| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 196, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.05118362124120281, |
| "grad_norm": 3.148853302001953, |
| "learning_rate": 4.5e-06, |
| "loss": 1.385, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.10236724248240563, |
| "grad_norm": 1.1139516830444336, |
| "learning_rate": 9.5e-06, |
| "loss": 1.2765, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.15355086372360843, |
| "grad_norm": 0.7387185096740723, |
| "learning_rate": 9.935617890443557e-06, |
| "loss": 1.1724, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.20473448496481125, |
| "grad_norm": 0.6481090784072876, |
| "learning_rate": 9.715190263989562e-06, |
| "loss": 1.1525, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.2559181062060141, |
| "grad_norm": 0.6280516982078552, |
| "learning_rate": 9.344925248293837e-06, |
| "loss": 1.1139, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.30710172744721687, |
| "grad_norm": 0.6205667853355408, |
| "learning_rate": 8.836588973708129e-06, |
| "loss": 1.1037, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.3582853486884197, |
| "grad_norm": 0.6342296600341797, |
| "learning_rate": 8.206335142623305e-06, |
| "loss": 1.0871, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.4094689699296225, |
| "grad_norm": 0.6090540885925293, |
| "learning_rate": 7.474191703716339e-06, |
| "loss": 1.0976, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.46065259117082535, |
| "grad_norm": 0.6706152558326721, |
| "learning_rate": 6.663424411982121e-06, |
| "loss": 1.0932, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.5118362124120281, |
| "grad_norm": 0.7046359777450562, |
| "learning_rate": 5.799797499079301e-06, |
| "loss": 1.0839, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.5630198336532309, |
| "grad_norm": 0.6165784001350403, |
| "learning_rate": 4.91075494810577e-06, |
| "loss": 1.0782, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.6142034548944337, |
| "grad_norm": 0.6227678656578064, |
| "learning_rate": 4.02454838991936e-06, |
| "loss": 1.0738, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.6653870761356366, |
| "grad_norm": 0.5915654897689819, |
| "learning_rate": 3.169339334358105e-06, |
| "loss": 1.0797, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.7165706973768394, |
| "grad_norm": 0.5963186621665955, |
| "learning_rate": 2.372304265289436e-06, |
| "loss": 1.0836, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.7677543186180422, |
| "grad_norm": 0.5568503737449646, |
| "learning_rate": 1.6587710374121203e-06, |
| "loss": 1.074, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.818937939859245, |
| "grad_norm": 0.5133649110794067, |
| "learning_rate": 1.0514140180404202e-06, |
| "loss": 1.0639, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.8701215611004478, |
| "grad_norm": 0.5275949239730835, |
| "learning_rate": 5.69533550325988e-07, |
| "loss": 1.062, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.9213051823416507, |
| "grad_norm": 0.510567843914032, |
| "learning_rate": 2.2844263484068097e-07, |
| "loss": 1.0698, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.9724888035828535, |
| "grad_norm": 0.513010561466217, |
| "learning_rate": 3.8980319302407976e-08, |
| "loss": 1.0612, |
| "step": 190 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 196, |
| "total_flos": 9.416011658066657e+17, |
| "train_loss": 1.113203457423619, |
| "train_runtime": 3266.8922, |
| "train_samples_per_second": 7.653, |
| "train_steps_per_second": 0.06 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 196, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 196, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 9.416011658066657e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
