| { |
| "best_metric": 0.4504155218601227, |
| "best_model_checkpoint": "tiny_bert_rand_100_v1_sst2/checkpoint-264", |
| "epoch": 6.0, |
| "eval_steps": 500, |
| "global_step": 1584, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 6.8471856117248535, |
| "learning_rate": 4.9e-05, |
| "loss": 0.4222, |
| "step": 264 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8096330275229358, |
| "eval_loss": 0.4504155218601227, |
| "eval_runtime": 0.3288, |
| "eval_samples_per_second": 2651.993, |
| "eval_steps_per_second": 12.165, |
| "step": 264 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 11.654817581176758, |
| "learning_rate": 4.8e-05, |
| "loss": 0.2388, |
| "step": 528 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.7798165137614679, |
| "eval_loss": 0.5902100801467896, |
| "eval_runtime": 0.3273, |
| "eval_samples_per_second": 2664.024, |
| "eval_steps_per_second": 12.22, |
| "step": 528 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 6.675928115844727, |
| "learning_rate": 4.7e-05, |
| "loss": 0.1889, |
| "step": 792 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.7935779816513762, |
| "eval_loss": 0.5325756072998047, |
| "eval_runtime": 0.3114, |
| "eval_samples_per_second": 2800.041, |
| "eval_steps_per_second": 12.844, |
| "step": 792 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 5.466443061828613, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 0.1546, |
| "step": 1056 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8038990825688074, |
| "eval_loss": 0.5878260135650635, |
| "eval_runtime": 0.3116, |
| "eval_samples_per_second": 2798.524, |
| "eval_steps_per_second": 12.837, |
| "step": 1056 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 7.747689247131348, |
| "learning_rate": 4.5e-05, |
| "loss": 0.1291, |
| "step": 1320 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.7889908256880734, |
| "eval_loss": 0.7141419649124146, |
| "eval_runtime": 0.3227, |
| "eval_samples_per_second": 2702.092, |
| "eval_steps_per_second": 12.395, |
| "step": 1320 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 9.751855850219727, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 0.1088, |
| "step": 1584 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.783256880733945, |
| "eval_loss": 0.8531506061553955, |
| "eval_runtime": 0.3141, |
| "eval_samples_per_second": 2776.367, |
| "eval_steps_per_second": 12.736, |
| "step": 1584 |
| }, |
| { |
| "epoch": 6.0, |
| "step": 1584, |
| "total_flos": 1.0596790573590528e+16, |
| "train_loss": 0.20706348467354824, |
| "train_runtime": 270.293, |
| "train_samples_per_second": 12458.518, |
| "train_steps_per_second": 48.836 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 13200, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 50, |
| "save_steps": 500, |
| "total_flos": 1.0596790573590528e+16, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
