| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.564102564102564, | |
| "eval_steps": 100, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5128205128205128, | |
| "grad_norm": 73.68424224853516, | |
| "learning_rate": 9.9907e-06, | |
| "loss": 3.1457, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5128205128205128, | |
| "eval_loss": 2.2357213497161865, | |
| "eval_runtime": 36.4689, | |
| "eval_samples_per_second": 10.776, | |
| "eval_steps_per_second": 1.371, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0256410256410255, | |
| "grad_norm": 57.47202682495117, | |
| "learning_rate": 9.980800000000001e-06, | |
| "loss": 2.1614, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.0256410256410255, | |
| "eval_loss": 2.0913825035095215, | |
| "eval_runtime": 36.349, | |
| "eval_samples_per_second": 10.812, | |
| "eval_steps_per_second": 1.376, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": 176.88357543945312, | |
| "learning_rate": 9.970800000000001e-06, | |
| "loss": 2.0388, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "eval_loss": 2.003911018371582, | |
| "eval_runtime": 36.2551, | |
| "eval_samples_per_second": 10.84, | |
| "eval_steps_per_second": 1.379, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.051282051282051, | |
| "grad_norm": 55.31132507324219, | |
| "learning_rate": 9.960800000000001e-06, | |
| "loss": 1.9285, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.051282051282051, | |
| "eval_loss": 1.9796075820922852, | |
| "eval_runtime": 36.4437, | |
| "eval_samples_per_second": 10.784, | |
| "eval_steps_per_second": 1.372, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.564102564102564, | |
| "grad_norm": 41.900753021240234, | |
| "learning_rate": 9.9508e-06, | |
| "loss": 1.9523, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.564102564102564, | |
| "eval_loss": 1.936122179031372, | |
| "eval_runtime": 36.5845, | |
| "eval_samples_per_second": 10.742, | |
| "eval_steps_per_second": 1.367, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 100000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 513, | |
| "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": 1.91121583104e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |