| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9993360523570142, | |
| "eval_steps": 500, | |
| "global_step": 1317, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 2.6666550636291504, | |
| "learning_rate": 1.5151515151515153e-05, | |
| "loss": 1.75, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 1.9126778841018677, | |
| "learning_rate": 1.983794055463009e-05, | |
| "loss": 0.9131, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 2.010279655456543, | |
| "learning_rate": 1.90244256701717e-05, | |
| "loss": 0.921, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 1.661656141281128, | |
| "learning_rate": 1.7580334804873595e-05, | |
| "loss": 0.8664, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 1.8409279584884644, | |
| "learning_rate": 1.5606572885773613e-05, | |
| "loss": 0.8562, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 1.8635607957839966, | |
| "learning_rate": 1.324105526655396e-05, | |
| "loss": 0.8561, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 1.4191073179244995, | |
| "learning_rate": 1.0649070980273363e-05, | |
| "loss": 0.8621, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 1.4062063694000244, | |
| "learning_rate": 8.011733273733208e-06, | |
| "loss": 0.8523, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 1.7386995553970337, | |
| "learning_rate": 5.51332443501349e-06, | |
| "loss": 0.8277, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 1.6414889097213745, | |
| "learning_rate": 3.3284191862731585e-06, | |
| "loss": 0.8406, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 1.6184569597244263, | |
| "learning_rate": 1.6096863865200606e-06, | |
| "loss": 0.8189, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 1.6727625131607056, | |
| "learning_rate": 4.772213925798331e-07, | |
| "loss": 0.837, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 1.7798255681991577, | |
| "learning_rate": 1.0154472728808318e-08, | |
| "loss": 0.8195, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 1317, | |
| "total_flos": 2.5585123528237056e+16, | |
| "train_loss": 0.9235503957773034, | |
| "train_runtime": 6177.2242, | |
| "train_samples_per_second": 1.707, | |
| "train_steps_per_second": 0.213 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 1317, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 2.5585123528237056e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |