| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 4.993927617196988, |
| "eval_steps": 500, |
| "global_step": 2570, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.9715812484819043, |
| "grad_norm": 0.0, |
| "learning_rate": 1.9460259489596192e-05, |
| "loss": 0.0282, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.9987855234393976, |
| "eval_reranking_1_loss": 0.182732954621315, |
| "eval_reranking_1_runtime": 1.2858, |
| "eval_reranking_1_samples_per_second": 29.553, |
| "eval_reranking_1_steps_per_second": 14.777, |
| "step": 514 |
| }, |
| { |
| "epoch": 0.9987855234393976, |
| "eval_retrival_1_loss": 0.1305331587791443, |
| "eval_retrival_1_runtime": 26.5236, |
| "eval_retrival_1_samples_per_second": 32.726, |
| "eval_retrival_1_steps_per_second": 16.363, |
| "step": 514 |
| }, |
| { |
| "epoch": 0.9987855234393976, |
| "eval_sts_1_loss": 0.2950426936149597, |
| "eval_sts_1_runtime": 0.2829, |
| "eval_sts_1_samples_per_second": 35.351, |
| "eval_sts_1_steps_per_second": 17.676, |
| "step": 514 |
| }, |
| { |
| "epoch": 1.9431624969638086, |
| "grad_norm": 6.779000282287598, |
| "learning_rate": 1.5325659218524745e-05, |
| "loss": 0.0555, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.999514209375759, |
| "eval_reranking_1_loss": 0.3932221829891205, |
| "eval_reranking_1_runtime": 1.258, |
| "eval_reranking_1_samples_per_second": 30.208, |
| "eval_reranking_1_steps_per_second": 15.104, |
| "step": 1029 |
| }, |
| { |
| "epoch": 1.999514209375759, |
| "eval_retrival_1_loss": 0.06928794831037521, |
| "eval_retrival_1_runtime": 28.2993, |
| "eval_retrival_1_samples_per_second": 30.672, |
| "eval_retrival_1_steps_per_second": 15.336, |
| "step": 1029 |
| }, |
| { |
| "epoch": 1.999514209375759, |
| "eval_sts_1_loss": 0.8648566007614136, |
| "eval_sts_1_runtime": 0.2978, |
| "eval_sts_1_samples_per_second": 33.582, |
| "eval_sts_1_steps_per_second": 16.791, |
| "step": 1029 |
| }, |
| { |
| "epoch": 2.914743745445713, |
| "grad_norm": 0.030390629544854164, |
| "learning_rate": 8.827829529818852e-06, |
| "loss": 0.0151, |
| "step": 1500 |
| }, |
| { |
| "epoch": 2.998299732815157, |
| "eval_reranking_1_loss": 0.21115952730178833, |
| "eval_reranking_1_runtime": 1.2048, |
| "eval_reranking_1_samples_per_second": 31.54, |
| "eval_reranking_1_steps_per_second": 15.77, |
| "step": 1543 |
| }, |
| { |
| "epoch": 2.998299732815157, |
| "eval_retrival_1_loss": 0.05546686798334122, |
| "eval_retrival_1_runtime": 26.8806, |
| "eval_retrival_1_samples_per_second": 32.291, |
| "eval_retrival_1_steps_per_second": 16.145, |
| "step": 1543 |
| }, |
| { |
| "epoch": 2.998299732815157, |
| "eval_sts_1_loss": 0.5478371977806091, |
| "eval_sts_1_runtime": 0.2864, |
| "eval_sts_1_samples_per_second": 34.913, |
| "eval_sts_1_steps_per_second": 17.457, |
| "step": 1543 |
| }, |
| { |
| "epoch": 3.886324993927617, |
| "grad_norm": 0.0, |
| "learning_rate": 2.8501434747835012e-06, |
| "loss": 0.0036, |
| "step": 2000 |
| }, |
| { |
| "epoch": 3.999028418751518, |
| "eval_reranking_1_loss": 0.19206289947032928, |
| "eval_reranking_1_runtime": 1.196, |
| "eval_reranking_1_samples_per_second": 31.774, |
| "eval_reranking_1_steps_per_second": 15.887, |
| "step": 2058 |
| }, |
| { |
| "epoch": 3.999028418751518, |
| "eval_retrival_1_loss": 0.04320598766207695, |
| "eval_retrival_1_runtime": 27.2793, |
| "eval_retrival_1_samples_per_second": 31.819, |
| "eval_retrival_1_steps_per_second": 15.909, |
| "step": 2058 |
| }, |
| { |
| "epoch": 3.999028418751518, |
| "eval_sts_1_loss": 0.591204047203064, |
| "eval_sts_1_runtime": 0.2948, |
| "eval_sts_1_samples_per_second": 33.923, |
| "eval_sts_1_steps_per_second": 16.961, |
| "step": 2058 |
| }, |
| { |
| "epoch": 4.857906242409522, |
| "grad_norm": 0.0018939984729513526, |
| "learning_rate": 4.5163479025036596e-08, |
| "loss": 0.0013, |
| "step": 2500 |
| }, |
| { |
| "epoch": 4.993927617196988, |
| "eval_reranking_1_loss": 0.19038808345794678, |
| "eval_reranking_1_runtime": 1.207, |
| "eval_reranking_1_samples_per_second": 31.484, |
| "eval_reranking_1_steps_per_second": 15.742, |
| "step": 2570 |
| }, |
| { |
| "epoch": 4.993927617196988, |
| "eval_retrival_1_loss": 0.04124879837036133, |
| "eval_retrival_1_runtime": 27.5211, |
| "eval_retrival_1_samples_per_second": 31.539, |
| "eval_retrival_1_steps_per_second": 15.77, |
| "step": 2570 |
| }, |
| { |
| "epoch": 4.993927617196988, |
| "eval_sts_1_loss": 0.6356238722801208, |
| "eval_sts_1_runtime": 0.3051, |
| "eval_sts_1_samples_per_second": 32.781, |
| "eval_sts_1_steps_per_second": 16.39, |
| "step": 2570 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2570, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "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": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
