| { | |
| "best_metric": 0.15075480937957764, | |
| "best_model_checkpoint": "/home/paperspace/microsoft_deberta-v3-base_cpt_64aa255e/checkpoint-9820", | |
| "epoch": 7.0, | |
| "eval_steps": 500, | |
| "global_step": 17185, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.709048588885654e-07, | |
| "loss": 0.5526, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 9.418097177771311e-07, | |
| "loss": 0.2449, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 9.127145766656967e-07, | |
| "loss": 0.1637, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 8.836194355542625e-07, | |
| "loss": 0.1627, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9574516238542492, | |
| "eval_f1": 0.9576402605174089, | |
| "eval_loss": 0.15390127897262573, | |
| "eval_precision": 0.9583932523988209, | |
| "eval_recall": 0.9574516238542492, | |
| "eval_runtime": 11.3772, | |
| "eval_samples_per_second": 776.73, | |
| "eval_steps_per_second": 48.606, | |
| "step": 2455 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 8.54524294442828e-07, | |
| "loss": 0.1536, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 8.254291533313936e-07, | |
| "loss": 0.1497, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 7.963340122199592e-07, | |
| "loss": 0.1478, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 7.672388711085248e-07, | |
| "loss": 0.1452, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 7.381437299970904e-07, | |
| "loss": 0.149, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9596016747765078, | |
| "eval_f1": 0.9597684084567597, | |
| "eval_loss": 0.15375804901123047, | |
| "eval_precision": 0.9604205146694305, | |
| "eval_recall": 0.9596016747765078, | |
| "eval_runtime": 11.4943, | |
| "eval_samples_per_second": 768.813, | |
| "eval_steps_per_second": 48.111, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 7.090485888856561e-07, | |
| "loss": 0.1415, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 6.799534477742217e-07, | |
| "loss": 0.1358, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 6.508583066627873e-07, | |
| "loss": 0.1382, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 6.217631655513529e-07, | |
| "loss": 0.1289, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 5.926680244399185e-07, | |
| "loss": 0.1329, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9591490324770849, | |
| "eval_f1": 0.9593624018161547, | |
| "eval_loss": 0.16056260466575623, | |
| "eval_precision": 0.9603821831580927, | |
| "eval_recall": 0.9591490324770849, | |
| "eval_runtime": 11.3768, | |
| "eval_samples_per_second": 776.759, | |
| "eval_steps_per_second": 48.608, | |
| "step": 7365 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 5.63572883328484e-07, | |
| "loss": 0.1321, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 5.344777422170497e-07, | |
| "loss": 0.1324, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 5.053826011056153e-07, | |
| "loss": 0.1299, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 4.7628745999418097e-07, | |
| "loss": 0.136, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 4.4719231888274657e-07, | |
| "loss": 0.1308, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9608464410999208, | |
| "eval_f1": 0.9610329418449746, | |
| "eval_loss": 0.15075480937957764, | |
| "eval_precision": 0.9618808519987467, | |
| "eval_recall": 0.9608464410999208, | |
| "eval_runtime": 11.2225, | |
| "eval_samples_per_second": 787.436, | |
| "eval_steps_per_second": 49.276, | |
| "step": 9820 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 4.1809717777131217e-07, | |
| "loss": 0.1211, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 3.890020366598778e-07, | |
| "loss": 0.1233, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 3.599068955484434e-07, | |
| "loss": 0.1241, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 3.3081175443700896e-07, | |
| "loss": 0.1209, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 3.017166133255746e-07, | |
| "loss": 0.1225, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9617517256987665, | |
| "eval_f1": 0.9619212980183091, | |
| "eval_loss": 0.15455789864063263, | |
| "eval_precision": 0.9626580984908996, | |
| "eval_recall": 0.9617517256987665, | |
| "eval_runtime": 11.421, | |
| "eval_samples_per_second": 773.752, | |
| "eval_steps_per_second": 48.42, | |
| "step": 12275 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 2.726214722141402e-07, | |
| "loss": 0.1164, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 2.4352633110270586e-07, | |
| "loss": 0.1227, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "learning_rate": 2.1443118999127143e-07, | |
| "loss": 0.1134, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 1.8533604887983705e-07, | |
| "loss": 0.125, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 1.5624090776840268e-07, | |
| "loss": 0.1181, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9615254045490551, | |
| "eval_f1": 0.9617002293060223, | |
| "eval_loss": 0.15432989597320557, | |
| "eval_precision": 0.9624729485181595, | |
| "eval_recall": 0.9615254045490551, | |
| "eval_runtime": 11.4696, | |
| "eval_samples_per_second": 770.472, | |
| "eval_steps_per_second": 48.214, | |
| "step": 14730 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 1.2714576665696827e-07, | |
| "loss": 0.1203, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 6.31, | |
| "learning_rate": 9.80506255455339e-08, | |
| "loss": 0.1054, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "learning_rate": 6.89554844340995e-08, | |
| "loss": 0.1154, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 3.986034332266511e-08, | |
| "loss": 0.1164, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "learning_rate": 1.0765202211230723e-08, | |
| "loss": 0.1321, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9624306891479009, | |
| "eval_f1": 0.9625909933285097, | |
| "eval_loss": 0.15378057956695557, | |
| "eval_precision": 0.9632742135234372, | |
| "eval_recall": 0.9624306891479009, | |
| "eval_runtime": 11.6127, | |
| "eval_samples_per_second": 760.975, | |
| "eval_steps_per_second": 47.62, | |
| "step": 17185 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 17185, | |
| "num_train_epochs": 7, | |
| "save_steps": 500, | |
| "total_flos": 6667692884621040.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |