| { | |
| "best_metric": 1.606531023979187, | |
| "best_model_checkpoint": "distilbert_final_tweet_dataset_200_epoch/checkpoint-230", | |
| "epoch": 43.0, | |
| "global_step": 4945, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6327160493827161, | |
| "eval_f1": 0.6368645566163996, | |
| "eval_loss": 2.3408091068267822, | |
| "eval_runtime": 0.7378, | |
| "eval_samples_per_second": 439.117, | |
| "eval_steps_per_second": 55.567, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6728395061728395, | |
| "eval_f1": 0.6724357294978492, | |
| "eval_loss": 1.606531023979187, | |
| "eval_runtime": 0.7455, | |
| "eval_samples_per_second": 434.608, | |
| "eval_steps_per_second": 54.997, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6635802469135802, | |
| "eval_f1": 0.6659200702678963, | |
| "eval_loss": 2.096076250076294, | |
| "eval_runtime": 0.7198, | |
| "eval_samples_per_second": 450.123, | |
| "eval_steps_per_second": 56.96, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.6296296296296297, | |
| "eval_f1": 0.6251138433515483, | |
| "eval_loss": 2.2798941135406494, | |
| "eval_runtime": 0.7194, | |
| "eval_samples_per_second": 450.35, | |
| "eval_steps_per_second": 56.989, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 4.891304347826087e-05, | |
| "loss": 0.1025, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.6512345679012346, | |
| "eval_f1": 0.6431049313635814, | |
| "eval_loss": 2.6507568359375, | |
| "eval_runtime": 0.7337, | |
| "eval_samples_per_second": 441.574, | |
| "eval_steps_per_second": 55.878, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.6697530864197531, | |
| "eval_f1": 0.6715964982923955, | |
| "eval_loss": 2.2207276821136475, | |
| "eval_runtime": 0.8004, | |
| "eval_samples_per_second": 404.806, | |
| "eval_steps_per_second": 51.225, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.6728395061728395, | |
| "eval_f1": 0.6722509202387013, | |
| "eval_loss": 2.337564706802368, | |
| "eval_runtime": 0.7663, | |
| "eval_samples_per_second": 422.784, | |
| "eval_steps_per_second": 53.5, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.6604938271604939, | |
| "eval_f1": 0.6652170891831549, | |
| "eval_loss": 2.6886019706726074, | |
| "eval_runtime": 0.7308, | |
| "eval_samples_per_second": 443.343, | |
| "eval_steps_per_second": 56.102, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "learning_rate": 4.782608695652174e-05, | |
| "loss": 0.0591, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.6728395061728395, | |
| "eval_f1": 0.6669062733756546, | |
| "eval_loss": 2.4700207710266113, | |
| "eval_runtime": 0.7607, | |
| "eval_samples_per_second": 425.94, | |
| "eval_steps_per_second": 53.9, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.654320987654321, | |
| "eval_f1": 0.6600467030032732, | |
| "eval_loss": 2.461507797241211, | |
| "eval_runtime": 0.7355, | |
| "eval_samples_per_second": 440.496, | |
| "eval_steps_per_second": 55.742, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.6851851851851852, | |
| "eval_f1": 0.6826296938167441, | |
| "eval_loss": 2.5344278812408447, | |
| "eval_runtime": 0.7295, | |
| "eval_samples_per_second": 444.161, | |
| "eval_steps_per_second": 56.206, | |
| "step": 1265 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.6820987654320988, | |
| "eval_f1": 0.6847534599635866, | |
| "eval_loss": 2.6750032901763916, | |
| "eval_runtime": 0.8174, | |
| "eval_samples_per_second": 396.364, | |
| "eval_steps_per_second": 50.157, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.6574074074074074, | |
| "eval_f1": 0.6621576835862549, | |
| "eval_loss": 2.416313648223877, | |
| "eval_runtime": 0.7489, | |
| "eval_samples_per_second": 432.618, | |
| "eval_steps_per_second": 54.745, | |
| "step": 1495 | |
| }, | |
| { | |
| "epoch": 13.04, | |
| "learning_rate": 4.673913043478261e-05, | |
| "loss": 0.0346, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.6574074074074074, | |
| "eval_f1": 0.6600444146104354, | |
| "eval_loss": 2.7329800128936768, | |
| "eval_runtime": 0.7311, | |
| "eval_samples_per_second": 443.144, | |
| "eval_steps_per_second": 56.077, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.654320987654321, | |
| "eval_f1": 0.6504462260925387, | |
| "eval_loss": 2.4202656745910645, | |
| "eval_runtime": 0.7386, | |
| "eval_samples_per_second": 438.686, | |
| "eval_steps_per_second": 55.513, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.7006172839506173, | |
| "eval_f1": 0.7004058172662825, | |
| "eval_loss": 2.3290841579437256, | |
| "eval_runtime": 0.7341, | |
| "eval_samples_per_second": 441.353, | |
| "eval_steps_per_second": 55.85, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_f1": 0.6603541359368218, | |
| "eval_loss": 2.7727530002593994, | |
| "eval_runtime": 0.727, | |
| "eval_samples_per_second": 445.679, | |
| "eval_steps_per_second": 56.398, | |
| "step": 1955 | |
| }, | |
| { | |
| "epoch": 17.39, | |
| "learning_rate": 4.565217391304348e-05, | |
| "loss": 0.0247, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.6574074074074074, | |
| "eval_f1": 0.6600831890627571, | |
| "eval_loss": 2.668175458908081, | |
| "eval_runtime": 0.8752, | |
| "eval_samples_per_second": 370.214, | |
| "eval_steps_per_second": 46.848, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_f1": 0.6703415017567717, | |
| "eval_loss": 2.8486380577087402, | |
| "eval_runtime": 0.7459, | |
| "eval_samples_per_second": 434.347, | |
| "eval_steps_per_second": 54.964, | |
| "step": 2185 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6635802469135802, | |
| "eval_f1": 0.6654895433909519, | |
| "eval_loss": 2.988004446029663, | |
| "eval_runtime": 0.7495, | |
| "eval_samples_per_second": 432.284, | |
| "eval_steps_per_second": 54.703, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.6604938271604939, | |
| "eval_f1": 0.6629249499004221, | |
| "eval_loss": 2.923362970352173, | |
| "eval_runtime": 0.7413, | |
| "eval_samples_per_second": 437.091, | |
| "eval_steps_per_second": 55.311, | |
| "step": 2415 | |
| }, | |
| { | |
| "epoch": 21.74, | |
| "learning_rate": 4.456521739130435e-05, | |
| "loss": 0.0264, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.6512345679012346, | |
| "eval_f1": 0.6561078483445887, | |
| "eval_loss": 2.6863272190093994, | |
| "eval_runtime": 0.749, | |
| "eval_samples_per_second": 432.552, | |
| "eval_steps_per_second": 54.736, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.6604938271604939, | |
| "eval_f1": 0.6610722610722611, | |
| "eval_loss": 2.7173354625701904, | |
| "eval_runtime": 0.7384, | |
| "eval_samples_per_second": 438.801, | |
| "eval_steps_per_second": 55.527, | |
| "step": 2645 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.6481481481481481, | |
| "eval_f1": 0.6504829054920129, | |
| "eval_loss": 3.2829830646514893, | |
| "eval_runtime": 0.8839, | |
| "eval_samples_per_second": 366.573, | |
| "eval_steps_per_second": 46.387, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.6851851851851852, | |
| "eval_f1": 0.6787650339814832, | |
| "eval_loss": 2.6303372383117676, | |
| "eval_runtime": 0.7774, | |
| "eval_samples_per_second": 416.749, | |
| "eval_steps_per_second": 52.737, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.6604938271604939, | |
| "eval_f1": 0.6618789271005957, | |
| "eval_loss": 2.580350875854492, | |
| "eval_runtime": 0.8987, | |
| "eval_samples_per_second": 360.512, | |
| "eval_steps_per_second": 45.62, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 26.09, | |
| "learning_rate": 4.347826086956522e-05, | |
| "loss": 0.0178, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.6296296296296297, | |
| "eval_f1": 0.631715246325266, | |
| "eval_loss": 3.3269691467285156, | |
| "eval_runtime": 0.7462, | |
| "eval_samples_per_second": 434.183, | |
| "eval_steps_per_second": 54.943, | |
| "step": 3105 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.6512345679012346, | |
| "eval_f1": 0.646016361656172, | |
| "eval_loss": 2.600759267807007, | |
| "eval_runtime": 0.754, | |
| "eval_samples_per_second": 429.696, | |
| "eval_steps_per_second": 54.375, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.6759259259259259, | |
| "eval_f1": 0.6760610574156681, | |
| "eval_loss": 2.3673853874206543, | |
| "eval_runtime": 0.7318, | |
| "eval_samples_per_second": 442.773, | |
| "eval_steps_per_second": 56.03, | |
| "step": 3335 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.6728395061728395, | |
| "eval_f1": 0.6779632769589728, | |
| "eval_loss": 2.884216547012329, | |
| "eval_runtime": 0.8346, | |
| "eval_samples_per_second": 388.205, | |
| "eval_steps_per_second": 49.125, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 30.43, | |
| "learning_rate": 4.239130434782609e-05, | |
| "loss": 0.0265, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.691358024691358, | |
| "eval_f1": 0.6760321881467606, | |
| "eval_loss": 2.432506799697876, | |
| "eval_runtime": 0.7578, | |
| "eval_samples_per_second": 427.542, | |
| "eval_steps_per_second": 54.103, | |
| "step": 3565 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.6759259259259259, | |
| "eval_f1": 0.6731011257710287, | |
| "eval_loss": 2.599379062652588, | |
| "eval_runtime": 0.883, | |
| "eval_samples_per_second": 366.946, | |
| "eval_steps_per_second": 46.434, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.7067901234567902, | |
| "eval_f1": 0.695461794954067, | |
| "eval_loss": 2.5045433044433594, | |
| "eval_runtime": 0.7331, | |
| "eval_samples_per_second": 441.973, | |
| "eval_steps_per_second": 55.929, | |
| "step": 3795 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.6697530864197531, | |
| "eval_f1": 0.6731205747259303, | |
| "eval_loss": 3.0988411903381348, | |
| "eval_runtime": 0.7479, | |
| "eval_samples_per_second": 433.231, | |
| "eval_steps_per_second": 54.822, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 34.78, | |
| "learning_rate": 4.130434782608696e-05, | |
| "loss": 0.0161, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.6604938271604939, | |
| "eval_f1": 0.6623841608728461, | |
| "eval_loss": 3.1595075130462646, | |
| "eval_runtime": 0.7269, | |
| "eval_samples_per_second": 445.742, | |
| "eval_steps_per_second": 56.406, | |
| "step": 4025 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.6820987654320988, | |
| "eval_f1": 0.6742414417588002, | |
| "eval_loss": 2.7971243858337402, | |
| "eval_runtime": 0.9256, | |
| "eval_samples_per_second": 350.06, | |
| "eval_steps_per_second": 44.298, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.6728395061728395, | |
| "eval_f1": 0.6738584667507038, | |
| "eval_loss": 2.8675856590270996, | |
| "eval_runtime": 0.7764, | |
| "eval_samples_per_second": 417.318, | |
| "eval_steps_per_second": 52.809, | |
| "step": 4255 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.6759259259259259, | |
| "eval_f1": 0.678580671598335, | |
| "eval_loss": 3.1342642307281494, | |
| "eval_runtime": 0.7436, | |
| "eval_samples_per_second": 435.727, | |
| "eval_steps_per_second": 55.138, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_f1": 0.6685957490826878, | |
| "eval_loss": 3.1532750129699707, | |
| "eval_runtime": 0.736, | |
| "eval_samples_per_second": 440.237, | |
| "eval_steps_per_second": 55.709, | |
| "step": 4485 | |
| }, | |
| { | |
| "epoch": 39.13, | |
| "learning_rate": 4.021739130434783e-05, | |
| "loss": 0.0057, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.6697530864197531, | |
| "eval_f1": 0.6710645630658144, | |
| "eval_loss": 3.224386215209961, | |
| "eval_runtime": 0.7446, | |
| "eval_samples_per_second": 435.153, | |
| "eval_steps_per_second": 55.066, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.6697530864197531, | |
| "eval_f1": 0.6710645630658144, | |
| "eval_loss": 3.2694830894470215, | |
| "eval_runtime": 0.7256, | |
| "eval_samples_per_second": 446.497, | |
| "eval_steps_per_second": 56.501, | |
| "step": 4715 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.654320987654321, | |
| "eval_f1": 0.6527479860813193, | |
| "eval_loss": 3.1891162395477295, | |
| "eval_runtime": 1.0318, | |
| "eval_samples_per_second": 314.002, | |
| "eval_steps_per_second": 39.735, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.6450617283950617, | |
| "eval_f1": 0.6456619146444574, | |
| "eval_loss": 3.0968563556671143, | |
| "eval_runtime": 0.7581, | |
| "eval_samples_per_second": 427.411, | |
| "eval_steps_per_second": 54.086, | |
| "step": 4945 | |
| } | |
| ], | |
| "max_steps": 23000, | |
| "num_train_epochs": 200, | |
| "total_flos": 1595848204716012.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |