| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.0, | |
| "eval_steps": 500, | |
| "global_step": 1908, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.950235849056605e-06, | |
| "loss": 6.539, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 6.494007587432861, | |
| "eval_runtime": 2.5292, | |
| "eval_samples_per_second": 267.281, | |
| "eval_steps_per_second": 33.608, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 9.900235849056603e-06, | |
| "loss": 6.4697, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 6.410468101501465, | |
| "eval_runtime": 2.6306, | |
| "eval_samples_per_second": 256.98, | |
| "eval_steps_per_second": 32.313, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 9.850235849056604e-06, | |
| "loss": 6.3924, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 6.319283962249756, | |
| "eval_runtime": 2.6112, | |
| "eval_samples_per_second": 258.881, | |
| "eval_steps_per_second": 32.552, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 9.800235849056604e-06, | |
| "loss": 6.3093, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 6.226834297180176, | |
| "eval_runtime": 2.5547, | |
| "eval_samples_per_second": 264.612, | |
| "eval_steps_per_second": 33.272, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 9.750235849056605e-06, | |
| "loss": 6.216, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 6.127103328704834, | |
| "eval_runtime": 2.5792, | |
| "eval_samples_per_second": 262.1, | |
| "eval_steps_per_second": 32.956, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 9.700235849056605e-06, | |
| "loss": 6.1217, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 6.023599147796631, | |
| "eval_runtime": 2.6119, | |
| "eval_samples_per_second": 258.818, | |
| "eval_steps_per_second": 32.544, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 9.650235849056606e-06, | |
| "loss": 6.0274, | |
| "step": 1484 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 5.916015625, | |
| "eval_runtime": 2.7327, | |
| "eval_samples_per_second": 247.379, | |
| "eval_steps_per_second": 31.105, | |
| "step": 1484 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 9.600235849056605e-06, | |
| "loss": 5.9233, | |
| "step": 1696 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 5.803537368774414, | |
| "eval_runtime": 2.6768, | |
| "eval_samples_per_second": 252.536, | |
| "eval_steps_per_second": 31.754, | |
| "step": 1696 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 9.550235849056605e-06, | |
| "loss": 5.8234, | |
| "step": 1908 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 5.689106464385986, | |
| "eval_runtime": 2.688, | |
| "eval_samples_per_second": 251.488, | |
| "eval_steps_per_second": 31.622, | |
| "step": 1908 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 42400, | |
| "num_train_epochs": 200, | |
| "save_steps": 500, | |
| "total_flos": 2563585967589252.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |