| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.03, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.877551020408163e-07, | |
| "loss": 1.375, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.622448979591836e-07, | |
| "loss": 1.2193, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.36734693877551e-07, | |
| "loss": 1.1523, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.1122448979591835e-07, | |
| "loss": 1.0932, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 3.857142857142857e-07, | |
| "loss": 1.0807, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.6020408163265303e-07, | |
| "loss": 0.9713, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3.346938775510204e-07, | |
| "loss": 0.8942, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3.091836734693877e-07, | |
| "loss": 0.8368, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.836734693877551e-07, | |
| "loss": 0.8457, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.5816326530612243e-07, | |
| "loss": 0.8327, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.3265306122448977e-07, | |
| "loss": 0.7346, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2.0714285714285714e-07, | |
| "loss": 0.7187, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.816326530612245e-07, | |
| "loss": 0.6946, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.5612244897959184e-07, | |
| "loss": 0.6741, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.3061224489795918e-07, | |
| "loss": 0.6666, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.0510204081632652e-07, | |
| "loss": 0.6905, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 7.959183673469387e-08, | |
| "loss": 0.7062, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5.408163265306123e-08, | |
| "loss": 0.7401, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 2.857142857142857e-08, | |
| "loss": 0.7371, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.0612244897959183e-09, | |
| "loss": 1.1042, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "step": 500, | |
| "total_flos": 7.8780432384e+17, | |
| "train_loss": 0.8883990364074708, | |
| "train_runtime": 3323.2103, | |
| "train_samples_per_second": 9.629, | |
| "train_steps_per_second": 0.15 | |
| } | |
| ], | |
| "max_steps": 500, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 7.8780432384e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |