| { | |
| "best_metric": 0.6569345593452454, | |
| "best_model_checkpoint": "distilbert_lda_100_v1_qqp/checkpoint-4266", | |
| "epoch": 8.0, | |
| "eval_steps": 500, | |
| "global_step": 11376, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.2662235498428345, | |
| "learning_rate": 0.00098, | |
| "loss": 0.667, | |
| "step": 1422 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6318327974276527, | |
| "eval_combined_score": 0.3159163987138264, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.6585862040519714, | |
| "eval_runtime": 16.9764, | |
| "eval_samples_per_second": 2381.542, | |
| "eval_steps_per_second": 9.307, | |
| "step": 1422 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.10064509510993958, | |
| "learning_rate": 0.00096, | |
| "loss": 0.659, | |
| "step": 2844 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6318327974276527, | |
| "eval_combined_score": 0.3159163987138264, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.6569439768791199, | |
| "eval_runtime": 17.3915, | |
| "eval_samples_per_second": 2324.697, | |
| "eval_steps_per_second": 9.085, | |
| "step": 2844 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.05541796237230301, | |
| "learning_rate": 0.00094, | |
| "loss": 0.6585, | |
| "step": 4266 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6318327974276527, | |
| "eval_combined_score": 0.3159163987138264, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.6569345593452454, | |
| "eval_runtime": 17.0052, | |
| "eval_samples_per_second": 2377.504, | |
| "eval_steps_per_second": 9.291, | |
| "step": 4266 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.0837196335196495, | |
| "learning_rate": 0.00092, | |
| "loss": 0.6585, | |
| "step": 5688 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.6318327974276527, | |
| "eval_combined_score": 0.3159163987138264, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.6573521494865417, | |
| "eval_runtime": 17.1979, | |
| "eval_samples_per_second": 2350.873, | |
| "eval_steps_per_second": 9.187, | |
| "step": 5688 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.12371832132339478, | |
| "learning_rate": 0.0009000000000000001, | |
| "loss": 0.6585, | |
| "step": 7110 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.6318327974276527, | |
| "eval_combined_score": 0.3159163987138264, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.6573521494865417, | |
| "eval_runtime": 16.9747, | |
| "eval_samples_per_second": 2381.777, | |
| "eval_steps_per_second": 9.308, | |
| "step": 7110 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.04144879803061485, | |
| "learning_rate": 0.00088, | |
| "loss": 0.6586, | |
| "step": 8532 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.6318327974276527, | |
| "eval_combined_score": 0.3159163987138264, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.6577603816986084, | |
| "eval_runtime": 17.1651, | |
| "eval_samples_per_second": 2355.356, | |
| "eval_steps_per_second": 9.205, | |
| "step": 8532 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 0.050063714385032654, | |
| "learning_rate": 0.00086, | |
| "loss": 0.6585, | |
| "step": 9954 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.6318327974276527, | |
| "eval_combined_score": 0.3159163987138264, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.6573427319526672, | |
| "eval_runtime": 17.1073, | |
| "eval_samples_per_second": 2363.321, | |
| "eval_steps_per_second": 9.236, | |
| "step": 9954 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.11186650395393372, | |
| "learning_rate": 0.00084, | |
| "loss": 0.6586, | |
| "step": 11376 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.6318327974276527, | |
| "eval_combined_score": 0.3159163987138264, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.6573427319526672, | |
| "eval_runtime": 17.0733, | |
| "eval_samples_per_second": 2368.021, | |
| "eval_steps_per_second": 9.254, | |
| "step": 11376 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "step": 11376, | |
| "total_flos": 1.927909325255639e+17, | |
| "train_loss": 0.6596396455617226, | |
| "train_runtime": 2840.4842, | |
| "train_samples_per_second": 6404.647, | |
| "train_steps_per_second": 25.031 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 71100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 5 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.927909325255639e+17, | |
| "train_batch_size": 256, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |