| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0007848622214619568, | |
| "eval_steps": 13, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.012467234517838e-05, | |
| "eval_loss": 2.3407986164093018, | |
| "eval_runtime": 869.0554, | |
| "eval_samples_per_second": 24.076, | |
| "eval_steps_per_second": 12.038, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002012467234517838, | |
| "grad_norm": 7.7000651359558105, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 1.6249, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00026162074048731893, | |
| "eval_loss": 1.553385853767395, | |
| "eval_runtime": 871.0063, | |
| "eval_samples_per_second": 24.022, | |
| "eval_steps_per_second": 12.011, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0004024934469035676, | |
| "grad_norm": 1.1939016580581665, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.2342, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0005232414809746379, | |
| "eval_loss": 1.50654935836792, | |
| "eval_runtime": 869.7048, | |
| "eval_samples_per_second": 24.058, | |
| "eval_steps_per_second": 12.029, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0006037401703553514, | |
| "grad_norm": 0.6607839465141296, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 1.2162, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0007848622214619568, | |
| "eval_loss": 1.4915814399719238, | |
| "eval_runtime": 870.7377, | |
| "eval_samples_per_second": 24.029, | |
| "eval_steps_per_second": 12.015, | |
| "step": 39 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9029906941870080.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |