| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 15, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3e-05, | |
| "loss": 2.3721, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.06414321574844761, | |
| "eval_loss": 2.21484375, | |
| "eval_runtime": 1.2171, | |
| "eval_samples_per_second": 23.828, | |
| "eval_steps_per_second": 0.822, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3e-05, | |
| "loss": 2.241, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_accuracy": 0.06414321574844761, | |
| "eval_loss": 2.21484375, | |
| "eval_runtime": 1.292, | |
| "eval_samples_per_second": 22.446, | |
| "eval_steps_per_second": 0.774, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2.9672214011007087e-05, | |
| "loss": 2.469, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_accuracy": 0.06526621746597966, | |
| "eval_loss": 2.134765625, | |
| "eval_runtime": 1.0981, | |
| "eval_samples_per_second": 26.409, | |
| "eval_steps_per_second": 0.911, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2.8703181864639013e-05, | |
| "loss": 2.3735, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_accuracy": 0.06480380499405469, | |
| "eval_loss": 2.130859375, | |
| "eval_runtime": 0.8874, | |
| "eval_samples_per_second": 32.681, | |
| "eval_steps_per_second": 1.127, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2.7135254915624213e-05, | |
| "loss": 2.2755, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.06520015854141895, | |
| "eval_loss": 2.11328125, | |
| "eval_runtime": 1.0131, | |
| "eval_samples_per_second": 28.625, | |
| "eval_steps_per_second": 0.987, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 2.5036959095382875e-05, | |
| "loss": 2.0428, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_accuracy": 0.06586074778702602, | |
| "eval_loss": 2.09375, | |
| "eval_runtime": 0.9993, | |
| "eval_samples_per_second": 29.021, | |
| "eval_steps_per_second": 1.001, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.25e-05, | |
| "loss": 1.764, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_accuracy": 0.06592680671158674, | |
| "eval_loss": 2.078125, | |
| "eval_runtime": 0.6991, | |
| "eval_samples_per_second": 41.485, | |
| "eval_steps_per_second": 1.431, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 1.963525491562421e-05, | |
| "loss": 1.7458, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_accuracy": 0.06605892456070815, | |
| "eval_loss": 2.078125, | |
| "eval_runtime": 0.9029, | |
| "eval_samples_per_second": 32.119, | |
| "eval_steps_per_second": 1.108, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 1.6567926949014805e-05, | |
| "loss": 1.868, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_accuracy": 0.06599286563614744, | |
| "eval_loss": 2.08203125, | |
| "eval_runtime": 1.2995, | |
| "eval_samples_per_second": 22.316, | |
| "eval_steps_per_second": 0.77, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.3432073050985201e-05, | |
| "loss": 1.9548, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.06632316025895098, | |
| "eval_loss": 2.0703125, | |
| "eval_runtime": 1.0961, | |
| "eval_samples_per_second": 26.458, | |
| "eval_steps_per_second": 0.912, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 1.036474508437579e-05, | |
| "loss": 1.6772, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_accuracy": 0.0664552781080724, | |
| "eval_loss": 2.060546875, | |
| "eval_runtime": 1.0956, | |
| "eval_samples_per_second": 26.469, | |
| "eval_steps_per_second": 0.913, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 7.500000000000004e-06, | |
| "loss": 1.3997, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_accuracy": 0.06678557273087594, | |
| "eval_loss": 2.056640625, | |
| "eval_runtime": 1.3048, | |
| "eval_samples_per_second": 22.226, | |
| "eval_steps_per_second": 0.766, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 4.963040904617131e-06, | |
| "loss": 1.3717, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "eval_accuracy": 0.06691769057999736, | |
| "eval_loss": 2.0546875, | |
| "eval_runtime": 1.0974, | |
| "eval_samples_per_second": 26.426, | |
| "eval_steps_per_second": 0.911, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 2.86474508437579e-06, | |
| "loss": 1.5284, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_accuracy": 0.06671951380631523, | |
| "eval_loss": 2.0546875, | |
| "eval_runtime": 1.2969, | |
| "eval_samples_per_second": 22.361, | |
| "eval_steps_per_second": 0.771, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 1.2968181353609854e-06, | |
| "loss": 1.2264, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.06691769057999736, | |
| "eval_loss": 2.056640625, | |
| "eval_runtime": 0.8003, | |
| "eval_samples_per_second": 36.234, | |
| "eval_steps_per_second": 1.249, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 15, | |
| "total_flos": 1415705001984.0, | |
| "train_loss": 1.8873453776041667, | |
| "train_runtime": 59.0651, | |
| "train_samples_per_second": 7.923, | |
| "train_steps_per_second": 0.254 | |
| } | |
| ], | |
| "max_steps": 15, | |
| "num_train_epochs": 3, | |
| "total_flos": 1415705001984.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |