| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 37.0, |
| "eval_steps": 0, |
| "global_step": 37, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "learning_rate": 1e-05, |
| "loss": 0.0024, |
| "step": 1 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.4253398134168846, |
| "learning_rate": 9.722222222222223e-06, |
| "loss": 0.0121, |
| "step": 2 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.4253398134168846, |
| "learning_rate": 9.444444444444445e-06, |
| "loss": 0.0033, |
| "step": 3 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.22690383364334638, |
| "learning_rate": 9.166666666666666e-06, |
| "loss": -0.0017, |
| "step": 4 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.22690383364334638, |
| "learning_rate": 8.888888888888888e-06, |
| "loss": 0.0072, |
| "step": 5 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 0.2819672320111151, |
| "learning_rate": 8.611111111111112e-06, |
| "loss": 0.0002, |
| "step": 6 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 0.2819672320111151, |
| "learning_rate": 8.333333333333334e-06, |
| "loss": 0.0021, |
| "step": 7 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 0.3119764207686187, |
| "learning_rate": 8.055555555555557e-06, |
| "loss": -0.0022, |
| "step": 8 |
| }, |
| { |
| "epoch": 9.0, |
| "grad_norm": 0.3119764207686187, |
| "learning_rate": 7.77777777777778e-06, |
| "loss": 0.0015, |
| "step": 9 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 0.4897427977762324, |
| "learning_rate": 7.500000000000001e-06, |
| "loss": 0.003, |
| "step": 10 |
| }, |
| { |
| "epoch": 11.0, |
| "grad_norm": 0.4897427977762324, |
| "learning_rate": 7.222222222222223e-06, |
| "loss": -0.0014, |
| "step": 11 |
| }, |
| { |
| "epoch": 12.0, |
| "grad_norm": 0.48226237819687684, |
| "learning_rate": 6.944444444444445e-06, |
| "loss": -0.0036, |
| "step": 12 |
| }, |
| { |
| "epoch": 13.0, |
| "grad_norm": 0.48226237819687684, |
| "learning_rate": 6.666666666666667e-06, |
| "loss": -0.0055, |
| "step": 13 |
| }, |
| { |
| "epoch": 14.0, |
| "grad_norm": 0.6552012201520575, |
| "learning_rate": 6.3888888888888885e-06, |
| "loss": -0.0035, |
| "step": 14 |
| }, |
| { |
| "epoch": 15.0, |
| "grad_norm": 0.6552012201520575, |
| "learning_rate": 6.111111111111112e-06, |
| "loss": -0.006, |
| "step": 15 |
| }, |
| { |
| "epoch": 16.0, |
| "grad_norm": 0.8260274732302099, |
| "learning_rate": 5.833333333333334e-06, |
| "loss": -0.0059, |
| "step": 16 |
| }, |
| { |
| "epoch": 17.0, |
| "grad_norm": 0.8260274732302099, |
| "learning_rate": 5.555555555555557e-06, |
| "loss": -0.0069, |
| "step": 17 |
| }, |
| { |
| "epoch": 18.0, |
| "grad_norm": 1.029848111009817, |
| "learning_rate": 5.2777777777777785e-06, |
| "loss": -0.0052, |
| "step": 18 |
| }, |
| { |
| "epoch": 19.0, |
| "grad_norm": 1.029848111009817, |
| "learning_rate": 5e-06, |
| "loss": -0.0126, |
| "step": 19 |
| }, |
| { |
| "epoch": 20.0, |
| "grad_norm": 1.2452709404165625, |
| "learning_rate": 4.722222222222222e-06, |
| "loss": -0.012, |
| "step": 20 |
| }, |
| { |
| "epoch": 21.0, |
| "grad_norm": 1.2452709404165625, |
| "learning_rate": 4.444444444444444e-06, |
| "loss": -0.0114, |
| "step": 21 |
| }, |
| { |
| "epoch": 22.0, |
| "grad_norm": 1.4963944132529878, |
| "learning_rate": 4.166666666666667e-06, |
| "loss": -0.0143, |
| "step": 22 |
| }, |
| { |
| "epoch": 23.0, |
| "grad_norm": 1.4963944132529878, |
| "learning_rate": 3.88888888888889e-06, |
| "loss": -0.0176, |
| "step": 23 |
| }, |
| { |
| "epoch": 24.0, |
| "grad_norm": 1.6791895753102362, |
| "learning_rate": 3.6111111111111115e-06, |
| "loss": -0.0169, |
| "step": 24 |
| }, |
| { |
| "epoch": 25.0, |
| "grad_norm": 1.6791895753102362, |
| "learning_rate": 3.3333333333333333e-06, |
| "loss": -0.0128, |
| "step": 25 |
| }, |
| { |
| "epoch": 26.0, |
| "grad_norm": 1.9217862070985101, |
| "learning_rate": 3.055555555555556e-06, |
| "loss": -0.018, |
| "step": 26 |
| }, |
| { |
| "epoch": 27.0, |
| "grad_norm": 1.9217862070985101, |
| "learning_rate": 2.7777777777777783e-06, |
| "loss": -0.0242, |
| "step": 27 |
| }, |
| { |
| "epoch": 28.0, |
| "grad_norm": 2.0777822012451024, |
| "learning_rate": 2.5e-06, |
| "loss": -0.0239, |
| "step": 28 |
| }, |
| { |
| "epoch": 29.0, |
| "grad_norm": 2.0777822012451024, |
| "learning_rate": 2.222222222222222e-06, |
| "loss": -0.0212, |
| "step": 29 |
| }, |
| { |
| "epoch": 30.0, |
| "grad_norm": 2.1920367677528696, |
| "learning_rate": 1.944444444444445e-06, |
| "loss": -0.0269, |
| "step": 30 |
| }, |
| { |
| "epoch": 31.0, |
| "grad_norm": 2.1920367677528696, |
| "learning_rate": 1.6666666666666667e-06, |
| "loss": -0.0263, |
| "step": 31 |
| }, |
| { |
| "epoch": 32.0, |
| "grad_norm": 2.35990621212608, |
| "learning_rate": 1.3888888888888892e-06, |
| "loss": -0.0303, |
| "step": 32 |
| }, |
| { |
| "epoch": 33.0, |
| "grad_norm": 2.35990621212608, |
| "learning_rate": 1.111111111111111e-06, |
| "loss": -0.03, |
| "step": 33 |
| }, |
| { |
| "epoch": 34.0, |
| "grad_norm": 2.339123283228121, |
| "learning_rate": 8.333333333333333e-07, |
| "loss": -0.0326, |
| "step": 34 |
| }, |
| { |
| "epoch": 35.0, |
| "grad_norm": 2.339123283228121, |
| "learning_rate": 5.555555555555555e-07, |
| "loss": -0.0331, |
| "step": 35 |
| }, |
| { |
| "epoch": 36.0, |
| "grad_norm": 2.2802824352717295, |
| "learning_rate": 2.7777777777777776e-07, |
| "loss": -0.0311, |
| "step": 36 |
| }, |
| { |
| "epoch": 37.0, |
| "grad_norm": 2.2802824352717295, |
| "learning_rate": 0.0, |
| "loss": -0.0353, |
| "step": 37 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 37, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 37, |
| "save_steps": 3, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
