| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.003565888708613404, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.131777417226809e-05, | |
| "eval_loss": 6.896366119384766, | |
| "eval_runtime": 13.1029, | |
| "eval_samples_per_second": 450.589, | |
| "eval_steps_per_second": 225.294, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007131777417226808, | |
| "grad_norm": 0.8091431260108948, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 6.8868, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0009271310642394851, | |
| "eval_loss": 6.856056213378906, | |
| "eval_runtime": 12.3516, | |
| "eval_samples_per_second": 477.993, | |
| "eval_steps_per_second": 238.997, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0014263554834453617, | |
| "grad_norm": 0.7809100151062012, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 6.8414, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0018542621284789703, | |
| "eval_loss": 6.819371223449707, | |
| "eval_runtime": 12.4693, | |
| "eval_samples_per_second": 473.481, | |
| "eval_steps_per_second": 236.741, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0021395332251680425, | |
| "grad_norm": 0.5226926207542419, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 6.8229, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0027813931927184554, | |
| "eval_loss": 6.807439804077148, | |
| "eval_runtime": 12.4673, | |
| "eval_samples_per_second": 473.558, | |
| "eval_steps_per_second": 236.779, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0028527109668907234, | |
| "grad_norm": 0.44697293639183044, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 6.8026, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.003565888708613404, | |
| "grad_norm": 0.324945330619812, | |
| "learning_rate": 0.0, | |
| "loss": 6.7972, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 76463161344.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |