| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 106, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009433962264150943, | |
| "grad_norm": 5.985288575079748, | |
| "learning_rate": 1.8181818181818183e-06, | |
| "loss": 0.6499, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04716981132075472, | |
| "grad_norm": 5.814438570238304, | |
| "learning_rate": 9.090909090909091e-06, | |
| "loss": 0.5661, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09433962264150944, | |
| "grad_norm": 5.784780010142115, | |
| "learning_rate": 1.8181818181818182e-05, | |
| "loss": 0.661, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14150943396226415, | |
| "grad_norm": 11.34990477900501, | |
| "learning_rate": 1.9912640693269754e-05, | |
| "loss": 0.7798, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.18867924528301888, | |
| "grad_norm": 13.42523247607025, | |
| "learning_rate": 1.9560357815343577e-05, | |
| "loss": 0.7601, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2358490566037736, | |
| "grad_norm": 4.324162158047662, | |
| "learning_rate": 1.8947293298207637e-05, | |
| "loss": 0.7358, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2830188679245283, | |
| "grad_norm": 7.9124387033173145, | |
| "learning_rate": 1.8090169943749477e-05, | |
| "loss": 0.7747, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.330188679245283, | |
| "grad_norm": 12.067384487954993, | |
| "learning_rate": 1.7012367842724887e-05, | |
| "loss": 0.7998, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.37735849056603776, | |
| "grad_norm": 6.22835019020897, | |
| "learning_rate": 1.5743286626829437e-05, | |
| "loss": 0.724, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.42452830188679247, | |
| "grad_norm": 6.796713146623649, | |
| "learning_rate": 1.4317543523384928e-05, | |
| "loss": 0.7593, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4716981132075472, | |
| "grad_norm": 4.733778471400881, | |
| "learning_rate": 1.2774029087618448e-05, | |
| "loss": 0.7201, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5188679245283019, | |
| "grad_norm": 449.44276588082573, | |
| "learning_rate": 1.1154846369695864e-05, | |
| "loss": 0.7419, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.5660377358490566, | |
| "grad_norm": 9.159227195595605, | |
| "learning_rate": 9.504162453267776e-06, | |
| "loss": 0.7403, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6132075471698113, | |
| "grad_norm": 5.2750906217882765, | |
| "learning_rate": 7.867003692562533e-06, | |
| "loss": 0.6968, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.660377358490566, | |
| "grad_norm": 14.875356296901776, | |
| "learning_rate": 6.2880275108177915e-06, | |
| "loss": 0.7952, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7075471698113207, | |
| "grad_norm": 3.905855499670756, | |
| "learning_rate": 4.8103042621878515e-06, | |
| "loss": 0.6757, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.7547169811320755, | |
| "grad_norm": 6.381379535048558, | |
| "learning_rate": 3.4741423847583134e-06, | |
| "loss": 0.735, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8018867924528302, | |
| "grad_norm": 3.4881845137428154, | |
| "learning_rate": 2.315988891431412e-06, | |
| "loss": 0.6972, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.8490566037735849, | |
| "grad_norm": 3.873409886533883, | |
| "learning_rate": 1.367435190424261e-06, | |
| "loss": 0.6924, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8962264150943396, | |
| "grad_norm": 3.2267692661670075, | |
| "learning_rate": 6.543553540053926e-07, | |
| "loss": 0.7133, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.9433962264150944, | |
| "grad_norm": 7.343399360027914, | |
| "learning_rate": 1.9620034125190645e-07, | |
| "loss": 0.6743, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9905660377358491, | |
| "grad_norm": 2.875162947751637, | |
| "learning_rate": 5.467426590739511e-09, | |
| "loss": 0.6652, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.47219160199165344, | |
| "eval_runtime": 6.471, | |
| "eval_samples_per_second": 25.035, | |
| "eval_steps_per_second": 0.464, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 106, | |
| "total_flos": 22194243502080.0, | |
| "train_loss": 0.7179017213155638, | |
| "train_runtime": 1325.9838, | |
| "train_samples_per_second": 5.109, | |
| "train_steps_per_second": 0.08 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 106, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 22194243502080.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |