| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9241341396371632, | |
| "eval_steps": 1000, | |
| "global_step": 7000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00011454256850621083, | |
| "loss": 1.5046, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 2.7397329807281494, | |
| "eval_runtime": 3.8318, | |
| "eval_samples_per_second": 232.268, | |
| "eval_steps_per_second": 29.229, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 8.099382692526634e-05, | |
| "loss": 1.1958, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 2.4763500690460205, | |
| "eval_runtime": 3.7761, | |
| "eval_samples_per_second": 235.692, | |
| "eval_steps_per_second": 29.66, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 6.613118276073197e-05, | |
| "loss": 1.0733, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 2.391991138458252, | |
| "eval_runtime": 3.7954, | |
| "eval_samples_per_second": 234.495, | |
| "eval_steps_per_second": 29.51, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 5.7271284253105416e-05, | |
| "loss": 0.9219, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_loss": 2.3582706451416016, | |
| "eval_runtime": 3.7454, | |
| "eval_samples_per_second": 237.627, | |
| "eval_steps_per_second": 29.904, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 5.1224993899462795e-05, | |
| "loss": 0.7324, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "eval_loss": 2.3552770614624023, | |
| "eval_runtime": 3.775, | |
| "eval_samples_per_second": 235.76, | |
| "eval_steps_per_second": 29.669, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 4.676180777800049e-05, | |
| "loss": 0.7311, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "eval_loss": 2.318331003189087, | |
| "eval_runtime": 3.7693, | |
| "eval_samples_per_second": 236.117, | |
| "eval_steps_per_second": 29.714, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 4.329302154257329e-05, | |
| "loss": 0.7289, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 2.3413245677948, | |
| "eval_runtime": 3.7689, | |
| "eval_samples_per_second": 236.14, | |
| "eval_steps_per_second": 29.717, | |
| "step": 7000 | |
| } | |
| ], | |
| "logging_steps": 1000, | |
| "max_steps": 10914, | |
| "num_train_epochs": 3, | |
| "save_steps": 1000, | |
| "total_flos": 5.261490028422758e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |