| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9890909090909092, | |
| "eval_steps": 5, | |
| "global_step": 136, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07272727272727272, | |
| "eval_loss": 0.8767483830451965, | |
| "eval_runtime": 30.8146, | |
| "eval_samples_per_second": 15.285, | |
| "eval_steps_per_second": 3.829, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.14545454545454545, | |
| "grad_norm": 3.115849256515503, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 3.2126, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14545454545454545, | |
| "eval_loss": 0.779396116733551, | |
| "eval_runtime": 27.2217, | |
| "eval_samples_per_second": 17.302, | |
| "eval_steps_per_second": 4.335, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.21818181818181817, | |
| "eval_loss": 0.7435232996940613, | |
| "eval_runtime": 27.2836, | |
| "eval_samples_per_second": 17.263, | |
| "eval_steps_per_second": 4.325, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2909090909090909, | |
| "grad_norm": 2.84679913520813, | |
| "learning_rate": 7.142857142857143e-05, | |
| "loss": 2.9019, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2909090909090909, | |
| "eval_loss": 0.6930269598960876, | |
| "eval_runtime": 27.2747, | |
| "eval_samples_per_second": 17.269, | |
| "eval_steps_per_second": 4.326, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "eval_loss": 0.6732496619224548, | |
| "eval_runtime": 27.2843, | |
| "eval_samples_per_second": 17.263, | |
| "eval_steps_per_second": 4.325, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.43636363636363634, | |
| "grad_norm": 2.5042567253112793, | |
| "learning_rate": 9.998342337571565e-05, | |
| "loss": 2.9314, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.43636363636363634, | |
| "eval_loss": 0.6518906950950623, | |
| "eval_runtime": 27.2739, | |
| "eval_samples_per_second": 17.269, | |
| "eval_steps_per_second": 4.326, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.509090909090909, | |
| "eval_loss": 0.6448661088943481, | |
| "eval_runtime": 27.279, | |
| "eval_samples_per_second": 17.266, | |
| "eval_steps_per_second": 4.326, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5818181818181818, | |
| "grad_norm": 2.148580312728882, | |
| "learning_rate": 9.940439480455386e-05, | |
| "loss": 2.3866, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5818181818181818, | |
| "eval_loss": 0.6359825730323792, | |
| "eval_runtime": 27.2872, | |
| "eval_samples_per_second": 17.261, | |
| "eval_steps_per_second": 4.324, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6545454545454545, | |
| "eval_loss": 0.6275559663772583, | |
| "eval_runtime": 27.2773, | |
| "eval_samples_per_second": 17.267, | |
| "eval_steps_per_second": 4.326, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 3.116907835006714, | |
| "learning_rate": 9.800749368358009e-05, | |
| "loss": 2.7002, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "eval_loss": 0.6227777004241943, | |
| "eval_runtime": 27.2702, | |
| "eval_samples_per_second": 17.272, | |
| "eval_steps_per_second": 4.327, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 0.6195926070213318, | |
| "eval_runtime": 27.263, | |
| "eval_samples_per_second": 17.276, | |
| "eval_steps_per_second": 4.328, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.8727272727272727, | |
| "grad_norm": 4.004441738128662, | |
| "learning_rate": 9.581584522435024e-05, | |
| "loss": 2.5389, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.8727272727272727, | |
| "eval_loss": 0.6146515011787415, | |
| "eval_runtime": 27.269, | |
| "eval_samples_per_second": 17.272, | |
| "eval_steps_per_second": 4.327, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.9454545454545454, | |
| "eval_loss": 0.610045850276947, | |
| "eval_runtime": 27.3064, | |
| "eval_samples_per_second": 17.249, | |
| "eval_steps_per_second": 4.321, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.029090909090909, | |
| "grad_norm": 2.843431234359741, | |
| "learning_rate": 9.286573140381662e-05, | |
| "loss": 2.4095, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.029090909090909, | |
| "eval_loss": 0.6076003909111023, | |
| "eval_runtime": 27.2492, | |
| "eval_samples_per_second": 17.285, | |
| "eval_steps_per_second": 4.33, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.1018181818181818, | |
| "eval_loss": 0.6160494089126587, | |
| "eval_runtime": 27.2598, | |
| "eval_samples_per_second": 17.278, | |
| "eval_steps_per_second": 4.329, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.1745454545454546, | |
| "grad_norm": 4.093331336975098, | |
| "learning_rate": 8.920599032883554e-05, | |
| "loss": 2.0692, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.1745454545454546, | |
| "eval_loss": 0.6218172311782837, | |
| "eval_runtime": 27.2772, | |
| "eval_samples_per_second": 17.267, | |
| "eval_steps_per_second": 4.326, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.2472727272727273, | |
| "eval_loss": 0.6184111833572388, | |
| "eval_runtime": 27.3075, | |
| "eval_samples_per_second": 17.248, | |
| "eval_steps_per_second": 4.321, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 2.453794240951538, | |
| "learning_rate": 8.489720773831717e-05, | |
| "loss": 1.8616, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_loss": 0.6163813471794128, | |
| "eval_runtime": 27.2607, | |
| "eval_samples_per_second": 17.278, | |
| "eval_steps_per_second": 4.329, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.3927272727272726, | |
| "eval_loss": 0.6139249801635742, | |
| "eval_runtime": 27.2587, | |
| "eval_samples_per_second": 17.279, | |
| "eval_steps_per_second": 4.329, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.4654545454545453, | |
| "grad_norm": 3.4409964084625244, | |
| "learning_rate": 8.001071402741842e-05, | |
| "loss": 2.1618, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.4654545454545453, | |
| "eval_loss": 0.6118062734603882, | |
| "eval_runtime": 27.245, | |
| "eval_samples_per_second": 17.288, | |
| "eval_steps_per_second": 4.331, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.538181818181818, | |
| "eval_loss": 0.610755205154419, | |
| "eval_runtime": 27.2505, | |
| "eval_samples_per_second": 17.284, | |
| "eval_steps_per_second": 4.33, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.6109090909090908, | |
| "grad_norm": 3.2959372997283936, | |
| "learning_rate": 7.462740339769324e-05, | |
| "loss": 2.0259, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.6109090909090908, | |
| "eval_loss": 0.6130332350730896, | |
| "eval_runtime": 27.2607, | |
| "eval_samples_per_second": 17.278, | |
| "eval_steps_per_second": 4.329, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.6836363636363636, | |
| "eval_loss": 0.6104254722595215, | |
| "eval_runtime": 27.2481, | |
| "eval_samples_per_second": 17.286, | |
| "eval_steps_per_second": 4.331, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.7563636363636363, | |
| "grad_norm": 2.7095448970794678, | |
| "learning_rate": 6.883639468175927e-05, | |
| "loss": 1.8146, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.7563636363636363, | |
| "eval_loss": 0.6095255613327026, | |
| "eval_runtime": 27.2419, | |
| "eval_samples_per_second": 17.29, | |
| "eval_steps_per_second": 4.332, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.829090909090909, | |
| "eval_loss": 0.6098220944404602, | |
| "eval_runtime": 27.2413, | |
| "eval_samples_per_second": 17.29, | |
| "eval_steps_per_second": 4.332, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.9018181818181819, | |
| "grad_norm": 3.7072970867156982, | |
| "learning_rate": 6.273355601206144e-05, | |
| "loss": 1.6977, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.9018181818181819, | |
| "eval_loss": 0.6083605289459229, | |
| "eval_runtime": 27.262, | |
| "eval_samples_per_second": 17.277, | |
| "eval_steps_per_second": 4.328, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.9745454545454546, | |
| "eval_loss": 0.6045976281166077, | |
| "eval_runtime": 27.2423, | |
| "eval_samples_per_second": 17.289, | |
| "eval_steps_per_second": 4.332, | |
| "step": 135 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 272, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.413948656205824e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |