| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 333.3636363636364, |
| "eval_steps": 500, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 16.727272727272727, |
| "grad_norm": 0.33923184871673584, |
| "learning_rate": 2.45e-05, |
| "loss": 4.6873, |
| "step": 50 |
| }, |
| { |
| "epoch": 33.36363636363637, |
| "grad_norm": 0.37357452511787415, |
| "learning_rate": 4.9500000000000004e-05, |
| "loss": 4.6739, |
| "step": 100 |
| }, |
| { |
| "epoch": 50.0, |
| "grad_norm": 2.4127211570739746, |
| "learning_rate": 4.727777777777778e-05, |
| "loss": 4.4116, |
| "step": 150 |
| }, |
| { |
| "epoch": 66.72727272727273, |
| "grad_norm": 1.6806278228759766, |
| "learning_rate": 4.4500000000000004e-05, |
| "loss": 4.0929, |
| "step": 200 |
| }, |
| { |
| "epoch": 83.36363636363636, |
| "grad_norm": 0.4469057321548462, |
| "learning_rate": 4.172222222222222e-05, |
| "loss": 3.816, |
| "step": 250 |
| }, |
| { |
| "epoch": 100.0, |
| "grad_norm": 0.5471809506416321, |
| "learning_rate": 3.894444444444444e-05, |
| "loss": 3.6948, |
| "step": 300 |
| }, |
| { |
| "epoch": 116.72727272727273, |
| "grad_norm": 1.806467056274414, |
| "learning_rate": 3.6166666666666674e-05, |
| "loss": 3.5223, |
| "step": 350 |
| }, |
| { |
| "epoch": 133.36363636363637, |
| "grad_norm": 0.54634028673172, |
| "learning_rate": 3.338888888888889e-05, |
| "loss": 3.37, |
| "step": 400 |
| }, |
| { |
| "epoch": 150.0, |
| "grad_norm": 0.6104632019996643, |
| "learning_rate": 3.061111111111111e-05, |
| "loss": 3.2749, |
| "step": 450 |
| }, |
| { |
| "epoch": 166.72727272727272, |
| "grad_norm": 0.5733019709587097, |
| "learning_rate": 2.7833333333333333e-05, |
| "loss": 3.2244, |
| "step": 500 |
| }, |
| { |
| "epoch": 183.36363636363637, |
| "grad_norm": 0.5145729184150696, |
| "learning_rate": 2.5055555555555555e-05, |
| "loss": 3.2001, |
| "step": 550 |
| }, |
| { |
| "epoch": 200.0, |
| "grad_norm": 0.6695804595947266, |
| "learning_rate": 2.2277777777777778e-05, |
| "loss": 3.1713, |
| "step": 600 |
| }, |
| { |
| "epoch": 216.72727272727272, |
| "grad_norm": 0.5976605415344238, |
| "learning_rate": 1.9500000000000003e-05, |
| "loss": 3.1485, |
| "step": 650 |
| }, |
| { |
| "epoch": 233.36363636363637, |
| "grad_norm": 0.5438806414604187, |
| "learning_rate": 1.6722222222222222e-05, |
| "loss": 3.1235, |
| "step": 700 |
| }, |
| { |
| "epoch": 250.0, |
| "grad_norm": 0.8038323521614075, |
| "learning_rate": 1.3944444444444446e-05, |
| "loss": 3.1177, |
| "step": 750 |
| }, |
| { |
| "epoch": 266.72727272727275, |
| "grad_norm": 0.5746641159057617, |
| "learning_rate": 1.1166666666666668e-05, |
| "loss": 3.1019, |
| "step": 800 |
| }, |
| { |
| "epoch": 283.3636363636364, |
| "grad_norm": 0.5870569944381714, |
| "learning_rate": 8.38888888888889e-06, |
| "loss": 3.0854, |
| "step": 850 |
| }, |
| { |
| "epoch": 300.0, |
| "grad_norm": 0.6904098391532898, |
| "learning_rate": 5.611111111111112e-06, |
| "loss": 3.0804, |
| "step": 900 |
| }, |
| { |
| "epoch": 316.72727272727275, |
| "grad_norm": 0.5719147324562073, |
| "learning_rate": 2.8333333333333335e-06, |
| "loss": 3.0819, |
| "step": 950 |
| }, |
| { |
| "epoch": 333.3636363636364, |
| "grad_norm": 0.663352906703949, |
| "learning_rate": 5.555555555555556e-08, |
| "loss": 3.0877, |
| "step": 1000 |
| }, |
| { |
| "epoch": 333.3636363636364, |
| "step": 1000, |
| "total_flos": 1.008388713480192e+16, |
| "train_loss": 3.4983248138427734, |
| "train_runtime": 1121.9949, |
| "train_samples_per_second": 14.26, |
| "train_steps_per_second": 0.891 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 334, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.008388713480192e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
