| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 1041, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.2881844380403458, |
| "grad_norm": 1.4422333240509033, |
| "learning_rate": 0.0001815561959654179, |
| "loss": 3.1655, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.5763688760806917, |
| "grad_norm": 1.9075777530670166, |
| "learning_rate": 0.00016234390009606147, |
| "loss": 0.8772, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.8645533141210374, |
| "grad_norm": 1.9097354412078857, |
| "learning_rate": 0.0001431316042267051, |
| "loss": 0.451, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.1527377521613833, |
| "grad_norm": 1.6237609386444092, |
| "learning_rate": 0.00012391930835734872, |
| "loss": 0.3981, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.440922190201729, |
| "grad_norm": 1.9261122941970825, |
| "learning_rate": 0.00010470701248799233, |
| "loss": 0.367, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.440922190201729, |
| "eval_runtime": 216.0803, |
| "eval_samples_per_second": 5.725, |
| "eval_steps_per_second": 2.865, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.729106628242075, |
| "grad_norm": 1.2721047401428223, |
| "learning_rate": 8.549471661863592e-05, |
| "loss": 0.3705, |
| "step": 600 |
| }, |
| { |
| "epoch": 2.0172910662824206, |
| "grad_norm": 1.371832251548767, |
| "learning_rate": 6.628242074927953e-05, |
| "loss": 0.3746, |
| "step": 700 |
| }, |
| { |
| "epoch": 2.3054755043227666, |
| "grad_norm": 1.7075700759887695, |
| "learning_rate": 4.7070124879923156e-05, |
| "loss": 0.3314, |
| "step": 800 |
| }, |
| { |
| "epoch": 2.5936599423631126, |
| "grad_norm": 1.1070783138275146, |
| "learning_rate": 2.7857829010566765e-05, |
| "loss": 0.3145, |
| "step": 900 |
| }, |
| { |
| "epoch": 2.881844380403458, |
| "grad_norm": 1.6173722743988037, |
| "learning_rate": 8.645533141210376e-06, |
| "loss": 0.3149, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.881844380403458, |
| "eval_runtime": 213.2376, |
| "eval_samples_per_second": 5.801, |
| "eval_steps_per_second": 2.903, |
| "step": 1000 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 1041, |
| "total_flos": 2.42193908736e+18, |
| "train_loss": 0.6824458238599852, |
| "train_runtime": 2058.2511, |
| "train_samples_per_second": 4.042, |
| "train_steps_per_second": 0.506 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 1041, |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.42193908736e+18, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
