| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 6.857266902923584, | |
| "learning_rate": 7.2000000000000005e-06, | |
| "loss": 1.585, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 2.489650011062622, | |
| "learning_rate": 1.5200000000000002e-05, | |
| "loss": 0.268, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 6.398056507110596, | |
| "learning_rate": 1.9984407641819812e-05, | |
| "loss": 0.2895, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.1504039317369461, | |
| "learning_rate": 1.9809551553491918e-05, | |
| "loss": 0.1859, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 1.2296534776687622, | |
| "learning_rate": 1.944376370237481e-05, | |
| "loss": 0.0984, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.012895800173282623, | |
| "learning_rate": 1.889416373291298e-05, | |
| "loss": 0.0668, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 2.1277153491973877, | |
| "learning_rate": 1.8171448983351284e-05, | |
| "loss": 0.1228, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 1.6015583276748657, | |
| "learning_rate": 1.7289686274214116e-05, | |
| "loss": 0.193, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.42995280027389526, | |
| "learning_rate": 1.6266038113644605e-05, | |
| "loss": 0.1573, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.2124607264995575, | |
| "learning_rate": 1.5120428648705716e-05, | |
| "loss": 0.0905, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.20811651647090912, | |
| "learning_rate": 1.3875155864521031e-05, | |
| "loss": 0.1169, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.7650100588798523, | |
| "learning_rate": 1.2554457579357906e-05, | |
| "loss": 0.125, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 0.23556451499462128, | |
| "learning_rate": 1.1184039683065014e-05, | |
| "loss": 0.0576, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.6805216073989868, | |
| "learning_rate": 9.790575801166432e-06, | |
| "loss": 0.0703, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.023868851363658905, | |
| "learning_rate": 8.401188123081653e-06, | |
| "loss": 0.049, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 1.3114885091781616, | |
| "learning_rate": 7.042919499559538e-06, | |
| "loss": 0.129, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.3599999999999999, | |
| "grad_norm": 0.2610754668712616, | |
| "learning_rate": 5.742207084349274e-06, | |
| "loss": 0.0652, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 2.7140579223632812, | |
| "learning_rate": 4.524367765074499e-06, | |
| "loss": 0.0147, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 1.237959384918213, | |
| "learning_rate": 3.4131053988131947e-06, | |
| "loss": 0.0694, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.09863968938589096, | |
| "learning_rate": 2.4300494434824373e-06, | |
| "loss": 0.0786, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.6800000000000002, | |
| "grad_norm": 0.009426446631550789, | |
| "learning_rate": 1.5943339650431578e-06, | |
| "loss": 0.0301, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 1.9068654775619507, | |
| "learning_rate": 9.222252146709143e-07, | |
| "loss": 0.025, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.8399999999999999, | |
| "grad_norm": 0.03250988572835922, | |
| "learning_rate": 4.268050246793276e-07, | |
| "loss": 0.0093, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 0.29542025923728943, | |
| "learning_rate": 1.1771618553447217e-07, | |
| "loss": 0.0756, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.12926587462425232, | |
| "learning_rate": 9.74759906957612e-10, | |
| "loss": 0.0351, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 250, | |
| "total_flos": 3.846009907091866e+16, | |
| "train_loss": 0.16032438999414445, | |
| "train_runtime": 2680.6813, | |
| "train_samples_per_second": 0.373, | |
| "train_steps_per_second": 0.093 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.846009907091866e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |