| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.09385265133740028, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003754106053496011, | |
| "grad_norm": 5.032824516296387, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 10.732, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003754106053496011, | |
| "eval_loss": 10.386579513549805, | |
| "eval_runtime": 23.6744, | |
| "eval_samples_per_second": 9.504, | |
| "eval_steps_per_second": 4.773, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007508212106992022, | |
| "grad_norm": 4.45830774307251, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 10.1977, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.011262318160488035, | |
| "grad_norm": 4.931914806365967, | |
| "learning_rate": 0.0001, | |
| "loss": 10.4683, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.015016424213984044, | |
| "grad_norm": 5.310385227203369, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 10.0276, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.018770530267480056, | |
| "grad_norm": 5.923955917358398, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 8.8427, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02252463632097607, | |
| "grad_norm": 6.323431015014648, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 8.1762, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02627874237447208, | |
| "grad_norm": 7.335643291473389, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 6.8706, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03003284842796809, | |
| "grad_norm": 8.605307579040527, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 5.6587, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0337869544814641, | |
| "grad_norm": 8.2649564743042, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 4.7449, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03754106053496011, | |
| "grad_norm": 8.937447547912598, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 3.5373, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.041295166588456125, | |
| "grad_norm": 7.276700019836426, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 2.5148, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04504927264195214, | |
| "grad_norm": 6.3739237785339355, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.8054, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.048803378695448145, | |
| "grad_norm": 9.503493309020996, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 1.4151, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.05255748474894416, | |
| "grad_norm": 7.375895977020264, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 1.3681, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05631159080244017, | |
| "grad_norm": 5.152674674987793, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.6395, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06006569685593618, | |
| "grad_norm": 3.77114200592041, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 0.529, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06381980290943219, | |
| "grad_norm": 5.566516876220703, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 1.0785, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0675739089629282, | |
| "grad_norm": 6.849836826324463, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.4344, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07132801501642422, | |
| "grad_norm": 1.5408703088760376, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.2114, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.07508212106992022, | |
| "grad_norm": 4.369248390197754, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 0.4968, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07883622712341623, | |
| "grad_norm": 7.375030040740967, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6239, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08259033317691225, | |
| "grad_norm": 3.9516844749450684, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 0.2511, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.08634443923040826, | |
| "grad_norm": 12.229116439819336, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.3429, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.09009854528390428, | |
| "grad_norm": 5.0463337898254395, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.156, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09385265133740028, | |
| "grad_norm": 6.648087978363037, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 0.1689, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09385265133740028, | |
| "eval_loss": 0.1127062663435936, | |
| "eval_runtime": 23.1821, | |
| "eval_samples_per_second": 9.706, | |
| "eval_steps_per_second": 4.874, | |
| "step": 25 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.49519346663424e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |