| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 5.0, |
| "eval_steps": 166, |
| "global_step": 1660, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.5, |
| "eval_retrieval-eval_cosine_accuracy": 0.9730818271636963, |
| "eval_runtime": 5.0818, |
| "eval_samples_per_second": 0.0, |
| "eval_steps_per_second": 0.0, |
| "step": 166 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_retrieval-eval_cosine_accuracy": 0.9785926342010498, |
| "eval_runtime": 5.1614, |
| "eval_samples_per_second": 0.0, |
| "eval_steps_per_second": 0.0, |
| "step": 332 |
| }, |
| { |
| "epoch": 1.5, |
| "eval_retrieval-eval_cosine_accuracy": 0.979440450668335, |
| "eval_runtime": 5.0153, |
| "eval_samples_per_second": 0.0, |
| "eval_steps_per_second": 0.0, |
| "step": 498 |
| }, |
| { |
| "epoch": 1.5060240963855422, |
| "grad_norm": 0.242173433303833, |
| "learning_rate": 1.5527199462726662e-05, |
| "loss": 0.0784, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_retrieval-eval_cosine_accuracy": 0.9815599918365479, |
| "eval_runtime": 5.097, |
| "eval_samples_per_second": 0.0, |
| "eval_steps_per_second": 0.0, |
| "step": 664 |
| }, |
| { |
| "epoch": 2.5, |
| "eval_retrieval-eval_cosine_accuracy": 0.9826197624206543, |
| "eval_runtime": 5.0153, |
| "eval_samples_per_second": 0.0, |
| "eval_steps_per_second": 0.0, |
| "step": 830 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_retrieval-eval_cosine_accuracy": 0.9834675788879395, |
| "eval_runtime": 5.1638, |
| "eval_samples_per_second": 0.0, |
| "eval_steps_per_second": 0.0, |
| "step": 996 |
| }, |
| { |
| "epoch": 3.0120481927710845, |
| "grad_norm": 0.21960429847240448, |
| "learning_rate": 8.811282740094024e-06, |
| "loss": 0.0259, |
| "step": 1000 |
| }, |
| { |
| "epoch": 3.5, |
| "eval_retrieval-eval_cosine_accuracy": 0.9819839000701904, |
| "eval_runtime": 5.2312, |
| "eval_samples_per_second": 0.0, |
| "eval_steps_per_second": 0.0, |
| "step": 1162 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_retrieval-eval_cosine_accuracy": 0.9834675788879395, |
| "eval_runtime": 5.0759, |
| "eval_samples_per_second": 0.0, |
| "eval_steps_per_second": 0.0, |
| "step": 1328 |
| }, |
| { |
| "epoch": 4.5, |
| "eval_retrieval-eval_cosine_accuracy": 0.9834675788879395, |
| "eval_runtime": 5.0083, |
| "eval_samples_per_second": 0.0, |
| "eval_steps_per_second": 0.0, |
| "step": 1494 |
| }, |
| { |
| "epoch": 4.518072289156627, |
| "grad_norm": 0.21867941319942474, |
| "learning_rate": 2.0953660174613837e-06, |
| "loss": 0.0227, |
| "step": 1500 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_retrieval-eval_cosine_accuracy": 0.9830436706542969, |
| "eval_runtime": 5.0895, |
| "eval_samples_per_second": 0.0, |
| "eval_steps_per_second": 0.0, |
| "step": 1660 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1660, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 332, |
| "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 |
| } |
|
|
