| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.504424778761062, | |
| "eval_steps": 500, | |
| "global_step": 170, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08849557522123894, | |
| "grad_norm": 0.2541367709636688, | |
| "learning_rate": 9.91645696388268e-05, | |
| "loss": 1.1092, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17699115044247787, | |
| "grad_norm": 0.4034251570701599, | |
| "learning_rate": 9.665301848904975e-05, | |
| "loss": 1.0661, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.26548672566371684, | |
| "grad_norm": 0.32995834946632385, | |
| "learning_rate": 9.255088935784784e-05, | |
| "loss": 1.1374, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.35398230088495575, | |
| "grad_norm": 0.331891268491745, | |
| "learning_rate": 8.699803935381485e-05, | |
| "loss": 1.2422, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4424778761061947, | |
| "grad_norm": 0.3209117352962494, | |
| "learning_rate": 8.018378615106108e-05, | |
| "loss": 1.076, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5309734513274337, | |
| "grad_norm": 0.3457571864128113, | |
| "learning_rate": 7.23404534331376e-05, | |
| "loss": 1.161, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6194690265486725, | |
| "grad_norm": 0.39896348118782043, | |
| "learning_rate": 6.373545009932168e-05, | |
| "loss": 1.1305, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7079646017699115, | |
| "grad_norm": 0.34675437211990356, | |
| "learning_rate": 5.466215328310079e-05, | |
| "loss": 1.181, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.7964601769911505, | |
| "grad_norm": 0.32737284898757935, | |
| "learning_rate": 4.542990601526297e-05, | |
| "loss": 1.2993, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8849557522123894, | |
| "grad_norm": 0.2711135745048523, | |
| "learning_rate": 3.635347054911746e-05, | |
| "loss": 1.133, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9734513274336283, | |
| "grad_norm": 0.3091948628425598, | |
| "learning_rate": 2.774229692390805e-05, | |
| "loss": 1.2181, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.0619469026548674, | |
| "grad_norm": 0.2637890875339508, | |
| "learning_rate": 1.9889972641710248e-05, | |
| "loss": 1.0807, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.1504424778761062, | |
| "grad_norm": 0.4912816286087036, | |
| "learning_rate": 1.3064213158260386e-05, | |
| "loss": 1.0842, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.238938053097345, | |
| "grad_norm": 0.4038459062576294, | |
| "learning_rate": 7.497734449769639e-06, | |
| "loss": 1.0192, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.3274336283185841, | |
| "grad_norm": 0.4583585858345032, | |
| "learning_rate": 3.380318844467728e-06, | |
| "loss": 1.1388, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.415929203539823, | |
| "grad_norm": 0.46843990683555603, | |
| "learning_rate": 8.523446247096445e-07, | |
| "loss": 0.9753, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.504424778761062, | |
| "grad_norm": 0.4107314646244049, | |
| "learning_rate": 0.0, | |
| "loss": 1.0707, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.504424778761062, | |
| "step": 170, | |
| "total_flos": 4.758511404711936e+16, | |
| "train_loss": 1.124874288895551, | |
| "train_runtime": 563.4945, | |
| "train_samples_per_second": 2.396, | |
| "train_steps_per_second": 0.302 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 170, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "total_flos": 4.758511404711936e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |