| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.876543209876543, | |
| "eval_steps": 500, | |
| "global_step": 800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.6172839506172839, | |
| "grad_norm": 14.113041877746582, | |
| "learning_rate": 9.953000000000001e-06, | |
| "loss": 9.3136, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.2345679012345678, | |
| "grad_norm": 11.032143592834473, | |
| "learning_rate": 9.903e-06, | |
| "loss": 8.8439, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.8518518518518519, | |
| "grad_norm": 21.83379554748535, | |
| "learning_rate": 9.853e-06, | |
| "loss": 8.9582, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.4691358024691357, | |
| "grad_norm": 13.823728561401367, | |
| "learning_rate": 9.803e-06, | |
| "loss": 8.5429, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.0864197530864197, | |
| "grad_norm": 14.090177536010742, | |
| "learning_rate": 9.753e-06, | |
| "loss": 8.0873, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.7037037037037037, | |
| "grad_norm": 16.695327758789062, | |
| "learning_rate": 9.703000000000002e-06, | |
| "loss": 7.5718, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.320987654320987, | |
| "grad_norm": 12.39268970489502, | |
| "learning_rate": 9.653e-06, | |
| "loss": 7.2107, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "grad_norm": 20.64848518371582, | |
| "learning_rate": 9.603000000000001e-06, | |
| "loss": 6.633, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.555555555555555, | |
| "grad_norm": 10.930610656738281, | |
| "learning_rate": 9.553000000000002e-06, | |
| "loss": 6.3085, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 6.172839506172839, | |
| "grad_norm": 7.421260833740234, | |
| "learning_rate": 9.503e-06, | |
| "loss": 5.9761, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.790123456790123, | |
| "grad_norm": 19.653493881225586, | |
| "learning_rate": 9.453e-06, | |
| "loss": 6.0252, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 7.407407407407407, | |
| "grad_norm": 10.195016860961914, | |
| "learning_rate": 9.403000000000001e-06, | |
| "loss": 5.9531, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 8.024691358024691, | |
| "grad_norm": 15.588345527648926, | |
| "learning_rate": 9.353000000000002e-06, | |
| "loss": 5.979, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 8.641975308641975, | |
| "grad_norm": 11.010184288024902, | |
| "learning_rate": 9.303e-06, | |
| "loss": 5.9684, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 9.25925925925926, | |
| "grad_norm": 12.536541938781738, | |
| "learning_rate": 9.253000000000001e-06, | |
| "loss": 6.0309, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 9.876543209876543, | |
| "grad_norm": 10.15280818939209, | |
| "learning_rate": 9.203000000000002e-06, | |
| "loss": 5.7873, | |
| "step": 800 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 10000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 124, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.057945329664e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |