88 lines
32 KiB
JSON
88 lines
32 KiB
JSON
|
{"eval_loss":1.0430654287,"eval_binary":0.0,"eval_rouge":0.733183046,"eval_llm_as_a_judge":0.0,"eval_runtime":27.2072,"eval_samples_per_second":0.882,"eval_steps_per_second":0.441,"epoch":0.0,"step":0,"loss":null,"grad_norm":null,"learning_rate":null,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.0492902208,"step":250,"loss":0.3684,"grad_norm":2.2935080528,"learning_rate":0.000012266,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.0985804416,"step":500,"loss":0.1488,"grad_norm":2.5750687122,"learning_rate":0.0000245813,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.1478706625,"step":750,"loss":0.1085,"grad_norm":2.2189350128,"learning_rate":0.0000368966,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.1971608833,"step":1000,"loss":0.0951,"grad_norm":1.3239541054,"learning_rate":0.0000492118,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.2464511041,"step":1250,"loss":0.0874,"grad_norm":1.6102173328,"learning_rate":0.0000493929,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.2957413249,"step":1500,"loss":0.0767,"grad_norm":0.7495298386,"learning_rate":0.0000487444,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.3450315457,"step":1750,"loss":0.0666,"grad_norm":0.6342540383,"learning_rate":0.0000480958,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.3943217666,"step":2000,"loss":0.0673,"grad_norm":0.5791177154,"learning_rate":0.0000474472,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.4436119874,"step":2250,"loss":0.0615,"grad_norm":0.5940623283,"learning_rate":0.0000467986,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.4929022082,"step":2500,"loss":0.0614,"grad_norm":0.8758848906,"learning_rate":0.0000461501,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.542192429,"step":2750,"loss":0.0598,"grad_norm":0.7535735369,"learning_rate":0.0000455015,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.5914826498,"step":3000,"loss":0.0567,"grad_norm":0.4846973121,"learning_rate":0.0000448529,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.6407728707,"step":3250,"loss":0.0554,"grad_norm":0.6059740186,"learning_rate":0.0000442043,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.6900630915,"step":3500,"loss":0.0578,"grad_norm":0.728974402,"learning_rate":0.0000435558,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.7393533123,"step":3750,"loss":0.0589,"grad_norm":0.290358007,"learning_rate":0.0000429072,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.7886435331,"step":4000,"loss":0.0543,"grad_norm":0.6766389608,"learning_rate":0.0000422586,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.8379337539,"step":4250,"loss":0.054,"grad_norm":0.6083502769,"learning_rate":0.00004161,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.8872239748,"step":4500,"loss":0.054,"grad_norm":0.4829879105,"learning_rate":0.0000409614,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.9365141956,"step":4750,"loss":0.0512,"grad_norm":0.4972564876,"learning_rate":0.0000403129,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.9858044164,"step":5000,"loss":0.0517,"grad_norm":0.3686705828,"learning_rate":0.0000396643,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":0.1299701184,"eval_binary":0.125,"eval_rouge":0.9386326589,"eval_llm_as_a_judge":0.25,"eval_runtime":39.8054,"eval_samples_per_second":0.603,"eval_steps_per_second":0.301,"epoch":1.0,"step":5072,"loss":null,"grad_norm":null,"learning_rate":null,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.0350946372,"step":5250,"loss":0.0502,"grad_norm":0.4273646474,"learning_rate":0.0000390157,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.084384858,"step":5500,"loss":0.0472,"grad_norm":0.6313160062,"learning_rate":0.0000383671,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.1336750789,"step":5750,"loss":0.0489,"grad_norm":0.4157578349,"learning_rate":0.0000377186,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.1829652997,"step":6000,"loss":0.0479,"grad_norm":0.7196144462,"learning_rate":0.00003707,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.2322555205,"step":6250,"loss":0.0487,"grad_norm":0.6047205329,"learning_rate":0.0000364214,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.2815457413,"step":6500,"loss":0.0443,"grad_norm":0.5429460406,"learning_rate":0.0000357728,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.3308359621,"step":6750,"loss":0.0493,"grad_norm":0.4342196286,"learning_rate":0.0000351243,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.380126183,"step":7000,"loss":0.0464,"grad_norm":0.3591873646,"learning_rate":0.0000344757,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.4294164038,"step":7250,"loss":0.0473,"grad_norm":0.5194702744,"learning_rate":0.0000338271,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.4787066246,"step":7500,"loss":0.0494,"grad_norm":0.7344044447,"learning_rate":0.0000331785,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.5279968454,"step":7750,"loss":0.0436,"grad_norm":0.3676634431,"learning_rate":0.00003253,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.5772870662,"step":8000,"loss":0.0462,"grad_norm":0.4753296077,"learning_rate":0.0000318814,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.6265772871,"step":8250,"loss":0.0439,"grad_norm":0.3276772201,"learning_rate":0.0000312328,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.6758675079,"step":8500,"loss":0.0485,"grad_norm":0.6114853621,"learning_rate":0.0000305842,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.7251577287,"step":8750,"loss":0.04,"grad_norm":0.5024742484,"learning_rate":0.0000299357,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.7744479495,"step":9000,"loss":0.0454,"grad_norm":0.3517335653,"learning_rate":0.0000292871,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.8237381703,"step":9250,"loss":0.0424,"grad_norm":0.313556999,"learning_rate":0.0000286385,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.8730283912,"step":9500,"loss":0.0457,"grad_norm":0.443523407,"learning_rate":0.0000279899,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.922318612,"step":9750,"loss":0.0421,"grad_norm":0.28051126,"learning_rate":0.0000273414,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.9716088328,"step":10000,"loss":0.042,"grad_norm":0.3193302751,"learning_rate":0.0000266928,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":0.1188709438,"eval_binary":0.1666666667,"eval_rouge":0.944201243,"eval_llm_as_a_judge":0.2083333333,"eval_runtime":36.7044,"eval_samples_per_second":0.654,"eval_steps_per_second":0.327,"epoch":2.0,"step":10144,"loss":null,"grad_norm":null,"learning_rate":null,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.0208990536,"step":10250,"loss":0.0417,"grad_norm":0.3642235696,"learning_rate":0.0000260442,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.0701892744,"step":10500,"loss":0.0406,"grad_norm":0.1294201016,"learning_rate":0.0000253956,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.1194794953,"step":10750,"loss":0.0393,"grad_norm":0.3784933686,"learning_rate":0.0000247471,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.1687697161,"step":11000,"loss":0.0387,"grad_norm":0.4146607816,"learning_rate":0.0000240985,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.2180599369,"step":11250,"loss":0.0392,"grad_norm":0.8603994846,"learning_rate":0.0000234499,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.2673501577,"step":11500,"loss":0.0398,"grad_norm":0.4274377227,"learning_rate":0.0000228013,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.3166403785,"step":11750,"loss":0.0396,"grad_norm":0.3474481404,"learning_rate":0.0000221528,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.3659305994,"step":12000,"loss":0.0387,"grad_norm":0.4806622267,"learning_rate":0.0000215042,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.4152208202,"step":12250,"loss":0.038,"grad_norm":0.428848356,"learning_rate":0.0000208556,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.464511041,"step":12500,"loss":0.0376,"grad_norm":0.3058715761,"learning_rate":0.000020207,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.5138012618,"step":12750,"loss":0.0363,"grad_norm":0.4138669372,"learning_rate":0.0000195584,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.5630914826,"step":13000,"loss":0.0396,"grad_norm":0.3111126125,"learning_rate":0.0000189099,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.6123817035,"step":13250,"loss":0.0387,"grad_norm":0.4284965694,"learning_rate":0.0000182613,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.6616719243,"step":13500,"loss":0.0419,"grad_norm":0.510720551,"learning_rate":0.0000176127,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.7109621451,"step":13750,"loss":0.0367,"grad_norm":0.2313570231,"learning_rate":0.0000169641,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.7602523659,"step":14000,"loss":0.0419,"grad_norm":0.5340784192,"learning_rate":0.0000163156,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.8095425868,"step":14250,"loss":0.0381,"grad_norm":0.5173833966,"learning_rate":0.000015667,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.8588328076,"step":14500,"loss":0.0373,"grad_norm":0.5786962509,"learning_rate":0.0000150184,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.9081230284,"step":14750,"loss":0.0388,"grad_norm":0.50079,"learning_rate":0.0000143698,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.9574132492,"step":15000,"loss":0.0385,"grad_norm":0.4137586057,"learning_rate":0.0000137213,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":0.1158077717,"eval_binary":0.2916666667,"eval_rouge":0.9513811085,"eval_llm_as_a_judge":0.3333333333,"eval_runtime":34.3655,"eval_samples_per_second":0.698,"eval_steps_per_second":0.349,"epoch":3.0,"step":15216,"loss":null,"grad_norm":null,"learning_rate":null,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.00670347,"step":15250,"loss":0.0364,"grad_norm":0.5562515855,"learning_rate":0.0000130727,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.0559936909,"step":15500,"loss":0.0338,"grad_norm":0.2910844982,"learning_rate":0.0000124241,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.1052839117,"step":15750,"loss":0.0318,"grad_norm":0.78729105,"learning_rate":0.0000117755,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.1545741325,"step":16000,"loss":0.0338,"grad_norm":0.4458884001,"learning_rate":0.000011127,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.2038643533,"step":16250,"loss":0.034,"grad_norm":0.4420760274,"learning_rate":0.0000104784,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.2531545741,"step":16500,"loss":0.0329,"grad_norm":0.267672807,"learning_rate":0.0000098298,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.302444795,"step":16750,"loss":0.0371,"grad_norm":0.4853881896,"learning_rate":0.0000091812,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.3517350158,"step":17000,"loss":0.0328,"grad_norm":0.3404028118,"learning_rate":0.0000085327,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.4010252366,"step":17250,"loss":0.033,"grad_norm":0.4997288585,"learning_rate":0.0000078841,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.4503154574,"step":17500,"loss":0.0337,"grad_norm":0.2257528454,"learning_rate":0.0000072355,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.4996056782,"step":17750,"loss":0.0332,"grad_norm":0.2345863581,"learning_rate":0.0000065869,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.5488958991,"step":18000,"loss":0.0337,"grad_norm":0.3713653386,"learning_rate":0.0000059384,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.5981861199,"step":18250,"loss":0.032,"grad_norm":0.5111656785,"learning_rate":0.0000052898,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.6474763407,"step":18500,"loss":0.0324,"grad_norm":0.7525674105,"learning_rate":0.0000046412,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.6967665615,"step":18750,"loss":0.0312,"grad_norm":0.8564553261,"learning_rate":0.0000039926,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.7460567823,"step":19000,"loss":0.0339,"grad_norm":0.4249573052,"learning_rate":0.0000033441,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.7953470032,"step":19250,"loss":0.0343,"grad_norm":0.4377053082,"learning_rate":0.0000026955,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.844637224,"step":19500,"loss":0.0317,"grad_norm":0.2595922649,"learning_rate":0.0000020469,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.8939274448,"step":19750,"loss":0.033,"grad_norm":0.6287868023,"learning_rate":0.0000013983,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.9432176656,"step":20000,"loss":0.0351,"grad_norm":0.1943079084,"learning_rate":0.0000007498,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.9925078864,"step":20250,"loss":0.0329,"grad_norm":0.4196478426,"learning_rate":0.0000001012,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":0.1175498664,"eval_binary":0.2916666667,"eval_rouge":0.9511809083,"eval_llm_as_a_judge":0.3043478261,"eval_runtime":33.9442,"eval_samples_per_second":0.707,"eval_steps_per_second":0.354,"epoch":4.0,"step":20288,"loss":null,"grad_norm":null,"learning_rate":null,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||
|
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":4.0,"step":20288,"loss":null,"grad_norm":null,"learning_rate":null,"train_runtime":3126.2875,"train_samples_per_second":12.978,"train_steps_per_second":6.489,"total_flos":2.855081305e+17,"train_loss":0.0505578586}
|