| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5379959650302623, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0026899798251513113, | |
| "eval_loss": NaN, | |
| "eval_runtime": 8.7455, | |
| "eval_samples_per_second": 17.952, | |
| "eval_steps_per_second": 9.033, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.026899798251513115, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019967573081342103, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05379959650302623, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08069939475453934, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019199794436588243, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10759919300605246, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001845190085543795, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13449899125756556, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13449899125756556, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.5255, | |
| "eval_samples_per_second": 20.862, | |
| "eval_steps_per_second": 10.498, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16139878950907868, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016324453755953773, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1882985877605918, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.21519838601210492, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013546048870425356, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.242098184263618, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012000256937760445, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.26899798251513113, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010402659401094152, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.26899798251513113, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.5278, | |
| "eval_samples_per_second": 20.856, | |
| "eval_steps_per_second": 10.494, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.29589778076664425, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.79463319744677e-05, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.32279757901815737, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.217825360835473e-05, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3496973772696705, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.713074385969457e-05, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3765971755211836, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3193525326884435e-05, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.4034969737726967, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.072756464904006e-05, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.4034969737726967, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.5235, | |
| "eval_samples_per_second": 20.868, | |
| "eval_steps_per_second": 10.5, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.43039677202420984, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0055723659649904e-05, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.45729657027572296, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1454397434679021e-05, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.484196368527236, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.146355805285452e-06, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.5110961667787491, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2949737362087156e-06, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.5379959650302623, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5379959650302623, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.5422, | |
| "eval_samples_per_second": 20.816, | |
| "eval_steps_per_second": 10.474, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.346581737472e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |