| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.49782202862476665, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002489110143123833, | |
| "eval_loss": 0.9195066690444946, | |
| "eval_runtime": 23.3565, | |
| "eval_samples_per_second": 7.278, | |
| "eval_steps_per_second": 3.639, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012445550715619166, | |
| "grad_norm": 0.41516172885894775, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8405, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.024891101431238332, | |
| "grad_norm": 0.49069398641586304, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8555, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.037336652146857496, | |
| "grad_norm": 0.47838833928108215, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 0.7939, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.049782202862476664, | |
| "grad_norm": 0.4284229874610901, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 0.7633, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06222775357809583, | |
| "grad_norm": 0.4661514163017273, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 0.7344, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07467330429371499, | |
| "grad_norm": 0.4893603026866913, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 0.7194, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08711885500933417, | |
| "grad_norm": 0.43292248249053955, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 0.7006, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09956440572495333, | |
| "grad_norm": 0.4947017431259155, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 0.6679, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11200995644057249, | |
| "grad_norm": 0.5688303709030151, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 0.6997, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.12445550715619166, | |
| "grad_norm": 0.49916303157806396, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 0.6653, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12445550715619166, | |
| "eval_loss": 0.6964214444160461, | |
| "eval_runtime": 23.7165, | |
| "eval_samples_per_second": 7.168, | |
| "eval_steps_per_second": 3.584, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13690105787181084, | |
| "grad_norm": 0.4102873206138611, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 0.6598, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.14934660858742999, | |
| "grad_norm": 0.38202807307243347, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 0.6622, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16179215930304916, | |
| "grad_norm": 0.4209064543247223, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 0.685, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.17423771001866833, | |
| "grad_norm": 0.38724252581596375, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 0.6239, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18668326073428748, | |
| "grad_norm": 0.4439085125923157, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 0.6336, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.19912881144990666, | |
| "grad_norm": 0.4706352651119232, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 0.6483, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.21157436216552583, | |
| "grad_norm": 0.44686415791511536, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 0.6689, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.22401991288114498, | |
| "grad_norm": 0.49500492215156555, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 0.6494, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.23646546359676415, | |
| "grad_norm": 0.5114937424659729, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 0.6358, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.24891101431238333, | |
| "grad_norm": 0.6060147285461426, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 0.6285, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.24891101431238333, | |
| "eval_loss": 0.6684794425964355, | |
| "eval_runtime": 23.6998, | |
| "eval_samples_per_second": 7.173, | |
| "eval_steps_per_second": 3.587, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2613565650280025, | |
| "grad_norm": 0.43980181217193604, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6639, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.2738021157436217, | |
| "grad_norm": 0.4440387189388275, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 0.6516, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2862476664592408, | |
| "grad_norm": 0.4302665591239929, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 0.675, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.29869321717485997, | |
| "grad_norm": 0.4859161972999573, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 0.6562, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3111387678904792, | |
| "grad_norm": 0.44831597805023193, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 0.6431, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.3235843186060983, | |
| "grad_norm": 0.45944055914878845, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 0.6367, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.33602986932171747, | |
| "grad_norm": 0.47598645091056824, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 0.6474, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.34847542003733667, | |
| "grad_norm": 0.4957188367843628, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 0.6438, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3609209707529558, | |
| "grad_norm": 0.5611866116523743, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 0.6454, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.37336652146857496, | |
| "grad_norm": 0.6384820938110352, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 0.6355, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.37336652146857496, | |
| "eval_loss": 0.6559966206550598, | |
| "eval_runtime": 23.6939, | |
| "eval_samples_per_second": 7.175, | |
| "eval_steps_per_second": 3.587, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.38581207218419417, | |
| "grad_norm": 0.4370613396167755, | |
| "learning_rate": 1.3213804466343421e-05, | |
| "loss": 0.6334, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.3982576228998133, | |
| "grad_norm": 0.4466401934623718, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 0.66, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.41070317361543246, | |
| "grad_norm": 0.4662153422832489, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 0.6684, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.42314872433105166, | |
| "grad_norm": 0.4657689034938812, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 0.6395, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.4355942750466708, | |
| "grad_norm": 0.4475195109844208, | |
| "learning_rate": 4.2113336672471245e-06, | |
| "loss": 0.6324, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.44803982576228996, | |
| "grad_norm": 0.5021995306015015, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 0.6082, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.46048537647790916, | |
| "grad_norm": 0.5292969942092896, | |
| "learning_rate": 1.5299867030334814e-06, | |
| "loss": 0.6197, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.4729309271935283, | |
| "grad_norm": 0.512756884098053, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 0.6318, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.48537647790914745, | |
| "grad_norm": 0.5493020415306091, | |
| "learning_rate": 1.7077534966650766e-07, | |
| "loss": 0.6164, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.49782202862476665, | |
| "grad_norm": 0.6884523034095764, | |
| "learning_rate": 0.0, | |
| "loss": 0.61, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.49782202862476665, | |
| "eval_loss": 0.651942789554596, | |
| "eval_runtime": 23.7036, | |
| "eval_samples_per_second": 7.172, | |
| "eval_steps_per_second": 3.586, | |
| "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": 1.295500028411904e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |