| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.8842105263157896, |
| "eval_steps": 500, |
| "global_step": 14, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.12631578947368421, |
| "grad_norm": 7.7602252982853495, |
| "learning_rate": 0.0, |
| "loss": 1.3139, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.25263157894736843, |
| "grad_norm": 7.982016234614304, |
| "learning_rate": 5e-06, |
| "loss": 1.3348, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.37894736842105264, |
| "grad_norm": 5.964368891457489, |
| "learning_rate": 1e-05, |
| "loss": 1.2368, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.5052631578947369, |
| "grad_norm": 2.5847054986030833, |
| "learning_rate": 9.829629131445342e-06, |
| "loss": 1.1371, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.631578947368421, |
| "grad_norm": 3.1863188468902393, |
| "learning_rate": 9.330127018922195e-06, |
| "loss": 1.1389, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.7578947368421053, |
| "grad_norm": 3.156652760285887, |
| "learning_rate": 8.535533905932739e-06, |
| "loss": 1.066, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.8842105263157894, |
| "grad_norm": 2.866354773592533, |
| "learning_rate": 7.500000000000001e-06, |
| "loss": 1.1584, |
| "step": 7 |
| }, |
| { |
| "epoch": 1.1263157894736842, |
| "grad_norm": 3.697072614287029, |
| "learning_rate": 6.294095225512604e-06, |
| "loss": 2.098, |
| "step": 8 |
| }, |
| { |
| "epoch": 1.2526315789473683, |
| "grad_norm": 1.9271757693537654, |
| "learning_rate": 5e-06, |
| "loss": 1.0779, |
| "step": 9 |
| }, |
| { |
| "epoch": 1.3789473684210527, |
| "grad_norm": 1.7719230361667835, |
| "learning_rate": 3.705904774487396e-06, |
| "loss": 0.9586, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.5052631578947369, |
| "grad_norm": 1.8624213018620617, |
| "learning_rate": 2.5000000000000015e-06, |
| "loss": 0.9933, |
| "step": 11 |
| }, |
| { |
| "epoch": 1.631578947368421, |
| "grad_norm": 1.4111496807712673, |
| "learning_rate": 1.4644660940672628e-06, |
| "loss": 1.0243, |
| "step": 12 |
| }, |
| { |
| "epoch": 1.7578947368421054, |
| "grad_norm": 1.6121507550711585, |
| "learning_rate": 6.698729810778065e-07, |
| "loss": 1.0271, |
| "step": 13 |
| }, |
| { |
| "epoch": 1.8842105263157896, |
| "grad_norm": 1.5600166623206193, |
| "learning_rate": 1.7037086855465902e-07, |
| "loss": 0.94, |
| "step": 14 |
| }, |
| { |
| "epoch": 1.8842105263157896, |
| "step": 14, |
| "total_flos": 1.0170584361074688e+16, |
| "train_loss": 1.1789321388517107, |
| "train_runtime": 367.3964, |
| "train_samples_per_second": 2.058, |
| "train_steps_per_second": 0.038 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 14, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 400, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.0170584361074688e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
