018642803877703208, | |
| "eval_loss": 0.25740864872932434, | |
| "eval_runtime": 511.7924, | |
| "eval_samples_per_second": 4.414, | |
| "eval_steps_per_second": 2.208, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01901565995525727, | |
| "grad_norm": 9.196285247802734, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.7973, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.019388516032811335, | |
| "grad_norm": 6.420137882232666, | |
| "learning_rate": 4.6270039165317605e-05, | |
| "loss": 1.7155, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.0197613721103654, | |
| "grad_norm": 6.166407585144043, | |
| "learning_rate": 4.264235636489542e-05, | |
| "loss": 1.1948, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.020134228187919462, | |
| "grad_norm": 7.9364776611328125, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 2.2336, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.020507084265473527, | |
| "grad_norm": 6.744062900543213, | |
| "learning_rate": 3.5721239031346066e-05, | |
| "loss": 2.0732, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.020879940343027592, | |
| "grad_norm": 6.412101745605469, | |
| "learning_rate": 3.244097923843398e-05, | |
| "loss": 2.3604, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.021252796420581657, | |
| "grad_norm": 7.558949947357178, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 1.5866, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.02162565249813572, | |
| "grad_norm": 5.778247356414795, | |
| "learning_rate": 2.6272266318987603e-05, | |
| "loss": 2.12, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.021998508575689784, | |
| "grad_norm": 9.419931411743164, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 2.0553, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.02237136465324385, | |
| "grad_norm": 7.691293716430664, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 2.2256, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.02274422073079791, | |
| "grad_norm": 6.940426826477051, | |
| "learning_rate": 1.808479557110081e-05, | |
| "loss": 2.3064, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.023117076808351976, | |
| "grad_norm": 8.362802505493164, | |
| "learning_rate": 1.566085541871145e-05, | |
| "loss": 2.308, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.02348993288590604, | |
| "grad_norm": 6.858037948608398, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 1.7986, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.023862788963460103, | |
| "grad_norm": 8.502093315124512, | |
| "learning_rate": 1.129891668217783e-05, | |
| "loss": 2.4218, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.024235645041014168, | |
| "grad_norm": 4.750255584716797, | |
| "learning_rate": 9.369221296335006e-06, | |
| "loss": 1.1287, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.024608501118568233, | |
| "grad_norm": 6.325159072875977, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 1.961, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.024981357196122298, | |
| "grad_norm": 5.899595737457275, | |
| "learning_rate": 6.030737921409169e-06, | |
| "loss": 1.5426, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.02535421327367636, | |
| "grad_norm": 9.170677185058594, | |
| "learning_rate": 4.628304925177318e-06, | |
| "loss": 2.2986, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.025727069351230425, | |
| "grad_norm": 11.1466646194458, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 1.9698, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.02609992542878449, | |
| "grad_norm": 5.2693190574646, | |
| "learning_rate": 2.3703992880066638e-06, | |
| "loss": 1.1575, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.02647278150633855, | |
| "grad_norm": 17.38636016845703, | |
| "learning_rate": 1.5192246987791981e-06, | |
| "loss": 2.5558, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.026845637583892617, | |
| "grad_norm": 7.246407985687256, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 2.2891, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.027218493661446682, | |
| "grad_norm": 11.300233840942383, | |
| "learning_rate": 3.805301908254455e-07, | |
| "loss": 2.0134, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.027591349739000747, | |
| "grad_norm": 7.813751220703125, | |
| "learning_rate": 9.517784181422019e-08, | |
| "loss": 2.4345, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.02796420581655481, | |
| "grad_norm": 9.342615127563477, | |
| "learning_rate": 0.0, | |
| "loss": 1.7863, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.02796420581655481, | |
| "eval_loss": 0.2411356121301651, | |
| "eval_runtime": 511.7025, | |
| "eval_samples_per_second": 4.415, | |
| "eval_steps_per_second": 2.208, | |
| "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": 1.9043369091072e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |