| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 100, | |
| "global_step": 621, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04830917874396135, | |
| "grad_norm": 37.65997314453125, | |
| "learning_rate": 4.0000000000000003e-07, | |
| "loss": 0.8115, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0966183574879227, | |
| "grad_norm": 49.085182189941406, | |
| "learning_rate": 8.000000000000001e-07, | |
| "loss": 0.7151, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14492753623188406, | |
| "grad_norm": 57.3139533996582, | |
| "learning_rate": 1.2000000000000002e-06, | |
| "loss": 0.5399, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1932367149758454, | |
| "grad_norm": 14.93040943145752, | |
| "learning_rate": 1.6000000000000001e-06, | |
| "loss": 0.4486, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.24154589371980675, | |
| "grad_norm": 40.2352409362793, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.2895, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2898550724637681, | |
| "grad_norm": 22.021743774414062, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 0.208, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.33816425120772947, | |
| "grad_norm": 3.9624946117401123, | |
| "learning_rate": 2.8000000000000003e-06, | |
| "loss": 0.158, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.3864734299516908, | |
| "grad_norm": 3.648684501647949, | |
| "learning_rate": 3.2000000000000003e-06, | |
| "loss": 0.1099, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.43478260869565216, | |
| "grad_norm": 1.9831331968307495, | |
| "learning_rate": 3.6000000000000003e-06, | |
| "loss": 0.0898, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.4830917874396135, | |
| "grad_norm": 1.1971267461776733, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0561, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4830917874396135, | |
| "eval_accuracy": 0.9926650366748166, | |
| "eval_accuracy_label_Clickbait": 0.9933110367892977, | |
| "eval_accuracy_label_Factual": 0.9922928709055877, | |
| "eval_f1": 0.9926701815332624, | |
| "eval_loss": 0.04882814362645149, | |
| "eval_precision": 0.9926880698400764, | |
| "eval_recall": 0.9926650366748166, | |
| "eval_runtime": 0.8226, | |
| "eval_samples_per_second": 994.464, | |
| "eval_steps_per_second": 63.218, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5314009661835749, | |
| "grad_norm": 0.8438642621040344, | |
| "learning_rate": 4.4e-06, | |
| "loss": 0.061, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.5797101449275363, | |
| "grad_norm": 0.5306077003479004, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 0.0523, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.6280193236714976, | |
| "grad_norm": 42.116844177246094, | |
| "learning_rate": 5.2e-06, | |
| "loss": 0.0555, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.6763285024154589, | |
| "grad_norm": 0.45348191261291504, | |
| "learning_rate": 5.600000000000001e-06, | |
| "loss": 0.0511, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.7246376811594203, | |
| "grad_norm": 0.273034930229187, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0461, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.7729468599033816, | |
| "grad_norm": 0.32376888394355774, | |
| "learning_rate": 6.4000000000000006e-06, | |
| "loss": 0.0355, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.821256038647343, | |
| "grad_norm": 0.46599268913269043, | |
| "learning_rate": 6.800000000000001e-06, | |
| "loss": 0.0057, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.8695652173913043, | |
| "grad_norm": 76.78250122070312, | |
| "learning_rate": 7.2000000000000005e-06, | |
| "loss": 0.0284, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.9178743961352657, | |
| "grad_norm": 0.27929720282554626, | |
| "learning_rate": 7.600000000000001e-06, | |
| "loss": 0.0154, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.966183574879227, | |
| "grad_norm": 0.09468149393796921, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0037, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.966183574879227, | |
| "eval_accuracy": 0.9987775061124694, | |
| "eval_accuracy_label_Clickbait": 0.9966555183946488, | |
| "eval_accuracy_label_Factual": 1.0, | |
| "eval_f1": 0.998777070551364, | |
| "eval_loss": 0.00973883830010891, | |
| "eval_precision": 0.9987798570622531, | |
| "eval_recall": 0.9987775061124694, | |
| "eval_runtime": 0.8161, | |
| "eval_samples_per_second": 1002.369, | |
| "eval_steps_per_second": 63.72, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.0144927536231885, | |
| "grad_norm": 11.390016555786133, | |
| "learning_rate": 8.400000000000001e-06, | |
| "loss": 0.033, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.0628019323671498, | |
| "grad_norm": 0.6215488910675049, | |
| "learning_rate": 8.8e-06, | |
| "loss": 0.0279, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": 0.1523633599281311, | |
| "learning_rate": 9.200000000000002e-06, | |
| "loss": 0.0093, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.1594202898550725, | |
| "grad_norm": 0.10952762514352798, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 0.022, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.2077294685990339, | |
| "grad_norm": 0.07856310158967972, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0309, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.2560386473429952, | |
| "grad_norm": 0.05758531391620636, | |
| "learning_rate": 1.04e-05, | |
| "loss": 0.0015, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.3043478260869565, | |
| "grad_norm": 0.049695733934640884, | |
| "learning_rate": 1.0800000000000002e-05, | |
| "loss": 0.0071, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.3526570048309179, | |
| "grad_norm": 0.19512628018856049, | |
| "learning_rate": 1.1200000000000001e-05, | |
| "loss": 0.0054, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.4009661835748792, | |
| "grad_norm": 0.049039632081985474, | |
| "learning_rate": 1.16e-05, | |
| "loss": 0.023, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.4492753623188406, | |
| "grad_norm": 0.06413820385932922, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.0012, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.4492753623188406, | |
| "eval_accuracy": 1.0, | |
| "eval_accuracy_label_Clickbait": 1.0, | |
| "eval_accuracy_label_Factual": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.0015956248389557004, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.8233, | |
| "eval_samples_per_second": 993.556, | |
| "eval_steps_per_second": 63.16, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.497584541062802, | |
| "grad_norm": 0.04210774227976799, | |
| "learning_rate": 1.2400000000000002e-05, | |
| "loss": 0.0012, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.5458937198067633, | |
| "grad_norm": 0.02976871468126774, | |
| "learning_rate": 1.2800000000000001e-05, | |
| "loss": 0.0079, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.5942028985507246, | |
| "grad_norm": 0.029957927763462067, | |
| "learning_rate": 1.3200000000000002e-05, | |
| "loss": 0.0008, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.642512077294686, | |
| "grad_norm": 12.84114933013916, | |
| "learning_rate": 1.3600000000000002e-05, | |
| "loss": 0.0168, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.6908212560386473, | |
| "grad_norm": 0.6662724018096924, | |
| "learning_rate": 1.4e-05, | |
| "loss": 0.0209, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.7391304347826086, | |
| "grad_norm": 0.036532897502183914, | |
| "learning_rate": 1.4400000000000001e-05, | |
| "loss": 0.0008, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.78743961352657, | |
| "grad_norm": 0.05894944816827774, | |
| "learning_rate": 1.48e-05, | |
| "loss": 0.0351, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.8357487922705316, | |
| "grad_norm": 0.03172897920012474, | |
| "learning_rate": 1.5200000000000002e-05, | |
| "loss": 0.0156, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.8840579710144927, | |
| "grad_norm": 60.220420837402344, | |
| "learning_rate": 1.5600000000000003e-05, | |
| "loss": 0.106, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.9323671497584543, | |
| "grad_norm": 0.045578889548778534, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.0012, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.9323671497584543, | |
| "eval_accuracy": 1.0, | |
| "eval_accuracy_label_Clickbait": 1.0, | |
| "eval_accuracy_label_Factual": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.001607110258191824, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.822, | |
| "eval_samples_per_second": 995.143, | |
| "eval_steps_per_second": 63.261, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.9806763285024154, | |
| "grad_norm": 0.038461122661828995, | |
| "learning_rate": 1.64e-05, | |
| "loss": 0.0011, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.028985507246377, | |
| "grad_norm": 0.024971311911940575, | |
| "learning_rate": 1.6800000000000002e-05, | |
| "loss": 0.0008, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.077294685990338, | |
| "grad_norm": 0.021732186898589134, | |
| "learning_rate": 1.72e-05, | |
| "loss": 0.0005, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.1256038647342996, | |
| "grad_norm": 22.902217864990234, | |
| "learning_rate": 1.76e-05, | |
| "loss": 0.0134, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.1739130434782608, | |
| "grad_norm": 0.05803954228758812, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.0005, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 0.016587387770414352, | |
| "learning_rate": 1.8400000000000003e-05, | |
| "loss": 0.0004, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.2705314009661834, | |
| "grad_norm": 0.014241261407732964, | |
| "learning_rate": 1.88e-05, | |
| "loss": 0.0004, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.318840579710145, | |
| "grad_norm": 0.013285420835018158, | |
| "learning_rate": 1.9200000000000003e-05, | |
| "loss": 0.0003, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.367149758454106, | |
| "grad_norm": 0.008689775131642818, | |
| "learning_rate": 1.9600000000000002e-05, | |
| "loss": 0.0003, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.4154589371980677, | |
| "grad_norm": 0.05173454433679581, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0433, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.4154589371980677, | |
| "eval_accuracy": 0.9987775061124694, | |
| "eval_accuracy_label_Clickbait": 0.9966555183946488, | |
| "eval_accuracy_label_Factual": 1.0, | |
| "eval_f1": 0.998777070551364, | |
| "eval_loss": 0.0020217353012412786, | |
| "eval_precision": 0.9987798570622531, | |
| "eval_recall": 0.9987775061124694, | |
| "eval_runtime": 0.8279, | |
| "eval_samples_per_second": 988.004, | |
| "eval_steps_per_second": 62.807, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.463768115942029, | |
| "grad_norm": 0.07507430762052536, | |
| "learning_rate": 1.834710743801653e-05, | |
| "loss": 0.0055, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.5120772946859904, | |
| "grad_norm": 42.797401428222656, | |
| "learning_rate": 1.669421487603306e-05, | |
| "loss": 0.0161, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.5603864734299515, | |
| "grad_norm": 0.01774718426167965, | |
| "learning_rate": 1.504132231404959e-05, | |
| "loss": 0.0006, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.608695652173913, | |
| "grad_norm": 0.022867949679493904, | |
| "learning_rate": 1.3388429752066117e-05, | |
| "loss": 0.0191, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.6570048309178746, | |
| "grad_norm": 0.013622589409351349, | |
| "learning_rate": 1.1735537190082646e-05, | |
| "loss": 0.0043, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.7053140096618358, | |
| "grad_norm": 0.012125013396143913, | |
| "learning_rate": 1.0082644628099174e-05, | |
| "loss": 0.0003, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.753623188405797, | |
| "grad_norm": 0.009969482198357582, | |
| "learning_rate": 8.429752066115703e-06, | |
| "loss": 0.0193, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.8019323671497585, | |
| "grad_norm": 0.010625869035720825, | |
| "learning_rate": 6.776859504132232e-06, | |
| "loss": 0.0008, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.85024154589372, | |
| "grad_norm": 0.010633111000061035, | |
| "learning_rate": 5.12396694214876e-06, | |
| "loss": 0.0143, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.898550724637681, | |
| "grad_norm": 0.011428612284362316, | |
| "learning_rate": 3.4710743801652895e-06, | |
| "loss": 0.0003, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.898550724637681, | |
| "eval_accuracy": 0.9951100244498777, | |
| "eval_accuracy_label_Clickbait": 0.9866220735785953, | |
| "eval_accuracy_label_Factual": 1.0, | |
| "eval_f1": 0.9951029456353522, | |
| "eval_loss": 0.016679394990205765, | |
| "eval_precision": 0.9951474238804714, | |
| "eval_recall": 0.9951100244498777, | |
| "eval_runtime": 0.8314, | |
| "eval_samples_per_second": 983.91, | |
| "eval_steps_per_second": 62.547, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.9468599033816423, | |
| "grad_norm": 0.010514287278056145, | |
| "learning_rate": 1.8181818181818183e-06, | |
| "loss": 0.0003, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 2.995169082125604, | |
| "grad_norm": 104.85121154785156, | |
| "learning_rate": 1.6528925619834713e-07, | |
| "loss": 0.0108, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 621, | |
| "total_flos": 29633646182400.0, | |
| "train_loss": 0.06926822083632517, | |
| "train_runtime": 68.411, | |
| "train_samples_per_second": 290.041, | |
| "train_steps_per_second": 9.077 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9951100244498777, | |
| "eval_accuracy_label_Clickbait": 0.9866220735785953, | |
| "eval_accuracy_label_Factual": 1.0, | |
| "eval_f1": 0.9951029456353522, | |
| "eval_loss": 0.017279641702771187, | |
| "eval_precision": 0.9951474238804714, | |
| "eval_recall": 0.9951100244498777, | |
| "eval_runtime": 0.8191, | |
| "eval_samples_per_second": 998.621, | |
| "eval_steps_per_second": 63.482, | |
| "step": 621 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 621, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 29633646182400.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |