| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9259259259259259, |
| "eval_steps": 500, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.046296296296296294, |
| "grad_norm": 1.7154957056045532, |
| "learning_rate": 2.2685185185185187e-05, |
| "loss": 0.6644, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.09259259259259259, |
| "grad_norm": 1.6062076091766357, |
| "learning_rate": 4.5833333333333334e-05, |
| "loss": 0.3737, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.1388888888888889, |
| "grad_norm": 1.5934187173843384, |
| "learning_rate": 4.7890946502057616e-05, |
| "loss": 0.3271, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.18518518518518517, |
| "grad_norm": 1.4217034578323364, |
| "learning_rate": 4.531893004115226e-05, |
| "loss": 0.309, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.23148148148148148, |
| "grad_norm": 1.151724934577942, |
| "learning_rate": 4.2746913580246915e-05, |
| "loss": 0.2706, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.2777777777777778, |
| "grad_norm": 1.5069067478179932, |
| "learning_rate": 4.017489711934157e-05, |
| "loss": 0.2587, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.32407407407407407, |
| "grad_norm": 1.3596380949020386, |
| "learning_rate": 3.760288065843622e-05, |
| "loss": 0.2629, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.37037037037037035, |
| "grad_norm": 1.3064409494400024, |
| "learning_rate": 3.503086419753087e-05, |
| "loss": 0.2518, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.4166666666666667, |
| "grad_norm": 1.3996431827545166, |
| "learning_rate": 3.245884773662551e-05, |
| "loss": 0.2492, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.46296296296296297, |
| "grad_norm": 1.3424209356307983, |
| "learning_rate": 2.9886831275720166e-05, |
| "loss": 0.228, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.5092592592592593, |
| "grad_norm": 1.3468494415283203, |
| "learning_rate": 2.7314814814814816e-05, |
| "loss": 0.2267, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.5555555555555556, |
| "grad_norm": 1.1546319723129272, |
| "learning_rate": 2.4742798353909465e-05, |
| "loss": 0.2222, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.6018518518518519, |
| "grad_norm": 1.1849355697631836, |
| "learning_rate": 2.2170781893004118e-05, |
| "loss": 0.2283, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.6481481481481481, |
| "grad_norm": 1.095701813697815, |
| "learning_rate": 1.9598765432098768e-05, |
| "loss": 0.2233, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.6944444444444444, |
| "grad_norm": 1.258505940437317, |
| "learning_rate": 1.7026748971193414e-05, |
| "loss": 0.2239, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.7407407407407407, |
| "grad_norm": 1.29531729221344, |
| "learning_rate": 1.4454732510288065e-05, |
| "loss": 0.2107, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.7870370370370371, |
| "grad_norm": 1.1493163108825684, |
| "learning_rate": 1.1882716049382716e-05, |
| "loss": 0.2205, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.8333333333333334, |
| "grad_norm": 1.197800636291504, |
| "learning_rate": 9.310699588477368e-06, |
| "loss": 0.2087, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.8796296296296297, |
| "grad_norm": 1.2553362846374512, |
| "learning_rate": 6.7386831275720164e-06, |
| "loss": 0.2129, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.9259259259259259, |
| "grad_norm": 1.1241569519042969, |
| "learning_rate": 4.166666666666667e-06, |
| "loss": 0.2103, |
| "step": 1000 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1080, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "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": 0.0, |
| "train_batch_size": 512, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
