| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 98, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.10204081632653061, |
| "grad_norm": 0.68359375, |
| "learning_rate": 7.314242018863303e-05, |
| "loss": 1.3342, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.20408163265306123, |
| "grad_norm": 0.48046875, |
| "learning_rate": 0.0001645704454244243, |
| "loss": 1.2171, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.30612244897959184, |
| "grad_norm": 0.42578125, |
| "learning_rate": 0.0002559984706602156, |
| "loss": 1.1262, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.40816326530612246, |
| "grad_norm": 0.431640625, |
| "learning_rate": 0.0003474264958960069, |
| "loss": 1.0323, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.5102040816326531, |
| "grad_norm": 0.33203125, |
| "learning_rate": 0.00043885452113179817, |
| "loss": 0.9787, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.6122448979591837, |
| "grad_norm": 0.3203125, |
| "learning_rate": 0.0005302825463675895, |
| "loss": 0.9541, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.7142857142857143, |
| "grad_norm": 0.35546875, |
| "learning_rate": 0.0006217105716033808, |
| "loss": 0.9082, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.8163265306122449, |
| "grad_norm": 0.34375, |
| "learning_rate": 0.0006384871160400743, |
| "loss": 0.9095, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.9183673469387755, |
| "grad_norm": 0.3125, |
| "learning_rate": 0.0006323890674048986, |
| "loss": 0.8862, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.9025439023971558, |
| "eval_runtime": 7.236, |
| "eval_samples_per_second": 27.501, |
| "eval_steps_per_second": 27.501, |
| "step": 49 |
| }, |
| { |
| "epoch": 1.0204081632653061, |
| "grad_norm": 0.5625, |
| "learning_rate": 0.0006217273735914285, |
| "loss": 0.8337, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.1224489795918366, |
| "grad_norm": 0.29296875, |
| "learning_rate": 0.0006067114062701753, |
| "loss": 0.6299, |
| "step": 55 |
| }, |
| { |
| "epoch": 1.2244897959183674, |
| "grad_norm": 0.3125, |
| "learning_rate": 0.0005876360452432976, |
| "loss": 0.6722, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.3265306122448979, |
| "grad_norm": 0.29296875, |
| "learning_rate": 0.0005648758876689657, |
| "loss": 0.6452, |
| "step": 65 |
| }, |
| { |
| "epoch": 1.4285714285714286, |
| "grad_norm": 0.265625, |
| "learning_rate": 0.0005388778918162697, |
| "loss": 0.6395, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.5306122448979593, |
| "grad_norm": 0.30078125, |
| "learning_rate": 0.000510152599810772, |
| "loss": 0.618, |
| "step": 75 |
| }, |
| { |
| "epoch": 1.6326530612244898, |
| "grad_norm": 0.328125, |
| "learning_rate": 0.00047926411173622446, |
| "loss": 0.6201, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.7346938775510203, |
| "grad_norm": 0.2578125, |
| "learning_rate": 0.0004468190079785287, |
| "loss": 0.5833, |
| "step": 85 |
| }, |
| { |
| "epoch": 1.836734693877551, |
| "grad_norm": 0.30078125, |
| "learning_rate": 0.0004134544373521701, |
| "loss": 0.6098, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.9387755102040818, |
| "grad_norm": 0.2890625, |
| "learning_rate": 0.00037982560493151593, |
| "loss": 0.6014, |
| "step": 95 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.7977187633514404, |
| "eval_runtime": 7.1408, |
| "eval_samples_per_second": 27.868, |
| "eval_steps_per_second": 27.868, |
| "step": 98 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 147, |
| "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": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.939659357683712e+17, |
| "train_batch_size": 100, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
