| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9230769230769231, | |
| "eval_steps": 10, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 2.272727272727273e-05, | |
| "loss": 1.7377, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 1.3826087713241577, | |
| "eval_runtime": 164.229, | |
| "eval_samples_per_second": 0.304, | |
| "eval_steps_per_second": 0.043, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 2.0202020202020203e-05, | |
| "loss": 1.0247, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 0.6683715581893921, | |
| "eval_runtime": 163.0119, | |
| "eval_samples_per_second": 0.307, | |
| "eval_steps_per_second": 0.043, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 1.7676767676767676e-05, | |
| "loss": 0.4914, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 0.34242257475852966, | |
| "eval_runtime": 164.0724, | |
| "eval_samples_per_second": 0.305, | |
| "eval_steps_per_second": 0.043, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.5151515151515153e-05, | |
| "loss": 0.3506, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 0.3160565197467804, | |
| "eval_runtime": 163.8993, | |
| "eval_samples_per_second": 0.305, | |
| "eval_steps_per_second": 0.043, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.2626262626262628e-05, | |
| "loss": 0.3133, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 0.3000437915325165, | |
| "eval_runtime": 163.2552, | |
| "eval_samples_per_second": 0.306, | |
| "eval_steps_per_second": 0.043, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 1.0101010101010101e-05, | |
| "loss": 0.3185, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 0.2911369800567627, | |
| "eval_runtime": 162.9849, | |
| "eval_samples_per_second": 0.307, | |
| "eval_steps_per_second": 0.043, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 7.5757575757575764e-06, | |
| "loss": 0.2703, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_loss": 0.2851818799972534, | |
| "eval_runtime": 163.5768, | |
| "eval_samples_per_second": 0.306, | |
| "eval_steps_per_second": 0.043, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 5.050505050505051e-06, | |
| "loss": 0.2451, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "eval_loss": 0.27840811014175415, | |
| "eval_runtime": 163.9369, | |
| "eval_samples_per_second": 0.305, | |
| "eval_steps_per_second": 0.043, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 2.5252525252525253e-06, | |
| "loss": 0.2702, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_loss": 0.2748894989490509, | |
| "eval_runtime": 162.9364, | |
| "eval_samples_per_second": 0.307, | |
| "eval_steps_per_second": 0.043, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.0, | |
| "loss": 0.2489, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 0.27365821599960327, | |
| "eval_runtime": 164.1174, | |
| "eval_samples_per_second": 0.305, | |
| "eval_steps_per_second": 0.043, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 10, | |
| "total_flos": 4359942624509952.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |