| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.8713160404573231, | |
| "global_step": 74000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00029941127294563693, | |
| "loss": 4.087, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0002988225458912739, | |
| "loss": 3.7168, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0002982338188369108, | |
| "loss": 3.5567, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00029764509178254774, | |
| "loss": 3.4939, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0002970563647281847, | |
| "loss": 3.4094, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00029646763767382164, | |
| "loss": 3.4297, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0002958789106194586, | |
| "loss": 3.3537, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0002952901835650955, | |
| "loss": 3.3117, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0002947014565107325, | |
| "loss": 3.2607, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0002941127294563694, | |
| "loss": 3.2741, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_gen_len": 18.9343, | |
| "eval_loss": 2.923264980316162, | |
| "eval_rouge1": 21.2236, | |
| "eval_rouge2": 9.7543, | |
| "eval_rougeL": 19.1786, | |
| "eval_rougeLsum": 19.782, | |
| "eval_runtime": 554.7643, | |
| "eval_samples_per_second": 18.026, | |
| "eval_steps_per_second": 2.253, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00029352400240200636, | |
| "loss": 3.2403, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0002929352753476433, | |
| "loss": 3.2089, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0002923465482932802, | |
| "loss": 3.1972, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0002917578212389172, | |
| "loss": 3.1384, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0002911690941845541, | |
| "loss": 3.1834, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0002905803671301911, | |
| "loss": 3.1484, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00028999164007582803, | |
| "loss": 3.1509, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00028940291302146493, | |
| "loss": 3.125, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00028881418596710194, | |
| "loss": 3.1113, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00028822545891273884, | |
| "loss": 3.1359, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_gen_len": 18.9427, | |
| "eval_loss": 2.825679302215576, | |
| "eval_rouge1": 23.1537, | |
| "eval_rouge2": 11.6804, | |
| "eval_rougeL": 21.2251, | |
| "eval_rougeLsum": 21.8301, | |
| "eval_runtime": 547.7371, | |
| "eval_samples_per_second": 18.257, | |
| "eval_steps_per_second": 2.282, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0002876367318583758, | |
| "loss": 3.085, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00028704800480401274, | |
| "loss": 3.0939, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0002864592777496497, | |
| "loss": 3.0683, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00028587055069528665, | |
| "loss": 3.0748, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00028528182364092355, | |
| "loss": 3.0484, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002846930965865605, | |
| "loss": 3.0441, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00028410436953219746, | |
| "loss": 3.0315, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002835156424778344, | |
| "loss": 3.0418, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00028292691542347137, | |
| "loss": 3.036, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00028233818836910827, | |
| "loss": 3.0571, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_gen_len": 18.8978, | |
| "eval_loss": 2.760854721069336, | |
| "eval_rouge1": 23.6484, | |
| "eval_rouge2": 12.3437, | |
| "eval_rougeL": 21.8478, | |
| "eval_rougeLsum": 22.4063, | |
| "eval_runtime": 548.4414, | |
| "eval_samples_per_second": 18.233, | |
| "eval_steps_per_second": 2.279, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0002817494613147452, | |
| "loss": 3.0305, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0002811607342603822, | |
| "loss": 3.0116, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00028057200720601913, | |
| "loss": 3.0284, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0002799832801516561, | |
| "loss": 3.0063, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.000279394553097293, | |
| "loss": 2.9533, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00027880582604292994, | |
| "loss": 2.9608, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0002782170989885669, | |
| "loss": 2.9796, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00027762837193420385, | |
| "loss": 2.9651, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0002770396448798408, | |
| "loss": 2.963, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0002764509178254777, | |
| "loss": 2.9887, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_gen_len": 18.9275, | |
| "eval_loss": 2.7225496768951416, | |
| "eval_rouge1": 24.3863, | |
| "eval_rouge2": 13.0699, | |
| "eval_rougeL": 22.5709, | |
| "eval_rougeLsum": 23.1191, | |
| "eval_runtime": 548.8094, | |
| "eval_samples_per_second": 18.221, | |
| "eval_steps_per_second": 2.278, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00027586219077111465, | |
| "loss": 2.9618, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0002752734637167516, | |
| "loss": 2.9229, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00027468473666238856, | |
| "loss": 2.9284, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0002740960096080255, | |
| "loss": 2.9324, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00027350728255366247, | |
| "loss": 2.941, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002729185554992994, | |
| "loss": 2.9216, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002723298284449363, | |
| "loss": 2.9258, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002717411013905733, | |
| "loss": 2.9075, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00027115237433621023, | |
| "loss": 2.9001, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0002705636472818472, | |
| "loss": 2.8939, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_gen_len": 18.8512, | |
| "eval_loss": 2.6895627975463867, | |
| "eval_rouge1": 23.8549, | |
| "eval_rouge2": 12.6254, | |
| "eval_rougeL": 22.1601, | |
| "eval_rougeLsum": 22.688, | |
| "eval_runtime": 544.7255, | |
| "eval_samples_per_second": 18.358, | |
| "eval_steps_per_second": 2.295, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00026997492022748414, | |
| "loss": 2.8947, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00026938619317312104, | |
| "loss": 2.9073, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.000268797466118758, | |
| "loss": 2.9035, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00026820873906439495, | |
| "loss": 2.9128, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0002676200120100319, | |
| "loss": 2.8639, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00026703128495566886, | |
| "loss": 2.8944, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00026644255790130575, | |
| "loss": 2.8952, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0002658538308469427, | |
| "loss": 2.8956, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00026526510379257966, | |
| "loss": 2.8959, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0002646763767382166, | |
| "loss": 2.8614, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_gen_len": 18.9345, | |
| "eval_loss": 2.6755456924438477, | |
| "eval_rouge1": 24.3321, | |
| "eval_rouge2": 13.0763, | |
| "eval_rougeL": 22.6103, | |
| "eval_rougeLsum": 23.1247, | |
| "eval_runtime": 546.9326, | |
| "eval_samples_per_second": 18.284, | |
| "eval_steps_per_second": 2.285, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00026408764968385357, | |
| "loss": 2.8459, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00026349892262949047, | |
| "loss": 2.8591, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0002629101955751274, | |
| "loss": 2.8291, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0002623214685207644, | |
| "loss": 2.8645, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00026173274146640133, | |
| "loss": 2.8185, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0002611440144120383, | |
| "loss": 2.8498, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0002605552873576752, | |
| "loss": 2.8384, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00025996656030331214, | |
| "loss": 2.8515, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0002593778332489491, | |
| "loss": 2.8378, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00025878910619458605, | |
| "loss": 2.849, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_gen_len": 18.8908, | |
| "eval_loss": 2.6249804496765137, | |
| "eval_rouge1": 24.2486, | |
| "eval_rouge2": 12.8938, | |
| "eval_rougeL": 22.5311, | |
| "eval_rougeLsum": 23.0375, | |
| "eval_runtime": 549.356, | |
| "eval_samples_per_second": 18.203, | |
| "eval_steps_per_second": 2.275, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.000258200379140223, | |
| "loss": 2.813, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00025761165208585996, | |
| "loss": 2.8157, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00025702292503149686, | |
| "loss": 2.83, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0002564341979771338, | |
| "loss": 2.8324, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00025584547092277076, | |
| "loss": 2.849, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0002552567438684077, | |
| "loss": 2.8163, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00025466801681404467, | |
| "loss": 2.8215, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00025407928975968157, | |
| "loss": 2.777, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0002534905627053185, | |
| "loss": 2.8147, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0002529018356509555, | |
| "loss": 2.7994, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_gen_len": 18.891, | |
| "eval_loss": 2.618790626525879, | |
| "eval_rouge1": 24.5722, | |
| "eval_rouge2": 13.3685, | |
| "eval_rougeL": 22.865, | |
| "eval_rougeLsum": 23.3852, | |
| "eval_runtime": 548.1205, | |
| "eval_samples_per_second": 18.244, | |
| "eval_steps_per_second": 2.281, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00025231310859659243, | |
| "loss": 2.7992, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0002517243815422294, | |
| "loss": 2.8235, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0002511356544878663, | |
| "loss": 2.8081, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00025054692743350324, | |
| "loss": 2.812, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0002499582003791402, | |
| "loss": 2.7941, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00024936947332477715, | |
| "loss": 2.8014, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0002487807462704141, | |
| "loss": 2.7778, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.000248192019216051, | |
| "loss": 2.7734, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00024760329216168796, | |
| "loss": 2.8093, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002470145651073249, | |
| "loss": 2.7899, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_gen_len": 18.9064, | |
| "eval_loss": 2.6196963787078857, | |
| "eval_rouge1": 24.3304, | |
| "eval_rouge2": 13.157, | |
| "eval_rougeL": 22.6459, | |
| "eval_rougeLsum": 23.1647, | |
| "eval_runtime": 540.7531, | |
| "eval_samples_per_second": 18.493, | |
| "eval_steps_per_second": 2.312, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00024642583805296187, | |
| "loss": 2.8157, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0002458371109985988, | |
| "loss": 2.7576, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0002452483839442357, | |
| "loss": 2.7482, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00024465965688987273, | |
| "loss": 2.7704, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00024407092983550963, | |
| "loss": 2.7597, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0002434822027811466, | |
| "loss": 2.765, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00024289347572678354, | |
| "loss": 2.7709, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00024230474867242046, | |
| "loss": 2.7519, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00024171602161805742, | |
| "loss": 2.74, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00024112729456369434, | |
| "loss": 2.786, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_gen_len": 18.8697, | |
| "eval_loss": 2.584320545196533, | |
| "eval_rouge1": 24.7437, | |
| "eval_rouge2": 13.5493, | |
| "eval_rougeL": 23.0267, | |
| "eval_rougeLsum": 23.5281, | |
| "eval_runtime": 542.416, | |
| "eval_samples_per_second": 18.436, | |
| "eval_steps_per_second": 2.305, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00024053856750933132, | |
| "loss": 2.7556, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00023994984045496825, | |
| "loss": 2.746, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00023936111340060518, | |
| "loss": 2.767, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00023877238634624213, | |
| "loss": 2.7261, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00023818365929187906, | |
| "loss": 2.773, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00023759493223751604, | |
| "loss": 2.7811, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00023700620518315297, | |
| "loss": 2.7727, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0002364174781287899, | |
| "loss": 2.75, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00023582875107442685, | |
| "loss": 2.7689, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0002352400240200638, | |
| "loss": 2.7765, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_gen_len": 18.8908, | |
| "eval_loss": 2.5723013877868652, | |
| "eval_rouge1": 24.55, | |
| "eval_rouge2": 13.501, | |
| "eval_rougeL": 22.8132, | |
| "eval_rougeLsum": 23.3216, | |
| "eval_runtime": 548.4906, | |
| "eval_samples_per_second": 18.232, | |
| "eval_steps_per_second": 2.279, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00023465129696570076, | |
| "loss": 2.7603, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00023406256991133768, | |
| "loss": 2.7369, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002334738428569746, | |
| "loss": 2.6958, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002328851158026116, | |
| "loss": 2.7746, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00023229638874824852, | |
| "loss": 2.7596, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00023170766169388547, | |
| "loss": 2.7118, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0002311189346395224, | |
| "loss": 2.7248, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00023053020758515932, | |
| "loss": 2.7307, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0002299414805307963, | |
| "loss": 2.7487, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00022935275347643323, | |
| "loss": 2.7591, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_gen_len": 18.8755, | |
| "eval_loss": 2.5769457817077637, | |
| "eval_rouge1": 24.78, | |
| "eval_rouge2": 13.6656, | |
| "eval_rougeL": 23.0842, | |
| "eval_rougeLsum": 23.6064, | |
| "eval_runtime": 548.2586, | |
| "eval_samples_per_second": 18.24, | |
| "eval_steps_per_second": 2.28, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0002287640264220702, | |
| "loss": 2.7621, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00022817529936770711, | |
| "loss": 2.7554, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00022758657231334404, | |
| "loss": 2.7484, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00022699784525898102, | |
| "loss": 2.7762, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00022640911820461795, | |
| "loss": 2.7248, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.0002258203911502549, | |
| "loss": 2.6949, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00022523166409589183, | |
| "loss": 2.7287, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0002246429370415288, | |
| "loss": 2.7017, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00022405420998716574, | |
| "loss": 2.6926, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00022346548293280266, | |
| "loss": 2.7254, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_gen_len": 18.8954, | |
| "eval_loss": 2.566603183746338, | |
| "eval_rouge1": 24.8284, | |
| "eval_rouge2": 13.73, | |
| "eval_rougeL": 23.0997, | |
| "eval_rougeLsum": 23.6334, | |
| "eval_runtime": 557.6451, | |
| "eval_samples_per_second": 17.933, | |
| "eval_steps_per_second": 2.242, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00022287675587843962, | |
| "loss": 2.7054, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00022228802882407655, | |
| "loss": 2.6841, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00022169930176971353, | |
| "loss": 2.7164, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00022111057471535045, | |
| "loss": 2.7272, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00022052184766098738, | |
| "loss": 2.715, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00021993312060662433, | |
| "loss": 2.6992, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0002193443935522613, | |
| "loss": 2.7124, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00021875566649789824, | |
| "loss": 2.685, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.00021816693944353517, | |
| "loss": 2.6867, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0002175782123891721, | |
| "loss": 2.6814, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_gen_len": 18.8313, | |
| "eval_loss": 2.5359628200531006, | |
| "eval_rouge1": 24.849, | |
| "eval_rouge2": 13.8366, | |
| "eval_rougeL": 23.1903, | |
| "eval_rougeLsum": 23.6941, | |
| "eval_runtime": 544.4942, | |
| "eval_samples_per_second": 18.366, | |
| "eval_steps_per_second": 2.296, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00021698948533480908, | |
| "loss": 2.6868, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.000216400758280446, | |
| "loss": 2.6849, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00021581203122608296, | |
| "loss": 2.705, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00021522330417171988, | |
| "loss": 2.7154, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0002146345771173568, | |
| "loss": 2.6585, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0002140458500629938, | |
| "loss": 2.6848, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00021345712300863072, | |
| "loss": 2.6787, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00021286839595426767, | |
| "loss": 2.646, | |
| "step": 74000 | |
| } | |
| ], | |
| "max_steps": 254787, | |
| "num_train_epochs": 3, | |
| "total_flos": 2.2883060458635264e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |