| { |
| "best_global_step": 798, |
| "best_metric": 0.959349593495935, |
| "best_model_checkpoint": "model_2cl_xlmr\r/checkpoint-798", |
| "epoch": 10.0, |
| "eval_steps": 500, |
| "global_step": 1330, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9471544715447154, |
| "eval_loss": 0.18127350509166718, |
| "eval_runtime": 1017.0073, |
| "eval_samples_per_second": 0.726, |
| "eval_steps_per_second": 0.046, |
| "step": 133 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.94579945799458, |
| "eval_loss": 0.22662535309791565, |
| "eval_runtime": 2992.6864, |
| "eval_samples_per_second": 0.247, |
| "eval_steps_per_second": 0.016, |
| "step": 266 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9552845528455285, |
| "eval_loss": 0.2268151044845581, |
| "eval_runtime": 1007.3343, |
| "eval_samples_per_second": 0.733, |
| "eval_steps_per_second": 0.047, |
| "step": 399 |
| }, |
| { |
| "epoch": 3.7593984962406015, |
| "grad_norm": 0.7479304671287537, |
| "learning_rate": 1.249624060150376e-05, |
| "loss": 0.0922, |
| "step": 500 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9552845528455285, |
| "eval_loss": 0.2308872640132904, |
| "eval_runtime": 997.6443, |
| "eval_samples_per_second": 0.74, |
| "eval_steps_per_second": 0.047, |
| "step": 532 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9566395663956639, |
| "eval_loss": 0.27437824010849, |
| "eval_runtime": 984.572, |
| "eval_samples_per_second": 0.75, |
| "eval_steps_per_second": 0.048, |
| "step": 665 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.959349593495935, |
| "eval_loss": 0.27316540479660034, |
| "eval_runtime": 982.9248, |
| "eval_samples_per_second": 0.751, |
| "eval_steps_per_second": 0.048, |
| "step": 798 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.9539295392953929, |
| "eval_loss": 0.3055616021156311, |
| "eval_runtime": 1029.7815, |
| "eval_samples_per_second": 0.717, |
| "eval_steps_per_second": 0.046, |
| "step": 931 |
| }, |
| { |
| "epoch": 7.518796992481203, |
| "grad_norm": 0.0025694917421787977, |
| "learning_rate": 4.977443609022557e-06, |
| "loss": 0.0053, |
| "step": 1000 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.9512195121951219, |
| "eval_loss": 0.3166494071483612, |
| "eval_runtime": 1090.0234, |
| "eval_samples_per_second": 0.677, |
| "eval_steps_per_second": 0.043, |
| "step": 1064 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.9525745257452575, |
| "eval_loss": 0.3175627887248993, |
| "eval_runtime": 1001.2794, |
| "eval_samples_per_second": 0.737, |
| "eval_steps_per_second": 0.047, |
| "step": 1197 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_accuracy": 0.9525745257452575, |
| "eval_loss": 0.32180824875831604, |
| "eval_runtime": 997.2825, |
| "eval_samples_per_second": 0.74, |
| "eval_steps_per_second": 0.047, |
| "step": 1330 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1330, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 5583216594739200.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
