| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01706229871819481, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.531149359097404e-05, | |
| "eval_loss": 6.49653434753418, | |
| "eval_runtime": 24.993, | |
| "eval_samples_per_second": 197.495, | |
| "eval_steps_per_second": 98.748, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004265574679548702, | |
| "grad_norm": 1567.8310546875, | |
| "learning_rate": 5e-05, | |
| "loss": 25.8137, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008531149359097404, | |
| "grad_norm": 2653.8134765625, | |
| "learning_rate": 0.0001, | |
| "loss": 25.3498, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0012796724038646107, | |
| "grad_norm": 2208.304443359375, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 25.5912, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0017062298718194808, | |
| "grad_norm": 2064.91796875, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 25.4036, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002132787339774351, | |
| "grad_norm": 2691.767333984375, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 25.6102, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0025593448077292215, | |
| "grad_norm": 4393.1435546875, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 25.4595, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0029859022756840914, | |
| "grad_norm": 4072.7802734375, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 25.2662, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0034124597436389617, | |
| "grad_norm": 3614.854736328125, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 25.2668, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.003839017211593832, | |
| "grad_norm": 7388.755859375, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 25.6505, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.004265574679548702, | |
| "grad_norm": 11540.400390625, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 26.6081, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.004265574679548702, | |
| "eval_loss": 6.401224613189697, | |
| "eval_runtime": 24.9179, | |
| "eval_samples_per_second": 198.091, | |
| "eval_steps_per_second": 99.045, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.004692132147503573, | |
| "grad_norm": 2004.597900390625, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 25.2635, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.005118689615458443, | |
| "grad_norm": 2496.34814453125, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 25.1822, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.005545247083413313, | |
| "grad_norm": 1549.2755126953125, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 25.4265, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.005971804551368183, | |
| "grad_norm": 2729.479736328125, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 24.4902, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.006398362019323053, | |
| "grad_norm": 5030.5810546875, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 25.0997, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.006824919487277923, | |
| "grad_norm": 3562.57080078125, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 25.0119, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.007251476955232794, | |
| "grad_norm": 3101.904296875, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 25.2636, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.007678034423187664, | |
| "grad_norm": 4114.76611328125, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 25.4234, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.008104591891142534, | |
| "grad_norm": 6624.58642578125, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 25.946, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.008531149359097405, | |
| "grad_norm": 4798.064453125, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 27.8184, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.008531149359097405, | |
| "eval_loss": 6.353697776794434, | |
| "eval_runtime": 24.8164, | |
| "eval_samples_per_second": 198.901, | |
| "eval_steps_per_second": 99.451, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.008957706827052275, | |
| "grad_norm": 2077.94482421875, | |
| "learning_rate": 5e-05, | |
| "loss": 25.34, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.009384264295007145, | |
| "grad_norm": 2370.22802734375, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 25.0022, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.009810821762962016, | |
| "grad_norm": 2061.1435546875, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 24.9655, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.010237379230916886, | |
| "grad_norm": 3513.1025390625, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 24.9782, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.010663936698871756, | |
| "grad_norm": 2901.8681640625, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 25.2934, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.011090494166826627, | |
| "grad_norm": 3363.347412109375, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 25.0829, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.011517051634781495, | |
| "grad_norm": 6415.22265625, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 25.3898, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.011943609102736365, | |
| "grad_norm": 10549.6650390625, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 24.9564, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.012370166570691236, | |
| "grad_norm": 7662.0546875, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 26.0062, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.012796724038646106, | |
| "grad_norm": 9534.7734375, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 26.9008, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.012796724038646106, | |
| "eval_loss": 6.327480792999268, | |
| "eval_runtime": 24.8751, | |
| "eval_samples_per_second": 198.431, | |
| "eval_steps_per_second": 99.216, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.013223281506600976, | |
| "grad_norm": 1876.852783203125, | |
| "learning_rate": 1.3213804466343421e-05, | |
| "loss": 25.144, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.013649838974555847, | |
| "grad_norm": 2335.78271484375, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 25.2943, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.014076396442510717, | |
| "grad_norm": 3630.992919921875, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 25.1845, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.014502953910465587, | |
| "grad_norm": 2973.1572265625, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 24.594, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.014929511378420458, | |
| "grad_norm": 3634.206298828125, | |
| "learning_rate": 4.2113336672471245e-06, | |
| "loss": 24.9778, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.015356068846375328, | |
| "grad_norm": 2996.556884765625, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 25.3784, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.0157826263143302, | |
| "grad_norm": 3305.250244140625, | |
| "learning_rate": 1.5299867030334814e-06, | |
| "loss": 25.3244, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.01620918378228507, | |
| "grad_norm": 3196.305908203125, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 25.3542, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.01663574125023994, | |
| "grad_norm": 4117.81396484375, | |
| "learning_rate": 1.7077534966650766e-07, | |
| "loss": 25.4969, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.01706229871819481, | |
| "grad_norm": 7214.310546875, | |
| "learning_rate": 0.0, | |
| "loss": 26.7657, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.01706229871819481, | |
| "eval_loss": 6.330908298492432, | |
| "eval_runtime": 24.964, | |
| "eval_samples_per_second": 197.725, | |
| "eval_steps_per_second": 98.862, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 77574684278784.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |