| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 6.0, |
| "eval_steps": 5000, |
| "global_step": 13668, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0004389815627743635, |
| "grad_norm": 12.308442115783691, |
| "learning_rate": 0.0, |
| "loss": 5.3655, |
| "step": 1 |
| }, |
| { |
| "epoch": 2.194907813871817, |
| "grad_norm": 5.572308540344238, |
| "learning_rate": 2.2396976347232385e-05, |
| "loss": 2.1423, |
| "step": 5000 |
| }, |
| { |
| "epoch": 2.194907813871817, |
| "eval_cosine_accuracy": 0.9412940740585327, |
| "eval_loss": 0.7694418430328369, |
| "eval_runtime": 32.5011, |
| "eval_samples_per_second": 292.451, |
| "eval_steps_per_second": 2.308, |
| "step": 5000 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 10.984454154968262, |
| "learning_rate": 2.085048010973937e-05, |
| "loss": 1.4316, |
| "step": 9112 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_cosine_accuracy": 0.9375065565109253, |
| "eval_loss": 0.7735732793807983, |
| "eval_runtime": 32.1541, |
| "eval_samples_per_second": 295.608, |
| "eval_steps_per_second": 2.333, |
| "step": 9112 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 10.955339431762695, |
| "learning_rate": 1.0434385002286237e-05, |
| "loss": 1.3415, |
| "step": 11390 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_cosine_accuracy": 0.9435034394264221, |
| "eval_loss": 0.7540939450263977, |
| "eval_runtime": 31.893, |
| "eval_samples_per_second": 298.028, |
| "eval_steps_per_second": 2.352, |
| "step": 11390 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 10.055571556091309, |
| "learning_rate": 2.2862368541380888e-08, |
| "loss": 1.2848, |
| "step": 13668 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_cosine_accuracy": 0.945607602596283, |
| "eval_loss": 0.7366093397140503, |
| "eval_runtime": 32.7761, |
| "eval_samples_per_second": 289.998, |
| "eval_steps_per_second": 2.288, |
| "step": 13668 |
| } |
| ], |
| "logging_steps": 5000, |
| "max_steps": 13668, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "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": 0.0, |
| "train_batch_size": 128, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
