| { |
| "best_metric": 0.07319068908691406, |
| "best_model_checkpoint": "clip_base_4b_aug/checkpoint-1125", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 1125, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.962625, |
| "eval_loss": 0.10090840607881546, |
| "eval_runtime": 231.5826, |
| "eval_samples_per_second": 103.635, |
| "eval_steps_per_second": 1.619, |
| "step": 375 |
| }, |
| { |
| "epoch": 1.3333333333333333, |
| "grad_norm": 22.520030975341797, |
| "learning_rate": 5.813953488372093e-07, |
| "loss": 0.196, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.970625, |
| "eval_loss": 0.08056605607271194, |
| "eval_runtime": 109.1814, |
| "eval_samples_per_second": 219.818, |
| "eval_steps_per_second": 3.435, |
| "step": 750 |
| }, |
| { |
| "epoch": 2.6666666666666665, |
| "grad_norm": 20.832218170166016, |
| "learning_rate": 1.1627906976744186e-07, |
| "loss": 0.0755, |
| "step": 1000 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9736666666666667, |
| "eval_loss": 0.07319068908691406, |
| "eval_runtime": 105.3698, |
| "eval_samples_per_second": 227.769, |
| "eval_steps_per_second": 3.559, |
| "step": 1125 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1125, |
| "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": 2.273880039240499e+19, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
