| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.47058823529411764, |
| "eval_steps": 500, |
| "global_step": 20, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "aux_loss": 8.000365376472473, |
| "entropy": 0.2743653440847993, |
| "epoch": 0.047058823529411764, |
| "grad_norm": 1.1965930461883545, |
| "learning_rate": 1e-05, |
| "loss": 0.9770854711532593, |
| "mean_token_accuracy": 0.8724694326519966, |
| "num_tokens": 1684928.0, |
| "step": 2 |
| }, |
| { |
| "aux_loss": 8.000365793704987, |
| "entropy": 0.27355292858555913, |
| "epoch": 0.09411764705882353, |
| "grad_norm": 1.1649320125579834, |
| "learning_rate": 3e-05, |
| "loss": 0.957563042640686, |
| "mean_token_accuracy": 0.8740394990891218, |
| "num_tokens": 3365468.0, |
| "step": 4 |
| }, |
| { |
| "aux_loss": 8.000367224216461, |
| "entropy": 0.2821843051351607, |
| "epoch": 0.1411764705882353, |
| "grad_norm": 0.9803799390792847, |
| "learning_rate": 5e-05, |
| "loss": 0.9228702783584595, |
| "mean_token_accuracy": 0.8784762397408485, |
| "num_tokens": 5039089.0, |
| "step": 6 |
| }, |
| { |
| "aux_loss": 8.000365853309631, |
| "entropy": 0.2994667002931237, |
| "epoch": 0.18823529411764706, |
| "grad_norm": 0.6679485440254211, |
| "learning_rate": 4.99248235291948e-05, |
| "loss": 0.8751057386398315, |
| "mean_token_accuracy": 0.89654197730124, |
| "num_tokens": 6721528.0, |
| "step": 8 |
| }, |
| { |
| "aux_loss": 8.000366061925888, |
| "entropy": 0.309249896556139, |
| "epoch": 0.23529411764705882, |
| "grad_norm": 0.4859698414802551, |
| "learning_rate": 4.969974623692023e-05, |
| "loss": 0.821368396282196, |
| "mean_token_accuracy": 0.9032865408807993, |
| "num_tokens": 8404019.0, |
| "step": 10 |
| }, |
| { |
| "aux_loss": 8.000365227460861, |
| "entropy": 0.31307727470993996, |
| "epoch": 0.2823529411764706, |
| "grad_norm": 0.3697640001773834, |
| "learning_rate": 4.9326121764495596e-05, |
| "loss": 0.8042377233505249, |
| "mean_token_accuracy": 0.9032355956733227, |
| "num_tokens": 10072372.0, |
| "step": 12 |
| }, |
| { |
| "aux_loss": 8.000364303588867, |
| "entropy": 0.3210192215628922, |
| "epoch": 0.32941176470588235, |
| "grad_norm": 0.36880186200141907, |
| "learning_rate": 4.880619713346039e-05, |
| "loss": 0.7694727778434753, |
| "mean_token_accuracy": 0.9131743311882019, |
| "num_tokens": 11749703.0, |
| "step": 14 |
| }, |
| { |
| "aux_loss": 8.000364184379578, |
| "entropy": 0.3031989838927984, |
| "epoch": 0.3764705882352941, |
| "grad_norm": 0.3208371102809906, |
| "learning_rate": 4.814309923172227e-05, |
| "loss": 0.7714658379554749, |
| "mean_token_accuracy": 0.9173927679657936, |
| "num_tokens": 13416907.0, |
| "step": 16 |
| }, |
| { |
| "aux_loss": 8.000363111495972, |
| "entropy": 0.2881463272497058, |
| "epoch": 0.4235294117647059, |
| "grad_norm": 0.3084357976913452, |
| "learning_rate": 4.734081600808531e-05, |
| "loss": 0.7655668258666992, |
| "mean_token_accuracy": 0.9174891654402018, |
| "num_tokens": 15099572.0, |
| "step": 18 |
| }, |
| { |
| "aux_loss": 8.00036308169365, |
| "entropy": 0.2687815367244184, |
| "epoch": 0.47058823529411764, |
| "grad_norm": 0.2413734644651413, |
| "learning_rate": 4.640417248825667e-05, |
| "loss": 0.7443982362747192, |
| "mean_token_accuracy": 0.9256936926394701, |
| "num_tokens": 16764901.0, |
| "step": 20 |
| } |
| ], |
| "logging_steps": 2, |
| "max_steps": 86, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 5, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 8.589923510984376e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
