| { | |
| "best_metric": 0.9153493642807007, | |
| "best_model_checkpoint": "distilbert_lda_100_v1_stsb/checkpoint-230", | |
| "epoch": 15.0, | |
| "eval_steps": 500, | |
| "global_step": 345, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 6.528723239898682, | |
| "learning_rate": 4.9e-05, | |
| "loss": 2.622, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_combined_score": 0.09512879196662656, | |
| "eval_loss": 2.529794216156006, | |
| "eval_pearson": 0.10113703827077289, | |
| "eval_runtime": 0.6476, | |
| "eval_samples_per_second": 2316.18, | |
| "eval_spearmanr": 0.08912054566248023, | |
| "eval_steps_per_second": 9.265, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 14.141378402709961, | |
| "learning_rate": 4.8e-05, | |
| "loss": 1.8404, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_combined_score": 0.46451389801303666, | |
| "eval_loss": 2.334291458129883, | |
| "eval_pearson": 0.4642190872924477, | |
| "eval_runtime": 0.6424, | |
| "eval_samples_per_second": 2334.917, | |
| "eval_spearmanr": 0.4648087087336257, | |
| "eval_steps_per_second": 9.34, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 15.804608345031738, | |
| "learning_rate": 4.7e-05, | |
| "loss": 1.3143, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_combined_score": 0.6702617110676681, | |
| "eval_loss": 1.2509400844573975, | |
| "eval_pearson": 0.6735628956208805, | |
| "eval_runtime": 0.7279, | |
| "eval_samples_per_second": 2060.6, | |
| "eval_spearmanr": 0.6669605265144558, | |
| "eval_steps_per_second": 8.242, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 13.790794372558594, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 0.8809, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_combined_score": 0.7213381248378519, | |
| "eval_loss": 1.3873708248138428, | |
| "eval_pearson": 0.7172298554270424, | |
| "eval_runtime": 0.6538, | |
| "eval_samples_per_second": 2294.292, | |
| "eval_spearmanr": 0.7254463942486612, | |
| "eval_steps_per_second": 9.177, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 12.30782699584961, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.6317, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_combined_score": 0.7164477017307784, | |
| "eval_loss": 1.583528757095337, | |
| "eval_pearson": 0.7090720167762655, | |
| "eval_runtime": 0.6363, | |
| "eval_samples_per_second": 2357.515, | |
| "eval_spearmanr": 0.7238233866852912, | |
| "eval_steps_per_second": 9.43, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 10.6016845703125, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.5139, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_combined_score": 0.7456445881950656, | |
| "eval_loss": 1.279284954071045, | |
| "eval_pearson": 0.744296040490723, | |
| "eval_runtime": 0.6455, | |
| "eval_samples_per_second": 2323.754, | |
| "eval_spearmanr": 0.7469931358994083, | |
| "eval_steps_per_second": 9.295, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 6.149612903594971, | |
| "learning_rate": 4.3e-05, | |
| "loss": 0.3919, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_combined_score": 0.7555569821393648, | |
| "eval_loss": 1.0237528085708618, | |
| "eval_pearson": 0.7576470777149404, | |
| "eval_runtime": 0.6495, | |
| "eval_samples_per_second": 2309.412, | |
| "eval_spearmanr": 0.7534668865637894, | |
| "eval_steps_per_second": 9.238, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 5.594114303588867, | |
| "learning_rate": 4.2e-05, | |
| "loss": 0.3125, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_combined_score": 0.734024640227608, | |
| "eval_loss": 1.4519073963165283, | |
| "eval_pearson": 0.7331238450711645, | |
| "eval_runtime": 0.6526, | |
| "eval_samples_per_second": 2298.344, | |
| "eval_spearmanr": 0.7349254353840515, | |
| "eval_steps_per_second": 9.193, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 7.766717910766602, | |
| "learning_rate": 4.1e-05, | |
| "loss": 0.281, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_combined_score": 0.7381812541060337, | |
| "eval_loss": 1.256384253501892, | |
| "eval_pearson": 0.7389521632675855, | |
| "eval_runtime": 0.6521, | |
| "eval_samples_per_second": 2300.157, | |
| "eval_spearmanr": 0.7374103449444821, | |
| "eval_steps_per_second": 9.201, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 7.7253313064575195, | |
| "learning_rate": 4e-05, | |
| "loss": 0.2395, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_combined_score": 0.7731133282988156, | |
| "eval_loss": 0.9153493642807007, | |
| "eval_pearson": 0.775833107495325, | |
| "eval_runtime": 0.654, | |
| "eval_samples_per_second": 2293.525, | |
| "eval_spearmanr": 0.7703935491023064, | |
| "eval_steps_per_second": 9.174, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "grad_norm": 8.97021484375, | |
| "learning_rate": 3.9000000000000006e-05, | |
| "loss": 0.2219, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_combined_score": 0.7508687271969791, | |
| "eval_loss": 1.2410622835159302, | |
| "eval_pearson": 0.7508843218702125, | |
| "eval_runtime": 0.6479, | |
| "eval_samples_per_second": 2315.036, | |
| "eval_spearmanr": 0.7508531325237456, | |
| "eval_steps_per_second": 9.26, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 7.8722004890441895, | |
| "learning_rate": 3.8e-05, | |
| "loss": 0.1923, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_combined_score": 0.7436207323425442, | |
| "eval_loss": 1.5144480466842651, | |
| "eval_pearson": 0.7428768737971987, | |
| "eval_runtime": 0.6534, | |
| "eval_samples_per_second": 2295.818, | |
| "eval_spearmanr": 0.7443645908878898, | |
| "eval_steps_per_second": 9.183, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "grad_norm": 5.461670398712158, | |
| "learning_rate": 3.7e-05, | |
| "loss": 0.1688, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_combined_score": 0.7493074527202994, | |
| "eval_loss": 1.0667222738265991, | |
| "eval_pearson": 0.7517996606156556, | |
| "eval_runtime": 0.6697, | |
| "eval_samples_per_second": 2239.742, | |
| "eval_spearmanr": 0.7468152448249431, | |
| "eval_steps_per_second": 8.959, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "grad_norm": 4.178849220275879, | |
| "learning_rate": 3.6e-05, | |
| "loss": 0.1494, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_combined_score": 0.7492505592661682, | |
| "eval_loss": 1.2371269464492798, | |
| "eval_pearson": 0.750178139345508, | |
| "eval_runtime": 0.6719, | |
| "eval_samples_per_second": 2232.526, | |
| "eval_spearmanr": 0.7483229791868286, | |
| "eval_steps_per_second": 8.93, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "grad_norm": 4.821505069732666, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.1498, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_combined_score": 0.7453157328804569, | |
| "eval_loss": 1.1066056489944458, | |
| "eval_pearson": 0.7473142192268427, | |
| "eval_runtime": 0.6418, | |
| "eval_samples_per_second": 2337.353, | |
| "eval_spearmanr": 0.7433172465340713, | |
| "eval_steps_per_second": 9.349, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "step": 345, | |
| "total_flos": 5711561202147840.0, | |
| "train_loss": 0.6606892288595007, | |
| "train_runtime": 116.1909, | |
| "train_samples_per_second": 2473.946, | |
| "train_steps_per_second": 9.898 | |
| } | |
| ], | |
| "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": 5711561202147840.0, | |
| "train_batch_size": 256, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |