| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 300.0, | |
| "global_step": 2826, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 15.699420928955078, | |
| "learning_rate": 1.6927223719676552e-05, | |
| "loss": 1.5106, | |
| "step": 942 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_f1": 0.7668134917297256, | |
| "eval_loss": 0.8142930269241333, | |
| "eval_runtime": 1955.7939, | |
| "eval_samples_per_second": 6.6, | |
| "eval_steps_per_second": 0.207, | |
| "step": 942 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 4.08961820602417, | |
| "learning_rate": 8.463611859838276e-06, | |
| "loss": 0.7033, | |
| "step": 1884 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_f1": 0.7984619452840845, | |
| "eval_loss": 0.6980345845222473, | |
| "eval_runtime": 1952.7483, | |
| "eval_samples_per_second": 6.61, | |
| "eval_steps_per_second": 0.207, | |
| "step": 1884 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 25.8586483001709, | |
| "learning_rate": 0.0, | |
| "loss": 0.511, | |
| "step": 2826 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_f1": 0.8045510528812365, | |
| "eval_loss": 0.6810711622238159, | |
| "eval_runtime": 1950.0401, | |
| "eval_samples_per_second": 6.619, | |
| "eval_steps_per_second": 0.207, | |
| "step": 2826 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 2826, | |
| "total_flos": 2.377533515518771e+16, | |
| "train_loss": 0.9083002715438119, | |
| "train_runtime": 52770.4686, | |
| "train_samples_per_second": 1.712, | |
| "train_steps_per_second": 0.054 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2826, | |
| "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": 2.377533515518771e+16, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |