| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03073140749846343, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006146281499692685, | |
| "eval_loss": 32.18796920776367, | |
| "eval_runtime": 9.9698, | |
| "eval_samples_per_second": 68.708, | |
| "eval_steps_per_second": 34.404, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003073140749846343, | |
| "grad_norm": 1042.032958984375, | |
| "learning_rate": 5e-05, | |
| "loss": 151.3782, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006146281499692686, | |
| "grad_norm": 1655.912109375, | |
| "learning_rate": 0.0001, | |
| "loss": 90.5781, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006146281499692686, | |
| "eval_loss": 32.177650451660156, | |
| "eval_runtime": 7.9223, | |
| "eval_samples_per_second": 86.465, | |
| "eval_steps_per_second": 43.296, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00921942224953903, | |
| "grad_norm": 1991.4852294921875, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 130.4381, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012292562999385371, | |
| "grad_norm": 642.9652099609375, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 99.3049, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.012292562999385371, | |
| "eval_loss": 32.11423873901367, | |
| "eval_runtime": 7.9533, | |
| "eval_samples_per_second": 86.128, | |
| "eval_steps_per_second": 43.127, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.015365703749231715, | |
| "grad_norm": 820.176513671875, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 36.4627, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01843884449907806, | |
| "grad_norm": 483.0568542480469, | |
| "learning_rate": 5e-05, | |
| "loss": 69.362, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01843884449907806, | |
| "eval_loss": 32.029048919677734, | |
| "eval_runtime": 8.109, | |
| "eval_samples_per_second": 84.474, | |
| "eval_steps_per_second": 42.299, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0215119852489244, | |
| "grad_norm": 1287.2490234375, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 60.0403, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.024585125998770743, | |
| "grad_norm": 5726.9609375, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 177.8988, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.024585125998770743, | |
| "eval_loss": 32.00729751586914, | |
| "eval_runtime": 7.9572, | |
| "eval_samples_per_second": 86.086, | |
| "eval_steps_per_second": 43.106, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.027658266748617086, | |
| "grad_norm": 1328.4888916015625, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 125.6105, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03073140749846343, | |
| "grad_norm": 929.8414306640625, | |
| "learning_rate": 0.0, | |
| "loss": 61.2684, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03073140749846343, | |
| "eval_loss": 31.988927841186523, | |
| "eval_runtime": 7.9558, | |
| "eval_samples_per_second": 86.101, | |
| "eval_steps_per_second": 43.113, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "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": 92199173750784.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |