| { | |
| "best_metric": 0.561651885509491, | |
| "best_model_checkpoint": "autotrain-c0qmd-8o6a3/checkpoint-57", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 57, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.15789473684210525, | |
| "grad_norm": 0.7351207137107849, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.7116, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "grad_norm": 0.5466904640197754, | |
| "learning_rate": 3e-05, | |
| "loss": 0.6971, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.47368421052631576, | |
| "grad_norm": 0.6673880815505981, | |
| "learning_rate": 2.823529411764706e-05, | |
| "loss": 0.6825, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 0.7052972912788391, | |
| "learning_rate": 2.647058823529412e-05, | |
| "loss": 0.6449, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.7894736842105263, | |
| "grad_norm": 0.5568715929985046, | |
| "learning_rate": 2.4705882352941174e-05, | |
| "loss": 0.6452, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.9473684210526315, | |
| "grad_norm": 0.48849067091941833, | |
| "learning_rate": 2.2941176470588233e-05, | |
| "loss": 0.6618, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.5993797779083252, | |
| "eval_runtime": 0.3867, | |
| "eval_samples_per_second": 95.693, | |
| "eval_steps_per_second": 7.759, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.1052631578947367, | |
| "grad_norm": 0.4476867616176605, | |
| "learning_rate": 2.1176470588235296e-05, | |
| "loss": 0.6781, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.263157894736842, | |
| "grad_norm": 0.5001488924026489, | |
| "learning_rate": 1.9411764705882355e-05, | |
| "loss": 0.5805, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.4210526315789473, | |
| "grad_norm": 0.4495070278644562, | |
| "learning_rate": 1.7647058823529414e-05, | |
| "loss": 0.6048, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.5789473684210527, | |
| "grad_norm": 0.4159792959690094, | |
| "learning_rate": 1.5882352941176473e-05, | |
| "loss": 0.5883, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.736842105263158, | |
| "grad_norm": 0.4267251789569855, | |
| "learning_rate": 1.411764705882353e-05, | |
| "loss": 0.6472, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.8947368421052633, | |
| "grad_norm": 0.4449743926525116, | |
| "learning_rate": 1.2352941176470587e-05, | |
| "loss": 0.6126, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.5694108605384827, | |
| "eval_runtime": 0.4725, | |
| "eval_samples_per_second": 78.3, | |
| "eval_steps_per_second": 6.349, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.0526315789473686, | |
| "grad_norm": 0.4716056287288666, | |
| "learning_rate": 1.0588235294117648e-05, | |
| "loss": 0.575, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.2105263157894735, | |
| "grad_norm": 0.42344826459884644, | |
| "learning_rate": 8.823529411764707e-06, | |
| "loss": 0.6379, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.3684210526315788, | |
| "grad_norm": 0.4396233856678009, | |
| "learning_rate": 7.058823529411765e-06, | |
| "loss": 0.6299, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.526315789473684, | |
| "grad_norm": 0.4188365340232849, | |
| "learning_rate": 5.294117647058824e-06, | |
| "loss": 0.5225, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.6842105263157894, | |
| "grad_norm": 0.3908810019493103, | |
| "learning_rate": 3.5294117647058825e-06, | |
| "loss": 0.5441, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.8421052631578947, | |
| "grad_norm": 0.45354488492012024, | |
| "learning_rate": 1.7647058823529412e-06, | |
| "loss": 0.6127, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 1.0902165174484253, | |
| "learning_rate": 0.0, | |
| "loss": 0.573, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.561651885509491, | |
| "eval_runtime": 0.2142, | |
| "eval_samples_per_second": 172.751, | |
| "eval_steps_per_second": 14.007, | |
| "step": 57 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 57, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |