| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.8, |
| "eval_steps": 200, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.08, |
| "grad_norm": 10.467041015625, |
| "learning_rate": 4.6200000000000005e-05, |
| "loss": 2.8162, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 3.9829273223876953, |
| "learning_rate": 4.22e-05, |
| "loss": 1.9308, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 4.000159740447998, |
| "learning_rate": 3.82e-05, |
| "loss": 1.6849, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 1.9223499298095703, |
| "learning_rate": 3.4200000000000005e-05, |
| "loss": 1.5359, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 1.8478671312332153, |
| "learning_rate": 3.02e-05, |
| "loss": 1.571, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 2.243217945098877, |
| "learning_rate": 2.6200000000000003e-05, |
| "loss": 1.5199, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 2.793548345565796, |
| "learning_rate": 2.22e-05, |
| "loss": 1.5036, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 1.5502959489822388, |
| "learning_rate": 1.8200000000000002e-05, |
| "loss": 1.4294, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 5.679831504821777, |
| "learning_rate": 1.42e-05, |
| "loss": 1.4503, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 1.3757414817810059, |
| "learning_rate": 1.02e-05, |
| "loss": 1.4753, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_loss": 1.129705786705017, |
| "eval_runtime": 1533.624, |
| "eval_samples_per_second": 0.652, |
| "eval_steps_per_second": 0.326, |
| "step": 200 |
| } |
| ], |
| "logging_steps": 20, |
| "max_steps": 250, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.2517969149952e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
