| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 7.847290640394089, |
| "eval_steps": 500, |
| "global_step": 400, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.49261083743842365, |
| "grad_norm": 0.15254946053028107, |
| "learning_rate": 0.0001446153846153846, |
| "loss": 1.5160433959960937, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.9852216748768473, |
| "grad_norm": 0.20539413392543793, |
| "learning_rate": 0.000135, |
| "loss": 1.0721150970458984, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.4729064039408866, |
| "grad_norm": 0.3349456489086151, |
| "learning_rate": 0.00012538461538461537, |
| "loss": 0.889725341796875, |
| "step": 75 |
| }, |
| { |
| "epoch": 1.9655172413793105, |
| "grad_norm": 0.38187605142593384, |
| "learning_rate": 0.00011576923076923076, |
| "loss": 0.8153521728515625, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.4532019704433496, |
| "grad_norm": 0.40065380930900574, |
| "learning_rate": 0.00010615384615384615, |
| "loss": 0.6382305145263671, |
| "step": 125 |
| }, |
| { |
| "epoch": 2.945812807881773, |
| "grad_norm": 0.34503671526908875, |
| "learning_rate": 9.653846153846153e-05, |
| "loss": 0.6294133377075195, |
| "step": 150 |
| }, |
| { |
| "epoch": 3.4334975369458127, |
| "grad_norm": 0.5113261342048645, |
| "learning_rate": 8.692307692307692e-05, |
| "loss": 0.47971511840820313, |
| "step": 175 |
| }, |
| { |
| "epoch": 3.9261083743842367, |
| "grad_norm": 0.4824973940849304, |
| "learning_rate": 7.730769230769229e-05, |
| "loss": 0.4443168640136719, |
| "step": 200 |
| }, |
| { |
| "epoch": 4.413793103448276, |
| "grad_norm": 0.5395641326904297, |
| "learning_rate": 6.769230769230768e-05, |
| "loss": 0.37861297607421873, |
| "step": 225 |
| }, |
| { |
| "epoch": 4.906403940886699, |
| "grad_norm": 0.5288678407669067, |
| "learning_rate": 5.8076923076923076e-05, |
| "loss": 0.32240795135498046, |
| "step": 250 |
| }, |
| { |
| "epoch": 5.394088669950739, |
| "grad_norm": 0.5405877828598022, |
| "learning_rate": 4.846153846153846e-05, |
| "loss": 0.24867280960083007, |
| "step": 275 |
| }, |
| { |
| "epoch": 5.886699507389163, |
| "grad_norm": 0.47326216101646423, |
| "learning_rate": 3.884615384615385e-05, |
| "loss": 0.22707448959350585, |
| "step": 300 |
| }, |
| { |
| "epoch": 6.374384236453202, |
| "grad_norm": 0.48245593905448914, |
| "learning_rate": 2.9230769230769227e-05, |
| "loss": 0.1732488441467285, |
| "step": 325 |
| }, |
| { |
| "epoch": 6.8669950738916254, |
| "grad_norm": 0.8283548355102539, |
| "learning_rate": 1.9615384615384613e-05, |
| "loss": 0.1669930076599121, |
| "step": 350 |
| }, |
| { |
| "epoch": 7.3546798029556655, |
| "grad_norm": 0.33281880617141724, |
| "learning_rate": 9.999999999999999e-06, |
| "loss": 0.15444289207458495, |
| "step": 375 |
| }, |
| { |
| "epoch": 7.847290640394089, |
| "grad_norm": 0.5502084493637085, |
| "learning_rate": 3.846153846153846e-07, |
| "loss": 0.11810269355773925, |
| "step": 400 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 400, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 8, |
| "save_steps": 400, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 8.033178029351731e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
