| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6432109088570143, | |
| "global_step": 10000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "eval_accuracy": 0.9246465960844621, | |
| "eval_f1": 0.6907879797138747, | |
| "eval_loss": 0.22821231186389923, | |
| "eval_precision": 0.6817570596145226, | |
| "eval_recall": 0.7000613685179503, | |
| "eval_runtime": 6.5662, | |
| "eval_samples_per_second": 761.48, | |
| "eval_steps_per_second": 47.669, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3487, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_accuracy": 0.9631217838765008, | |
| "eval_f1": 0.809284332688588, | |
| "eval_loss": 0.12138580530881882, | |
| "eval_precision": 0.8162946776962697, | |
| "eval_recall": 0.8023933722000613, | |
| "eval_runtime": 6.1509, | |
| "eval_samples_per_second": 812.889, | |
| "eval_steps_per_second": 50.887, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.972200863547643, | |
| "eval_f1": 0.8519850072668859, | |
| "eval_loss": 0.09331324696540833, | |
| "eval_precision": 0.849580472921434, | |
| "eval_recall": 0.8544031911629334, | |
| "eval_runtime": 6.1413, | |
| "eval_samples_per_second": 814.163, | |
| "eval_steps_per_second": 50.967, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.1124, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_accuracy": 0.9786478973206364, | |
| "eval_f1": 0.879148016669239, | |
| "eval_loss": 0.06928630918264389, | |
| "eval_precision": 0.884472049689441, | |
| "eval_recall": 0.873887695612151, | |
| "eval_runtime": 6.1606, | |
| "eval_samples_per_second": 811.616, | |
| "eval_steps_per_second": 50.807, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.9816939729106288, | |
| "eval_f1": 0.8951911220715166, | |
| "eval_loss": 0.05397827923297882, | |
| "eval_precision": 0.899349643852586, | |
| "eval_recall": 0.8910708806382326, | |
| "eval_runtime": 6.3033, | |
| "eval_samples_per_second": 793.233, | |
| "eval_steps_per_second": 49.656, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.0667, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_accuracy": 0.9856568285325604, | |
| "eval_f1": 0.8993278219887197, | |
| "eval_loss": 0.0473916195333004, | |
| "eval_precision": 0.9058365758754864, | |
| "eval_recall": 0.8929119361767414, | |
| "eval_runtime": 6.1626, | |
| "eval_samples_per_second": 811.344, | |
| "eval_steps_per_second": 50.79, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_accuracy": 0.9864553143668303, | |
| "eval_f1": 0.9233126484333103, | |
| "eval_loss": 0.04179921746253967, | |
| "eval_precision": 0.9221117061973986, | |
| "eval_recall": 0.9245167229211415, | |
| "eval_runtime": 6.1411, | |
| "eval_samples_per_second": 814.192, | |
| "eval_steps_per_second": 50.968, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0492, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_accuracy": 0.9902850890163838, | |
| "eval_f1": 0.9392408937863483, | |
| "eval_loss": 0.02944410778582096, | |
| "eval_precision": 0.9369465648854962, | |
| "eval_recall": 0.9415464866523473, | |
| "eval_runtime": 6.1192, | |
| "eval_samples_per_second": 817.096, | |
| "eval_steps_per_second": 51.15, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_accuracy": 0.9910687880759449, | |
| "eval_f1": 0.9478869986914018, | |
| "eval_loss": 0.026342397555708885, | |
| "eval_precision": 0.9511818322261703, | |
| "eval_recall": 0.944614912549862, | |
| "eval_runtime": 6.3093, | |
| "eval_samples_per_second": 792.485, | |
| "eval_steps_per_second": 49.61, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.0372, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_accuracy": 0.9915419648666233, | |
| "eval_f1": 0.9496049704686661, | |
| "eval_loss": 0.022303204983472824, | |
| "eval_precision": 0.9495321368308023, | |
| "eval_recall": 0.949677815280761, | |
| "eval_runtime": 6.0806, | |
| "eval_samples_per_second": 822.284, | |
| "eval_steps_per_second": 51.475, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_accuracy": 0.9923256639261844, | |
| "eval_f1": 0.9521689059500958, | |
| "eval_loss": 0.02121582068502903, | |
| "eval_precision": 0.9529737206085753, | |
| "eval_recall": 0.951365449524394, | |
| "eval_runtime": 6.1313, | |
| "eval_samples_per_second": 815.488, | |
| "eval_steps_per_second": 51.05, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0308, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_accuracy": 0.993331164606376, | |
| "eval_f1": 0.9572163760657499, | |
| "eval_loss": 0.01765192300081253, | |
| "eval_precision": 0.9584679280110752, | |
| "eval_recall": 0.9559680883706658, | |
| "eval_runtime": 6.2521, | |
| "eval_samples_per_second": 799.734, | |
| "eval_steps_per_second": 50.063, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_accuracy": 0.9936269001005501, | |
| "eval_f1": 0.9616329036218538, | |
| "eval_loss": 0.016909204423427582, | |
| "eval_precision": 0.9619281547436291, | |
| "eval_recall": 0.9613378336913163, | |
| "eval_runtime": 6.055, | |
| "eval_samples_per_second": 825.759, | |
| "eval_steps_per_second": 51.693, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0261, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_accuracy": 0.9951055775714202, | |
| "eval_f1": 0.9675833461361193, | |
| "eval_loss": 0.013973040506243706, | |
| "eval_precision": 0.9689230769230769, | |
| "eval_recall": 0.9662473151273396, | |
| "eval_runtime": 6.0884, | |
| "eval_samples_per_second": 821.237, | |
| "eval_steps_per_second": 51.409, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_accuracy": 0.9945436801324895, | |
| "eval_f1": 0.9640552995391705, | |
| "eval_loss": 0.013004946522414684, | |
| "eval_precision": 0.9652414641648723, | |
| "eval_recall": 0.9628720466400736, | |
| "eval_runtime": 6.2303, | |
| "eval_samples_per_second": 802.527, | |
| "eval_steps_per_second": 50.238, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0214, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_accuracy": 0.9952534453185071, | |
| "eval_f1": 0.965559655596556, | |
| "eval_loss": 0.01268522348254919, | |
| "eval_precision": 0.9676425269645609, | |
| "eval_recall": 0.9634857318195765, | |
| "eval_runtime": 6.0895, | |
| "eval_samples_per_second": 821.082, | |
| "eval_steps_per_second": 51.4, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_accuracy": 0.9958744898562726, | |
| "eval_f1": 0.971147943523634, | |
| "eval_loss": 0.010873218066990376, | |
| "eval_precision": 0.9714461160577218, | |
| "eval_recall": 0.9708499539736115, | |
| "eval_runtime": 6.1229, | |
| "eval_samples_per_second": 816.611, | |
| "eval_steps_per_second": 51.12, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.0177, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_accuracy": 0.9961406518010292, | |
| "eval_f1": 0.9733630152759652, | |
| "eval_loss": 0.010330266319215298, | |
| "eval_precision": 0.9740359502227685, | |
| "eval_recall": 0.9726910095121203, | |
| "eval_runtime": 6.0936, | |
| "eval_samples_per_second": 820.536, | |
| "eval_steps_per_second": 51.366, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_accuracy": 0.9963328798722423, | |
| "eval_f1": 0.9755760368663594, | |
| "eval_loss": 0.010118774138391018, | |
| "eval_precision": 0.9767763764995386, | |
| "eval_recall": 0.9743786437557533, | |
| "eval_runtime": 6.2563, | |
| "eval_samples_per_second": 799.199, | |
| "eval_steps_per_second": 50.03, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0, | |
| "loss": 0.0159, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_accuracy": 0.9965251079434554, | |
| "eval_f1": 0.9750441526529986, | |
| "eval_loss": 0.009783624671399593, | |
| "eval_precision": 0.9760184473481937, | |
| "eval_recall": 0.9740718011660019, | |
| "eval_runtime": 6.0731, | |
| "eval_samples_per_second": 823.307, | |
| "eval_steps_per_second": 51.539, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "step": 10000, | |
| "total_flos": 2.25374565312e+16, | |
| "train_loss": 0.07261505832672119, | |
| "train_runtime": 1985.8061, | |
| "train_samples_per_second": 322.287, | |
| "train_steps_per_second": 5.036 | |
| } | |
| ], | |
| "max_steps": 10000, | |
| "num_train_epochs": 1, | |
| "total_flos": 2.25374565312e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |