| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.011475127660795226, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 5e-08, | |
| "loss": 0.6931, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2.5e-07, | |
| "loss": 0.6931, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 5e-07, | |
| "loss": 0.6922, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.96201938253052e-07, | |
| "loss": 0.689, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.849231551964771e-07, | |
| "loss": 0.6841, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.6650635094610966e-07, | |
| "loss": 0.6785, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.415111107797445e-07, | |
| "loss": 0.6716, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.106969024216348e-07, | |
| "loss": 0.6645, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 3.75e-07, | |
| "loss": 0.6583, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 3.355050358314172e-07, | |
| "loss": 0.6513, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.934120444167326e-07, | |
| "loss": 0.6454, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.5e-07, | |
| "loss": 0.6396, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.065879555832674e-07, | |
| "loss": 0.635, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.6449496416858282e-07, | |
| "loss": 0.6302, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.2500000000000005e-07, | |
| "loss": 0.6281, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 8.930309757836516e-08, | |
| "loss": 0.6258, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5.848888922025552e-08, | |
| "loss": 0.6249, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 3.349364905389032e-08, | |
| "loss": 0.6218, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.507684480352292e-08, | |
| "loss": 0.6206, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 3.798061746947995e-09, | |
| "loss": 0.6223, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0, | |
| "loss": 0.6206, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "step": 100, | |
| "total_flos": 1.4145053855737446e+17, | |
| "train_loss": 0.6498598456382751, | |
| "train_runtime": 1109.6734, | |
| "train_samples_per_second": 1.442, | |
| "train_steps_per_second": 0.09 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 1.4145053855737446e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |