| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.06389776357827476, |
| "eval_steps": 8, |
| "global_step": 30, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.002129925452609159, |
| "eval_loss": 3.5438625812530518, |
| "eval_runtime": 25.4787, |
| "eval_samples_per_second": 7.771, |
| "eval_steps_per_second": 3.886, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.006389776357827476, |
| "grad_norm": 2.2887728214263916, |
| "learning_rate": 6e-05, |
| "loss": 3.4855, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.012779552715654952, |
| "grad_norm": 2.4641361236572266, |
| "learning_rate": 0.00012, |
| "loss": 3.5091, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.01703940362087327, |
| "eval_loss": 2.8688793182373047, |
| "eval_runtime": 25.4627, |
| "eval_samples_per_second": 7.776, |
| "eval_steps_per_second": 3.888, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.019169329073482427, |
| "grad_norm": 2.2242677211761475, |
| "learning_rate": 0.00018, |
| "loss": 2.8897, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.025559105431309903, |
| "grad_norm": 2.309509515762329, |
| "learning_rate": 0.00019510565162951537, |
| "loss": 2.7125, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.03194888178913738, |
| "grad_norm": 2.2507786750793457, |
| "learning_rate": 0.00017071067811865476, |
| "loss": 2.6185, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.03407880724174654, |
| "eval_loss": 2.331763505935669, |
| "eval_runtime": 25.5887, |
| "eval_samples_per_second": 7.738, |
| "eval_steps_per_second": 3.869, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.038338658146964855, |
| "grad_norm": 1.899119257926941, |
| "learning_rate": 0.00013090169943749476, |
| "loss": 2.4637, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.04472843450479233, |
| "grad_norm": 2.4376401901245117, |
| "learning_rate": 8.435655349597689e-05, |
| "loss": 1.9915, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.051118210862619806, |
| "grad_norm": 2.1409995555877686, |
| "learning_rate": 4.12214747707527e-05, |
| "loss": 2.3439, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.051118210862619806, |
| "eval_loss": 2.130235195159912, |
| "eval_runtime": 25.6379, |
| "eval_samples_per_second": 7.723, |
| "eval_steps_per_second": 3.861, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.05750798722044728, |
| "grad_norm": 2.9437363147735596, |
| "learning_rate": 1.0899347581163221e-05, |
| "loss": 2.297, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.06389776357827476, |
| "grad_norm": 2.069322347640991, |
| "learning_rate": 0.0, |
| "loss": 2.0593, |
| "step": 30 |
| } |
| ], |
| "logging_steps": 3, |
| "max_steps": 30, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 10, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.112830925340672e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
