| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0027231632264037905, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.446326452807581e-05, | |
| "eval_loss": 1.8793249130249023, | |
| "eval_runtime": 621.2907, | |
| "eval_samples_per_second": 12.443, | |
| "eval_steps_per_second": 6.223, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002723163226403791, | |
| "grad_norm": 5.56035852432251, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7265, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005446326452807582, | |
| "grad_norm": 6.478335857391357, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3897, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005446326452807582, | |
| "eval_loss": 1.1497383117675781, | |
| "eval_runtime": 623.1647, | |
| "eval_samples_per_second": 12.406, | |
| "eval_steps_per_second": 6.204, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008169489679211372, | |
| "grad_norm": 5.012179851531982, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.9838, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0010892652905615163, | |
| "grad_norm": 6.457354545593262, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5266, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0010892652905615163, | |
| "eval_loss": 0.6337934136390686, | |
| "eval_runtime": 620.9628, | |
| "eval_samples_per_second": 12.45, | |
| "eval_steps_per_second": 6.226, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0013615816132018952, | |
| "grad_norm": 5.459563732147217, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.6118, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0016338979358422744, | |
| "grad_norm": 4.611813068389893, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5736, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0016338979358422744, | |
| "eval_loss": 0.524707019329071, | |
| "eval_runtime": 620.7623, | |
| "eval_samples_per_second": 12.454, | |
| "eval_steps_per_second": 6.228, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0019062142584826535, | |
| "grad_norm": 3.6113362312316895, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.525, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0021785305811230326, | |
| "grad_norm": 4.558568954467773, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.4886, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0021785305811230326, | |
| "eval_loss": 0.47880464792251587, | |
| "eval_runtime": 622.0545, | |
| "eval_samples_per_second": 12.428, | |
| "eval_steps_per_second": 6.215, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0024508469037634118, | |
| "grad_norm": 5.0720930099487305, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.5172, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0027231632264037905, | |
| "grad_norm": 4.553873538970947, | |
| "learning_rate": 0.0, | |
| "loss": 0.3429, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0027231632264037905, | |
| "eval_loss": 0.4715513586997986, | |
| "eval_runtime": 621.6087, | |
| "eval_samples_per_second": 12.437, | |
| "eval_steps_per_second": 6.219, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9555457081344000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |