| { |
| "best_global_step": 1510, |
| "best_metric": 0.018495939671993256, |
| "best_model_checkpoint": "emotion_stress_model/checkpoint-1510", |
| "epoch": 10.0, |
| "eval_steps": 500, |
| "global_step": 1510, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.05536646023392677, |
| "eval_runtime": 14.5462, |
| "eval_samples_per_second": 85.727, |
| "eval_steps_per_second": 10.724, |
| "step": 151 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.03860075771808624, |
| "eval_runtime": 14.4066, |
| "eval_samples_per_second": 86.558, |
| "eval_steps_per_second": 10.828, |
| "step": 302 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.030712995678186417, |
| "eval_runtime": 14.3715, |
| "eval_samples_per_second": 86.769, |
| "eval_steps_per_second": 10.855, |
| "step": 453 |
| }, |
| { |
| "epoch": 3.3112582781456954, |
| "grad_norm": 0.020936382934451103, |
| "learning_rate": 0.00033476821192052983, |
| "loss": 0.1517, |
| "step": 500 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.02631240151822567, |
| "eval_runtime": 14.4578, |
| "eval_samples_per_second": 86.251, |
| "eval_steps_per_second": 10.79, |
| "step": 604 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 0.02286081574857235, |
| "eval_runtime": 14.2973, |
| "eval_samples_per_second": 87.219, |
| "eval_steps_per_second": 10.911, |
| "step": 755 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 0.02147683873772621, |
| "eval_runtime": 14.3247, |
| "eval_samples_per_second": 87.052, |
| "eval_steps_per_second": 10.89, |
| "step": 906 |
| }, |
| { |
| "epoch": 6.622516556291391, |
| "grad_norm": 0.053765054792165756, |
| "learning_rate": 0.000169205298013245, |
| "loss": 0.0175, |
| "step": 1000 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 0.01996658369898796, |
| "eval_runtime": 14.3047, |
| "eval_samples_per_second": 87.174, |
| "eval_steps_per_second": 10.906, |
| "step": 1057 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 0.019040055572986603, |
| "eval_runtime": 14.3217, |
| "eval_samples_per_second": 87.071, |
| "eval_steps_per_second": 10.893, |
| "step": 1208 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 0.018699418753385544, |
| "eval_runtime": 14.3379, |
| "eval_samples_per_second": 86.972, |
| "eval_steps_per_second": 10.88, |
| "step": 1359 |
| }, |
| { |
| "epoch": 9.933774834437086, |
| "grad_norm": 0.08323920518159866, |
| "learning_rate": 3.642384105960265e-06, |
| "loss": 0.0117, |
| "step": 1500 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 0.018495939671993256, |
| "eval_runtime": 16.41, |
| "eval_samples_per_second": 75.99, |
| "eval_steps_per_second": 9.506, |
| "step": 1510 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1510, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.743064374973235e+18, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
