| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9972714870395634, | |
| "eval_steps": 500, | |
| "global_step": 366, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.054570259208731244, | |
| "grad_norm": 2.4109368924528636, | |
| "learning_rate": 2.702702702702703e-06, | |
| "loss": 0.7385, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10914051841746249, | |
| "grad_norm": 1.411542387667167, | |
| "learning_rate": 5.405405405405406e-06, | |
| "loss": 0.6258, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.16371077762619374, | |
| "grad_norm": 1.1090603733773723, | |
| "learning_rate": 8.108108108108109e-06, | |
| "loss": 0.5777, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21828103683492497, | |
| "grad_norm": 1.0114013426864816, | |
| "learning_rate": 9.997948550797227e-06, | |
| "loss": 0.5768, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2728512960436562, | |
| "grad_norm": 1.0925544693817912, | |
| "learning_rate": 9.961525153583327e-06, | |
| "loss": 0.5571, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3274215552523875, | |
| "grad_norm": 1.1229468005660994, | |
| "learning_rate": 9.879896064123961e-06, | |
| "loss": 0.5579, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3819918144611187, | |
| "grad_norm": 1.1457306310920201, | |
| "learning_rate": 9.75380502539778e-06, | |
| "loss": 0.5437, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.43656207366984995, | |
| "grad_norm": 1.0550317300389418, | |
| "learning_rate": 9.584400884284546e-06, | |
| "loss": 0.5459, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.49113233287858116, | |
| "grad_norm": 1.1312778139498736, | |
| "learning_rate": 9.373227124134888e-06, | |
| "loss": 0.5455, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5457025920873124, | |
| "grad_norm": 1.0356499530726737, | |
| "learning_rate": 9.122207801708802e-06, | |
| "loss": 0.5388, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6002728512960437, | |
| "grad_norm": 1.0985324135142938, | |
| "learning_rate": 8.833630016614976e-06, | |
| "loss": 0.5489, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.654843110504775, | |
| "grad_norm": 1.1083844896783392, | |
| "learning_rate": 8.51012307297624e-06, | |
| "loss": 0.5442, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7094133697135061, | |
| "grad_norm": 1.0400224538030558, | |
| "learning_rate": 8.154634523184389e-06, | |
| "loss": 0.5359, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.7639836289222374, | |
| "grad_norm": 1.0744202310569617, | |
| "learning_rate": 7.77040331201572e-06, | |
| "loss": 0.5318, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.8185538881309686, | |
| "grad_norm": 1.0968285492605718, | |
| "learning_rate": 7.360930265797934e-06, | |
| "loss": 0.5323, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.8731241473396999, | |
| "grad_norm": 1.021879688858344, | |
| "learning_rate": 6.929946195508933e-06, | |
| "loss": 0.5171, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.927694406548431, | |
| "grad_norm": 1.0678204884195794, | |
| "learning_rate": 6.481377904428171e-06, | |
| "loss": 0.5234, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.9822646657571623, | |
| "grad_norm": 0.9343628148722539, | |
| "learning_rate": 6.019312410053286e-06, | |
| "loss": 0.5209, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.0368349249658937, | |
| "grad_norm": 1.2427110143315105, | |
| "learning_rate": 5.547959706265068e-06, | |
| "loss": 0.4878, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0914051841746248, | |
| "grad_norm": 1.0091906053534088, | |
| "learning_rate": 5.071614405023938e-06, | |
| "loss": 0.4144, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.145975443383356, | |
| "grad_norm": 1.007806012878209, | |
| "learning_rate": 4.594616607090028e-06, | |
| "loss": 0.4102, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.2005457025920874, | |
| "grad_norm": 0.9761625285978685, | |
| "learning_rate": 4.121312358283464e-06, | |
| "loss": 0.3954, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.2551159618008185, | |
| "grad_norm": 0.9057196288186306, | |
| "learning_rate": 3.656014051577713e-06, | |
| "loss": 0.4026, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.30968622100955, | |
| "grad_norm": 0.9923780381040166, | |
| "learning_rate": 3.202961135812437e-06, | |
| "loss": 0.4061, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.364256480218281, | |
| "grad_norm": 0.9366887214418035, | |
| "learning_rate": 2.766281489018482e-06, | |
| "loss": 0.4072, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.4188267394270122, | |
| "grad_norm": 0.9615122411717134, | |
| "learning_rate": 2.3499538082923607e-06, | |
| "loss": 0.4081, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.4733969986357436, | |
| "grad_norm": 0.9926176178093427, | |
| "learning_rate": 1.9577713588953797e-06, | |
| "loss": 0.4033, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.5279672578444747, | |
| "grad_norm": 0.940790518539519, | |
| "learning_rate": 1.5933074128684333e-06, | |
| "loss": 0.4045, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.5825375170532059, | |
| "grad_norm": 0.9731821866758915, | |
| "learning_rate": 1.2598826920598773e-06, | |
| "loss": 0.4101, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.6371077762619373, | |
| "grad_norm": 0.9806874432871104, | |
| "learning_rate": 9.605351122011308e-07, | |
| "loss": 0.4028, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.6916780354706686, | |
| "grad_norm": 0.9218297203583149, | |
| "learning_rate": 6.979921036993042e-07, | |
| "loss": 0.4015, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.7462482946793996, | |
| "grad_norm": 0.9247290967153217, | |
| "learning_rate": 4.7464576133899043e-07, | |
| "loss": 0.3958, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.800818553888131, | |
| "grad_norm": 0.9418425606930034, | |
| "learning_rate": 2.925310493105099e-07, | |
| "loss": 0.4015, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.8553888130968623, | |
| "grad_norm": 0.9321370632360508, | |
| "learning_rate": 1.5330726014397668e-07, | |
| "loss": 0.3974, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.9099590723055935, | |
| "grad_norm": 0.9562537189946939, | |
| "learning_rate": 5.824289648152126e-08, | |
| "loss": 0.3824, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.9645293315143246, | |
| "grad_norm": 0.9275908894260719, | |
| "learning_rate": 8.204113433559202e-09, | |
| "loss": 0.4059, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.9972714870395634, | |
| "step": 366, | |
| "total_flos": 53584849797120.0, | |
| "train_loss": 0.48227007988372134, | |
| "train_runtime": 1900.9535, | |
| "train_samples_per_second": 24.658, | |
| "train_steps_per_second": 0.193 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 366, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 53584849797120.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |