| { | |
| "best_metric": 0.2981628179550171, | |
| "best_model_checkpoint": "outputs/electra-nli-efl-tweeteval/checkpoint-978", | |
| "epoch": 10.997323135755257, | |
| "global_step": 1793, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.499999999999999e-07, | |
| "loss": 0.4384, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7444061962134251, | |
| "eval_f1": 0.7308261375858633, | |
| "eval_loss": 0.39615127444267273, | |
| "eval_runtime": 9.0599, | |
| "eval_samples_per_second": 256.514, | |
| "eval_steps_per_second": 32.119, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 9e-07, | |
| "loss": 0.3447, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.76592082616179, | |
| "eval_f1": 0.7552159046464709, | |
| "eval_loss": 0.3409559428691864, | |
| "eval_runtime": 9.4378, | |
| "eval_samples_per_second": 246.244, | |
| "eval_steps_per_second": 30.833, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 8.499999999999999e-07, | |
| "loss": 0.3057, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7749569707401033, | |
| "eval_f1": 0.768808341108185, | |
| "eval_loss": 0.32338443398475647, | |
| "eval_runtime": 9.0418, | |
| "eval_samples_per_second": 257.028, | |
| "eval_steps_per_second": 32.184, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 8e-07, | |
| "loss": 0.287, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7857142857142857, | |
| "eval_f1": 0.7778970154753132, | |
| "eval_loss": 0.3068828284740448, | |
| "eval_runtime": 9.3662, | |
| "eval_samples_per_second": 248.128, | |
| "eval_steps_per_second": 31.069, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 7.5e-07, | |
| "loss": 0.2742, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7887263339070568, | |
| "eval_f1": 0.7821763089027973, | |
| "eval_loss": 0.30303624272346497, | |
| "eval_runtime": 8.908, | |
| "eval_samples_per_second": 260.89, | |
| "eval_steps_per_second": 32.667, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 7e-07, | |
| "loss": 0.2676, | |
| "step": 978 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.7938898450946644, | |
| "eval_f1": 0.7850614050415754, | |
| "eval_loss": 0.2981628179550171, | |
| "eval_runtime": 9.0189, | |
| "eval_samples_per_second": 257.681, | |
| "eval_steps_per_second": 32.266, | |
| "step": 978 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 6.5e-07, | |
| "loss": 0.2585, | |
| "step": 1141 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.7908777969018933, | |
| "eval_f1": 0.7821955847641968, | |
| "eval_loss": 0.3001907467842102, | |
| "eval_runtime": 8.8872, | |
| "eval_samples_per_second": 261.499, | |
| "eval_steps_per_second": 32.744, | |
| "step": 1141 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 6e-07, | |
| "loss": 0.2526, | |
| "step": 1304 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7943201376936316, | |
| "eval_f1": 0.7876461988304093, | |
| "eval_loss": 0.30516260862350464, | |
| "eval_runtime": 9.0042, | |
| "eval_samples_per_second": 258.103, | |
| "eval_steps_per_second": 32.318, | |
| "step": 1304 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 5.5e-07, | |
| "loss": 0.2479, | |
| "step": 1467 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.7938898450946644, | |
| "eval_f1": 0.784665589216992, | |
| "eval_loss": 0.2996860444545746, | |
| "eval_runtime": 9.1157, | |
| "eval_samples_per_second": 254.944, | |
| "eval_steps_per_second": 31.923, | |
| "step": 1467 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 5e-07, | |
| "loss": 0.2451, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.7956110154905336, | |
| "eval_f1": 0.787314593871832, | |
| "eval_loss": 0.3013566732406616, | |
| "eval_runtime": 9.3541, | |
| "eval_samples_per_second": 248.446, | |
| "eval_steps_per_second": 31.109, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 4.5e-07, | |
| "loss": 0.2397, | |
| "step": 1793 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.7943201376936316, | |
| "eval_f1": 0.7872381827932275, | |
| "eval_loss": 0.30036163330078125, | |
| "eval_runtime": 9.1941, | |
| "eval_samples_per_second": 252.771, | |
| "eval_steps_per_second": 31.651, | |
| "step": 1793 | |
| } | |
| ], | |
| "max_steps": 3260, | |
| "num_train_epochs": 20, | |
| "total_flos": 3.348318385671187e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |