| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.1646223369916076, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.9875000000000002e-05, | |
| "loss": 1.9446, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.9736111111111115e-05, | |
| "loss": 1.7941, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.9597222222222224e-05, | |
| "loss": 1.5361, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.9458333333333333e-05, | |
| "loss": 1.1041, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 1.9319444444444446e-05, | |
| "loss": 0.6053, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 1.918055555555556e-05, | |
| "loss": 0.4088, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 1.9041666666666668e-05, | |
| "loss": 0.3813, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 1.890277777777778e-05, | |
| "loss": 0.3733, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.876388888888889e-05, | |
| "loss": 0.3678, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.8625000000000002e-05, | |
| "loss": 0.3604, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1.8486111111111115e-05, | |
| "loss": 0.3368, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 1.8347222222222224e-05, | |
| "loss": 0.3356, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 1.8208333333333333e-05, | |
| "loss": 0.3439, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 1.8069444444444446e-05, | |
| "loss": 0.3277, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 1.793055555555556e-05, | |
| "loss": 0.3288, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 1.7791666666666668e-05, | |
| "loss": 0.3227, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 1.765277777777778e-05, | |
| "loss": 0.3213, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 1.751388888888889e-05, | |
| "loss": 0.3128, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 1.7375000000000002e-05, | |
| "loss": 0.3071, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 1.7236111111111115e-05, | |
| "loss": 0.3022, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 1.7097222222222224e-05, | |
| "loss": 0.2968, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 1.6958333333333333e-05, | |
| "loss": 0.3023, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 1.6819444444444446e-05, | |
| "loss": 0.2889, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 1.668055555555556e-05, | |
| "loss": 0.2763, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 1.6541666666666668e-05, | |
| "loss": 0.2778, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 2880, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 1.584297707925504e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |