| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.8188331627430911, |
| "eval_steps": 500, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.04094165813715456, |
| "grad_norm": 7.529000759124756, |
| "learning_rate": 9.000000000000001e-07, |
| "loss": 6.639524841308594, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.08188331627430911, |
| "grad_norm": 7.1427388191223145, |
| "learning_rate": 1.9000000000000002e-06, |
| "loss": 6.582770538330078, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.12282497441146366, |
| "grad_norm": 6.251121997833252, |
| "learning_rate": 2.9e-06, |
| "loss": 6.114261245727539, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.16376663254861823, |
| "grad_norm": 7.014133453369141, |
| "learning_rate": 3.900000000000001e-06, |
| "loss": 6.333962631225586, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.2047082906857728, |
| "grad_norm": 7.072969913482666, |
| "learning_rate": 4.9000000000000005e-06, |
| "loss": 6.248543930053711, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.24564994882292732, |
| "grad_norm": 5.674424171447754, |
| "learning_rate": 5.9e-06, |
| "loss": 5.6220745086669925, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.2865916069600819, |
| "grad_norm": 5.3739800453186035, |
| "learning_rate": 6.9e-06, |
| "loss": 5.0251930236816404, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.32753326509723646, |
| "grad_norm": 6.372293472290039, |
| "learning_rate": 7.9e-06, |
| "loss": 5.033017349243164, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.368474923234391, |
| "grad_norm": 7.22106409072876, |
| "learning_rate": 8.900000000000001e-06, |
| "loss": 3.514456939697266, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.4094165813715456, |
| "grad_norm": 4.990958213806152, |
| "learning_rate": 9.9e-06, |
| "loss": 2.256962776184082, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.4503582395087001, |
| "grad_norm": 3.2661993503570557, |
| "learning_rate": 9.76923076923077e-06, |
| "loss": 2.0482555389404298, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.49129989764585463, |
| "grad_norm": 2.997323513031006, |
| "learning_rate": 9.512820512820514e-06, |
| "loss": 1.6077747344970703, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.5322415557830092, |
| "grad_norm": 2.422741413116455, |
| "learning_rate": 9.256410256410257e-06, |
| "loss": 1.538028621673584, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.5731832139201638, |
| "grad_norm": 2.4594290256500244, |
| "learning_rate": 9e-06, |
| "loss": 1.5614049911499024, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.6141248720573184, |
| "grad_norm": 2.7256577014923096, |
| "learning_rate": 8.743589743589743e-06, |
| "loss": 1.7180768966674804, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.6550665301944729, |
| "grad_norm": 2.6614902019500732, |
| "learning_rate": 8.487179487179488e-06, |
| "loss": 1.6412044525146485, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.6960081883316275, |
| "grad_norm": 2.1517934799194336, |
| "learning_rate": 8.230769230769232e-06, |
| "loss": 1.729467010498047, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.736949846468782, |
| "grad_norm": 2.4588229656219482, |
| "learning_rate": 7.974358974358975e-06, |
| "loss": 1.305363941192627, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.7778915046059366, |
| "grad_norm": 2.5282061100006104, |
| "learning_rate": 7.717948717948718e-06, |
| "loss": 1.4986873626708985, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.8188331627430911, |
| "grad_norm": 3.699396848678589, |
| "learning_rate": 7.461538461538462e-06, |
| "loss": 1.5059691429138184, |
| "step": 200 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 490, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 5850613446242304.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
