| { |
| "best_metric": 0.03475998714566231, |
| "best_model_checkpoint": "t5/checkpoint-785", |
| "epoch": 8.0, |
| "eval_steps": 500, |
| "global_step": 1256, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.17618757486343384, |
| "learning_rate": 1.9e-05, |
| "loss": 0.0618, |
| "step": 157 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.6860511590727418, |
| "eval_loss": 0.041351497173309326, |
| "eval_runtime": 60.885, |
| "eval_samples_per_second": 82.188, |
| "eval_steps_per_second": 0.328, |
| "step": 157 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.18060798943042755, |
| "learning_rate": 1.8e-05, |
| "loss": 0.0423, |
| "step": 314 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.707234212629896, |
| "eval_loss": 0.03738662600517273, |
| "eval_runtime": 60.1479, |
| "eval_samples_per_second": 83.195, |
| "eval_steps_per_second": 0.333, |
| "step": 314 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.20145682990550995, |
| "learning_rate": 1.7e-05, |
| "loss": 0.0368, |
| "step": 471 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.7208233413269385, |
| "eval_loss": 0.03572960942983627, |
| "eval_runtime": 59.3756, |
| "eval_samples_per_second": 84.277, |
| "eval_steps_per_second": 0.337, |
| "step": 471 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.20047585666179657, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 0.0326, |
| "step": 628 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.7262190247801759, |
| "eval_loss": 0.03503531962633133, |
| "eval_runtime": 59.034, |
| "eval_samples_per_second": 84.765, |
| "eval_steps_per_second": 0.339, |
| "step": 628 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.1549680233001709, |
| "learning_rate": 1.5000000000000002e-05, |
| "loss": 0.0293, |
| "step": 785 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.7294164668265388, |
| "eval_loss": 0.03475998714566231, |
| "eval_runtime": 59.2862, |
| "eval_samples_per_second": 84.404, |
| "eval_steps_per_second": 0.337, |
| "step": 785 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 0.19214752316474915, |
| "learning_rate": 1.4e-05, |
| "loss": 0.0266, |
| "step": 942 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.7352118305355716, |
| "eval_loss": 0.0347641222178936, |
| "eval_runtime": 59.4378, |
| "eval_samples_per_second": 84.189, |
| "eval_steps_per_second": 0.336, |
| "step": 942 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 0.1793193817138672, |
| "learning_rate": 1.3000000000000001e-05, |
| "loss": 0.0243, |
| "step": 1099 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.7328137490007993, |
| "eval_loss": 0.03488365188241005, |
| "eval_runtime": 59.8565, |
| "eval_samples_per_second": 83.6, |
| "eval_steps_per_second": 0.334, |
| "step": 1099 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 0.19961176812648773, |
| "learning_rate": 1.2e-05, |
| "loss": 0.0223, |
| "step": 1256 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.7356115107913669, |
| "eval_loss": 0.03529239445924759, |
| "eval_runtime": 58.7625, |
| "eval_samples_per_second": 85.156, |
| "eval_steps_per_second": 0.34, |
| "step": 1256 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 3140, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 20, |
| "save_steps": 500, |
| "total_flos": 4.333072619596493e+16, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
