| { | |
| "best_metric": 0.9776214833759592, | |
| "best_model_checkpoint": "test/model\\checkpoint-1500", | |
| "epoch": 9.146341463414634, | |
| "global_step": 1500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.61, | |
| "eval_accuracy": 0.9168925867065533, | |
| "eval_f1": 0.531752104055088, | |
| "eval_loss": 0.2909819185733795, | |
| "eval_precision": 0.6453110492107706, | |
| "eval_recall": 0.4521795705920625, | |
| "eval_runtime": 7.6557, | |
| "eval_samples_per_second": 19.332, | |
| "eval_steps_per_second": 9.666, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "eval_accuracy": 0.9672805459474619, | |
| "eval_f1": 0.8156667702828723, | |
| "eval_loss": 0.1369905024766922, | |
| "eval_precision": 0.780952380952381, | |
| "eval_recall": 0.8536109303838647, | |
| "eval_runtime": 7.6461, | |
| "eval_samples_per_second": 19.356, | |
| "eval_steps_per_second": 9.678, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "eval_accuracy": 0.9770028980087875, | |
| "eval_f1": 0.87900466562986, | |
| "eval_loss": 0.0756949633359909, | |
| "eval_precision": 0.8420738974970202, | |
| "eval_recall": 0.9193233571893299, | |
| "eval_runtime": 7.6257, | |
| "eval_samples_per_second": 19.408, | |
| "eval_steps_per_second": 9.704, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "eval_accuracy": 0.9902776479386743, | |
| "eval_f1": 0.9516539440203563, | |
| "eval_loss": 0.04403918609023094, | |
| "eval_precision": 0.9309271935283137, | |
| "eval_recall": 0.9733246584255042, | |
| "eval_runtime": 7.6305, | |
| "eval_samples_per_second": 19.396, | |
| "eval_steps_per_second": 9.698, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 9.5e-06, | |
| "loss": 0.2309, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "eval_accuracy": 0.9855099560624474, | |
| "eval_f1": 0.9462231893068076, | |
| "eval_loss": 0.047688089311122894, | |
| "eval_precision": 0.905952380952381, | |
| "eval_recall": 0.9902407286922577, | |
| "eval_runtime": 7.6227, | |
| "eval_samples_per_second": 19.416, | |
| "eval_steps_per_second": 9.708, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "eval_accuracy": 0.9955127605870805, | |
| "eval_f1": 0.982028241335045, | |
| "eval_loss": 0.022968417033553123, | |
| "eval_precision": 0.9689677010766308, | |
| "eval_recall": 0.9954456733897202, | |
| "eval_runtime": 7.6581, | |
| "eval_samples_per_second": 19.326, | |
| "eval_steps_per_second": 9.663, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "eval_accuracy": 0.9834533046648593, | |
| "eval_f1": 0.9442905509387505, | |
| "eval_loss": 0.04970035329461098, | |
| "eval_precision": 0.8960280373831776, | |
| "eval_recall": 0.9980481457384516, | |
| "eval_runtime": 7.634, | |
| "eval_samples_per_second": 19.387, | |
| "eval_steps_per_second": 9.693, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "eval_accuracy": 0.9912124894830326, | |
| "eval_f1": 0.969046114971573, | |
| "eval_loss": 0.03323974087834358, | |
| "eval_precision": 0.941682013505218, | |
| "eval_recall": 0.9980481457384516, | |
| "eval_runtime": 7.674, | |
| "eval_samples_per_second": 19.286, | |
| "eval_steps_per_second": 9.643, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "eval_accuracy": 0.9900906796298028, | |
| "eval_f1": 0.9653870358716173, | |
| "eval_loss": 0.031032076105475426, | |
| "eval_precision": 0.9347958561852528, | |
| "eval_recall": 0.9980481457384516, | |
| "eval_runtime": 7.6489, | |
| "eval_samples_per_second": 19.349, | |
| "eval_steps_per_second": 9.675, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "learning_rate": 9e-06, | |
| "loss": 0.0211, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "eval_accuracy": 0.9921473310273908, | |
| "eval_f1": 0.9724072312083729, | |
| "eval_loss": 0.02703050896525383, | |
| "eval_precision": 0.9486386138613861, | |
| "eval_recall": 0.9973975276512687, | |
| "eval_runtime": 7.623, | |
| "eval_samples_per_second": 19.415, | |
| "eval_steps_per_second": 9.707, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 6.71, | |
| "eval_accuracy": 0.9914929419463401, | |
| "eval_f1": 0.9699652228896617, | |
| "eval_loss": 0.03206472471356392, | |
| "eval_precision": 0.9434194341943419, | |
| "eval_recall": 0.9980481457384516, | |
| "eval_runtime": 7.6405, | |
| "eval_samples_per_second": 19.37, | |
| "eval_steps_per_second": 9.685, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "eval_accuracy": 0.9970085070580537, | |
| "eval_f1": 0.9877181641887525, | |
| "eval_loss": 0.016345446929335594, | |
| "eval_precision": 0.9813744380218369, | |
| "eval_recall": 0.9941444372153546, | |
| "eval_runtime": 7.742, | |
| "eval_samples_per_second": 19.117, | |
| "eval_steps_per_second": 9.558, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "eval_accuracy": 0.9908385528652893, | |
| "eval_f1": 0.9684542586750788, | |
| "eval_loss": 0.031482577323913574, | |
| "eval_precision": 0.939987752602572, | |
| "eval_recall": 0.9986987638256344, | |
| "eval_runtime": 7.6808, | |
| "eval_samples_per_second": 19.269, | |
| "eval_steps_per_second": 9.634, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 8.54, | |
| "eval_accuracy": 0.9920538468729551, | |
| "eval_f1": 0.9720989220038045, | |
| "eval_loss": 0.029911138117313385, | |
| "eval_precision": 0.948051948051948, | |
| "eval_recall": 0.9973975276512687, | |
| "eval_runtime": 7.6156, | |
| "eval_samples_per_second": 19.434, | |
| "eval_steps_per_second": 9.717, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 9.15, | |
| "learning_rate": 8.5e-06, | |
| "loss": 0.0158, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 9.15, | |
| "eval_accuracy": 0.993643077498364, | |
| "eval_f1": 0.9776214833759592, | |
| "eval_loss": 0.025822490453720093, | |
| "eval_precision": 0.9610307982401005, | |
| "eval_recall": 0.9947950553025374, | |
| "eval_runtime": 7.6981, | |
| "eval_samples_per_second": 19.226, | |
| "eval_steps_per_second": 9.613, | |
| "step": 1500 | |
| } | |
| ], | |
| "max_steps": 10000, | |
| "num_train_epochs": 61, | |
| "total_flos": 793919609690112.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |