| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.799086757990867, | |
| "eval_steps": 500, | |
| "global_step": 130, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 1.4708, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00011111111111111112, | |
| "loss": 1.4228, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0001999048221581858, | |
| "loss": 1.2725, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 1.2311, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00018870108331782217, | |
| "loss": 1.1712, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0001766044443118978, | |
| "loss": 1.1559, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 1.1649807691574097, | |
| "eval_runtime": 283.9384, | |
| "eval_samples_per_second": 2.134, | |
| "eval_steps_per_second": 0.535, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 1.1485, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.00014226182617406996, | |
| "loss": 1.11, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.00012164396139381029, | |
| "loss": 1.1045, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0982, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 7.835603860618972e-05, | |
| "loss": 1.0887, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "eval_loss": 1.1555219888687134, | |
| "eval_runtime": 283.2377, | |
| "eval_samples_per_second": 2.14, | |
| "eval_steps_per_second": 0.537, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 5.773817382593008e-05, | |
| "loss": 1.0711, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 1.0764, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 1.04, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 1.129891668217783e-05, | |
| "loss": 1.0344, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 1.0026, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 9.517784181422019e-08, | |
| "loss": 1.0566, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "eval_loss": 1.1623399257659912, | |
| "eval_runtime": 283.2011, | |
| "eval_samples_per_second": 2.14, | |
| "eval_steps_per_second": 0.537, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 6.453951129574644e-05, | |
| "loss": 1.0309, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 5.234312799786921e-05, | |
| "loss": 1.0264, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 6.95, | |
| "eval_loss": 1.168891191482544, | |
| "eval_runtime": 208.2969, | |
| "eval_samples_per_second": 2.909, | |
| "eval_steps_per_second": 0.365, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "learning_rate": 4.100445599768774e-05, | |
| "loss": 1.0037, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "learning_rate": 3.072756464904006e-05, | |
| "loss": 1.0055, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 7.97, | |
| "learning_rate": 2.1697413758237784e-05, | |
| "loss": 0.9977, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 7.97, | |
| "eval_loss": 1.1778818368911743, | |
| "eval_runtime": 208.3439, | |
| "eval_samples_per_second": 2.909, | |
| "eval_steps_per_second": 0.365, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 8.34, | |
| "learning_rate": 1.4076524743778319e-05, | |
| "loss": 0.9801, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "learning_rate": 8.002055634117578e-06, | |
| "loss": 0.9808, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.1819604635238647, | |
| "eval_runtime": 208.427, | |
| "eval_samples_per_second": 2.907, | |
| "eval_steps_per_second": 0.365, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "learning_rate": 3.5833325466437694e-06, | |
| "loss": 0.9842, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 9.43, | |
| "learning_rate": 8.998820754091531e-07, | |
| "loss": 0.9813, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "learning_rate": 0.0, | |
| "loss": 0.9791, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "eval_loss": 1.1828593015670776, | |
| "eval_runtime": 208.4043, | |
| "eval_samples_per_second": 2.908, | |
| "eval_steps_per_second": 0.365, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "step": 130, | |
| "total_flos": 384243276447744.0, | |
| "train_loss": 0.37551442659818207, | |
| "train_runtime": 8428.1057, | |
| "train_samples_per_second": 2.07, | |
| "train_steps_per_second": 0.015 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 130, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 384243276447744.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |