| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.041666666666666664, |
| "eval_steps": 500, |
| "global_step": 250, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "grad_norm": 1.1998956203460693, |
| "learning_rate": 1.5e-06, |
| "loss": 0.0948, |
| "step": 10 |
| }, |
| { |
| "grad_norm": 1.149483561515808, |
| "learning_rate": 3.1666666666666667e-06, |
| "loss": 0.1133, |
| "step": 20 |
| }, |
| { |
| "grad_norm": 0.5785359144210815, |
| "learning_rate": 4.833333333333333e-06, |
| "loss": 0.0921, |
| "step": 30 |
| }, |
| { |
| "grad_norm": 0.5978452563285828, |
| "learning_rate": 6.5000000000000004e-06, |
| "loss": 0.0424, |
| "step": 40 |
| }, |
| { |
| "grad_norm": 0.5148229598999023, |
| "learning_rate": 8.166666666666666e-06, |
| "loss": 0.0314, |
| "step": 50 |
| }, |
| { |
| "grad_norm": 0.456398606300354, |
| "learning_rate": 9.833333333333333e-06, |
| "loss": 0.0311, |
| "step": 60 |
| }, |
| { |
| "grad_norm": 0.2702748775482178, |
| "learning_rate": 1.1500000000000002e-05, |
| "loss": 0.0249, |
| "step": 70 |
| }, |
| { |
| "grad_norm": 0.2341022789478302, |
| "learning_rate": 1.3166666666666667e-05, |
| "loss": 0.0208, |
| "step": 80 |
| }, |
| { |
| "grad_norm": 0.24386702477931976, |
| "learning_rate": 1.4833333333333334e-05, |
| "loss": 0.0168, |
| "step": 90 |
| }, |
| { |
| "grad_norm": 0.15167136490345, |
| "learning_rate": 1.65e-05, |
| "loss": 0.0114, |
| "step": 100 |
| }, |
| { |
| "grad_norm": 0.12867538630962372, |
| "learning_rate": 1.8166666666666667e-05, |
| "loss": 0.015, |
| "step": 110 |
| }, |
| { |
| "grad_norm": 0.11734911054372787, |
| "learning_rate": 1.9833333333333332e-05, |
| "loss": 0.0108, |
| "step": 120 |
| }, |
| { |
| "grad_norm": 0.10739504545927048, |
| "learning_rate": 2.15e-05, |
| "loss": 0.0085, |
| "step": 130 |
| }, |
| { |
| "grad_norm": 0.11796178668737411, |
| "learning_rate": 2.316666666666667e-05, |
| "loss": 0.0108, |
| "step": 140 |
| }, |
| { |
| "grad_norm": 0.1394447386264801, |
| "learning_rate": 2.483333333333333e-05, |
| "loss": 0.0111, |
| "step": 150 |
| }, |
| { |
| "grad_norm": 0.1239742562174797, |
| "learning_rate": 2.65e-05, |
| "loss": 0.01, |
| "step": 160 |
| }, |
| { |
| "grad_norm": 0.15108101069927216, |
| "learning_rate": 2.8166666666666666e-05, |
| "loss": 0.0088, |
| "step": 170 |
| }, |
| { |
| "grad_norm": 0.10625599324703217, |
| "learning_rate": 2.9833333333333335e-05, |
| "loss": 0.0073, |
| "step": 180 |
| }, |
| { |
| "grad_norm": 0.18963077664375305, |
| "learning_rate": 2.9999822989428527e-05, |
| "loss": 0.0086, |
| "step": 190 |
| }, |
| { |
| "grad_norm": 0.13748835027217865, |
| "learning_rate": 2.9999211106396838e-05, |
| "loss": 0.008, |
| "step": 200 |
| }, |
| { |
| "grad_norm": 0.11299511790275574, |
| "learning_rate": 2.9998162183413746e-05, |
| "loss": 0.0084, |
| "step": 210 |
| }, |
| { |
| "grad_norm": 0.09556759148836136, |
| "learning_rate": 2.9996676251042288e-05, |
| "loss": 0.0075, |
| "step": 220 |
| }, |
| { |
| "grad_norm": 0.13729563355445862, |
| "learning_rate": 2.9994753352578854e-05, |
| "loss": 0.0078, |
| "step": 230 |
| }, |
| { |
| "grad_norm": 0.13592101633548737, |
| "learning_rate": 2.999239354405195e-05, |
| "loss": 0.0087, |
| "step": 240 |
| }, |
| { |
| "grad_norm": 0.13999280333518982, |
| "learning_rate": 2.9989596894220574e-05, |
| "loss": 0.0072, |
| "step": 250 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 6000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9223372036854775807, |
| "save_steps": 250, |
| "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": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
