| { | |
| "best_metric": 2.283433198928833, | |
| "best_model_checkpoint": "distilbert_lda_100_v1_stsb/checkpoint-69", | |
| "epoch": 8.0, | |
| "eval_steps": 500, | |
| "global_step": 184, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 4.36644172668457, | |
| "learning_rate": 0.00098, | |
| "loss": 5.2042, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_combined_score": NaN, | |
| "eval_loss": 2.2958452701568604, | |
| "eval_pearson": NaN, | |
| "eval_runtime": 0.6458, | |
| "eval_samples_per_second": 2322.538, | |
| "eval_spearmanr": NaN, | |
| "eval_steps_per_second": 9.29, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 3.7728922367095947, | |
| "learning_rate": 0.00096, | |
| "loss": 2.2241, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_combined_score": NaN, | |
| "eval_loss": 2.8777623176574707, | |
| "eval_pearson": NaN, | |
| "eval_runtime": 0.641, | |
| "eval_samples_per_second": 2339.956, | |
| "eval_spearmanr": NaN, | |
| "eval_steps_per_second": 9.36, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 3.375149965286255, | |
| "learning_rate": 0.00094, | |
| "loss": 2.1945, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_combined_score": NaN, | |
| "eval_loss": 2.283433198928833, | |
| "eval_pearson": NaN, | |
| "eval_runtime": 0.6368, | |
| "eval_samples_per_second": 2355.423, | |
| "eval_spearmanr": NaN, | |
| "eval_steps_per_second": 9.422, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 18.793352127075195, | |
| "learning_rate": 0.00092, | |
| "loss": 2.2493, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_combined_score": NaN, | |
| "eval_loss": 2.3354201316833496, | |
| "eval_pearson": NaN, | |
| "eval_runtime": 0.6344, | |
| "eval_samples_per_second": 2364.427, | |
| "eval_spearmanr": NaN, | |
| "eval_steps_per_second": 9.458, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 17.609710693359375, | |
| "learning_rate": 0.0009000000000000001, | |
| "loss": 2.2051, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_combined_score": NaN, | |
| "eval_loss": 2.5273873805999756, | |
| "eval_pearson": NaN, | |
| "eval_runtime": 0.6294, | |
| "eval_samples_per_second": 2383.05, | |
| "eval_spearmanr": NaN, | |
| "eval_steps_per_second": 9.532, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 4.918025016784668, | |
| "learning_rate": 0.00088, | |
| "loss": 2.1982, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_combined_score": NaN, | |
| "eval_loss": 2.3758695125579834, | |
| "eval_pearson": NaN, | |
| "eval_runtime": 0.6533, | |
| "eval_samples_per_second": 2296.056, | |
| "eval_spearmanr": NaN, | |
| "eval_steps_per_second": 9.184, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 24.767385482788086, | |
| "learning_rate": 0.00086, | |
| "loss": 2.1983, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_combined_score": NaN, | |
| "eval_loss": 2.8532462120056152, | |
| "eval_pearson": NaN, | |
| "eval_runtime": 0.6508, | |
| "eval_samples_per_second": 2304.905, | |
| "eval_spearmanr": NaN, | |
| "eval_steps_per_second": 9.22, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 9.223726272583008, | |
| "learning_rate": 0.00084, | |
| "loss": 2.1885, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_combined_score": NaN, | |
| "eval_loss": 2.7600629329681396, | |
| "eval_pearson": NaN, | |
| "eval_runtime": 0.6498, | |
| "eval_samples_per_second": 2308.561, | |
| "eval_spearmanr": NaN, | |
| "eval_steps_per_second": 9.234, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "step": 184, | |
| "total_flos": 3046165974478848.0, | |
| "train_loss": 2.5827721512835957, | |
| "train_runtime": 60.8667, | |
| "train_samples_per_second": 4722.617, | |
| "train_steps_per_second": 18.894 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 1150, | |
| "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": 3046165974478848.0, | |
| "train_batch_size": 256, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |