| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 3643, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02744990392533626, | |
| "grad_norm": 1.856189489364624, | |
| "learning_rate": 4.865495470765852e-05, | |
| "loss": 1.7566, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.05489980785067252, | |
| "grad_norm": 1.998369574546814, | |
| "learning_rate": 4.728245951139171e-05, | |
| "loss": 1.7366, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.08234971177600878, | |
| "grad_norm": 1.8302088975906372, | |
| "learning_rate": 4.59099643151249e-05, | |
| "loss": 1.7086, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.10979961570134504, | |
| "grad_norm": 1.9259424209594727, | |
| "learning_rate": 4.453746911885809e-05, | |
| "loss": 1.688, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.1372495196266813, | |
| "grad_norm": 1.6357027292251587, | |
| "learning_rate": 4.316497392259127e-05, | |
| "loss": 1.7272, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.16469942355201755, | |
| "grad_norm": 1.7630338668823242, | |
| "learning_rate": 4.179247872632446e-05, | |
| "loss": 1.7032, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.19214932747735383, | |
| "grad_norm": 2.0980162620544434, | |
| "learning_rate": 4.041998353005765e-05, | |
| "loss": 1.7523, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.21959923140269008, | |
| "grad_norm": 1.4029771089553833, | |
| "learning_rate": 3.904748833379083e-05, | |
| "loss": 1.6537, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.24704913532802636, | |
| "grad_norm": 1.5694669485092163, | |
| "learning_rate": 3.767499313752402e-05, | |
| "loss": 1.7099, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.2744990392533626, | |
| "grad_norm": 1.5211464166641235, | |
| "learning_rate": 3.630249794125721e-05, | |
| "loss": 1.688, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.30194894317869886, | |
| "grad_norm": 1.527065396308899, | |
| "learning_rate": 3.493000274499039e-05, | |
| "loss": 1.6995, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.3293988471040351, | |
| "grad_norm": 1.5144612789154053, | |
| "learning_rate": 3.355750754872358e-05, | |
| "loss": 1.6237, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.3568487510293714, | |
| "grad_norm": 1.7216092348098755, | |
| "learning_rate": 3.218501235245677e-05, | |
| "loss": 1.6544, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.38429865495470766, | |
| "grad_norm": 1.5754574537277222, | |
| "learning_rate": 3.081251715618996e-05, | |
| "loss": 1.6567, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.4117485588800439, | |
| "grad_norm": 1.5684128999710083, | |
| "learning_rate": 2.944002195992314e-05, | |
| "loss": 1.6806, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.43919846280538016, | |
| "grad_norm": 1.3534952402114868, | |
| "learning_rate": 2.8067526763656326e-05, | |
| "loss": 1.5953, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.46664836673071647, | |
| "grad_norm": 1.4534939527511597, | |
| "learning_rate": 2.669503156738952e-05, | |
| "loss": 1.6146, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.4940982706560527, | |
| "grad_norm": 1.3850529193878174, | |
| "learning_rate": 2.53225363711227e-05, | |
| "loss": 1.5718, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.5215481745813889, | |
| "grad_norm": 1.536191701889038, | |
| "learning_rate": 2.395004117485589e-05, | |
| "loss": 1.6358, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.5489980785067252, | |
| "grad_norm": 1.4949287176132202, | |
| "learning_rate": 2.2577545978589075e-05, | |
| "loss": 1.6173, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.5764479824320615, | |
| "grad_norm": 1.489922046661377, | |
| "learning_rate": 2.1205050782322264e-05, | |
| "loss": 1.6291, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.6038978863573977, | |
| "grad_norm": 2.090135097503662, | |
| "learning_rate": 1.983255558605545e-05, | |
| "loss": 1.6579, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.631347790282734, | |
| "grad_norm": 1.798261284828186, | |
| "learning_rate": 1.8460060389788635e-05, | |
| "loss": 1.7008, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.6587976942080702, | |
| "grad_norm": 1.43966805934906, | |
| "learning_rate": 1.7087565193521824e-05, | |
| "loss": 1.5593, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.6862475981334065, | |
| "grad_norm": 1.5113532543182373, | |
| "learning_rate": 1.571506999725501e-05, | |
| "loss": 1.576, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.7136975020587428, | |
| "grad_norm": 1.5978457927703857, | |
| "learning_rate": 1.4342574800988198e-05, | |
| "loss": 1.6075, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.741147405984079, | |
| "grad_norm": 1.7422983646392822, | |
| "learning_rate": 1.2970079604721382e-05, | |
| "loss": 1.634, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.7685973099094153, | |
| "grad_norm": 1.7618128061294556, | |
| "learning_rate": 1.1597584408454571e-05, | |
| "loss": 1.6333, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.7960472138347516, | |
| "grad_norm": 1.4939252138137817, | |
| "learning_rate": 1.0225089212187758e-05, | |
| "loss": 1.5678, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.8234971177600878, | |
| "grad_norm": 1.3491543531417847, | |
| "learning_rate": 8.852594015920946e-06, | |
| "loss": 1.5577, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.8509470216854241, | |
| "grad_norm": 1.800729751586914, | |
| "learning_rate": 7.480098819654131e-06, | |
| "loss": 1.5562, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.8783969256107603, | |
| "grad_norm": 1.4192384481430054, | |
| "learning_rate": 6.107603623387318e-06, | |
| "loss": 1.6218, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.9058468295360966, | |
| "grad_norm": 1.487561583518982, | |
| "learning_rate": 4.735108427120506e-06, | |
| "loss": 1.6313, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.9332967334614329, | |
| "grad_norm": 1.393309235572815, | |
| "learning_rate": 3.3626132308536925e-06, | |
| "loss": 1.5928, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.9607466373867691, | |
| "grad_norm": 1.397757649421692, | |
| "learning_rate": 1.990118034586879e-06, | |
| "loss": 1.568, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.9881965413121054, | |
| "grad_norm": 1.2685039043426514, | |
| "learning_rate": 6.176228383200659e-07, | |
| "loss": 1.5983, | |
| "step": 3600 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 3643, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3643, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1045534257958093e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |