| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.8979591836734695, | |
| "eval_steps": 100, | |
| "global_step": 72, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04081632653061224, | |
| "grad_norm": 1.2617460855146998, | |
| "learning_rate": 3.333333333333333e-07, | |
| "loss": 0.6466, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.20408163265306123, | |
| "grad_norm": 1.2307112921782883, | |
| "learning_rate": 9.979284212657656e-07, | |
| "loss": 0.6466, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.40816326530612246, | |
| "grad_norm": 0.9893742709347572, | |
| "learning_rate": 9.748198494501595e-07, | |
| "loss": 0.6334, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6122448979591837, | |
| "grad_norm": 0.9574758858591964, | |
| "learning_rate": 9.272097022732443e-07, | |
| "loss": 0.633, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.8163265306122449, | |
| "grad_norm": 0.8990830302056602, | |
| "learning_rate": 8.575547506774497e-07, | |
| "loss": 0.6254, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.8629610978352574, | |
| "learning_rate": 7.694493179577878e-07, | |
| "loss": 0.6227, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.2040816326530612, | |
| "grad_norm": 0.8914142018310824, | |
| "learning_rate": 6.67439806085493e-07, | |
| "loss": 0.6122, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.4081632653061225, | |
| "grad_norm": 0.8718894603865037, | |
| "learning_rate": 5.567900930252374e-07, | |
| "loss": 0.6222, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.6122448979591837, | |
| "grad_norm": 0.8776590773869387, | |
| "learning_rate": 4.432099069747625e-07, | |
| "loss": 0.6149, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.816326530612245, | |
| "grad_norm": 0.8051676993692058, | |
| "learning_rate": 3.325601939145069e-07, | |
| "loss": 0.6133, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.3450560122195294, | |
| "learning_rate": 2.3055068204221223e-07, | |
| "loss": 0.6142, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.204081632653061, | |
| "grad_norm": 0.7696769584574001, | |
| "learning_rate": 1.4244524932255026e-07, | |
| "loss": 0.6085, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.4081632653061225, | |
| "grad_norm": 0.7274720970155071, | |
| "learning_rate": 7.279029772675571e-08, | |
| "loss": 0.6062, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.612244897959184, | |
| "grad_norm": 0.8283831918644999, | |
| "learning_rate": 2.5180150549840406e-08, | |
| "loss": 0.6193, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.816326530612245, | |
| "grad_norm": 0.8832217131922668, | |
| "learning_rate": 2.071578734234358e-09, | |
| "loss": 0.6122, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.8979591836734695, | |
| "step": 72, | |
| "total_flos": 5.75195770215465e+16, | |
| "train_loss": 0.6201117345028453, | |
| "train_runtime": 1887.4578, | |
| "train_samples_per_second": 0.62, | |
| "train_steps_per_second": 0.038 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 72, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.75195770215465e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |