| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 2436, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12, | |
| "eval_f1": 0.0956468424279583, | |
| "eval_loss": 1.3489933013916016, | |
| "eval_runtime": 12.0925, | |
| "eval_samples_per_second": 38.454, | |
| "eval_steps_per_second": 7.691, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_f1": 0.0956468424279583, | |
| "eval_loss": 1.4751325845718384, | |
| "eval_runtime": 2.7372, | |
| "eval_samples_per_second": 169.883, | |
| "eval_steps_per_second": 33.977, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_f1": 0.24267804768973908, | |
| "eval_loss": 0.9687431454658508, | |
| "eval_runtime": 2.7453, | |
| "eval_samples_per_second": 169.381, | |
| "eval_steps_per_second": 33.876, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_f1": 0.189060606060606, | |
| "eval_loss": 1.0624897480010986, | |
| "eval_runtime": 2.7393, | |
| "eval_samples_per_second": 169.753, | |
| "eval_steps_per_second": 33.951, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.9737274220032846e-05, | |
| "loss": 1.2336, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_f1": 0.1949172949812336, | |
| "eval_loss": 1.0953644514083862, | |
| "eval_runtime": 2.7252, | |
| "eval_samples_per_second": 170.632, | |
| "eval_steps_per_second": 34.126, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_f1": 0.3080140543853414, | |
| "eval_loss": 0.9969261288642883, | |
| "eval_runtime": 2.7252, | |
| "eval_samples_per_second": 170.632, | |
| "eval_steps_per_second": 34.126, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_f1": 0.3174607190495667, | |
| "eval_loss": 0.917083203792572, | |
| "eval_runtime": 2.7253, | |
| "eval_samples_per_second": 170.626, | |
| "eval_steps_per_second": 34.125, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_f1": 0.3136389264934501, | |
| "eval_loss": 0.9600306153297424, | |
| "eval_runtime": 2.7547, | |
| "eval_samples_per_second": 168.801, | |
| "eval_steps_per_second": 33.76, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_f1": 0.3161058727288384, | |
| "eval_loss": 0.9637317061424255, | |
| "eval_runtime": 2.7379, | |
| "eval_samples_per_second": 169.835, | |
| "eval_steps_per_second": 33.967, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 2.947454844006568e-05, | |
| "loss": 1.0269, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_f1": 0.32568520729341943, | |
| "eval_loss": 0.9592134356498718, | |
| "eval_runtime": 2.7586, | |
| "eval_samples_per_second": 168.567, | |
| "eval_steps_per_second": 33.713, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_f1": 0.33416337186541306, | |
| "eval_loss": 0.9117490649223328, | |
| "eval_runtime": 2.7292, | |
| "eval_samples_per_second": 170.381, | |
| "eval_steps_per_second": 34.076, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_f1": 0.32049717164329167, | |
| "eval_loss": 0.8890902996063232, | |
| "eval_runtime": 2.7191, | |
| "eval_samples_per_second": 171.014, | |
| "eval_steps_per_second": 34.203, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_f1": 0.33748089562391775, | |
| "eval_loss": 0.8135806918144226, | |
| "eval_runtime": 2.7319, | |
| "eval_samples_per_second": 170.209, | |
| "eval_steps_per_second": 34.042, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_f1": 0.3299982086985783, | |
| "eval_loss": 0.9675911664962769, | |
| "eval_runtime": 2.7207, | |
| "eval_samples_per_second": 170.911, | |
| "eval_steps_per_second": 34.182, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 1.921182266009852e-05, | |
| "loss": 0.8592, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "eval_f1": 0.3315730877046458, | |
| "eval_loss": 0.8777754306793213, | |
| "eval_runtime": 2.7307, | |
| "eval_samples_per_second": 170.287, | |
| "eval_steps_per_second": 34.057, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_f1": 0.33789886027350413, | |
| "eval_loss": 0.840674102306366, | |
| "eval_runtime": 2.7102, | |
| "eval_samples_per_second": 171.575, | |
| "eval_steps_per_second": 34.315, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "eval_f1": 0.33685244804747255, | |
| "eval_loss": 0.8408811092376709, | |
| "eval_runtime": 2.7395, | |
| "eval_samples_per_second": 169.74, | |
| "eval_steps_per_second": 33.948, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_f1": 0.3342829560124293, | |
| "eval_loss": 0.8817650675773621, | |
| "eval_runtime": 2.7283, | |
| "eval_samples_per_second": 170.435, | |
| "eval_steps_per_second": 34.087, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "eval_f1": 0.3385578564861433, | |
| "eval_loss": 0.9258896708488464, | |
| "eval_runtime": 2.7323, | |
| "eval_samples_per_second": 170.186, | |
| "eval_steps_per_second": 34.037, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 8.949096880131364e-06, | |
| "loss": 0.7521, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "eval_f1": 0.33802107795500247, | |
| "eval_loss": 0.941909670829773, | |
| "eval_runtime": 2.7353, | |
| "eval_samples_per_second": 169.998, | |
| "eval_steps_per_second": 34.0, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "eval_f1": 0.3473817078391378, | |
| "eval_loss": 0.8049965500831604, | |
| "eval_runtime": 2.7367, | |
| "eval_samples_per_second": 169.913, | |
| "eval_steps_per_second": 33.983, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "eval_f1": 0.4052810578970328, | |
| "eval_loss": 0.7772806286811829, | |
| "eval_runtime": 2.7323, | |
| "eval_samples_per_second": 170.185, | |
| "eval_steps_per_second": 34.037, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "eval_f1": 0.43365497482920284, | |
| "eval_loss": 0.7114064693450928, | |
| "eval_runtime": 2.7465, | |
| "eval_samples_per_second": 169.308, | |
| "eval_steps_per_second": 33.862, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_f1": 0.43148798131355104, | |
| "eval_loss": 0.7161591649055481, | |
| "eval_runtime": 2.7392, | |
| "eval_samples_per_second": 169.755, | |
| "eval_steps_per_second": 33.951, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 2436, | |
| "total_flos": 1184978465021280.0, | |
| "train_loss": 0.9243036530092237, | |
| "train_runtime": 435.0692, | |
| "train_samples_per_second": 27.968, | |
| "train_steps_per_second": 5.599 | |
| } | |
| ], | |
| "max_steps": 2436, | |
| "num_train_epochs": 3, | |
| "total_flos": 1184978465021280.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |