| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0060779189205616, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000121558378411232, | |
| "grad_norm": 1.3522109985351562, | |
| "learning_rate": 2e-05, | |
| "loss": 9.0768, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000121558378411232, | |
| "eval_loss": 2.5203659534454346, | |
| "eval_runtime": 130.544, | |
| "eval_samples_per_second": 26.535, | |
| "eval_steps_per_second": 13.268, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000243116756822464, | |
| "grad_norm": 0.9176049828529358, | |
| "learning_rate": 4e-05, | |
| "loss": 8.9894, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000364675135233696, | |
| "grad_norm": 1.0146596431732178, | |
| "learning_rate": 6e-05, | |
| "loss": 9.935, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000486233513644928, | |
| "grad_norm": 1.0469788312911987, | |
| "learning_rate": 8e-05, | |
| "loss": 9.3424, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00060779189205616, | |
| "grad_norm": 0.8254321813583374, | |
| "learning_rate": 0.0001, | |
| "loss": 8.339, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000729350270467392, | |
| "grad_norm": 1.032138705253601, | |
| "learning_rate": 0.00012, | |
| "loss": 9.6692, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000850908648878624, | |
| "grad_norm": 1.692064881324768, | |
| "learning_rate": 0.00014, | |
| "loss": 9.8725, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.000972467027289856, | |
| "grad_norm": 1.5163041353225708, | |
| "learning_rate": 0.00016, | |
| "loss": 9.3607, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001094025405701088, | |
| "grad_norm": 3.152874231338501, | |
| "learning_rate": 0.00018, | |
| "loss": 9.9624, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00121558378411232, | |
| "grad_norm": 1.7264574766159058, | |
| "learning_rate": 0.0002, | |
| "loss": 10.4001, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0013371421625235518, | |
| "grad_norm": 4.396702766418457, | |
| "learning_rate": 0.0001999863304992469, | |
| "loss": 8.8946, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.001458700540934784, | |
| "grad_norm": 1.9022140502929688, | |
| "learning_rate": 0.00019994532573409262, | |
| "loss": 10.3819, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.001580258919346016, | |
| "grad_norm": 2.1845006942749023, | |
| "learning_rate": 0.00019987699691483048, | |
| "loss": 9.6356, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.001701817297757248, | |
| "grad_norm": 2.10140061378479, | |
| "learning_rate": 0.00019978136272187747, | |
| "loss": 9.6127, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0018233756761684798, | |
| "grad_norm": 2.068610668182373, | |
| "learning_rate": 0.000199658449300667, | |
| "loss": 11.08, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.001944934054579712, | |
| "grad_norm": 3.655803680419922, | |
| "learning_rate": 0.00019950829025450114, | |
| "loss": 10.0545, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002066492432990944, | |
| "grad_norm": 1.8618426322937012, | |
| "learning_rate": 0.00019933092663536382, | |
| "loss": 9.6545, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.002188050811402176, | |
| "grad_norm": 1.8773517608642578, | |
| "learning_rate": 0.00019912640693269752, | |
| "loss": 7.7819, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.002309609189813408, | |
| "grad_norm": 2.198024272918701, | |
| "learning_rate": 0.00019889478706014687, | |
| "loss": 9.8384, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00243116756822464, | |
| "grad_norm": 2.1132476329803467, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 8.5882, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0025527259466358717, | |
| "grad_norm": 2.646947145462036, | |
| "learning_rate": 0.00019835050748723824, | |
| "loss": 9.4244, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0026742843250471037, | |
| "grad_norm": 2.169708728790283, | |
| "learning_rate": 0.00019803799658748094, | |
| "loss": 8.9, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.002795842703458336, | |
| "grad_norm": 4.217128276824951, | |
| "learning_rate": 0.00019769868307835994, | |
| "loss": 8.5476, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.002917401081869568, | |
| "grad_norm": 1.9587572813034058, | |
| "learning_rate": 0.0001973326597248006, | |
| "loss": 9.5256, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0030389594602808, | |
| "grad_norm": 4.422936916351318, | |
| "learning_rate": 0.00019694002659393305, | |
| "loss": 8.403, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.003160517838692032, | |
| "grad_norm": 1.6125566959381104, | |
| "learning_rate": 0.00019652089102773488, | |
| "loss": 9.2696, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.003282076217103264, | |
| "grad_norm": 1.9092199802398682, | |
| "learning_rate": 0.00019607536761368484, | |
| "loss": 9.0772, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.003403634595514496, | |
| "grad_norm": 3.2192418575286865, | |
| "learning_rate": 0.00019560357815343577, | |
| "loss": 9.7968, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0035251929739257277, | |
| "grad_norm": 2.5830280780792236, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 9.7017, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0036467513523369597, | |
| "grad_norm": 2.7067151069641113, | |
| "learning_rate": 0.00019458172417006347, | |
| "loss": 10.3412, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0037683097307481916, | |
| "grad_norm": 3.9291067123413086, | |
| "learning_rate": 0.00019403193901161613, | |
| "loss": 9.8539, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.003889868109159424, | |
| "grad_norm": 1.7529088258743286, | |
| "learning_rate": 0.0001934564464599461, | |
| "loss": 8.7478, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.004011426487570656, | |
| "grad_norm": 1.7117114067077637, | |
| "learning_rate": 0.00019285540384897073, | |
| "loss": 8.765, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.004132984865981888, | |
| "grad_norm": 1.856972575187683, | |
| "learning_rate": 0.00019222897549773848, | |
| "loss": 9.777, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.00425454324439312, | |
| "grad_norm": 2.3596813678741455, | |
| "learning_rate": 0.00019157733266550575, | |
| "loss": 9.5862, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.004376101622804352, | |
| "grad_norm": 2.5083954334259033, | |
| "learning_rate": 0.00019090065350491626, | |
| "loss": 9.3247, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.004497660001215584, | |
| "grad_norm": 1.3706068992614746, | |
| "learning_rate": 0.00019019912301329592, | |
| "loss": 9.3214, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.004619218379626816, | |
| "grad_norm": 1.7020275592803955, | |
| "learning_rate": 0.00018947293298207635, | |
| "loss": 8.5611, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.004740776758038048, | |
| "grad_norm": 1.8647181987762451, | |
| "learning_rate": 0.0001887222819443612, | |
| "loss": 9.9951, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.00486233513644928, | |
| "grad_norm": 2.506580352783203, | |
| "learning_rate": 0.0001879473751206489, | |
| "loss": 9.6237, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0049838935148605115, | |
| "grad_norm": 1.9629899263381958, | |
| "learning_rate": 0.00018714842436272773, | |
| "loss": 9.371, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0051054518932717435, | |
| "grad_norm": 2.3143656253814697, | |
| "learning_rate": 0.00018632564809575742, | |
| "loss": 9.235, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.005227010271682975, | |
| "grad_norm": 2.5331368446350098, | |
| "learning_rate": 0.0001854792712585539, | |
| "loss": 10.1562, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.005348568650094207, | |
| "grad_norm": 4.555860996246338, | |
| "learning_rate": 0.00018460952524209355, | |
| "loss": 8.2419, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.005470127028505439, | |
| "grad_norm": 1.6661875247955322, | |
| "learning_rate": 0.00018371664782625287, | |
| "loss": 8.2566, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.005591685406916672, | |
| "grad_norm": 1.7546186447143555, | |
| "learning_rate": 0.00018280088311480201, | |
| "loss": 9.1446, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.005713243785327904, | |
| "grad_norm": 1.751132845878601, | |
| "learning_rate": 0.00018186248146866927, | |
| "loss": 8.6259, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.005834802163739136, | |
| "grad_norm": 2.203023672103882, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 9.3622, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.005956360542150368, | |
| "grad_norm": 2.7363836765289307, | |
| "learning_rate": 0.0001799187996894925, | |
| "loss": 8.0726, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0060779189205616, | |
| "grad_norm": 2.010042905807495, | |
| "learning_rate": 0.00017891405093963938, | |
| "loss": 9.8848, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0060779189205616, | |
| "eval_loss": 2.22426700592041, | |
| "eval_runtime": 130.4637, | |
| "eval_samples_per_second": 26.551, | |
| "eval_steps_per_second": 13.276, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9283870679629824.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |