| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.8363636363636364, | |
| "eval_steps": 500, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07272727272727272, | |
| "grad_norm": 4.296287165248239e+19, | |
| "learning_rate": 5e-06, | |
| "loss": 1.811, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 48.877031489724665, | |
| "learning_rate": 1.9959742939952393e-05, | |
| "loss": 1.7621, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 5.706010348947357, | |
| "learning_rate": 1.8584487936018663e-05, | |
| "loss": 1.5976, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9454545454545454, | |
| "eval_loss": 1.3575862646102905, | |
| "eval_runtime": 17.2916, | |
| "eval_samples_per_second": 23.19, | |
| "eval_steps_per_second": 0.405, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.0909090909090908, | |
| "grad_norm": 16.400604039606975, | |
| "learning_rate": 1.5508969814521026e-05, | |
| "loss": 1.3631, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.4545454545454546, | |
| "grad_norm": 1.8322885262016182, | |
| "learning_rate": 1.1342332658176556e-05, | |
| "loss": 1.1959, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.8181818181818183, | |
| "grad_norm": 1.2870157302557228, | |
| "learning_rate": 6.909830056250527e-06, | |
| "loss": 1.1144, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.9636363636363636, | |
| "eval_loss": 1.1654328107833862, | |
| "eval_runtime": 16.9503, | |
| "eval_samples_per_second": 23.657, | |
| "eval_steps_per_second": 0.413, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.1818181818181817, | |
| "grad_norm": 1.1371806878234814, | |
| "learning_rate": 3.089373510131354e-06, | |
| "loss": 1.0157, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.5454545454545454, | |
| "grad_norm": 1.0068430758916334, | |
| "learning_rate": 6.37651293602628e-07, | |
| "loss": 0.9179, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.8363636363636364, | |
| "eval_loss": 1.1494024991989136, | |
| "eval_runtime": 16.7788, | |
| "eval_samples_per_second": 23.899, | |
| "eval_steps_per_second": 0.417, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.8363636363636364, | |
| "step": 39, | |
| "total_flos": 50553107251200.0, | |
| "train_loss": 1.2458087847783015, | |
| "train_runtime": 1582.9273, | |
| "train_samples_per_second": 6.635, | |
| "train_steps_per_second": 0.025 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 39, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 50553107251200.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |