| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9997659723847414, | |
| "eval_steps": 500, | |
| "global_step": 2136, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0468055230517201, | |
| "grad_norm": 1.0054835081100464, | |
| "learning_rate": 1.1533520599250935e-05, | |
| "loss": 1.4107, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0936110461034402, | |
| "grad_norm": 1.0428086519241333, | |
| "learning_rate": 1.0967041198501872e-05, | |
| "loss": 1.0774, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.14041656915516032, | |
| "grad_norm": 0.6874257326126099, | |
| "learning_rate": 1.0400561797752808e-05, | |
| "loss": 1.0431, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.1872220922068804, | |
| "grad_norm": 0.8036668300628662, | |
| "learning_rate": 9.834082397003745e-06, | |
| "loss": 1.0286, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.23402761525860052, | |
| "grad_norm": 0.7824677228927612, | |
| "learning_rate": 9.26760299625468e-06, | |
| "loss": 1.0153, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.28083313831032064, | |
| "grad_norm": 0.6508174538612366, | |
| "learning_rate": 8.701123595505617e-06, | |
| "loss": 1.0063, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.32763866136204073, | |
| "grad_norm": 0.7692238688468933, | |
| "learning_rate": 8.134644194756553e-06, | |
| "loss": 1.0015, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.3744441844137608, | |
| "grad_norm": 0.7233865261077881, | |
| "learning_rate": 7.56816479400749e-06, | |
| "loss": 0.9951, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.4212497074654809, | |
| "grad_norm": 0.7237682342529297, | |
| "learning_rate": 7.0016853932584264e-06, | |
| "loss": 0.9893, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.46805523051720105, | |
| "grad_norm": 0.7689889669418335, | |
| "learning_rate": 6.435205992509363e-06, | |
| "loss": 0.9864, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.5148607535689211, | |
| "grad_norm": 0.7110843658447266, | |
| "learning_rate": 5.868726591760299e-06, | |
| "loss": 0.9783, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.5616662766206413, | |
| "grad_norm": 0.8957160115242004, | |
| "learning_rate": 5.3022471910112355e-06, | |
| "loss": 0.9781, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.6084717996723613, | |
| "grad_norm": 0.6917927861213684, | |
| "learning_rate": 4.735767790262172e-06, | |
| "loss": 0.9782, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.6552773227240815, | |
| "grad_norm": 0.83516526222229, | |
| "learning_rate": 4.169288389513108e-06, | |
| "loss": 0.9715, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.7020828457758015, | |
| "grad_norm": 0.6937043070793152, | |
| "learning_rate": 3.602808988764045e-06, | |
| "loss": 0.9682, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.7488883688275216, | |
| "grad_norm": 0.6241235136985779, | |
| "learning_rate": 3.0363295880149813e-06, | |
| "loss": 0.9673, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.7956938918792418, | |
| "grad_norm": 0.7788057327270508, | |
| "learning_rate": 2.4698501872659176e-06, | |
| "loss": 0.9646, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.8424994149309618, | |
| "grad_norm": 0.8091927766799927, | |
| "learning_rate": 1.9033707865168538e-06, | |
| "loss": 0.9625, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.889304937982682, | |
| "grad_norm": 0.7234342098236084, | |
| "learning_rate": 1.3368913857677903e-06, | |
| "loss": 0.9598, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.9361104610344021, | |
| "grad_norm": 0.73792564868927, | |
| "learning_rate": 7.704119850187266e-07, | |
| "loss": 0.96, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.9829159840861221, | |
| "grad_norm": 0.6532009243965149, | |
| "learning_rate": 2.039325842696629e-07, | |
| "loss": 0.9626, | |
| "step": 2100 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2136, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1092390198683107e+19, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |