| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 21873, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06857769853243725, | |
| "grad_norm": 1.0945861339569092, | |
| "learning_rate": 4.8857038357792714e-05, | |
| "loss": 0.318, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.1371553970648745, | |
| "grad_norm": 0.6745380163192749, | |
| "learning_rate": 4.7714076715585427e-05, | |
| "loss": 0.1574, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.20573309559731176, | |
| "grad_norm": 0.7351590991020203, | |
| "learning_rate": 4.657111507337814e-05, | |
| "loss": 0.1403, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.274310794129749, | |
| "grad_norm": 0.8816856145858765, | |
| "learning_rate": 4.542815343117085e-05, | |
| "loss": 0.1308, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.34288849266218624, | |
| "grad_norm": 0.8210085034370422, | |
| "learning_rate": 4.428519178896356e-05, | |
| "loss": 0.1228, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.4114661911946235, | |
| "grad_norm": 0.6685318350791931, | |
| "learning_rate": 4.314223014675628e-05, | |
| "loss": 0.1219, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.48004388972706075, | |
| "grad_norm": 0.7579106092453003, | |
| "learning_rate": 4.199926850454899e-05, | |
| "loss": 0.117, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.548621588259498, | |
| "grad_norm": 1.059991478919983, | |
| "learning_rate": 4.0856306862341706e-05, | |
| "loss": 0.1127, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.6171992867919353, | |
| "grad_norm": 0.9921385049819946, | |
| "learning_rate": 3.971334522013441e-05, | |
| "loss": 0.1126, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.6857769853243725, | |
| "grad_norm": 0.6036443114280701, | |
| "learning_rate": 3.857038357792713e-05, | |
| "loss": 0.1099, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.7543546838568098, | |
| "grad_norm": 0.88544762134552, | |
| "learning_rate": 3.7427421935719835e-05, | |
| "loss": 0.1063, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.822932382389247, | |
| "grad_norm": 0.6532144546508789, | |
| "learning_rate": 3.6284460293512554e-05, | |
| "loss": 0.1065, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.8915100809216843, | |
| "grad_norm": 0.755144476890564, | |
| "learning_rate": 3.5141498651305266e-05, | |
| "loss": 0.106, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.9600877794541215, | |
| "grad_norm": 0.9388787150382996, | |
| "learning_rate": 3.399853700909797e-05, | |
| "loss": 0.1029, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.0286654779865587, | |
| "grad_norm": 0.8779000043869019, | |
| "learning_rate": 3.285557536689069e-05, | |
| "loss": 0.1011, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.097243176518996, | |
| "grad_norm": 0.8181456923484802, | |
| "learning_rate": 3.1712613724683396e-05, | |
| "loss": 0.0941, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.1658208750514332, | |
| "grad_norm": 0.7053276300430298, | |
| "learning_rate": 3.0569652082476115e-05, | |
| "loss": 0.0943, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.2343985735838705, | |
| "grad_norm": 0.9002987146377563, | |
| "learning_rate": 2.9426690440268827e-05, | |
| "loss": 0.0942, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.3029762721163078, | |
| "grad_norm": 0.5714060664176941, | |
| "learning_rate": 2.8283728798061536e-05, | |
| "loss": 0.0937, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.371553970648745, | |
| "grad_norm": 0.7014051079750061, | |
| "learning_rate": 2.714076715585425e-05, | |
| "loss": 0.0925, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.4401316691811823, | |
| "grad_norm": 0.9592730402946472, | |
| "learning_rate": 2.599780551364696e-05, | |
| "loss": 0.0949, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.5087093677136196, | |
| "grad_norm": 0.6313921213150024, | |
| "learning_rate": 2.4854843871439675e-05, | |
| "loss": 0.0923, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.5772870662460567, | |
| "grad_norm": 0.8395763039588928, | |
| "learning_rate": 2.3711882229232387e-05, | |
| "loss": 0.0911, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.645864764778494, | |
| "grad_norm": 0.7302150130271912, | |
| "learning_rate": 2.25689205870251e-05, | |
| "loss": 0.0911, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.7144424633109314, | |
| "grad_norm": 0.5918404459953308, | |
| "learning_rate": 2.142595894481781e-05, | |
| "loss": 0.0896, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.7830201618433685, | |
| "grad_norm": 0.7551326155662537, | |
| "learning_rate": 2.0282997302610527e-05, | |
| "loss": 0.0905, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.8515978603758056, | |
| "grad_norm": 1.6809072494506836, | |
| "learning_rate": 1.914003566040324e-05, | |
| "loss": 0.0891, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.920175558908243, | |
| "grad_norm": 0.6433506011962891, | |
| "learning_rate": 1.799707401819595e-05, | |
| "loss": 0.0894, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.9887532574406803, | |
| "grad_norm": 0.7609830498695374, | |
| "learning_rate": 1.6854112375988663e-05, | |
| "loss": 0.0892, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 2.0573309559731174, | |
| "grad_norm": 0.611824095249176, | |
| "learning_rate": 1.5711150733781376e-05, | |
| "loss": 0.0847, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.125908654505555, | |
| "grad_norm": 0.7075466513633728, | |
| "learning_rate": 1.456818909157409e-05, | |
| "loss": 0.0841, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 2.194486353037992, | |
| "grad_norm": 0.6217673420906067, | |
| "learning_rate": 1.3425227449366801e-05, | |
| "loss": 0.0827, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.2630640515704292, | |
| "grad_norm": 0.862660825252533, | |
| "learning_rate": 1.2282265807159512e-05, | |
| "loss": 0.0841, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 2.3316417501028663, | |
| "grad_norm": 0.832482635974884, | |
| "learning_rate": 1.1139304164952224e-05, | |
| "loss": 0.0832, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.400219448635304, | |
| "grad_norm": 0.8499016761779785, | |
| "learning_rate": 9.996342522744938e-06, | |
| "loss": 0.0835, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 2.468797147167741, | |
| "grad_norm": 0.5063202977180481, | |
| "learning_rate": 8.85338088053765e-06, | |
| "loss": 0.082, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.537374845700178, | |
| "grad_norm": 0.8636651635169983, | |
| "learning_rate": 7.710419238330362e-06, | |
| "loss": 0.0816, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 2.6059525442326157, | |
| "grad_norm": 0.7150306105613708, | |
| "learning_rate": 6.567457596123075e-06, | |
| "loss": 0.0827, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.674530242765053, | |
| "grad_norm": 0.6820867657661438, | |
| "learning_rate": 5.424495953915787e-06, | |
| "loss": 0.0829, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 2.74310794129749, | |
| "grad_norm": 0.8032534718513489, | |
| "learning_rate": 4.2815343117085e-06, | |
| "loss": 0.0819, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.8116856398299275, | |
| "grad_norm": 0.6814680099487305, | |
| "learning_rate": 3.1385726695012116e-06, | |
| "loss": 0.0825, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 2.8802633383623646, | |
| "grad_norm": 0.5674154162406921, | |
| "learning_rate": 1.995611027293924e-06, | |
| "loss": 0.0791, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 2.9488410368948017, | |
| "grad_norm": 0.8843555450439453, | |
| "learning_rate": 8.526493850866365e-07, | |
| "loss": 0.0823, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 21873, | |
| "total_flos": 797101335136512.0, | |
| "train_loss": 0.09493603817759208, | |
| "train_runtime": 3874.7393, | |
| "train_samples_per_second": 45.156, | |
| "train_steps_per_second": 5.645 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 21873, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 797101335136512.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |