| { | |
| "best_metric": 0.9679633867276888, | |
| "best_model_checkpoint": "/content/drive/MyDrive/Papers/RAG_3GPP/models/checkpoints/embedding/bge-small-telecom_10e_256bs/checkpoint-150", | |
| "epoch": 6.857142857142857, | |
| "eval_steps": 15, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 1.681250810623169, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 0.824, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "eval_loss": 0.13330750167369843, | |
| "eval_runtime": 3.6814, | |
| "eval_samples_per_second": 356.115, | |
| "eval_steps_per_second": 1.63, | |
| "eval_telecom-ir-eval_cosine_accuracy@1": 0.9397406559877955, | |
| "eval_telecom-ir-eval_cosine_accuracy@10": 0.9931350114416476, | |
| "eval_telecom-ir-eval_cosine_accuracy@3": 0.9839816933638444, | |
| "eval_telecom-ir-eval_cosine_accuracy@5": 0.9893211289092296, | |
| "eval_telecom-ir-eval_cosine_map@100": 0.9625163452108533, | |
| "eval_telecom-ir-eval_cosine_mrr@10": 0.9623769568849659, | |
| "eval_telecom-ir-eval_cosine_ndcg@10": 0.9701258981216676, | |
| "eval_telecom-ir-eval_cosine_precision@1": 0.9397406559877955, | |
| "eval_telecom-ir-eval_cosine_recall@1": 0.9397406559877955, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.380952380952381, | |
| "grad_norm": 0.8189207315444946, | |
| "learning_rate": 4.972077065562821e-05, | |
| "loss": 0.1731, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.380952380952381, | |
| "eval_loss": 0.07593704760074615, | |
| "eval_runtime": 4.0688, | |
| "eval_samples_per_second": 322.209, | |
| "eval_steps_per_second": 1.475, | |
| "eval_telecom-ir-eval_cosine_accuracy@1": 0.9565217391304348, | |
| "eval_telecom-ir-eval_cosine_accuracy@10": 0.9938977879481312, | |
| "eval_telecom-ir-eval_cosine_accuracy@3": 0.9877955758962624, | |
| "eval_telecom-ir-eval_cosine_accuracy@5": 0.9908466819221968, | |
| "eval_telecom-ir-eval_cosine_map@100": 0.9723266300874301, | |
| "eval_telecom-ir-eval_cosine_mrr@10": 0.9721883210441564, | |
| "eval_telecom-ir-eval_cosine_ndcg@10": 0.9776352051817517, | |
| "eval_telecom-ir-eval_cosine_precision@1": 0.9565217391304348, | |
| "eval_telecom-ir-eval_cosine_recall@1": 0.9565217391304348, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.0476190476190474, | |
| "grad_norm": 0.7057574391365051, | |
| "learning_rate": 4.803690529676019e-05, | |
| "loss": 0.0917, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.0476190476190474, | |
| "eval_loss": 0.06566686183214188, | |
| "eval_runtime": 3.7186, | |
| "eval_samples_per_second": 352.553, | |
| "eval_steps_per_second": 1.614, | |
| "eval_telecom-ir-eval_cosine_accuracy@1": 0.9649122807017544, | |
| "eval_telecom-ir-eval_cosine_accuracy@10": 0.9931350114416476, | |
| "eval_telecom-ir-eval_cosine_accuracy@3": 0.9900839054157132, | |
| "eval_telecom-ir-eval_cosine_accuracy@5": 0.9908466819221968, | |
| "eval_telecom-ir-eval_cosine_map@100": 0.9768047979761636, | |
| "eval_telecom-ir-eval_cosine_mrr@10": 0.9765700483091787, | |
| "eval_telecom-ir-eval_cosine_ndcg@10": 0.9807364362901521, | |
| "eval_telecom-ir-eval_cosine_precision@1": 0.9649122807017544, | |
| "eval_telecom-ir-eval_cosine_recall@1": 0.9649122807017544, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.761904761904762, | |
| "grad_norm": 0.7498806118965149, | |
| "learning_rate": 4.4928312680573064e-05, | |
| "loss": 0.0676, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.761904761904762, | |
| "eval_loss": 0.06091764196753502, | |
| "eval_runtime": 3.7927, | |
| "eval_samples_per_second": 345.667, | |
| "eval_steps_per_second": 1.582, | |
| "eval_telecom-ir-eval_cosine_accuracy@1": 0.9641495041952708, | |
| "eval_telecom-ir-eval_cosine_accuracy@10": 0.9931350114416476, | |
| "eval_telecom-ir-eval_cosine_accuracy@3": 0.9916094584286804, | |
| "eval_telecom-ir-eval_cosine_accuracy@5": 0.9916094584286804, | |
| "eval_telecom-ir-eval_cosine_map@100": 0.977428148947981, | |
| "eval_telecom-ir-eval_cosine_mrr@10": 0.9771802695143658, | |
| "eval_telecom-ir-eval_cosine_ndcg@10": 0.9812569737659373, | |
| "eval_telecom-ir-eval_cosine_precision@1": 0.9641495041952708, | |
| "eval_telecom-ir-eval_cosine_recall@1": 0.9641495041952708, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.4285714285714284, | |
| "grad_norm": 0.48658156394958496, | |
| "learning_rate": 4.058724504646834e-05, | |
| "loss": 0.0435, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.4285714285714284, | |
| "eval_loss": 0.05956002324819565, | |
| "eval_runtime": 4.2667, | |
| "eval_samples_per_second": 307.261, | |
| "eval_steps_per_second": 1.406, | |
| "eval_telecom-ir-eval_cosine_accuracy@1": 0.9649122807017544, | |
| "eval_telecom-ir-eval_cosine_accuracy@10": 0.9931350114416476, | |
| "eval_telecom-ir-eval_cosine_accuracy@3": 0.9916094584286804, | |
| "eval_telecom-ir-eval_cosine_accuracy@5": 0.9916094584286804, | |
| "eval_telecom-ir-eval_cosine_map@100": 0.978052610298987, | |
| "eval_telecom-ir-eval_cosine_mrr@10": 0.9778295376121463, | |
| "eval_telecom-ir-eval_cosine_ndcg@10": 0.9817518617980646, | |
| "eval_telecom-ir-eval_cosine_precision@1": 0.9649122807017544, | |
| "eval_telecom-ir-eval_cosine_recall@1": 0.9649122807017544, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 4.095238095238095, | |
| "grad_norm": 0.4985809624195099, | |
| "learning_rate": 3.5282177578265296e-05, | |
| "loss": 0.038, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 4.095238095238095, | |
| "eval_loss": 0.060632411390542984, | |
| "eval_runtime": 4.6488, | |
| "eval_samples_per_second": 282.008, | |
| "eval_steps_per_second": 1.291, | |
| "eval_telecom-ir-eval_cosine_accuracy@1": 0.9649122807017544, | |
| "eval_telecom-ir-eval_cosine_accuracy@10": 0.9931350114416476, | |
| "eval_telecom-ir-eval_cosine_accuracy@3": 0.9916094584286804, | |
| "eval_telecom-ir-eval_cosine_accuracy@5": 0.992372234935164, | |
| "eval_telecom-ir-eval_cosine_map@100": 0.9775869566334031, | |
| "eval_telecom-ir-eval_cosine_mrr@10": 0.9773646071700992, | |
| "eval_telecom-ir-eval_cosine_ndcg@10": 0.9813932046352999, | |
| "eval_telecom-ir-eval_cosine_precision@1": 0.9649122807017544, | |
| "eval_telecom-ir-eval_cosine_recall@1": 0.9649122807017544, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 4.809523809523809, | |
| "grad_norm": 0.4105435609817505, | |
| "learning_rate": 2.9341204441673266e-05, | |
| "loss": 0.0332, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 4.809523809523809, | |
| "eval_loss": 0.05935605987906456, | |
| "eval_runtime": 4.0644, | |
| "eval_samples_per_second": 322.554, | |
| "eval_steps_per_second": 1.476, | |
| "eval_telecom-ir-eval_cosine_accuracy@1": 0.965675057208238, | |
| "eval_telecom-ir-eval_cosine_accuracy@10": 0.9931350114416476, | |
| "eval_telecom-ir-eval_cosine_accuracy@3": 0.9916094584286804, | |
| "eval_telecom-ir-eval_cosine_accuracy@5": 0.992372234935164, | |
| "eval_telecom-ir-eval_cosine_map@100": 0.9783638236659703, | |
| "eval_telecom-ir-eval_cosine_mrr@10": 0.9781273836765828, | |
| "eval_telecom-ir-eval_cosine_ndcg@10": 0.9819743331685896, | |
| "eval_telecom-ir-eval_cosine_precision@1": 0.965675057208238, | |
| "eval_telecom-ir-eval_cosine_recall@1": 0.965675057208238, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 5.476190476190476, | |
| "grad_norm": 0.468258261680603, | |
| "learning_rate": 2.3131747660339394e-05, | |
| "loss": 0.0269, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 5.476190476190476, | |
| "eval_loss": 0.060672808438539505, | |
| "eval_runtime": 4.0797, | |
| "eval_samples_per_second": 321.343, | |
| "eval_steps_per_second": 1.471, | |
| "eval_telecom-ir-eval_cosine_accuracy@1": 0.9664378337147216, | |
| "eval_telecom-ir-eval_cosine_accuracy@10": 0.9931350114416476, | |
| "eval_telecom-ir-eval_cosine_accuracy@3": 0.9908466819221968, | |
| "eval_telecom-ir-eval_cosine_accuracy@5": 0.9916094584286804, | |
| "eval_telecom-ir-eval_cosine_map@100": 0.9780891289133677, | |
| "eval_telecom-ir-eval_cosine_mrr@10": 0.9778688871938299, | |
| "eval_telecom-ir-eval_cosine_ndcg@10": 0.9817380288044749, | |
| "eval_telecom-ir-eval_cosine_precision@1": 0.9664378337147216, | |
| "eval_telecom-ir-eval_cosine_recall@1": 0.9664378337147216, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 6.142857142857143, | |
| "grad_norm": 0.192308709025383, | |
| "learning_rate": 1.7037833743707892e-05, | |
| "loss": 0.0219, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 6.142857142857143, | |
| "eval_loss": 0.06004022806882858, | |
| "eval_runtime": 3.6988, | |
| "eval_samples_per_second": 354.443, | |
| "eval_steps_per_second": 1.622, | |
| "eval_telecom-ir-eval_cosine_accuracy@1": 0.965675057208238, | |
| "eval_telecom-ir-eval_cosine_accuracy@10": 0.9938977879481312, | |
| "eval_telecom-ir-eval_cosine_accuracy@3": 0.9908466819221968, | |
| "eval_telecom-ir-eval_cosine_accuracy@5": 0.9916094584286804, | |
| "eval_telecom-ir-eval_cosine_map@100": 0.9779666698415427, | |
| "eval_telecom-ir-eval_cosine_mrr@10": 0.9778095601322145, | |
| "eval_telecom-ir-eval_cosine_ndcg@10": 0.9818676160795978, | |
| "eval_telecom-ir-eval_cosine_precision@1": 0.965675057208238, | |
| "eval_telecom-ir-eval_cosine_recall@1": 0.965675057208238, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 6.857142857142857, | |
| "grad_norm": 0.3330775499343872, | |
| "learning_rate": 1.1436343403356017e-05, | |
| "loss": 0.0244, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 6.857142857142857, | |
| "eval_loss": 0.05985964834690094, | |
| "eval_runtime": 3.8386, | |
| "eval_samples_per_second": 341.53, | |
| "eval_steps_per_second": 1.563, | |
| "eval_telecom-ir-eval_cosine_accuracy@1": 0.9679633867276888, | |
| "eval_telecom-ir-eval_cosine_accuracy@10": 0.992372234935164, | |
| "eval_telecom-ir-eval_cosine_accuracy@3": 0.9916094584286804, | |
| "eval_telecom-ir-eval_cosine_accuracy@5": 0.9916094584286804, | |
| "eval_telecom-ir-eval_cosine_map@100": 0.9791402442094453, | |
| "eval_telecom-ir-eval_cosine_mrr@10": 0.9788647342995168, | |
| "eval_telecom-ir-eval_cosine_ndcg@10": 0.9823240649953693, | |
| "eval_telecom-ir-eval_cosine_precision@1": 0.9679633867276888, | |
| "eval_telecom-ir-eval_cosine_recall@1": 0.9679633867276888, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 15, | |
| "max_steps": 210, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 15, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 256, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |