| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.10040160642570281, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004016064257028112, | |
| "grad_norm": 0.7228589057922363, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.6631, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004016064257028112, | |
| "eval_loss": 1.0697861909866333, | |
| "eval_runtime": 32.5901, | |
| "eval_samples_per_second": 6.444, | |
| "eval_steps_per_second": 0.828, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008032128514056224, | |
| "grad_norm": 1.0123487710952759, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.6836, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.012048192771084338, | |
| "grad_norm": 1.005481481552124, | |
| "learning_rate": 6e-06, | |
| "loss": 1.9228, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01606425702811245, | |
| "grad_norm": 0.8270795941352844, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 2.45, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.020080321285140562, | |
| "grad_norm": 0.9999402165412903, | |
| "learning_rate": 1e-05, | |
| "loss": 2.668, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.024096385542168676, | |
| "grad_norm": 0.9072601199150085, | |
| "learning_rate": 1.2e-05, | |
| "loss": 1.8627, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.028112449799196786, | |
| "grad_norm": 1.1333314180374146, | |
| "learning_rate": 1.4e-05, | |
| "loss": 2.8953, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0321285140562249, | |
| "grad_norm": 0.9936800003051758, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 2.2984, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03614457831325301, | |
| "grad_norm": 0.7884902954101562, | |
| "learning_rate": 1.8e-05, | |
| "loss": 1.4, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03614457831325301, | |
| "eval_loss": 1.0618449449539185, | |
| "eval_runtime": 32.5955, | |
| "eval_samples_per_second": 6.443, | |
| "eval_steps_per_second": 0.828, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.040160642570281124, | |
| "grad_norm": 1.1049511432647705, | |
| "learning_rate": 2e-05, | |
| "loss": 2.3974, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04417670682730924, | |
| "grad_norm": 1.0087590217590332, | |
| "learning_rate": 1.999390827019096e-05, | |
| "loss": 2.1244, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04819277108433735, | |
| "grad_norm": 1.021081805229187, | |
| "learning_rate": 1.9975640502598243e-05, | |
| "loss": 1.6924, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05220883534136546, | |
| "grad_norm": 0.8872256278991699, | |
| "learning_rate": 1.9945218953682736e-05, | |
| "loss": 1.8039, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.05622489959839357, | |
| "grad_norm": 1.019092321395874, | |
| "learning_rate": 1.9902680687415704e-05, | |
| "loss": 1.8685, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.060240963855421686, | |
| "grad_norm": 1.4794679880142212, | |
| "learning_rate": 1.9848077530122083e-05, | |
| "loss": 2.1413, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0642570281124498, | |
| "grad_norm": 1.2401800155639648, | |
| "learning_rate": 1.9781476007338058e-05, | |
| "loss": 2.1287, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06827309236947791, | |
| "grad_norm": 1.0547970533370972, | |
| "learning_rate": 1.9702957262759964e-05, | |
| "loss": 1.1896, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07228915662650602, | |
| "grad_norm": 1.1523879766464233, | |
| "learning_rate": 1.961261695938319e-05, | |
| "loss": 1.5816, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07228915662650602, | |
| "eval_loss": 0.985172688961029, | |
| "eval_runtime": 32.6746, | |
| "eval_samples_per_second": 6.427, | |
| "eval_steps_per_second": 0.826, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07630522088353414, | |
| "grad_norm": 1.4140926599502563, | |
| "learning_rate": 1.9510565162951538e-05, | |
| "loss": 1.9035, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.08032128514056225, | |
| "grad_norm": 1.519662618637085, | |
| "learning_rate": 1.9396926207859085e-05, | |
| "loss": 1.9739, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08433734939759036, | |
| "grad_norm": 0.977906346321106, | |
| "learning_rate": 1.9271838545667876e-05, | |
| "loss": 1.1063, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08835341365461848, | |
| "grad_norm": 1.301216959953308, | |
| "learning_rate": 1.913545457642601e-05, | |
| "loss": 1.7746, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.09236947791164658, | |
| "grad_norm": 1.1488702297210693, | |
| "learning_rate": 1.8987940462991673e-05, | |
| "loss": 1.5895, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0963855421686747, | |
| "grad_norm": 1.351751685142517, | |
| "learning_rate": 1.8829475928589272e-05, | |
| "loss": 2.5842, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.10040160642570281, | |
| "grad_norm": 1.2297149896621704, | |
| "learning_rate": 1.866025403784439e-05, | |
| "loss": 1.935, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "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": 3.173894848512e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |