| { | |
| "best_global_step": 7500, | |
| "best_metric": 0.7842453714436081, | |
| "best_model_checkpoint": "./distilbert-base-AuthId/checkpoint-7500", | |
| "epoch": 3.642544924720738, | |
| "eval_steps": 500, | |
| "global_step": 7500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.24283632831471588, | |
| "grad_norm": 10.536812782287598, | |
| "learning_rate": 4.8446601941747576e-05, | |
| "loss": 2.4424, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.24283632831471588, | |
| "eval_accuracy": 0.4645176810199663, | |
| "eval_f1_macro": 0.38214194553778474, | |
| "eval_loss": 1.7513902187347412, | |
| "eval_precision_macro": 0.42410548716505947, | |
| "eval_recall_macro": 0.4570777134531091, | |
| "eval_runtime": 44.1019, | |
| "eval_samples_per_second": 94.259, | |
| "eval_steps_per_second": 5.895, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.48567265662943176, | |
| "grad_norm": 8.661422729492188, | |
| "learning_rate": 7.989001438410175e-05, | |
| "loss": 1.3721, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.48567265662943176, | |
| "eval_accuracy": 0.5208082751984604, | |
| "eval_f1_macro": 0.4454367070109959, | |
| "eval_loss": 1.5558406114578247, | |
| "eval_precision_macro": 0.49026128200564273, | |
| "eval_recall_macro": 0.5024706104342445, | |
| "eval_runtime": 44.445, | |
| "eval_samples_per_second": 93.531, | |
| "eval_steps_per_second": 5.85, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.7285089849441476, | |
| "grad_norm": 11.807583808898926, | |
| "learning_rate": 7.837406915300635e-05, | |
| "loss": 0.9647, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.7285089849441476, | |
| "eval_accuracy": 0.6812605244166466, | |
| "eval_f1_macro": 0.5864448295094548, | |
| "eval_loss": 1.1119331121444702, | |
| "eval_precision_macro": 0.5984183492980578, | |
| "eval_recall_macro": 0.6268369019392432, | |
| "eval_runtime": 44.5983, | |
| "eval_samples_per_second": 93.21, | |
| "eval_steps_per_second": 5.83, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.9713453132588635, | |
| "grad_norm": 27.49161720275879, | |
| "learning_rate": 7.514108265155405e-05, | |
| "loss": 0.7867, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.9713453132588635, | |
| "eval_accuracy": 0.713014192927592, | |
| "eval_f1_macro": 0.6520857054306285, | |
| "eval_loss": 1.003157615661621, | |
| "eval_precision_macro": 0.6618591636767543, | |
| "eval_recall_macro": 0.6977243147676733, | |
| "eval_runtime": 45.2348, | |
| "eval_samples_per_second": 91.898, | |
| "eval_steps_per_second": 5.748, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.2141816415735793, | |
| "grad_norm": 17.49410629272461, | |
| "learning_rate": 7.033571431701654e-05, | |
| "loss": 0.5712, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.2141816415735793, | |
| "eval_accuracy": 0.7101274957902334, | |
| "eval_f1_macro": 0.6578185186923463, | |
| "eval_loss": 1.0687695741653442, | |
| "eval_precision_macro": 0.6947126776112352, | |
| "eval_recall_macro": 0.6807690177369954, | |
| "eval_runtime": 45.4304, | |
| "eval_samples_per_second": 91.503, | |
| "eval_steps_per_second": 5.723, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.4570179698882952, | |
| "grad_norm": 14.797587394714355, | |
| "learning_rate": 6.417297954733794e-05, | |
| "loss": 0.5118, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.4570179698882952, | |
| "eval_accuracy": 0.7466923261967765, | |
| "eval_f1_macro": 0.6802785705299167, | |
| "eval_loss": 0.9464945197105408, | |
| "eval_precision_macro": 0.6962547831411214, | |
| "eval_recall_macro": 0.7067511752266095, | |
| "eval_runtime": 45.0782, | |
| "eval_samples_per_second": 92.217, | |
| "eval_steps_per_second": 5.768, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.6998542982030111, | |
| "grad_norm": 11.592080116271973, | |
| "learning_rate": 5.692862887331573e-05, | |
| "loss": 0.4238, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.6998542982030111, | |
| "eval_accuracy": 0.7529468366610537, | |
| "eval_f1_macro": 0.6887735293131003, | |
| "eval_loss": 1.0284276008605957, | |
| "eval_precision_macro": 0.7004815690389604, | |
| "eval_recall_macro": 0.7209895448469402, | |
| "eval_runtime": 45.0958, | |
| "eval_samples_per_second": 92.182, | |
| "eval_steps_per_second": 5.766, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.942690626517727, | |
| "grad_norm": 1.7279024124145508, | |
| "learning_rate": 4.892680954747708e-05, | |
| "loss": 0.383, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.942690626517727, | |
| "eval_accuracy": 0.7784459947077219, | |
| "eval_f1_macro": 0.7004470067611618, | |
| "eval_loss": 0.9373700618743896, | |
| "eval_precision_macro": 0.7012745858922871, | |
| "eval_recall_macro": 0.7363165995805543, | |
| "eval_runtime": 45.0166, | |
| "eval_samples_per_second": 92.344, | |
| "eval_steps_per_second": 5.776, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.1855269548324427, | |
| "grad_norm": 11.464333534240723, | |
| "learning_rate": 4.052556162978074e-05, | |
| "loss": 0.2498, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.1855269548324427, | |
| "eval_accuracy": 0.7897522251623768, | |
| "eval_f1_macro": 0.736934271206392, | |
| "eval_loss": 0.8516831398010254, | |
| "eval_precision_macro": 0.7471052855094972, | |
| "eval_recall_macro": 0.7513822718605427, | |
| "eval_runtime": 45.2063, | |
| "eval_samples_per_second": 91.956, | |
| "eval_steps_per_second": 5.751, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.4283632831471587, | |
| "grad_norm": 13.227448463439941, | |
| "learning_rate": 3.2100797545350794e-05, | |
| "loss": 0.2012, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.4283632831471587, | |
| "eval_accuracy": 0.7952850613423141, | |
| "eval_f1_macro": 0.7384644794255656, | |
| "eval_loss": 0.8422956466674805, | |
| "eval_precision_macro": 0.7407858112231859, | |
| "eval_recall_macro": 0.7593629429944239, | |
| "eval_runtime": 45.0668, | |
| "eval_samples_per_second": 92.241, | |
| "eval_steps_per_second": 5.769, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.6711996114618746, | |
| "grad_norm": 14.610297203063965, | |
| "learning_rate": 2.402948194623674e-05, | |
| "loss": 0.1888, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.6711996114618746, | |
| "eval_accuracy": 0.8383449603079144, | |
| "eval_f1_macro": 0.7668856441209034, | |
| "eval_loss": 0.7612192034721375, | |
| "eval_precision_macro": 0.759848794474667, | |
| "eval_recall_macro": 0.7875978932242379, | |
| "eval_runtime": 44.9628, | |
| "eval_samples_per_second": 92.454, | |
| "eval_steps_per_second": 5.783, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.9140359397765905, | |
| "grad_norm": 2.9459526538848877, | |
| "learning_rate": 1.667276449145691e-05, | |
| "loss": 0.1478, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.9140359397765905, | |
| "eval_accuracy": 0.8284820784219389, | |
| "eval_f1_macro": 0.7648949869466338, | |
| "eval_loss": 0.7956407070159912, | |
| "eval_precision_macro": 0.7582819516660327, | |
| "eval_recall_macro": 0.7872534623468304, | |
| "eval_runtime": 45.0026, | |
| "eval_samples_per_second": 92.372, | |
| "eval_steps_per_second": 5.777, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.1568722680913064, | |
| "grad_norm": 0.04966867342591286, | |
| "learning_rate": 1.035982026624521e-05, | |
| "loss": 0.0805, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 3.1568722680913064, | |
| "eval_accuracy": 0.8397883088765937, | |
| "eval_f1_macro": 0.779163123362359, | |
| "eval_loss": 0.7845637798309326, | |
| "eval_precision_macro": 0.7736785485737475, | |
| "eval_recall_macro": 0.7972932500440235, | |
| "eval_runtime": 44.623, | |
| "eval_samples_per_second": 93.158, | |
| "eval_steps_per_second": 5.827, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 3.3997085964060223, | |
| "grad_norm": 0.054828643798828125, | |
| "learning_rate": 5.373120898224163e-06, | |
| "loss": 0.054, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 3.3997085964060223, | |
| "eval_accuracy": 0.8390666345922541, | |
| "eval_f1_macro": 0.7789886096417518, | |
| "eval_loss": 0.8231712579727173, | |
| "eval_precision_macro": 0.7722144919792829, | |
| "eval_recall_macro": 0.7985903156380745, | |
| "eval_runtime": 44.6487, | |
| "eval_samples_per_second": 93.105, | |
| "eval_steps_per_second": 5.823, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 3.642544924720738, | |
| "grad_norm": 8.141491889953613, | |
| "learning_rate": 1.935795411934156e-06, | |
| "loss": 0.0683, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 3.642544924720738, | |
| "eval_accuracy": 0.8448400288669714, | |
| "eval_f1_macro": 0.7842453714436081, | |
| "eval_loss": 0.7753947377204895, | |
| "eval_precision_macro": 0.7754804853445821, | |
| "eval_recall_macro": 0.8051232260351716, | |
| "eval_runtime": 45.7414, | |
| "eval_samples_per_second": 90.881, | |
| "eval_steps_per_second": 5.684, | |
| "step": 7500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 8236, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.5900281427207168e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |