| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.001444616995918957, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001444616995918957, | |
| "grad_norm": 21.63092613220215, | |
| "learning_rate": 2e-05, | |
| "loss": 21.8834, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001444616995918957, | |
| "eval_loss": 4.276644229888916, | |
| "eval_runtime": 92.2624, | |
| "eval_samples_per_second": 31.595, | |
| "eval_steps_per_second": 15.803, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002889233991837914, | |
| "grad_norm": 21.212491989135742, | |
| "learning_rate": 4e-05, | |
| "loss": 18.1309, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0004333850987756871, | |
| "grad_norm": 16.177396774291992, | |
| "learning_rate": 6e-05, | |
| "loss": 11.7434, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004333850987756871, | |
| "eval_loss": 4.244970321655273, | |
| "eval_runtime": 92.214, | |
| "eval_samples_per_second": 31.611, | |
| "eval_steps_per_second": 15.811, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005778467983675828, | |
| "grad_norm": 22.770856857299805, | |
| "learning_rate": 8e-05, | |
| "loss": 15.3734, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0007223084979594785, | |
| "grad_norm": 55.7369384765625, | |
| "learning_rate": 0.0001, | |
| "loss": 16.1757, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008667701975513742, | |
| "grad_norm": 26.890945434570312, | |
| "learning_rate": 0.00012, | |
| "loss": 13.9323, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0008667701975513742, | |
| "eval_loss": 3.9386675357818604, | |
| "eval_runtime": 92.3516, | |
| "eval_samples_per_second": 31.564, | |
| "eval_steps_per_second": 15.787, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0010112318971432699, | |
| "grad_norm": 26.319618225097656, | |
| "learning_rate": 0.00014, | |
| "loss": 21.9336, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0011556935967351656, | |
| "grad_norm": 22.64849090576172, | |
| "learning_rate": 0.00016, | |
| "loss": 17.5867, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0013001552963270613, | |
| "grad_norm": 21.528902053833008, | |
| "learning_rate": 0.00018, | |
| "loss": 12.9675, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0013001552963270613, | |
| "eval_loss": 3.3029394149780273, | |
| "eval_runtime": 92.3148, | |
| "eval_samples_per_second": 31.577, | |
| "eval_steps_per_second": 15.794, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001444616995918957, | |
| "grad_norm": 15.71590805053711, | |
| "learning_rate": 0.0002, | |
| "loss": 11.5817, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1628749242040320.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |