| { | |
| "best_metric": 1.093665599822998, | |
| "best_model_checkpoint": "/kaggle/output/checkpoint-8000", | |
| "epoch": 0.3259452411994785, | |
| "eval_steps": 1000, | |
| "global_step": 8000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2.7777777777777777e-11, | |
| "loss": 1.0722, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.7750000000000004e-08, | |
| "loss": 1.1407, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.32914171656686625, | |
| "eval_loss": 1.1048731803894043, | |
| "eval_runtime": 57.3781, | |
| "eval_samples_per_second": 87.316, | |
| "eval_steps_per_second": 10.928, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 5.5527777777777784e-08, | |
| "loss": 1.1253, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.3377245508982036, | |
| "eval_loss": 1.1033366918563843, | |
| "eval_runtime": 57.3237, | |
| "eval_samples_per_second": 87.398, | |
| "eval_steps_per_second": 10.938, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.327777777777778e-08, | |
| "loss": 1.1179, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.3502994011976048, | |
| "eval_loss": 1.104222059249878, | |
| "eval_runtime": 57.4527, | |
| "eval_samples_per_second": 87.202, | |
| "eval_steps_per_second": 10.913, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.1105555555555557e-07, | |
| "loss": 1.1197, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.3457085828343313, | |
| "eval_loss": 1.1000728607177734, | |
| "eval_runtime": 57.5257, | |
| "eval_samples_per_second": 87.091, | |
| "eval_steps_per_second": 10.899, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.3883333333333335e-07, | |
| "loss": 1.1202, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.3383233532934132, | |
| "eval_loss": 1.099381923675537, | |
| "eval_runtime": 57.825, | |
| "eval_samples_per_second": 86.641, | |
| "eval_steps_per_second": 10.843, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.6661111111111112e-07, | |
| "loss": 1.1166, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_accuracy": 0.35409181636726544, | |
| "eval_loss": 1.0975825786590576, | |
| "eval_runtime": 57.6509, | |
| "eval_samples_per_second": 86.902, | |
| "eval_steps_per_second": 10.876, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.9436111111111112e-07, | |
| "loss": 1.1126, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_accuracy": 0.35508982035928144, | |
| "eval_loss": 1.0957295894622803, | |
| "eval_runtime": 57.5423, | |
| "eval_samples_per_second": 87.066, | |
| "eval_steps_per_second": 10.896, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.2213888888888891e-07, | |
| "loss": 1.1091, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_accuracy": 0.36666666666666664, | |
| "eval_loss": 1.093665599822998, | |
| "eval_runtime": 57.2594, | |
| "eval_samples_per_second": 87.497, | |
| "eval_steps_per_second": 10.95, | |
| "step": 8000 | |
| } | |
| ], | |
| "logging_steps": 1000, | |
| "max_steps": 10000000, | |
| "num_train_epochs": 408, | |
| "save_steps": 1000, | |
| "total_flos": 1.6722841042944e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |