| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 40, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.09427768311273457, | |
| "learning_rate": 0.0, | |
| "loss": 1.855, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.09778659963968744, | |
| "learning_rate": 0.0005, | |
| "loss": 1.9926, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.12674692464296522, | |
| "learning_rate": 0.0004991893270335525, | |
| "loss": 1.9287, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.12674692464296522, | |
| "learning_rate": 0.0004967625656594782, | |
| "loss": 1.8474, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 0.36642915731116843, | |
| "learning_rate": 0.000492735454356513, | |
| "loss": 1.7066, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.6400000000000001, | |
| "grad_norm": 0.2438134233289673, | |
| "learning_rate": 0.00048713411048678635, | |
| "loss": 1.7842, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 4.8082003549998875, | |
| "learning_rate": 0.0004799948609147061, | |
| "loss": 1.9638, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 4.8082003549998875, | |
| "learning_rate": 0.00047136400641330245, | |
| "loss": 1.4371, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "grad_norm": 0.754644989928602, | |
| "learning_rate": 0.00046129752138594874, | |
| "loss": 1.5702, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "grad_norm": 0.417785191148716, | |
| "learning_rate": 0.0004498606908508753, | |
| "loss": 1.5766, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "grad_norm": 0.38965423086075246, | |
| "learning_rate": 0.00043712768704277526, | |
| "loss": 1.6673, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.38965423086075246, | |
| "learning_rate": 0.00042318108837739987, | |
| "loss": 0.9923, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "grad_norm": 0.7188928421966629, | |
| "learning_rate": 0.0004081113438988443, | |
| "loss": 1.3999, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "grad_norm": 0.33670324960252385, | |
| "learning_rate": 0.00039201618668278893, | |
| "loss": 1.3814, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "grad_norm": 0.8523334225631511, | |
| "learning_rate": 0.000375, | |
| "loss": 1.5521, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.8523334225631511, | |
| "learning_rate": 0.0003571731403507635, | |
| "loss": 0.5314, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "grad_norm": 0.9203487384340774, | |
| "learning_rate": 0.0003386512217606339, | |
| "loss": 1.2162, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "grad_norm": 0.3844738769917824, | |
| "learning_rate": 0.00031955436597911317, | |
| "loss": 1.1437, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "grad_norm": 0.42543839777774844, | |
| "learning_rate": 0.00030000642344401115, | |
| "loss": 1.3204, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.42543839777774844, | |
| "learning_rate": 0.0002801341700638307, | |
| "loss": 0.2303, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "grad_norm": 0.5954782183138615, | |
| "learning_rate": 0.0002600664850273538, | |
| "loss": 1.0226, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "grad_norm": 0.3578324027806071, | |
| "learning_rate": 0.0002399335149726463, | |
| "loss": 0.9033, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "grad_norm": 0.3087513406734602, | |
| "learning_rate": 0.00021986582993616926, | |
| "loss": 1.1052, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.3087513406734602, | |
| "learning_rate": 0.00019999357655598894, | |
| "loss": 0.0874, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 6.32, | |
| "grad_norm": 0.5415808858308819, | |
| "learning_rate": 0.00018044563402088684, | |
| "loss": 0.8196, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "grad_norm": 0.4637990119991802, | |
| "learning_rate": 0.00016134877823936609, | |
| "loss": 0.7204, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "grad_norm": 0.3474152048127694, | |
| "learning_rate": 0.00014282685964923643, | |
| "loss": 0.9226, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 0.3474152048127694, | |
| "learning_rate": 0.00012500000000000006, | |
| "loss": 0.0373, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "grad_norm": 0.4807748949297924, | |
| "learning_rate": 0.00010798381331721108, | |
| "loss": 0.6355, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "grad_norm": 0.34627613444713096, | |
| "learning_rate": 9.18886561011557e-05, | |
| "loss": 0.5716, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "grad_norm": 0.3283871089314191, | |
| "learning_rate": 7.681891162260016e-05, | |
| "loss": 0.7817, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.39552696145395244, | |
| "learning_rate": 6.28723129572247e-05, | |
| "loss": 0.0173, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "grad_norm": 0.3739147314715054, | |
| "learning_rate": 5.013930914912476e-05, | |
| "loss": 0.5251, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "grad_norm": 0.34909539841860754, | |
| "learning_rate": 3.870247861405135e-05, | |
| "loss": 0.4799, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "grad_norm": 0.351398312323561, | |
| "learning_rate": 2.863599358669755e-05, | |
| "loss": 0.69, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 0.351398312323561, | |
| "learning_rate": 2.0005139085293944e-05, | |
| "loss": 0.0119, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "grad_norm": 0.3420837234101173, | |
| "learning_rate": 1.286588951321363e-05, | |
| "loss": 0.4581, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 9.64, | |
| "grad_norm": 0.31158076013727876, | |
| "learning_rate": 7.2645456434869975e-06, | |
| "loss": 0.4337, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 9.96, | |
| "grad_norm": 0.3480780673204436, | |
| "learning_rate": 3.2374343405217886e-06, | |
| "loss": 0.6543, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.3480780673204436, | |
| "learning_rate": 8.106729664475177e-07, | |
| "loss": 0.0109, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 40, | |
| "total_flos": 80308774895616.0, | |
| "train_loss": 0.9996304717613385, | |
| "train_runtime": 1628.4466, | |
| "train_samples_per_second": 0.608, | |
| "train_steps_per_second": 0.025 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 40, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 80308774895616.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |