| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 16890, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14801657785671996, | |
| "grad_norm": 25.402847290039062, | |
| "learning_rate": 4.852279455298994e-05, | |
| "loss": 0.2711, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.2960331557134399, | |
| "grad_norm": 0.0805608406662941, | |
| "learning_rate": 4.7042628774422734e-05, | |
| "loss": 0.2527, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.44404973357015987, | |
| "grad_norm": 40.26156234741211, | |
| "learning_rate": 4.556246299585554e-05, | |
| "loss": 0.2312, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.5920663114268798, | |
| "grad_norm": 0.35373732447624207, | |
| "learning_rate": 4.408229721728834e-05, | |
| "loss": 0.2016, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.7400828892835998, | |
| "grad_norm": 35.57596206665039, | |
| "learning_rate": 4.2602131438721137e-05, | |
| "loss": 0.2324, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.8880994671403197, | |
| "grad_norm": 0.23570013046264648, | |
| "learning_rate": 4.112196566015394e-05, | |
| "loss": 0.1932, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.0361160449970397, | |
| "grad_norm": 0.12335730344057083, | |
| "learning_rate": 3.9641799881586736e-05, | |
| "loss": 0.1941, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.1841326228537596, | |
| "grad_norm": 0.3553510010242462, | |
| "learning_rate": 3.816163410301954e-05, | |
| "loss": 0.1373, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.3321492007104796, | |
| "grad_norm": 6.933666706085205, | |
| "learning_rate": 3.668146832445234e-05, | |
| "loss": 0.1504, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.4801657785671996, | |
| "grad_norm": 0.09979640692472458, | |
| "learning_rate": 3.520130254588514e-05, | |
| "loss": 0.1503, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.6281823564239195, | |
| "grad_norm": 0.14943279325962067, | |
| "learning_rate": 3.372113676731794e-05, | |
| "loss": 0.1666, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.7761989342806395, | |
| "grad_norm": 0.1044839397072792, | |
| "learning_rate": 3.224097098875074e-05, | |
| "loss": 0.1375, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.9242155121373594, | |
| "grad_norm": 0.11174246668815613, | |
| "learning_rate": 3.076080521018354e-05, | |
| "loss": 0.1583, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.0722320899940794, | |
| "grad_norm": 0.32959309220314026, | |
| "learning_rate": 2.928063943161634e-05, | |
| "loss": 0.1054, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.2202486678507993, | |
| "grad_norm": 41.20267105102539, | |
| "learning_rate": 2.7800473653049143e-05, | |
| "loss": 0.0878, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.3682652457075193, | |
| "grad_norm": 12.859502792358398, | |
| "learning_rate": 2.6320307874481943e-05, | |
| "loss": 0.1646, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.5162818235642392, | |
| "grad_norm": 0.30566394329071045, | |
| "learning_rate": 2.4840142095914743e-05, | |
| "loss": 0.1215, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.664298401420959, | |
| "grad_norm": 0.12033539265394211, | |
| "learning_rate": 2.3359976317347542e-05, | |
| "loss": 0.1075, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.812314979277679, | |
| "grad_norm": 49.766090393066406, | |
| "learning_rate": 2.1879810538780342e-05, | |
| "loss": 0.1169, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 2.960331557134399, | |
| "grad_norm": 0.19112378358840942, | |
| "learning_rate": 2.0399644760213145e-05, | |
| "loss": 0.1558, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 3.108348134991119, | |
| "grad_norm": 0.11650295555591583, | |
| "learning_rate": 1.8919478981645945e-05, | |
| "loss": 0.142, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 3.256364712847839, | |
| "grad_norm": 20.20573616027832, | |
| "learning_rate": 1.7439313203078744e-05, | |
| "loss": 0.1383, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 3.404381290704559, | |
| "grad_norm": 0.13151119649410248, | |
| "learning_rate": 1.5959147424511547e-05, | |
| "loss": 0.123, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 3.552397868561279, | |
| "grad_norm": 0.18407081067562103, | |
| "learning_rate": 1.4478981645944349e-05, | |
| "loss": 0.1375, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 3.700414446417999, | |
| "grad_norm": 2.9082658290863037, | |
| "learning_rate": 1.2998815867377148e-05, | |
| "loss": 0.0923, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 3.848431024274719, | |
| "grad_norm": 0.0763067901134491, | |
| "learning_rate": 1.1518650088809948e-05, | |
| "loss": 0.1202, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 3.996447602131439, | |
| "grad_norm": 0.06192115694284439, | |
| "learning_rate": 1.0038484310242748e-05, | |
| "loss": 0.076, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 4.144464179988159, | |
| "grad_norm": 0.030562452971935272, | |
| "learning_rate": 8.558318531675547e-06, | |
| "loss": 0.0725, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 4.292480757844879, | |
| "grad_norm": 1.4049798250198364, | |
| "learning_rate": 7.0781527531083485e-06, | |
| "loss": 0.0652, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 4.440497335701599, | |
| "grad_norm": 0.03495749458670616, | |
| "learning_rate": 5.597986974541149e-06, | |
| "loss": 0.0639, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 4.588513913558319, | |
| "grad_norm": 256.4950256347656, | |
| "learning_rate": 4.117821195973949e-06, | |
| "loss": 0.0536, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 4.736530491415039, | |
| "grad_norm": 0.05225745961070061, | |
| "learning_rate": 2.6376554174067496e-06, | |
| "loss": 0.0534, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 4.8845470692717585, | |
| "grad_norm": 3.503504991531372, | |
| "learning_rate": 1.15748963883955e-06, | |
| "loss": 0.0631, | |
| "step": 16500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 16890, | |
| "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": 7.10847138266112e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |