| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 4455, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.3367003367003367, |
| "grad_norm": 14.949820518493652, |
| "learning_rate": 4.9978441082243424e-05, |
| "loss": 1.6348, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.3367003367003367, |
| "eval_accuracy": 0.7818, |
| "eval_f1": 0.7707654278149872, |
| "eval_loss": 0.7248653173446655, |
| "eval_prauc": 0.8471943467878073, |
| "eval_precision": 0.7777639682274672, |
| "eval_recall": 0.7818, |
| "eval_runtime": 6.5782, |
| "eval_samples_per_second": 760.089, |
| "eval_steps_per_second": 95.011, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.6734006734006734, |
| "grad_norm": 8.724627494812012, |
| "learning_rate": 4.7689101828499175e-05, |
| "loss": 0.6566, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.6734006734006734, |
| "eval_accuracy": 0.8194, |
| "eval_f1": 0.8125511449697567, |
| "eval_loss": 0.5900622606277466, |
| "eval_prauc": 0.883177875981317, |
| "eval_precision": 0.8170544867915973, |
| "eval_recall": 0.8194, |
| "eval_runtime": 6.2222, |
| "eval_samples_per_second": 803.57, |
| "eval_steps_per_second": 100.446, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.0101010101010102, |
| "grad_norm": 8.932344436645508, |
| "learning_rate": 4.196084543323817e-05, |
| "loss": 0.5695, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.0101010101010102, |
| "eval_accuracy": 0.8298, |
| "eval_f1": 0.8214116862727279, |
| "eval_loss": 0.5388458967208862, |
| "eval_prauc": 0.8942335681618219, |
| "eval_precision": 0.824507012622034, |
| "eval_recall": 0.8298, |
| "eval_runtime": 6.9973, |
| "eval_samples_per_second": 714.564, |
| "eval_steps_per_second": 89.32, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.3468013468013469, |
| "grad_norm": 11.769265174865723, |
| "learning_rate": 3.366188603986574e-05, |
| "loss": 0.3954, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.3468013468013469, |
| "eval_accuracy": 0.832, |
| "eval_f1": 0.8276523330085487, |
| "eval_loss": 0.5264924764633179, |
| "eval_prauc": 0.8980912722084475, |
| "eval_precision": 0.828413850188029, |
| "eval_recall": 0.832, |
| "eval_runtime": 6.9005, |
| "eval_samples_per_second": 724.583, |
| "eval_steps_per_second": 90.573, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.6835016835016834, |
| "grad_norm": 12.866188049316406, |
| "learning_rate": 2.4050071311561374e-05, |
| "loss": 0.3735, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.6835016835016834, |
| "eval_accuracy": 0.843, |
| "eval_f1": 0.8369456713438264, |
| "eval_loss": 0.5062804222106934, |
| "eval_prauc": 0.9023592788997854, |
| "eval_precision": 0.8391826013500971, |
| "eval_recall": 0.843, |
| "eval_runtime": 6.7126, |
| "eval_samples_per_second": 744.87, |
| "eval_steps_per_second": 93.109, |
| "step": 2500 |
| }, |
| { |
| "epoch": 2.0202020202020203, |
| "grad_norm": 7.454126834869385, |
| "learning_rate": 1.4582234342913715e-05, |
| "loss": 0.3436, |
| "step": 3000 |
| }, |
| { |
| "epoch": 2.0202020202020203, |
| "eval_accuracy": 0.84, |
| "eval_f1": 0.8369555486562935, |
| "eval_loss": 0.5169184803962708, |
| "eval_prauc": 0.9039284056011966, |
| "eval_precision": 0.8386328079429232, |
| "eval_recall": 0.84, |
| "eval_runtime": 6.0064, |
| "eval_samples_per_second": 832.444, |
| "eval_steps_per_second": 104.055, |
| "step": 3000 |
| }, |
| { |
| "epoch": 2.356902356902357, |
| "grad_norm": 10.186031341552734, |
| "learning_rate": 6.693385963821353e-06, |
| "loss": 0.1677, |
| "step": 3500 |
| }, |
| { |
| "epoch": 2.356902356902357, |
| "eval_accuracy": 0.8408, |
| "eval_f1": 0.8384862313439404, |
| "eval_loss": 0.5824030041694641, |
| "eval_prauc": 0.9009043897343983, |
| "eval_precision": 0.8396918530177993, |
| "eval_recall": 0.8408, |
| "eval_runtime": 7.0427, |
| "eval_samples_per_second": 709.957, |
| "eval_steps_per_second": 88.745, |
| "step": 3500 |
| }, |
| { |
| "epoch": 2.6936026936026938, |
| "grad_norm": 8.157699584960938, |
| "learning_rate": 1.5792145767053622e-06, |
| "loss": 0.1491, |
| "step": 4000 |
| }, |
| { |
| "epoch": 2.6936026936026938, |
| "eval_accuracy": 0.8422, |
| "eval_f1": 0.8391634085924852, |
| "eval_loss": 0.5748035907745361, |
| "eval_prauc": 0.903134748047534, |
| "eval_precision": 0.8388717647632293, |
| "eval_recall": 0.8422, |
| "eval_runtime": 7.0678, |
| "eval_samples_per_second": 707.436, |
| "eval_steps_per_second": 88.429, |
| "step": 4000 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 4455, |
| "total_flos": 1.1103474080022912e+16, |
| "train_loss": 0.4963774555861348, |
| "train_runtime": 674.1321, |
| "train_samples_per_second": 422.766, |
| "train_steps_per_second": 6.608 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8426, |
| "eval_f1": 0.8397110808761383, |
| "eval_loss": 0.5739430785179138, |
| "eval_prauc": 0.9033464177917727, |
| "eval_precision": 0.8396082701885788, |
| "eval_recall": 0.8426, |
| "eval_runtime": 6.1808, |
| "eval_samples_per_second": 808.953, |
| "eval_steps_per_second": 101.119, |
| "step": 4455 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 4455, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": false, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.1103474080022912e+16, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
