| { |
| "best_metric": 0.27617308497428894, |
| "best_model_checkpoint": "checkpoints/instrucode/low-shot-task-specific-500-ex/emotion/checkpoint-87", |
| "epoch": 6.96, |
| "eval_steps": 500, |
| "global_step": 87, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.8, |
| "learning_rate": 7.333333333333333e-05, |
| "loss": 5.8573, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.96, |
| "eval_loss": 4.265514373779297, |
| "eval_runtime": 3.4719, |
| "eval_samples_per_second": 28.803, |
| "eval_steps_per_second": 3.744, |
| "step": 12 |
| }, |
| { |
| "epoch": 1.6, |
| "learning_rate": 6.666666666666667e-05, |
| "loss": 3.8105, |
| "step": 20 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 1.5850574970245361, |
| "eval_runtime": 3.4571, |
| "eval_samples_per_second": 28.926, |
| "eval_steps_per_second": 3.76, |
| "step": 25 |
| }, |
| { |
| "epoch": 2.4, |
| "learning_rate": 6.0666666666666666e-05, |
| "loss": 1.7041, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.96, |
| "eval_loss": 0.5069144368171692, |
| "eval_runtime": 3.4616, |
| "eval_samples_per_second": 28.889, |
| "eval_steps_per_second": 3.756, |
| "step": 37 |
| }, |
| { |
| "epoch": 3.2, |
| "learning_rate": 5.4000000000000005e-05, |
| "loss": 0.6618, |
| "step": 40 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 4.7333333333333336e-05, |
| "loss": 0.3247, |
| "step": 50 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.33890244364738464, |
| "eval_runtime": 3.4571, |
| "eval_samples_per_second": 28.926, |
| "eval_steps_per_second": 3.76, |
| "step": 50 |
| }, |
| { |
| "epoch": 4.8, |
| "learning_rate": 4.066666666666667e-05, |
| "loss": 0.271, |
| "step": 60 |
| }, |
| { |
| "epoch": 4.96, |
| "eval_loss": 0.3074319362640381, |
| "eval_runtime": 3.4533, |
| "eval_samples_per_second": 28.958, |
| "eval_steps_per_second": 3.765, |
| "step": 62 |
| }, |
| { |
| "epoch": 5.6, |
| "learning_rate": 3.4e-05, |
| "loss": 0.2088, |
| "step": 70 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 0.29454201459884644, |
| "eval_runtime": 3.448, |
| "eval_samples_per_second": 29.002, |
| "eval_steps_per_second": 3.77, |
| "step": 75 |
| }, |
| { |
| "epoch": 6.4, |
| "learning_rate": 2.7333333333333335e-05, |
| "loss": 0.1924, |
| "step": 80 |
| }, |
| { |
| "epoch": 6.96, |
| "eval_loss": 0.27617308497428894, |
| "eval_runtime": 3.4613, |
| "eval_samples_per_second": 28.89, |
| "eval_steps_per_second": 3.756, |
| "step": 87 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 120, |
| "num_train_epochs": 10, |
| "save_steps": 500, |
| "total_flos": 1.002400891600896e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
