google-flan-t5-small-e-snli-generation-label_and_explanation-selected-b64
/
last-checkpoint
/trainer_state.json
| { | |
| "best_metric": 1.7871696949005127, | |
| "best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/google-flan-t5-small-e-snli-generation-label_and_explanation-selected-b64/checkpoint-2000", | |
| "epoch": 2.562907735321528, | |
| "global_step": 22000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0004659832246039143, | |
| "loss": 1.4692, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_accuracy": 0.8211745580166633, | |
| "eval_bertscore_f1": 0.9286575317503936, | |
| "eval_bleu": 0.38561860316652036, | |
| "eval_f1": 0.8203013643438366, | |
| "eval_loss": 1.7871696949005127, | |
| "eval_rouge1": 0.5787165816995035, | |
| "eval_rouge2": 0.3685417962966523, | |
| "eval_rougeL": 0.5239321926914862, | |
| "eval_rougeLsum": 0.5257244126819034, | |
| "eval_runtime": 153.5231, | |
| "eval_samples_per_second": 64.108, | |
| "eval_steps_per_second": 1.003, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0009319664492078286, | |
| "loss": 1.2505, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_accuracy": 0.8262548262548263, | |
| "eval_bertscore_f1": 0.9307863125590817, | |
| "eval_bleu": 0.39038732251575425, | |
| "eval_f1": 0.8263713441477889, | |
| "eval_loss": 1.8808104991912842, | |
| "eval_rouge1": 0.5869703246365517, | |
| "eval_rouge2": 0.3748641547543645, | |
| "eval_rougeL": 0.5321311878885444, | |
| "eval_rougeLsum": 0.5336937989329478, | |
| "eval_runtime": 142.4217, | |
| "eval_samples_per_second": 69.105, | |
| "eval_steps_per_second": 1.081, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0009790552803256977, | |
| "loss": 1.2003, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_accuracy": 0.8474903474903475, | |
| "eval_bertscore_f1": 0.9325015043987053, | |
| "eval_bleu": 0.40037514315917067, | |
| "eval_f1": 0.8480955479827984, | |
| "eval_loss": 1.8476512432098389, | |
| "eval_rouge1": 0.5984358503927201, | |
| "eval_rouge2": 0.39129615048248045, | |
| "eval_rougeL": 0.5452371782543385, | |
| "eval_rougeLsum": 0.5468731108541084, | |
| "eval_runtime": 144.1204, | |
| "eval_samples_per_second": 68.29, | |
| "eval_steps_per_second": 1.069, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0009545298474518076, | |
| "loss": 1.1624, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_accuracy": 0.8598862019914651, | |
| "eval_bertscore_f1": 0.9334783476558407, | |
| "eval_bleu": 0.4024137500087889, | |
| "eval_f1": 0.8587313635433268, | |
| "eval_loss": 1.8243632316589355, | |
| "eval_rouge1": 0.602912531326099, | |
| "eval_rouge2": 0.39282903833995186, | |
| "eval_rougeL": 0.5440694412996867, | |
| "eval_rougeLsum": 0.5457091432223387, | |
| "eval_runtime": 142.2899, | |
| "eval_samples_per_second": 69.169, | |
| "eval_steps_per_second": 1.082, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.0009300044145779173, | |
| "loss": 1.1155, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_accuracy": 0.8695387116439748, | |
| "eval_bertscore_f1": 0.9330506412037212, | |
| "eval_bleu": 0.4022160428281426, | |
| "eval_f1": 0.868816289704145, | |
| "eval_loss": 1.8499114513397217, | |
| "eval_rouge1": 0.6082846765097942, | |
| "eval_rouge2": 0.4018899263767985, | |
| "eval_rougeL": 0.5518885347721499, | |
| "eval_rougeLsum": 0.5540212762276107, | |
| "eval_runtime": 150.2024, | |
| "eval_samples_per_second": 65.525, | |
| "eval_steps_per_second": 1.025, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.0009054789817040271, | |
| "loss": 1.0913, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_accuracy": 0.8691322901849218, | |
| "eval_bertscore_f1": 0.9338201101633912, | |
| "eval_bleu": 0.4012059786299585, | |
| "eval_f1": 0.8686267742768865, | |
| "eval_loss": 1.870266079902649, | |
| "eval_rouge1": 0.6062872493545299, | |
| "eval_rouge2": 0.39947246134905595, | |
| "eval_rougeL": 0.5500107773403655, | |
| "eval_rougeLsum": 0.5520562338476832, | |
| "eval_runtime": 151.4558, | |
| "eval_samples_per_second": 64.983, | |
| "eval_steps_per_second": 1.017, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.0008809535488301369, | |
| "loss": 1.0846, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_accuracy": 0.8750254013411908, | |
| "eval_bertscore_f1": 0.9330909099915095, | |
| "eval_bleu": 0.39881326611406565, | |
| "eval_f1": 0.875070205358106, | |
| "eval_loss": 1.832938551902771, | |
| "eval_rouge1": 0.6061633599628911, | |
| "eval_rouge2": 0.39694115489567416, | |
| "eval_rougeL": 0.550297473532996, | |
| "eval_rougeLsum": 0.5523036866159814, | |
| "eval_runtime": 154.4147, | |
| "eval_samples_per_second": 63.737, | |
| "eval_steps_per_second": 0.997, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.0008564281159562467, | |
| "loss": 1.0715, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_accuracy": 0.8753302174354806, | |
| "eval_bertscore_f1": 0.9349365859854345, | |
| "eval_bleu": 0.4116280426691763, | |
| "eval_f1": 0.8747037856852112, | |
| "eval_loss": 1.8349922895431519, | |
| "eval_rouge1": 0.6123794030106426, | |
| "eval_rouge2": 0.4063097561396414, | |
| "eval_rougeL": 0.5556039799857393, | |
| "eval_rougeLsum": 0.5576074204448696, | |
| "eval_runtime": 148.6901, | |
| "eval_samples_per_second": 66.191, | |
| "eval_steps_per_second": 1.036, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.0008319026830823564, | |
| "loss": 1.046, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "eval_accuracy": 0.8814265393212761, | |
| "eval_bertscore_f1": 0.933173856183393, | |
| "eval_bleu": 0.4004651404942737, | |
| "eval_f1": 0.8813416551856146, | |
| "eval_loss": 1.8824745416641235, | |
| "eval_rouge1": 0.609629583349967, | |
| "eval_rouge2": 0.4060413051850321, | |
| "eval_rougeL": 0.5545586773158176, | |
| "eval_rougeLsum": 0.5564322531473485, | |
| "eval_runtime": 157.9661, | |
| "eval_samples_per_second": 62.304, | |
| "eval_steps_per_second": 0.975, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 0.0008073772502084662, | |
| "loss": 1.0175, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "eval_accuracy": 0.8784799837431416, | |
| "eval_bertscore_f1": 0.9342269010537525, | |
| "eval_bleu": 0.4055653781578464, | |
| "eval_f1": 0.8790695152176341, | |
| "eval_loss": 1.841552734375, | |
| "eval_rouge1": 0.6082152523859634, | |
| "eval_rouge2": 0.40038271576095896, | |
| "eval_rougeL": 0.5521582299155425, | |
| "eval_rougeLsum": 0.5539512056315703, | |
| "eval_runtime": 145.4844, | |
| "eval_samples_per_second": 67.65, | |
| "eval_steps_per_second": 1.059, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 0.000782851817334576, | |
| "loss": 1.0166, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_accuracy": 0.8834586466165414, | |
| "eval_bertscore_f1": 0.9335280086325087, | |
| "eval_bleu": 0.39913777987686355, | |
| "eval_f1": 0.8834213943612278, | |
| "eval_loss": 1.833051323890686, | |
| "eval_rouge1": 0.6027866506270918, | |
| "eval_rouge2": 0.39444299838413255, | |
| "eval_rougeL": 0.5471957562329999, | |
| "eval_rougeLsum": 0.5488406273419931, | |
| "eval_runtime": 149.4283, | |
| "eval_samples_per_second": 65.864, | |
| "eval_steps_per_second": 1.031, | |
| "step": 22000 | |
| } | |
| ], | |
| "max_steps": 85840, | |
| "num_train_epochs": 10, | |
| "total_flos": 3.0178366029981696e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |