| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.433962264150944, | |
| "global_step": 5000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.748427672955975e-05, | |
| "loss": 1.3506, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 9.496855345911951e-05, | |
| "loss": 1.0358, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9021613276727133, | |
| "eval_f1": 0.6651721377101681, | |
| "eval_loss": 0.9438411593437195, | |
| "eval_precision": 0.6371165644171779, | |
| "eval_recall": 0.6958123953098827, | |
| "eval_runtime": 9.5281, | |
| "eval_samples_per_second": 162.152, | |
| "eval_steps_per_second": 10.18, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 9.245283018867925e-05, | |
| "loss": 0.9613, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 8.9937106918239e-05, | |
| "loss": 0.9255, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 8.742138364779875e-05, | |
| "loss": 0.9074, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9115099275269094, | |
| "eval_f1": 0.698074203024698, | |
| "eval_loss": 0.9242610335350037, | |
| "eval_precision": 0.6805982815317705, | |
| "eval_recall": 0.7164712451144611, | |
| "eval_runtime": 8.173, | |
| "eval_samples_per_second": 189.038, | |
| "eval_steps_per_second": 11.868, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 8.49056603773585e-05, | |
| "loss": 0.8659, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 8.238993710691824e-05, | |
| "loss": 0.8605, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9139971696899524, | |
| "eval_f1": 0.7123908477948492, | |
| "eval_loss": 0.9207843542098999, | |
| "eval_precision": 0.7052193894299158, | |
| "eval_recall": 0.7197096594081519, | |
| "eval_runtime": 9.4717, | |
| "eval_samples_per_second": 163.117, | |
| "eval_steps_per_second": 10.241, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 7.9874213836478e-05, | |
| "loss": 0.8467, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 7.735849056603774e-05, | |
| "loss": 0.817, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 7.484276729559749e-05, | |
| "loss": 0.8003, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9139757279471675, | |
| "eval_f1": 0.7284265336009113, | |
| "eval_loss": 0.9339075088500977, | |
| "eval_precision": 0.7081839274414681, | |
| "eval_recall": 0.7498604131769961, | |
| "eval_runtime": 7.979, | |
| "eval_samples_per_second": 193.634, | |
| "eval_steps_per_second": 12.157, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 7.232704402515723e-05, | |
| "loss": 0.7937, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 6.981132075471698e-05, | |
| "loss": 0.777, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 6.729559748427673e-05, | |
| "loss": 0.7759, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9262404048201037, | |
| "eval_f1": 0.7729500891265597, | |
| "eval_loss": 0.9294289946556091, | |
| "eval_precision": 0.7711459375347338, | |
| "eval_recall": 0.7747627024008934, | |
| "eval_runtime": 7.9554, | |
| "eval_samples_per_second": 194.207, | |
| "eval_steps_per_second": 12.193, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 6.477987421383648e-05, | |
| "loss": 0.7514, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "learning_rate": 6.226415094339622e-05, | |
| "loss": 0.7585, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9251039924525065, | |
| "eval_f1": 0.7699395015818395, | |
| "eval_loss": 0.932030200958252, | |
| "eval_precision": 0.765393952769808, | |
| "eval_recall": 0.7745393634840871, | |
| "eval_runtime": 7.9892, | |
| "eval_samples_per_second": 193.385, | |
| "eval_steps_per_second": 12.141, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 5.974842767295597e-05, | |
| "loss": 0.7529, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 6.42, | |
| "learning_rate": 5.7232704402515724e-05, | |
| "loss": 0.7338, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 6.79, | |
| "learning_rate": 5.4716981132075475e-05, | |
| "loss": 0.7357, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9156910673699559, | |
| "eval_f1": 0.732724471830986, | |
| "eval_loss": 0.9781692624092102, | |
| "eval_precision": 0.7221559483787008, | |
| "eval_recall": 0.743606923506421, | |
| "eval_runtime": 9.4609, | |
| "eval_samples_per_second": 163.304, | |
| "eval_steps_per_second": 10.253, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 7.17, | |
| "learning_rate": 5.220125786163522e-05, | |
| "loss": 0.7282, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 7.55, | |
| "learning_rate": 4.968553459119497e-05, | |
| "loss": 0.7249, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "learning_rate": 4.716981132075472e-05, | |
| "loss": 0.7207, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.917277756336035, | |
| "eval_f1": 0.757945684323743, | |
| "eval_loss": 0.9978876113891602, | |
| "eval_precision": 0.7310165975103734, | |
| "eval_recall": 0.7869346733668342, | |
| "eval_runtime": 7.9066, | |
| "eval_samples_per_second": 195.405, | |
| "eval_steps_per_second": 12.268, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 4.4654088050314466e-05, | |
| "loss": 0.7137, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 8.68, | |
| "learning_rate": 4.213836477987422e-05, | |
| "loss": 0.712, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9261117543633947, | |
| "eval_f1": 0.7805572280913022, | |
| "eval_loss": 0.9675424098968506, | |
| "eval_precision": 0.7655142795791282, | |
| "eval_recall": 0.7962032384142937, | |
| "eval_runtime": 7.9396, | |
| "eval_samples_per_second": 194.593, | |
| "eval_steps_per_second": 12.217, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 9.06, | |
| "learning_rate": 3.962264150943397e-05, | |
| "loss": 0.7111, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 9.43, | |
| "learning_rate": 3.710691823899371e-05, | |
| "loss": 0.7048, | |
| "step": 5000 | |
| } | |
| ], | |
| "max_steps": 7950, | |
| "num_train_epochs": 15, | |
| "total_flos": 4470902182940160.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |