| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2806848710854485, | |
| "eval_steps": 500, | |
| "global_step": 14000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01002445968162316, | |
| "grad_norm": 0.1908789426088333, | |
| "learning_rate": 2.969926620955131e-05, | |
| "loss": 0.0305, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.02004891936324632, | |
| "grad_norm": 0.2333366870880127, | |
| "learning_rate": 2.939853241910261e-05, | |
| "loss": 0.027, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.03007337904486948, | |
| "grad_norm": 0.18207737803459167, | |
| "learning_rate": 2.9097798628653917e-05, | |
| "loss": 0.026, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.04009783872649264, | |
| "grad_norm": 0.13153837621212006, | |
| "learning_rate": 2.879706483820522e-05, | |
| "loss": 0.0253, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.0501222984081158, | |
| "grad_norm": 0.20580655336380005, | |
| "learning_rate": 2.849633104775653e-05, | |
| "loss": 0.0249, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.06014675808973896, | |
| "grad_norm": 0.16466622054576874, | |
| "learning_rate": 2.8196198724888727e-05, | |
| "loss": 0.0239, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.07017121777136212, | |
| "grad_norm": 0.1590748131275177, | |
| "learning_rate": 2.7895464934440035e-05, | |
| "loss": 0.0239, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.08019567745298528, | |
| "grad_norm": 0.14150911569595337, | |
| "learning_rate": 2.759473114399134e-05, | |
| "loss": 0.0236, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.09022013713460844, | |
| "grad_norm": 0.09914161264896393, | |
| "learning_rate": 2.7293997353542647e-05, | |
| "loss": 0.0236, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.1002445968162316, | |
| "grad_norm": 0.16175945103168488, | |
| "learning_rate": 2.6993263563093947e-05, | |
| "loss": 0.0232, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.11026905649785476, | |
| "grad_norm": 0.14557033777236938, | |
| "learning_rate": 2.6692529772645255e-05, | |
| "loss": 0.0229, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.12029351617947792, | |
| "grad_norm": 0.14236459136009216, | |
| "learning_rate": 2.639179598219656e-05, | |
| "loss": 0.0228, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.13031797586110108, | |
| "grad_norm": 0.1859973669052124, | |
| "learning_rate": 2.6091062191747867e-05, | |
| "loss": 0.0226, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.14034243554272424, | |
| "grad_norm": 0.21533679962158203, | |
| "learning_rate": 2.5790929868880065e-05, | |
| "loss": 0.0226, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.1503668952243474, | |
| "grad_norm": 0.13067375123500824, | |
| "learning_rate": 2.5490196078431373e-05, | |
| "loss": 0.0222, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.16039135490597056, | |
| "grad_norm": 0.15966835618019104, | |
| "learning_rate": 2.518946228798268e-05, | |
| "loss": 0.0223, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.17041581458759372, | |
| "grad_norm": 0.16358782351016998, | |
| "learning_rate": 2.4888728497533985e-05, | |
| "loss": 0.0218, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.18044027426921688, | |
| "grad_norm": 0.2502037286758423, | |
| "learning_rate": 2.458799470708529e-05, | |
| "loss": 0.0219, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.19046473395084004, | |
| "grad_norm": 0.13426147401332855, | |
| "learning_rate": 2.4287260916636593e-05, | |
| "loss": 0.0221, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.2004891936324632, | |
| "grad_norm": 0.17509840428829193, | |
| "learning_rate": 2.39865271261879e-05, | |
| "loss": 0.0219, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.21051365331408636, | |
| "grad_norm": 0.12009692937135696, | |
| "learning_rate": 2.3685793335739205e-05, | |
| "loss": 0.0216, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.22053811299570952, | |
| "grad_norm": 0.1322207748889923, | |
| "learning_rate": 2.338505954529051e-05, | |
| "loss": 0.0211, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.23056257267733268, | |
| "grad_norm": 0.14883308112621307, | |
| "learning_rate": 2.308492722242271e-05, | |
| "loss": 0.0214, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.24058703235895584, | |
| "grad_norm": 0.13109040260314941, | |
| "learning_rate": 2.278419343197402e-05, | |
| "loss": 0.0211, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.25061149204057903, | |
| "grad_norm": 0.1747232973575592, | |
| "learning_rate": 2.2483459641525323e-05, | |
| "loss": 0.0214, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.26063595172220216, | |
| "grad_norm": 0.14633044600486755, | |
| "learning_rate": 2.2182725851076627e-05, | |
| "loss": 0.0212, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.27066041140382535, | |
| "grad_norm": 0.16928279399871826, | |
| "learning_rate": 2.188199206062793e-05, | |
| "loss": 0.0209, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.2806848710854485, | |
| "grad_norm": 0.1422567069530487, | |
| "learning_rate": 2.158125827017924e-05, | |
| "loss": 0.0206, | |
| "step": 14000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 49878, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "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": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |