diff --git "a/log/debug_0.log" "b/log/debug_0.log"
--- "a/log/debug_0.log"
+++ "b/log/debug_0.log"
@@ -2512,3 +2512,2506 @@ Use FP16 precision: False
 12/21/2021 22:21:51 - INFO - codeparrot_training - Evaluating and saving model checkpoint
 12/21/2021 22:49:57 - INFO - codeparrot_training - Batch size: torch.Size([0, 2048])
 12/21/2021 22:49:57 - INFO - codeparrot_training - Step 2500: {'loss/eval': 0.9031597971916199, 'perplexity': 2.4673871994018555}
+12/21/2021 22:50:27 - INFO - codeparrot_training - Step 2500: {'lr': 0.0004973184670148224, 'samples': 1280512, 'steps': 2500, 'batch_loss/train': 0.9076937567442656}
+12/21/2021 22:50:39 - INFO - codeparrot_training - Step 2501: {'lr': 0.0004973161639606864, 'samples': 1281024, 'steps': 2501, 'batch_loss/train': 0.969430792145431}
+12/21/2021 22:50:50 - INFO - codeparrot_training - Step 2502: {'lr': 0.0004973138599233148, 'samples': 1281536, 'steps': 2502, 'batch_loss/train': 0.8416600208729506}
+12/21/2021 22:51:01 - INFO - codeparrot_training - Step 2503: {'lr': 0.0004973115549027166, 'samples': 1282048, 'steps': 2503, 'batch_loss/train': 0.8591052221599966}
+12/21/2021 22:51:11 - INFO - codeparrot_training - Step 2504: {'lr': 0.0004973092488989011, 'samples': 1282560, 'steps': 2504, 'batch_loss/train': 0.9008149318397045}
+12/21/2021 22:51:23 - INFO - codeparrot_training - Step 2505: {'lr': 0.0004973069419118773, 'samples': 1283072, 'steps': 2505, 'batch_loss/train': 0.8336633089929819}
+12/21/2021 22:51:34 - INFO - codeparrot_training - Step 2506: {'lr': 0.0004973046339416545, 'samples': 1283584, 'steps': 2506, 'batch_loss/train': 0.9070305284112692}
+12/21/2021 22:51:44 - INFO - codeparrot_training - Step 2507: {'lr': 0.000497302324988242, 'samples': 1284096, 'steps': 2507, 'batch_loss/train': 0.9228264223784208}
+12/21/2021 22:51:57 - INFO - codeparrot_training - Step 2508: {'lr': 0.0004973000150516487, 'samples': 1284608, 'steps': 2508, 'batch_loss/train': 0.9444270497187972}
+12/21/2021 22:52:08 - INFO - codeparrot_training - Step 2509: {'lr': 0.0004972977041318839, 'samples': 1285120, 'steps': 2509, 'batch_loss/train': 0.953637545928359}
+12/21/2021 22:52:19 - INFO - codeparrot_training - Step 2510: {'lr': 0.0004972953922289569, 'samples': 1285632, 'steps': 2510, 'batch_loss/train': 0.8730979631654918}
+12/21/2021 22:52:31 - INFO - codeparrot_training - Step 2511: {'lr': 0.0004972930793428768, 'samples': 1286144, 'steps': 2511, 'batch_loss/train': 0.8727558553218842}
+12/21/2021 22:52:41 - INFO - codeparrot_training - Step 2512: {'lr': 0.0004972907654736527, 'samples': 1286656, 'steps': 2512, 'batch_loss/train': 0.877959605306387}
+12/21/2021 22:52:52 - INFO - codeparrot_training - Step 2513: {'lr': 0.0004972884506212939, 'samples': 1287168, 'steps': 2513, 'batch_loss/train': 0.8885626718401909}
+12/21/2021 22:53:02 - INFO - codeparrot_training - Step 2514: {'lr': 0.0004972861347858097, 'samples': 1287680, 'steps': 2514, 'batch_loss/train': 0.7683573863469064}
+12/21/2021 22:53:15 - INFO - codeparrot_training - Step 2515: {'lr': 0.0004972838179672091, 'samples': 1288192, 'steps': 2515, 'batch_loss/train': 0.9208315955474973}
+12/21/2021 22:53:26 - INFO - codeparrot_training - Step 2516: {'lr': 0.0004972815001655014, 'samples': 1288704, 'steps': 2516, 'batch_loss/train': 1.0412279767915606}
+12/21/2021 22:53:37 - INFO - codeparrot_training - Step 2517: {'lr': 0.0004972791813806958, 'samples': 1289216, 'steps': 2517, 'batch_loss/train': 0.7875987719744444}
+12/21/2021 22:53:49 - INFO - codeparrot_training - Step 2518: {'lr': 0.0004972768616128016, 'samples': 1289728, 'steps': 2518, 'batch_loss/train': 0.8762602936476469}
+12/21/2021 22:53:59 - INFO - codeparrot_training - Step 2519: {'lr': 0.000497274540861828, 'samples': 1290240, 'steps': 2519, 'batch_loss/train': 0.8094407469034195}
+12/21/2021 22:54:10 - INFO - codeparrot_training - Step 2520: {'lr': 0.0004972722191277842, 'samples': 1290752, 'steps': 2520, 'batch_loss/train': 0.8472680025734007}
+12/21/2021 22:54:22 - INFO - codeparrot_training - Step 2521: {'lr': 0.0004972698964106794, 'samples': 1291264, 'steps': 2521, 'batch_loss/train': 0.8058119593188167}
+12/21/2021 22:54:33 - INFO - codeparrot_training - Step 2522: {'lr': 0.0004972675727105228, 'samples': 1291776, 'steps': 2522, 'batch_loss/train': 0.8879459099844098}
+12/21/2021 22:54:43 - INFO - codeparrot_training - Step 2523: {'lr': 0.0004972652480273237, 'samples': 1292288, 'steps': 2523, 'batch_loss/train': 1.0259497240185738}
+12/21/2021 22:54:56 - INFO - codeparrot_training - Step 2524: {'lr': 0.0004972629223610914, 'samples': 1292800, 'steps': 2524, 'batch_loss/train': 0.8909566830843687}
+12/21/2021 22:55:07 - INFO - codeparrot_training - Step 2525: {'lr': 0.000497260595711835, 'samples': 1293312, 'steps': 2525, 'batch_loss/train': 0.8714152667671442}
+12/21/2021 22:55:17 - INFO - codeparrot_training - Step 2526: {'lr': 0.000497258268079564, 'samples': 1293824, 'steps': 2526, 'batch_loss/train': 0.8264178214594722}
+12/21/2021 22:55:28 - INFO - codeparrot_training - Step 2527: {'lr': 0.0004972559394642873, 'samples': 1294336, 'steps': 2527, 'batch_loss/train': 0.890899671241641}
+12/21/2021 22:55:40 - INFO - codeparrot_training - Step 2528: {'lr': 0.0004972536098660144, 'samples': 1294848, 'steps': 2528, 'batch_loss/train': 0.8058766731992364}
+12/21/2021 22:55:50 - INFO - codeparrot_training - Step 2529: {'lr': 0.0004972512792847546, 'samples': 1295360, 'steps': 2529, 'batch_loss/train': 0.8343138564378023}
+12/21/2021 22:56:01 - INFO - codeparrot_training - Step 2530: {'lr': 0.000497248947720517, 'samples': 1295872, 'steps': 2530, 'batch_loss/train': 0.976877330802381}
+12/21/2021 22:56:14 - INFO - codeparrot_training - Step 2531: {'lr': 0.000497246615173311, 'samples': 1296384, 'steps': 2531, 'batch_loss/train': 0.9488952672109008}
+12/21/2021 22:56:24 - INFO - codeparrot_training - Step 2532: {'lr': 0.0004972442816431456, 'samples': 1296896, 'steps': 2532, 'batch_loss/train': 0.8364651361480355}
+12/21/2021 22:56:35 - INFO - codeparrot_training - Step 2533: {'lr': 0.0004972419471300305, 'samples': 1297408, 'steps': 2533, 'batch_loss/train': 0.8487222855910659}
+12/21/2021 22:56:47 - INFO - codeparrot_training - Step 2534: {'lr': 0.0004972396116339747, 'samples': 1297920, 'steps': 2534, 'batch_loss/train': 0.8443860290572047}
+12/21/2021 22:56:58 - INFO - codeparrot_training - Step 2535: {'lr': 0.0004972372751549876, 'samples': 1298432, 'steps': 2535, 'batch_loss/train': 0.9987309090793133}
+12/21/2021 22:57:08 - INFO - codeparrot_training - Step 2536: {'lr': 0.0004972349376930784, 'samples': 1298944, 'steps': 2536, 'batch_loss/train': 0.8589098758529872}
+12/21/2021 22:57:19 - INFO - codeparrot_training - Step 2537: {'lr': 0.0004972325992482565, 'samples': 1299456, 'steps': 2537, 'batch_loss/train': 0.949855612590909}
+12/21/2021 22:57:31 - INFO - codeparrot_training - Step 2538: {'lr': 0.0004972302598205311, 'samples': 1299968, 'steps': 2538, 'batch_loss/train': 0.9207930257543921}
+12/21/2021 22:57:42 - INFO - codeparrot_training - Step 2539: {'lr': 0.0004972279194099115, 'samples': 1300480, 'steps': 2539, 'batch_loss/train': 0.8668918842449784}
+12/21/2021 22:57:52 - INFO - codeparrot_training - Step 2540: {'lr': 0.0004972255780164071, 'samples': 1300992, 'steps': 2540, 'batch_loss/train': 0.9496146347373724}
+12/21/2021 22:58:05 - INFO - codeparrot_training - Step 2541: {'lr': 0.0004972232356400271, 'samples': 1301504, 'steps': 2541, 'batch_loss/train': 0.9162016650661826}
+12/21/2021 22:58:15 - INFO - codeparrot_training - Step 2542: {'lr': 0.000497220892280781, 'samples': 1302016, 'steps': 2542, 'batch_loss/train': 0.9554236540570855}
+12/21/2021 22:58:26 - INFO - codeparrot_training - Step 2543: {'lr': 0.0004972185479386778, 'samples': 1302528, 'steps': 2543, 'batch_loss/train': 0.8487241314724088}
+12/21/2021 22:58:39 - INFO - codeparrot_training - Step 2544: {'lr': 0.0004972162026137271, 'samples': 1303040, 'steps': 2544, 'batch_loss/train': 0.9302274729125202}
+12/21/2021 22:58:49 - INFO - codeparrot_training - Step 2545: {'lr': 0.0004972138563059381, 'samples': 1303552, 'steps': 2545, 'batch_loss/train': 0.8458808241412044}
+12/21/2021 22:59:00 - INFO - codeparrot_training - Step 2546: {'lr': 0.0004972115090153201, 'samples': 1304064, 'steps': 2546, 'batch_loss/train': 0.8888266906142235}
+12/21/2021 22:59:12 - INFO - codeparrot_training - Step 2547: {'lr': 0.0004972091607418826, 'samples': 1304576, 'steps': 2547, 'batch_loss/train': 0.7463920973241329}
+12/21/2021 22:59:23 - INFO - codeparrot_training - Step 2548: {'lr': 0.0004972068114856347, 'samples': 1305088, 'steps': 2548, 'batch_loss/train': 0.9357333313673735}
+12/21/2021 22:59:33 - INFO - codeparrot_training - Step 2549: {'lr': 0.000497204461246586, 'samples': 1305600, 'steps': 2549, 'batch_loss/train': 0.8408659463748336}
+12/21/2021 22:59:44 - INFO - codeparrot_training - Step 2550: {'lr': 0.0004972021100247456, 'samples': 1306112, 'steps': 2550, 'batch_loss/train': 0.9263641079887748}
+12/21/2021 22:59:56 - INFO - codeparrot_training - Step 2551: {'lr': 0.000497199757820123, 'samples': 1306624, 'steps': 2551, 'batch_loss/train': 1.0148287108168006}
+12/21/2021 23:00:07 - INFO - codeparrot_training - Step 2552: {'lr': 0.0004971974046327274, 'samples': 1307136, 'steps': 2552, 'batch_loss/train': 0.9012897098436952}
+12/21/2021 23:00:17 - INFO - codeparrot_training - Step 2553: {'lr': 0.0004971950504625683, 'samples': 1307648, 'steps': 2553, 'batch_loss/train': 0.891429235227406}
+12/21/2021 23:00:30 - INFO - codeparrot_training - Step 2554: {'lr': 0.000497192695309655, 'samples': 1308160, 'steps': 2554, 'batch_loss/train': 0.831726127769798}
+12/21/2021 23:00:41 - INFO - codeparrot_training - Step 2555: {'lr': 0.0004971903391739969, 'samples': 1308672, 'steps': 2555, 'batch_loss/train': 0.9400324746966362}
+12/21/2021 23:00:52 - INFO - codeparrot_training - Step 2556: {'lr': 0.0004971879820556035, 'samples': 1309184, 'steps': 2556, 'batch_loss/train': 0.6422781564760953}
+12/21/2021 23:01:02 - INFO - codeparrot_training - Step 2557: {'lr': 0.0004971856239544838, 'samples': 1309696, 'steps': 2557, 'batch_loss/train': 0.8568375967442989}
+12/21/2021 23:01:14 - INFO - codeparrot_training - Step 2558: {'lr': 0.0004971832648706476, 'samples': 1310208, 'steps': 2558, 'batch_loss/train': 0.7511599408462644}
+12/21/2021 23:01:25 - INFO - codeparrot_training - Step 2559: {'lr': 0.0004971809048041039, 'samples': 1310720, 'steps': 2559, 'batch_loss/train': 0.8719435341190547}
+12/21/2021 23:01:36 - INFO - codeparrot_training - Step 2560: {'lr': 0.0004971785437548622, 'samples': 1311232, 'steps': 2560, 'batch_loss/train': 0.8061729660257697}
+12/21/2021 23:01:49 - INFO - codeparrot_training - Step 2561: {'lr': 0.0004971761817229321, 'samples': 1311744, 'steps': 2561, 'batch_loss/train': 0.8520532930269837}
+12/21/2021 23:01:59 - INFO - codeparrot_training - Step 2562: {'lr': 0.0004971738187083228, 'samples': 1312256, 'steps': 2562, 'batch_loss/train': 0.8292180690914392}
+12/21/2021 23:02:10 - INFO - codeparrot_training - Step 2563: {'lr': 0.0004971714547110437, 'samples': 1312768, 'steps': 2563, 'batch_loss/train': 0.8803146705031395}
+12/21/2021 23:02:22 - INFO - codeparrot_training - Step 2564: {'lr': 0.0004971690897311042, 'samples': 1313280, 'steps': 2564, 'batch_loss/train': 0.8979310672730207}
+12/21/2021 23:02:33 - INFO - codeparrot_training - Step 2565: {'lr': 0.0004971667237685138, 'samples': 1313792, 'steps': 2565, 'batch_loss/train': 0.895390348508954}
+12/21/2021 23:02:43 - INFO - codeparrot_training - Step 2566: {'lr': 0.0004971643568232818, 'samples': 1314304, 'steps': 2566, 'batch_loss/train': 0.8766223592683673}
+12/21/2021 23:02:54 - INFO - codeparrot_training - Step 2567: {'lr': 0.0004971619888954176, 'samples': 1314816, 'steps': 2567, 'batch_loss/train': 0.7394297434948385}
+12/21/2021 23:03:06 - INFO - codeparrot_training - Step 2568: {'lr': 0.0004971596199849306, 'samples': 1315328, 'steps': 2568, 'batch_loss/train': 0.8700663484632969}
+12/21/2021 23:03:16 - INFO - codeparrot_training - Step 2569: {'lr': 0.0004971572500918304, 'samples': 1315840, 'steps': 2569, 'batch_loss/train': 0.8787068529054523}
+12/21/2021 23:03:27 - INFO - codeparrot_training - Step 2570: {'lr': 0.0004971548792161263, 'samples': 1316352, 'steps': 2570, 'batch_loss/train': 0.8988667586818337}
+12/21/2021 23:03:40 - INFO - codeparrot_training - Step 2571: {'lr': 0.0004971525073578277, 'samples': 1316864, 'steps': 2571, 'batch_loss/train': 0.848110687918961}
+12/21/2021 23:03:50 - INFO - codeparrot_training - Step 2572: {'lr': 0.000497150134516944, 'samples': 1317376, 'steps': 2572, 'batch_loss/train': 0.8512084872927517}
+12/21/2021 23:04:01 - INFO - codeparrot_training - Step 2573: {'lr': 0.0004971477606934847, 'samples': 1317888, 'steps': 2573, 'batch_loss/train': 0.9369232738390565}
+12/21/2021 23:04:13 - INFO - codeparrot_training - Step 2574: {'lr': 0.0004971453858874593, 'samples': 1318400, 'steps': 2574, 'batch_loss/train': 0.8359151147305965}
+12/21/2021 23:04:24 - INFO - codeparrot_training - Step 2575: {'lr': 0.000497143010098877, 'samples': 1318912, 'steps': 2575, 'batch_loss/train': 0.8020782079547644}
+12/21/2021 23:04:34 - INFO - codeparrot_training - Step 2576: {'lr': 0.0004971406333277476, 'samples': 1319424, 'steps': 2576, 'batch_loss/train': 0.9667276088148355}
+12/21/2021 23:04:47 - INFO - codeparrot_training - Step 2577: {'lr': 0.0004971382555740803, 'samples': 1319936, 'steps': 2577, 'batch_loss/train': 0.8350053374888375}
+12/21/2021 23:04:57 - INFO - codeparrot_training - Step 2578: {'lr': 0.0004971358768378845, 'samples': 1320448, 'steps': 2578, 'batch_loss/train': 0.838725158944726}
+12/21/2021 23:05:08 - INFO - codeparrot_training - Step 2579: {'lr': 0.0004971334971191699, 'samples': 1320960, 'steps': 2579, 'batch_loss/train': 0.9367148522287607}
+12/21/2021 23:05:19 - INFO - codeparrot_training - Step 2580: {'lr': 0.0004971311164179458, 'samples': 1321472, 'steps': 2580, 'batch_loss/train': 0.9532340820878744}
+12/21/2021 23:05:31 - INFO - codeparrot_training - Step 2581: {'lr': 0.0004971287347342217, 'samples': 1321984, 'steps': 2581, 'batch_loss/train': 0.9852427393198013}
+12/21/2021 23:05:42 - INFO - codeparrot_training - Step 2582: {'lr': 0.000497126352068007, 'samples': 1322496, 'steps': 2582, 'batch_loss/train': 0.8499576719477773}
+12/21/2021 23:05:52 - INFO - codeparrot_training - Step 2583: {'lr': 0.0004971239684193112, 'samples': 1323008, 'steps': 2583, 'batch_loss/train': 0.8626180618302897}
+12/21/2021 23:06:05 - INFO - codeparrot_training - Step 2584: {'lr': 0.000497121583788144, 'samples': 1323520, 'steps': 2584, 'batch_loss/train': 1.097781540825963}
+12/21/2021 23:06:15 - INFO - codeparrot_training - Step 2585: {'lr': 0.0004971191981745145, 'samples': 1324032, 'steps': 2585, 'batch_loss/train': 0.8322471072897315}
+12/21/2021 23:06:26 - INFO - codeparrot_training - Step 2586: {'lr': 0.0004971168115784324, 'samples': 1324544, 'steps': 2586, 'batch_loss/train': 1.0926132048480213}
+12/21/2021 23:06:38 - INFO - codeparrot_training - Step 2587: {'lr': 0.0004971144239999073, 'samples': 1325056, 'steps': 2587, 'batch_loss/train': 0.8683037227019668}
+12/21/2021 23:06:49 - INFO - codeparrot_training - Step 2588: {'lr': 0.0004971120354389484, 'samples': 1325568, 'steps': 2588, 'batch_loss/train': 0.8266562519129366}
+12/21/2021 23:06:59 - INFO - codeparrot_training - Step 2589: {'lr': 0.0004971096458955655, 'samples': 1326080, 'steps': 2589, 'batch_loss/train': 0.8135174978524446}
+12/21/2021 23:07:10 - INFO - codeparrot_training - Step 2590: {'lr': 0.000497107255369768, 'samples': 1326592, 'steps': 2590, 'batch_loss/train': 0.8550618444569409}
+12/21/2021 23:07:23 - INFO - codeparrot_training - Step 2591: {'lr': 0.0004971048638615651, 'samples': 1327104, 'steps': 2591, 'batch_loss/train': 0.8892005924135447}
+12/21/2021 23:07:34 - INFO - codeparrot_training - Step 2592: {'lr': 0.0004971024713709668, 'samples': 1327616, 'steps': 2592, 'batch_loss/train': 0.815569675527513}
+12/21/2021 23:07:44 - INFO - codeparrot_training - Step 2593: {'lr': 0.0004971000778979822, 'samples': 1328128, 'steps': 2593, 'batch_loss/train': 0.8779277447611094}
+12/21/2021 23:07:56 - INFO - codeparrot_training - Step 2594: {'lr': 0.000497097683442621, 'samples': 1328640, 'steps': 2594, 'batch_loss/train': 0.6797101623378694}
+12/21/2021 23:08:07 - INFO - codeparrot_training - Step 2595: {'lr': 0.0004970952880048929, 'samples': 1329152, 'steps': 2595, 'batch_loss/train': 0.9521017652004957}
+12/21/2021 23:08:17 - INFO - codeparrot_training - Step 2596: {'lr': 0.000497092891584807, 'samples': 1329664, 'steps': 2596, 'batch_loss/train': 0.8435386172495782}
+12/21/2021 23:08:29 - INFO - codeparrot_training - Step 2597: {'lr': 0.0004970904941823732, 'samples': 1330176, 'steps': 2597, 'batch_loss/train': 0.8982730489224195}
+12/21/2021 23:08:40 - INFO - codeparrot_training - Step 2598: {'lr': 0.000497088095797601, 'samples': 1330688, 'steps': 2598, 'batch_loss/train': 0.8791788518428802}
+12/21/2021 23:08:51 - INFO - codeparrot_training - Step 2599: {'lr': 0.0004970856964304996, 'samples': 1331200, 'steps': 2599, 'batch_loss/train': 0.8541745794937015}
+12/21/2021 23:09:01 - INFO - codeparrot_training - Step 2600: {'lr': 0.000497083296081079, 'samples': 1331712, 'steps': 2600, 'batch_loss/train': 0.8430203646421432}
+12/21/2021 23:09:14 - INFO - codeparrot_training - Step 2601: {'lr': 0.0004970808947493483, 'samples': 1332224, 'steps': 2601, 'batch_loss/train': 0.7953534601256251}
+12/21/2021 23:09:25 - INFO - codeparrot_training - Step 2602: {'lr': 0.0004970784924353173, 'samples': 1332736, 'steps': 2602, 'batch_loss/train': 1.0203884337097406}
+12/21/2021 23:09:35 - INFO - codeparrot_training - Step 2603: {'lr': 0.0004970760891389956, 'samples': 1333248, 'steps': 2603, 'batch_loss/train': 0.8180944984778762}
+12/21/2021 23:09:48 - INFO - codeparrot_training - Step 2604: {'lr': 0.0004970736848603926, 'samples': 1333760, 'steps': 2604, 'batch_loss/train': 0.9121229574084282}
+12/21/2021 23:09:58 - INFO - codeparrot_training - Step 2605: {'lr': 0.0004970712795995179, 'samples': 1334272, 'steps': 2605, 'batch_loss/train': 0.8513930896297097}
+12/21/2021 23:10:09 - INFO - codeparrot_training - Step 2606: {'lr': 0.0004970688733563812, 'samples': 1334784, 'steps': 2606, 'batch_loss/train': 0.9241869505494833}
+12/21/2021 23:10:20 - INFO - codeparrot_training - Step 2607: {'lr': 0.0004970664661309918, 'samples': 1335296, 'steps': 2607, 'batch_loss/train': 0.788687966298312}
+12/21/2021 23:10:32 - INFO - codeparrot_training - Step 2608: {'lr': 0.0004970640579233594, 'samples': 1335808, 'steps': 2608, 'batch_loss/train': 0.871890461537987}
+12/21/2021 23:10:43 - INFO - codeparrot_training - Step 2609: {'lr': 0.0004970616487334937, 'samples': 1336320, 'steps': 2609, 'batch_loss/train': 0.8284319383092225}
+12/21/2021 23:10:53 - INFO - codeparrot_training - Step 2610: {'lr': 0.0004970592385614041, 'samples': 1336832, 'steps': 2610, 'batch_loss/train': 0.8617114580702037}
+12/21/2021 23:11:06 - INFO - codeparrot_training - Step 2611: {'lr': 0.0004970568274071004, 'samples': 1337344, 'steps': 2611, 'batch_loss/train': 0.9049709932878613}
+12/21/2021 23:11:16 - INFO - codeparrot_training - Step 2612: {'lr': 0.0004970544152705919, 'samples': 1337856, 'steps': 2612, 'batch_loss/train': 0.832271090708673}
+12/21/2021 23:11:27 - INFO - codeparrot_training - Step 2613: {'lr': 0.0004970520021518884, 'samples': 1338368, 'steps': 2613, 'batch_loss/train': 0.8715925868600607}
+12/21/2021 23:11:39 - INFO - codeparrot_training - Step 2614: {'lr': 0.0004970495880509993, 'samples': 1338880, 'steps': 2614, 'batch_loss/train': 0.978884952608496}
+12/21/2021 23:11:50 - INFO - codeparrot_training - Step 2615: {'lr': 0.0004970471729679345, 'samples': 1339392, 'steps': 2615, 'batch_loss/train': 0.8630227679386735}
+12/21/2021 23:12:00 - INFO - codeparrot_training - Step 2616: {'lr': 0.0004970447569027033, 'samples': 1339904, 'steps': 2616, 'batch_loss/train': 0.9812512015923858}
+12/21/2021 23:12:12 - INFO - codeparrot_training - Step 2617: {'lr': 0.0004970423398553154, 'samples': 1340416, 'steps': 2617, 'batch_loss/train': 0.8890673791756853}
+12/21/2021 23:12:23 - INFO - codeparrot_training - Step 2618: {'lr': 0.0004970399218257805, 'samples': 1340928, 'steps': 2618, 'batch_loss/train': 0.8740392103791237}
+12/21/2021 23:12:33 - INFO - codeparrot_training - Step 2619: {'lr': 0.0004970375028141081, 'samples': 1341440, 'steps': 2619, 'batch_loss/train': 0.9780873656272888}
+12/21/2021 23:12:44 - INFO - codeparrot_training - Step 2620: {'lr': 0.000497035082820308, 'samples': 1341952, 'steps': 2620, 'batch_loss/train': 0.8473696820437908}
+12/21/2021 23:12:57 - INFO - codeparrot_training - Step 2621: {'lr': 0.0004970326618443895, 'samples': 1342464, 'steps': 2621, 'batch_loss/train': 0.9232274442911148}
+12/21/2021 23:13:07 - INFO - codeparrot_training - Step 2622: {'lr': 0.0004970302398863625, 'samples': 1342976, 'steps': 2622, 'batch_loss/train': 0.8577353181317449}
+12/21/2021 23:13:18 - INFO - codeparrot_training - Step 2623: {'lr': 0.0004970278169462366, 'samples': 1343488, 'steps': 2623, 'batch_loss/train': 0.888273099437356}
+12/21/2021 23:13:32 - INFO - codeparrot_training - Step 2624: {'lr': 0.0004970253930240213, 'samples': 1344000, 'steps': 2624, 'batch_loss/train': 0.8390135131776333}
+12/21/2021 23:13:42 - INFO - codeparrot_training - Step 2625: {'lr': 0.0004970229681197264, 'samples': 1344512, 'steps': 2625, 'batch_loss/train': 0.949209351092577}
+12/21/2021 23:13:53 - INFO - codeparrot_training - Step 2626: {'lr': 0.0004970205422333613, 'samples': 1345024, 'steps': 2626, 'batch_loss/train': 0.7938872186932713}
+12/21/2021 23:14:05 - INFO - codeparrot_training - Step 2627: {'lr': 0.0004970181153649359, 'samples': 1345536, 'steps': 2627, 'batch_loss/train': 1.011822747066617}
+12/21/2021 23:14:16 - INFO - codeparrot_training - Step 2628: {'lr': 0.0004970156875144597, 'samples': 1346048, 'steps': 2628, 'batch_loss/train': 0.7088752770796418}
+12/21/2021 23:14:26 - INFO - codeparrot_training - Step 2629: {'lr': 0.0004970132586819424, 'samples': 1346560, 'steps': 2629, 'batch_loss/train': 0.9272313341498375}
+12/21/2021 23:14:38 - INFO - codeparrot_training - Step 2630: {'lr': 0.0004970108288673937, 'samples': 1347072, 'steps': 2630, 'batch_loss/train': 0.8952867351472378}
+12/21/2021 23:14:49 - INFO - codeparrot_training - Step 2631: {'lr': 0.0004970083980708232, 'samples': 1347584, 'steps': 2631, 'batch_loss/train': 0.7968609081581235}
+12/21/2021 23:15:00 - INFO - codeparrot_training - Step 2632: {'lr': 0.0004970059662922406, 'samples': 1348096, 'steps': 2632, 'batch_loss/train': 0.8547662980854511}
+12/21/2021 23:15:10 - INFO - codeparrot_training - Step 2633: {'lr': 0.0004970035335316555, 'samples': 1348608, 'steps': 2633, 'batch_loss/train': 0.9292575269937515}
+12/21/2021 23:15:23 - INFO - codeparrot_training - Step 2634: {'lr': 0.0004970010997890776, 'samples': 1349120, 'steps': 2634, 'batch_loss/train': 0.9456824958324432}
+12/21/2021 23:15:34 - INFO - codeparrot_training - Step 2635: {'lr': 0.0004969986650645166, 'samples': 1349632, 'steps': 2635, 'batch_loss/train': 0.8396728993393481}
+12/21/2021 23:15:45 - INFO - codeparrot_training - Step 2636: {'lr': 0.0004969962293579821, 'samples': 1350144, 'steps': 2636, 'batch_loss/train': 0.8499658210203052}
+12/21/2021 23:15:57 - INFO - codeparrot_training - Step 2637: {'lr': 0.0004969937926694839, 'samples': 1350656, 'steps': 2637, 'batch_loss/train': 0.8127735247835517}
+12/21/2021 23:16:07 - INFO - codeparrot_training - Step 2638: {'lr': 0.0004969913549990317, 'samples': 1351168, 'steps': 2638, 'batch_loss/train': 0.8123251209035516}
+12/21/2021 23:16:18 - INFO - codeparrot_training - Step 2639: {'lr': 0.0004969889163466351, 'samples': 1351680, 'steps': 2639, 'batch_loss/train': 0.9272226132452488}
+12/21/2021 23:16:30 - INFO - codeparrot_training - Step 2640: {'lr': 0.0004969864767123039, 'samples': 1352192, 'steps': 2640, 'batch_loss/train': 0.9494982548058033}
+12/21/2021 23:16:41 - INFO - codeparrot_training - Step 2641: {'lr': 0.0004969840360960477, 'samples': 1352704, 'steps': 2641, 'batch_loss/train': 0.8643590963911265}
+12/21/2021 23:16:52 - INFO - codeparrot_training - Step 2642: {'lr': 0.0004969815944978761, 'samples': 1353216, 'steps': 2642, 'batch_loss/train': 0.9265452940016985}
+12/21/2021 23:17:03 - INFO - codeparrot_training - Step 2643: {'lr': 0.0004969791519177991, 'samples': 1353728, 'steps': 2643, 'batch_loss/train': 0.8339579561725259}
+12/21/2021 23:17:15 - INFO - codeparrot_training - Step 2644: {'lr': 0.0004969767083558262, 'samples': 1354240, 'steps': 2644, 'batch_loss/train': 0.9131715372204781}
+12/21/2021 23:17:25 - INFO - codeparrot_training - Step 2645: {'lr': 0.0004969742638119671, 'samples': 1354752, 'steps': 2645, 'batch_loss/train': 0.8549335254356265}
+12/21/2021 23:17:36 - INFO - codeparrot_training - Step 2646: {'lr': 0.0004969718182862317, 'samples': 1355264, 'steps': 2646, 'batch_loss/train': 0.8345813578926027}
+12/21/2021 23:17:48 - INFO - codeparrot_training - Step 2647: {'lr': 0.0004969693717786295, 'samples': 1355776, 'steps': 2647, 'batch_loss/train': 0.881142670288682}
+12/21/2021 23:17:58 - INFO - codeparrot_training - Step 2648: {'lr': 0.0004969669242891703, 'samples': 1356288, 'steps': 2648, 'batch_loss/train': 0.8633270543068647}
+12/21/2021 23:18:09 - INFO - codeparrot_training - Step 2649: {'lr': 0.0004969644758178639, 'samples': 1356800, 'steps': 2649, 'batch_loss/train': 0.8655777284875512}
+12/21/2021 23:18:22 - INFO - codeparrot_training - Step 2650: {'lr': 0.0004969620263647201, 'samples': 1357312, 'steps': 2650, 'batch_loss/train': 0.8849942591041327}
+12/21/2021 23:18:33 - INFO - codeparrot_training - Step 2651: {'lr': 0.0004969595759297484, 'samples': 1357824, 'steps': 2651, 'batch_loss/train': 0.8167379070073366}
+12/21/2021 23:18:43 - INFO - codeparrot_training - Step 2652: {'lr': 0.0004969571245129587, 'samples': 1358336, 'steps': 2652, 'batch_loss/train': 0.756469989195466}
+12/21/2021 23:18:55 - INFO - codeparrot_training - Step 2653: {'lr': 0.0004969546721143608, 'samples': 1358848, 'steps': 2653, 'batch_loss/train': 0.8799095032736659}
+12/21/2021 23:19:06 - INFO - codeparrot_training - Step 2654: {'lr': 0.0004969522187339643, 'samples': 1359360, 'steps': 2654, 'batch_loss/train': 0.8422023504972458}
+12/21/2021 23:19:16 - INFO - codeparrot_training - Step 2655: {'lr': 0.000496949764371779, 'samples': 1359872, 'steps': 2655, 'batch_loss/train': 0.8282237350940704}
+12/21/2021 23:19:27 - INFO - codeparrot_training - Step 2656: {'lr': 0.0004969473090278147, 'samples': 1360384, 'steps': 2656, 'batch_loss/train': 0.9151206817477942}
+12/21/2021 23:19:39 - INFO - codeparrot_training - Step 2657: {'lr': 0.0004969448527020811, 'samples': 1360896, 'steps': 2657, 'batch_loss/train': 0.832263364456594}
+12/21/2021 23:19:50 - INFO - codeparrot_training - Step 2658: {'lr': 0.0004969423953945881, 'samples': 1361408, 'steps': 2658, 'batch_loss/train': 0.8922028904780746}
+12/21/2021 23:20:00 - INFO - codeparrot_training - Step 2659: {'lr': 0.0004969399371053453, 'samples': 1361920, 'steps': 2659, 'batch_loss/train': 0.6436726925894618}
+12/21/2021 23:20:13 - INFO - codeparrot_training - Step 2660: {'lr': 0.0004969374778343626, 'samples': 1362432, 'steps': 2660, 'batch_loss/train': 0.8898045094683766}
+12/21/2021 23:20:23 - INFO - codeparrot_training - Step 2661: {'lr': 0.0004969350175816497, 'samples': 1362944, 'steps': 2661, 'batch_loss/train': 0.7435582936741412}
+12/21/2021 23:20:34 - INFO - codeparrot_training - Step 2662: {'lr': 0.0004969325563472165, 'samples': 1363456, 'steps': 2662, 'batch_loss/train': 0.7861685073003173}
+12/21/2021 23:20:47 - INFO - codeparrot_training - Step 2663: {'lr': 0.0004969300941310726, 'samples': 1363968, 'steps': 2663, 'batch_loss/train': 0.8314899448305368}
+12/21/2021 23:20:57 - INFO - codeparrot_training - Step 2664: {'lr': 0.000496927630933228, 'samples': 1364480, 'steps': 2664, 'batch_loss/train': 0.8617793517187238}
+12/21/2021 23:21:08 - INFO - codeparrot_training - Step 2665: {'lr': 0.0004969251667536922, 'samples': 1364992, 'steps': 2665, 'batch_loss/train': 1.206850937800482}
+12/21/2021 23:21:19 - INFO - codeparrot_training - Step 2666: {'lr': 0.0004969227015924752, 'samples': 1365504, 'steps': 2666, 'batch_loss/train': 0.8822238245047629}
+12/21/2021 23:21:31 - INFO - codeparrot_training - Step 2667: {'lr': 0.0004969202354495869, 'samples': 1366016, 'steps': 2667, 'batch_loss/train': 0.9446771945804358}
+12/21/2021 23:21:41 - INFO - codeparrot_training - Step 2668: {'lr': 0.0004969177683250369, 'samples': 1366528, 'steps': 2668, 'batch_loss/train': 0.9044107217341661}
+12/21/2021 23:21:52 - INFO - codeparrot_training - Step 2669: {'lr': 0.000496915300218835, 'samples': 1367040, 'steps': 2669, 'batch_loss/train': 1.0803780667483807}
+12/21/2021 23:22:05 - INFO - codeparrot_training - Step 2670: {'lr': 0.0004969128311309912, 'samples': 1367552, 'steps': 2670, 'batch_loss/train': 0.854048520559445}
+12/21/2021 23:22:15 - INFO - codeparrot_training - Step 2671: {'lr': 0.0004969103610615153, 'samples': 1368064, 'steps': 2671, 'batch_loss/train': 0.9085577204823494}
+12/21/2021 23:22:26 - INFO - codeparrot_training - Step 2672: {'lr': 0.0004969078900104168, 'samples': 1368576, 'steps': 2672, 'batch_loss/train': 0.8956662062555552}
+12/21/2021 23:22:37 - INFO - codeparrot_training - Step 2673: {'lr': 0.0004969054179777059, 'samples': 1369088, 'steps': 2673, 'batch_loss/train': 0.8469512620940804}
+12/21/2021 23:22:49 - INFO - codeparrot_training - Step 2674: {'lr': 0.0004969029449633924, 'samples': 1369600, 'steps': 2674, 'batch_loss/train': 0.9123724950477481}
+12/21/2021 23:22:59 - INFO - codeparrot_training - Step 2675: {'lr': 0.0004969004709674858, 'samples': 1370112, 'steps': 2675, 'batch_loss/train': 0.8991649281233549}
+12/21/2021 23:23:10 - INFO - codeparrot_training - Step 2676: {'lr': 0.0004968979959899963, 'samples': 1370624, 'steps': 2676, 'batch_loss/train': 0.9092682749032974}
+12/21/2021 23:23:22 - INFO - codeparrot_training - Step 2677: {'lr': 0.0004968955200309335, 'samples': 1371136, 'steps': 2677, 'batch_loss/train': 0.9461671775206923}
+12/21/2021 23:23:33 - INFO - codeparrot_training - Step 2678: {'lr': 0.0004968930430903075, 'samples': 1371648, 'steps': 2678, 'batch_loss/train': 0.8685863772407174}
+12/21/2021 23:23:43 - INFO - codeparrot_training - Step 2679: {'lr': 0.0004968905651681278, 'samples': 1372160, 'steps': 2679, 'batch_loss/train': 1.840269047766924}
+12/21/2021 23:23:56 - INFO - codeparrot_training - Step 2680: {'lr': 0.0004968880862644045, 'samples': 1372672, 'steps': 2680, 'batch_loss/train': 0.9768112525343895}
+12/21/2021 23:24:07 - INFO - codeparrot_training - Step 2681: {'lr': 0.0004968856063791474, 'samples': 1373184, 'steps': 2681, 'batch_loss/train': 0.8325344668701291}
+12/21/2021 23:24:17 - INFO - codeparrot_training - Step 2682: {'lr': 0.0004968831255123663, 'samples': 1373696, 'steps': 2682, 'batch_loss/train': 0.8481564680114388}
+12/21/2021 23:24:28 - INFO - codeparrot_training - Step 2683: {'lr': 0.0004968806436640712, 'samples': 1374208, 'steps': 2683, 'batch_loss/train': 0.8954875534400344}
+12/21/2021 23:24:40 - INFO - codeparrot_training - Step 2684: {'lr': 0.0004968781608342718, 'samples': 1374720, 'steps': 2684, 'batch_loss/train': 0.9011481814086437}
+12/21/2021 23:24:50 - INFO - codeparrot_training - Step 2685: {'lr': 0.0004968756770229781, 'samples': 1375232, 'steps': 2685, 'batch_loss/train': 0.8864008858799934}
+12/21/2021 23:25:01 - INFO - codeparrot_training - Step 2686: {'lr': 0.0004968731922301999, 'samples': 1375744, 'steps': 2686, 'batch_loss/train': 0.9456286551430821}
+12/21/2021 23:25:13 - INFO - codeparrot_training - Step 2687: {'lr': 0.0004968707064559471, 'samples': 1376256, 'steps': 2687, 'batch_loss/train': 0.879870175383985}
+12/21/2021 23:25:24 - INFO - codeparrot_training - Step 2688: {'lr': 0.0004968682197002295, 'samples': 1376768, 'steps': 2688, 'batch_loss/train': 0.8257661666721106}
+12/21/2021 23:25:34 - INFO - codeparrot_training - Step 2689: {'lr': 0.0004968657319630572, 'samples': 1377280, 'steps': 2689, 'batch_loss/train': 0.9626553459092975}
+12/21/2021 23:25:47 - INFO - codeparrot_training - Step 2690: {'lr': 0.00049686324324444, 'samples': 1377792, 'steps': 2690, 'batch_loss/train': 0.8306416813284159}
+12/21/2021 23:25:57 - INFO - codeparrot_training - Step 2691: {'lr': 0.0004968607535443876, 'samples': 1378304, 'steps': 2691, 'batch_loss/train': 0.926137916278094}
+12/21/2021 23:26:08 - INFO - codeparrot_training - Step 2692: {'lr': 0.0004968582628629102, 'samples': 1378816, 'steps': 2692, 'batch_loss/train': 0.8321814527735114}
+12/21/2021 23:26:20 - INFO - codeparrot_training - Step 2693: {'lr': 0.0004968557712000174, 'samples': 1379328, 'steps': 2693, 'batch_loss/train': 0.8305544788017869}
+12/21/2021 23:26:31 - INFO - codeparrot_training - Step 2694: {'lr': 0.0004968532785557195, 'samples': 1379840, 'steps': 2694, 'batch_loss/train': 0.8677771054208279}
+12/21/2021 23:26:41 - INFO - codeparrot_training - Step 2695: {'lr': 0.000496850784930026, 'samples': 1380352, 'steps': 2695, 'batch_loss/train': 1.101633214391768}
+12/21/2021 23:26:52 - INFO - codeparrot_training - Step 2696: {'lr': 0.000496848290322947, 'samples': 1380864, 'steps': 2696, 'batch_loss/train': 0.8915745439007878}
+12/21/2021 23:27:05 - INFO - codeparrot_training - Step 2697: {'lr': 0.0004968457947344924, 'samples': 1381376, 'steps': 2697, 'batch_loss/train': 1.067648135125637}
+12/21/2021 23:27:15 - INFO - codeparrot_training - Step 2698: {'lr': 0.0004968432981646723, 'samples': 1381888, 'steps': 2698, 'batch_loss/train': 0.8309534005820751}
+12/21/2021 23:27:26 - INFO - codeparrot_training - Step 2699: {'lr': 0.0004968408006134962, 'samples': 1382400, 'steps': 2699, 'batch_loss/train': 0.8716224925592542}
+12/21/2021 23:27:38 - INFO - codeparrot_training - Step 2700: {'lr': 0.0004968383020809744, 'samples': 1382912, 'steps': 2700, 'batch_loss/train': 0.793915051035583}
+12/21/2021 23:27:49 - INFO - codeparrot_training - Step 2701: {'lr': 0.0004968358025671167, 'samples': 1383424, 'steps': 2701, 'batch_loss/train': 0.9377364721149206}
+12/21/2021 23:27:59 - INFO - codeparrot_training - Step 2702: {'lr': 0.000496833302071933, 'samples': 1383936, 'steps': 2702, 'batch_loss/train': 0.8213134435936809}
+12/21/2021 23:28:11 - INFO - codeparrot_training - Step 2703: {'lr': 0.0004968308005954333, 'samples': 1384448, 'steps': 2703, 'batch_loss/train': 0.9814783623442054}
+12/21/2021 23:28:22 - INFO - codeparrot_training - Step 2704: {'lr': 0.0004968282981376276, 'samples': 1384960, 'steps': 2704, 'batch_loss/train': 0.8629418667405844}
+12/21/2021 23:28:32 - INFO - codeparrot_training - Step 2705: {'lr': 0.0004968257946985257, 'samples': 1385472, 'steps': 2705, 'batch_loss/train': 0.8386291197966784}
+12/21/2021 23:28:45 - INFO - codeparrot_training - Step 2706: {'lr': 0.0004968232902781378, 'samples': 1385984, 'steps': 2706, 'batch_loss/train': 0.8490266920998693}
+12/21/2021 23:28:56 - INFO - codeparrot_training - Step 2707: {'lr': 0.0004968207848764735, 'samples': 1386496, 'steps': 2707, 'batch_loss/train': 0.6435901797376573}
+12/21/2021 23:29:06 - INFO - codeparrot_training - Step 2708: {'lr': 0.0004968182784935431, 'samples': 1387008, 'steps': 2708, 'batch_loss/train': 0.9010505508631468}
+12/21/2021 23:29:17 - INFO - codeparrot_training - Step 2709: {'lr': 0.0004968157711293564, 'samples': 1387520, 'steps': 2709, 'batch_loss/train': 0.7711103688925505}
+12/21/2021 23:29:30 - INFO - codeparrot_training - Step 2710: {'lr': 0.0004968132627839233, 'samples': 1388032, 'steps': 2710, 'batch_loss/train': 0.9176118718460202}
+12/21/2021 23:29:40 - INFO - codeparrot_training - Step 2711: {'lr': 0.0004968107534572539, 'samples': 1388544, 'steps': 2711, 'batch_loss/train': 0.8944595092907548}
+12/21/2021 23:29:51 - INFO - codeparrot_training - Step 2712: {'lr': 0.0004968082431493582, 'samples': 1389056, 'steps': 2712, 'batch_loss/train': 0.7738998178392649}
+12/21/2021 23:30:03 - INFO - codeparrot_training - Step 2713: {'lr': 0.000496805731860246, 'samples': 1389568, 'steps': 2713, 'batch_loss/train': 0.8671526871621609}
+12/21/2021 23:30:13 - INFO - codeparrot_training - Step 2714: {'lr': 0.0004968032195899275, 'samples': 1390080, 'steps': 2714, 'batch_loss/train': 0.8038806186523288}
+12/21/2021 23:30:24 - INFO - codeparrot_training - Step 2715: {'lr': 0.0004968007063384126, 'samples': 1390592, 'steps': 2715, 'batch_loss/train': 0.8965359330177307}
+12/21/2021 23:30:36 - INFO - codeparrot_training - Step 2716: {'lr': 0.0004967981921057112, 'samples': 1391104, 'steps': 2716, 'batch_loss/train': 0.8254398126155138}
+12/21/2021 23:30:47 - INFO - codeparrot_training - Step 2717: {'lr': 0.0004967956768918335, 'samples': 1391616, 'steps': 2717, 'batch_loss/train': 0.9515547091141343}
+12/21/2021 23:30:58 - INFO - codeparrot_training - Step 2718: {'lr': 0.0004967931606967892, 'samples': 1392128, 'steps': 2718, 'batch_loss/train': 1.0667793406173587}
+12/21/2021 23:31:08 - INFO - codeparrot_training - Step 2719: {'lr': 0.0004967906435205886, 'samples': 1392640, 'steps': 2719, 'batch_loss/train': 0.8525957148522139}
+12/21/2021 23:31:21 - INFO - codeparrot_training - Step 2720: {'lr': 0.0004967881253632416, 'samples': 1393152, 'steps': 2720, 'batch_loss/train': 0.8748413920402527}
+12/21/2021 23:31:31 - INFO - codeparrot_training - Step 2721: {'lr': 0.0004967856062247581, 'samples': 1393664, 'steps': 2721, 'batch_loss/train': 0.8947004042565823}
+12/21/2021 23:31:42 - INFO - codeparrot_training - Step 2722: {'lr': 0.0004967830861051482, 'samples': 1394176, 'steps': 2722, 'batch_loss/train': 0.8371201138943434}
+12/21/2021 23:31:54 - INFO - codeparrot_training - Step 2723: {'lr': 0.000496780565004422, 'samples': 1394688, 'steps': 2723, 'batch_loss/train': 0.8371166586875916}
+12/21/2021 23:32:05 - INFO - codeparrot_training - Step 2724: {'lr': 0.0004967780429225894, 'samples': 1395200, 'steps': 2724, 'batch_loss/train': 0.7864578813314438}
+12/21/2021 23:32:15 - INFO - codeparrot_training - Step 2725: {'lr': 0.0004967755198596606, 'samples': 1395712, 'steps': 2725, 'batch_loss/train': 0.9323317701928318}
+12/21/2021 23:32:29 - INFO - codeparrot_training - Step 2726: {'lr': 0.0004967729958156455, 'samples': 1396224, 'steps': 2726, 'batch_loss/train': 0.8089192556217313}
+12/21/2021 23:32:40 - INFO - codeparrot_training - Step 2727: {'lr': 0.000496770470790554, 'samples': 1396736, 'steps': 2727, 'batch_loss/train': 1.2252685157582164}
+12/21/2021 23:32:50 - INFO - codeparrot_training - Step 2728: {'lr': 0.0004967679447843964, 'samples': 1397248, 'steps': 2728, 'batch_loss/train': 2.0998979611322284}
+12/21/2021 23:33:01 - INFO - codeparrot_training - Step 2729: {'lr': 0.0004967654177971826, 'samples': 1397760, 'steps': 2729, 'batch_loss/train': 0.8694474725052714}
+12/21/2021 23:33:13 - INFO - codeparrot_training - Step 2730: {'lr': 0.0004967628898289227, 'samples': 1398272, 'steps': 2730, 'batch_loss/train': 0.9039225094020367}
+12/21/2021 23:33:24 - INFO - codeparrot_training - Step 2731: {'lr': 0.0004967603608796266, 'samples': 1398784, 'steps': 2731, 'batch_loss/train': 0.8972703805193305}
+12/21/2021 23:33:34 - INFO - codeparrot_training - Step 2732: {'lr': 0.0004967578309493046, 'samples': 1399296, 'steps': 2732, 'batch_loss/train': 0.8592028999701142}
+12/21/2021 23:33:46 - INFO - codeparrot_training - Step 2733: {'lr': 0.0004967553000379667, 'samples': 1399808, 'steps': 2733, 'batch_loss/train': 0.9384011151269078}
+12/21/2021 23:33:57 - INFO - codeparrot_training - Step 2734: {'lr': 0.0004967527681456228, 'samples': 1400320, 'steps': 2734, 'batch_loss/train': 1.017911254428327}
+12/21/2021 23:34:08 - INFO - codeparrot_training - Step 2735: {'lr': 0.000496750235272283, 'samples': 1400832, 'steps': 2735, 'batch_loss/train': 0.8836188307031989}
+12/21/2021 23:34:20 - INFO - codeparrot_training - Step 2736: {'lr': 0.0004967477014179575, 'samples': 1401344, 'steps': 2736, 'batch_loss/train': 0.8850441165268421}
+12/21/2021 23:34:31 - INFO - codeparrot_training - Step 2737: {'lr': 0.0004967451665826563, 'samples': 1401856, 'steps': 2737, 'batch_loss/train': 0.7825722214765847}
+12/21/2021 23:34:42 - INFO - codeparrot_training - Step 2738: {'lr': 0.0004967426307663895, 'samples': 1402368, 'steps': 2738, 'batch_loss/train': 0.9299429561942816}
+12/21/2021 23:34:54 - INFO - codeparrot_training - Step 2739: {'lr': 0.0004967400939691672, 'samples': 1402880, 'steps': 2739, 'batch_loss/train': 0.8927700808271766}
+12/21/2021 23:35:04 - INFO - codeparrot_training - Step 2740: {'lr': 0.0004967375561909994, 'samples': 1403392, 'steps': 2740, 'batch_loss/train': 0.9150375127792358}
+12/21/2021 23:35:15 - INFO - codeparrot_training - Step 2741: {'lr': 0.0004967350174318963, 'samples': 1403904, 'steps': 2741, 'batch_loss/train': 0.8059806269593537}
+12/21/2021 23:35:25 - INFO - codeparrot_training - Step 2742: {'lr': 0.0004967324776918679, 'samples': 1404416, 'steps': 2742, 'batch_loss/train': 0.7748554176650941}
+12/21/2021 23:35:38 - INFO - codeparrot_training - Step 2743: {'lr': 0.0004967299369709242, 'samples': 1404928, 'steps': 2743, 'batch_loss/train': 0.8595873732119799}
+12/21/2021 23:35:49 - INFO - codeparrot_training - Step 2744: {'lr': 0.0004967273952690756, 'samples': 1405440, 'steps': 2744, 'batch_loss/train': 0.953446839004755}
+12/21/2021 23:36:00 - INFO - codeparrot_training - Step 2745: {'lr': 0.0004967248525863321, 'samples': 1405952, 'steps': 2745, 'batch_loss/train': 0.9198706010356545}
+12/21/2021 23:36:12 - INFO - codeparrot_training - Step 2746: {'lr': 0.0004967223089227035, 'samples': 1406464, 'steps': 2746, 'batch_loss/train': 0.8563555241562426}
+12/21/2021 23:36:22 - INFO - codeparrot_training - Step 2747: {'lr': 0.0004967197642782004, 'samples': 1406976, 'steps': 2747, 'batch_loss/train': 0.8798938356339931}
+12/21/2021 23:36:33 - INFO - codeparrot_training - Step 2748: {'lr': 0.0004967172186528325, 'samples': 1407488, 'steps': 2748, 'batch_loss/train': 0.8090404313988984}
+12/21/2021 23:36:45 - INFO - codeparrot_training - Step 2749: {'lr': 0.0004967146720466103, 'samples': 1408000, 'steps': 2749, 'batch_loss/train': 1.0644350359216332}
+12/21/2021 23:36:56 - INFO - codeparrot_training - Step 2750: {'lr': 0.0004967121244595435, 'samples': 1408512, 'steps': 2750, 'batch_loss/train': 0.8782786931842566}
+12/21/2021 23:37:06 - INFO - codeparrot_training - Step 2751: {'lr': 0.0004967095758916426, 'samples': 1409024, 'steps': 2751, 'batch_loss/train': 0.8194076817017049}
+12/21/2021 23:37:17 - INFO - codeparrot_training - Step 2752: {'lr': 0.0004967070263429174, 'samples': 1409536, 'steps': 2752, 'batch_loss/train': 0.8952427394688129}
+12/21/2021 23:37:29 - INFO - codeparrot_training - Step 2753: {'lr': 0.0004967044758133784, 'samples': 1410048, 'steps': 2753, 'batch_loss/train': 0.984594602137804}
+12/21/2021 23:37:40 - INFO - codeparrot_training - Step 2754: {'lr': 0.0004967019243030355, 'samples': 1410560, 'steps': 2754, 'batch_loss/train': 0.8314443789422512}
+12/21/2021 23:37:50 - INFO - codeparrot_training - Step 2755: {'lr': 0.0004966993718118988, 'samples': 1411072, 'steps': 2755, 'batch_loss/train': 0.8793294029310346}
+12/21/2021 23:38:03 - INFO - codeparrot_training - Step 2756: {'lr': 0.0004966968183399787, 'samples': 1411584, 'steps': 2756, 'batch_loss/train': 0.8368006106466055}
+12/21/2021 23:38:14 - INFO - codeparrot_training - Step 2757: {'lr': 0.0004966942638872851, 'samples': 1412096, 'steps': 2757, 'batch_loss/train': 0.884452068246901}
+12/21/2021 23:38:24 - INFO - codeparrot_training - Step 2758: {'lr': 0.0004966917084538283, 'samples': 1412608, 'steps': 2758, 'batch_loss/train': 0.958603729493916}
+12/21/2021 23:38:36 - INFO - codeparrot_training - Step 2759: {'lr': 0.0004966891520396184, 'samples': 1413120, 'steps': 2759, 'batch_loss/train': 0.8930850634351373}
+12/21/2021 23:38:47 - INFO - codeparrot_training - Step 2760: {'lr': 0.0004966865946446656, 'samples': 1413632, 'steps': 2760, 'batch_loss/train': 0.8794597964733839}
+12/21/2021 23:38:57 - INFO - codeparrot_training - Step 2761: {'lr': 0.0004966840362689801, 'samples': 1414144, 'steps': 2761, 'batch_loss/train': 0.8583412365987897}
+12/21/2021 23:39:08 - INFO - codeparrot_training - Step 2762: {'lr': 0.0004966814769125718, 'samples': 1414656, 'steps': 2762, 'batch_loss/train': 0.9090088084340096}
+12/21/2021 23:39:20 - INFO - codeparrot_training - Step 2763: {'lr': 0.0004966789165754512, 'samples': 1415168, 'steps': 2763, 'batch_loss/train': 0.8443227065727115}
+12/21/2021 23:39:31 - INFO - codeparrot_training - Step 2764: {'lr': 0.0004966763552576285, 'samples': 1415680, 'steps': 2764, 'batch_loss/train': 0.719876506831497}
+12/21/2021 23:39:41 - INFO - codeparrot_training - Step 2765: {'lr': 0.0004966737929591136, 'samples': 1416192, 'steps': 2765, 'batch_loss/train': 0.76170210307464}
+12/21/2021 23:39:54 - INFO - codeparrot_training - Step 2766: {'lr': 0.000496671229679917, 'samples': 1416704, 'steps': 2766, 'batch_loss/train': 0.9373163082636893}
+12/21/2021 23:40:05 - INFO - codeparrot_training - Step 2767: {'lr': 0.0004966686654200486, 'samples': 1417216, 'steps': 2767, 'batch_loss/train': 0.8672814543824643}
+12/21/2021 23:40:15 - INFO - codeparrot_training - Step 2768: {'lr': 0.0004966661001795188, 'samples': 1417728, 'steps': 2768, 'batch_loss/train': 0.9686710042878985}
+12/21/2021 23:40:27 - INFO - codeparrot_training - Step 2769: {'lr': 0.0004966635339583377, 'samples': 1418240, 'steps': 2769, 'batch_loss/train': 0.8428207878023386}
+12/21/2021 23:40:38 - INFO - codeparrot_training - Step 2770: {'lr': 0.0004966609667565154, 'samples': 1418752, 'steps': 2770, 'batch_loss/train': 0.7251744972309098}
+12/21/2021 23:40:49 - INFO - codeparrot_training - Step 2771: {'lr': 0.0004966583985740624, 'samples': 1419264, 'steps': 2771, 'batch_loss/train': 0.8712121639400721}
+12/21/2021 23:40:59 - INFO - codeparrot_training - Step 2772: {'lr': 0.0004966558294109886, 'samples': 1419776, 'steps': 2772, 'batch_loss/train': 0.852354547358118}
+12/21/2021 23:41:11 - INFO - codeparrot_training - Step 2773: {'lr': 0.0004966532592673045, 'samples': 1420288, 'steps': 2773, 'batch_loss/train': 0.7654701012652367}
+12/21/2021 23:41:22 - INFO - codeparrot_training - Step 2774: {'lr': 0.0004966506881430201, 'samples': 1420800, 'steps': 2774, 'batch_loss/train': 0.8304709908552468}
+12/21/2021 23:41:33 - INFO - codeparrot_training - Step 2775: {'lr': 0.0004966481160381456, 'samples': 1421312, 'steps': 2775, 'batch_loss/train': 0.8790553957223892}
+12/21/2021 23:41:45 - INFO - codeparrot_training - Step 2776: {'lr': 0.0004966455429526915, 'samples': 1421824, 'steps': 2776, 'batch_loss/train': 0.7828576392494142}
+12/21/2021 23:41:56 - INFO - codeparrot_training - Step 2777: {'lr': 0.0004966429688866677, 'samples': 1422336, 'steps': 2777, 'batch_loss/train': 0.8534541856497526}
+12/21/2021 23:42:07 - INFO - codeparrot_training - Step 2778: {'lr': 0.0004966403938400847, 'samples': 1422848, 'steps': 2778, 'batch_loss/train': 0.7504670768976212}
+12/21/2021 23:42:19 - INFO - codeparrot_training - Step 2779: {'lr': 0.0004966378178129526, 'samples': 1423360, 'steps': 2779, 'batch_loss/train': 0.8033681497909129}
+12/21/2021 23:42:30 - INFO - codeparrot_training - Step 2780: {'lr': 0.0004966352408052817, 'samples': 1423872, 'steps': 2780, 'batch_loss/train': 0.8164720870554447}
+12/21/2021 23:42:40 - INFO - codeparrot_training - Step 2781: {'lr': 0.000496632662817082, 'samples': 1424384, 'steps': 2781, 'batch_loss/train': 0.8724935334175825}
+12/21/2021 23:42:52 - INFO - codeparrot_training - Step 2782: {'lr': 0.0004966300838483642, 'samples': 1424896, 'steps': 2782, 'batch_loss/train': 0.8145610201172531}
+12/21/2021 23:43:03 - INFO - codeparrot_training - Step 2783: {'lr': 0.0004966275038991382, 'samples': 1425408, 'steps': 2783, 'batch_loss/train': 0.8904623882845044}
+12/21/2021 23:43:14 - INFO - codeparrot_training - Step 2784: {'lr': 0.0004966249229694144, 'samples': 1425920, 'steps': 2784, 'batch_loss/train': 0.8781835101544857}
+12/21/2021 23:43:24 - INFO - codeparrot_training - Step 2785: {'lr': 0.000496622341059203, 'samples': 1426432, 'steps': 2785, 'batch_loss/train': 0.8815981792286038}
+12/21/2021 23:43:37 - INFO - codeparrot_training - Step 2786: {'lr': 0.0004966197581685143, 'samples': 1426944, 'steps': 2786, 'batch_loss/train': 0.8855038192123175}
+12/21/2021 23:43:48 - INFO - codeparrot_training - Step 2787: {'lr': 0.0004966171742973585, 'samples': 1427456, 'steps': 2787, 'batch_loss/train': 0.8718706956133246}
+12/21/2021 23:43:58 - INFO - codeparrot_training - Step 2788: {'lr': 0.000496614589445746, 'samples': 1427968, 'steps': 2788, 'batch_loss/train': 0.9071602299809456}
+12/21/2021 23:44:10 - INFO - codeparrot_training - Step 2789: {'lr': 0.000496612003613687, 'samples': 1428480, 'steps': 2789, 'batch_loss/train': 0.8452225644141436}
+12/21/2021 23:44:21 - INFO - codeparrot_training - Step 2790: {'lr': 0.0004966094168011918, 'samples': 1428992, 'steps': 2790, 'batch_loss/train': 0.8973483853042126}
+12/21/2021 23:44:32 - INFO - codeparrot_training - Step 2791: {'lr': 0.0004966068290082708, 'samples': 1429504, 'steps': 2791, 'batch_loss/train': 0.7372503913938999}
+12/21/2021 23:44:44 - INFO - codeparrot_training - Step 2792: {'lr': 0.000496604240234934, 'samples': 1430016, 'steps': 2792, 'batch_loss/train': 0.8342458037659526}
+12/21/2021 23:44:54 - INFO - codeparrot_training - Step 2793: {'lr': 0.0004966016504811919, 'samples': 1430528, 'steps': 2793, 'batch_loss/train': 0.8195690996944904}
+12/21/2021 23:45:05 - INFO - codeparrot_training - Step 2794: {'lr': 0.0004965990597470548, 'samples': 1431040, 'steps': 2794, 'batch_loss/train': 0.8199907764792442}
+12/21/2021 23:45:16 - INFO - codeparrot_training - Step 2795: {'lr': 0.0004965964680325328, 'samples': 1431552, 'steps': 2795, 'batch_loss/train': 0.8460550783202052}
+12/21/2021 23:45:28 - INFO - codeparrot_training - Step 2796: {'lr': 0.0004965938753376365, 'samples': 1432064, 'steps': 2796, 'batch_loss/train': 0.9620615616440773}
+12/21/2021 23:45:39 - INFO - codeparrot_training - Step 2797: {'lr': 0.000496591281662376, 'samples': 1432576, 'steps': 2797, 'batch_loss/train': 0.8256391501054168}
+12/21/2021 23:45:50 - INFO - codeparrot_training - Step 2798: {'lr': 0.0004965886870067617, 'samples': 1433088, 'steps': 2798, 'batch_loss/train': 0.7301017369609326}
+12/21/2021 23:46:02 - INFO - codeparrot_training - Step 2799: {'lr': 0.0004965860913708039, 'samples': 1433600, 'steps': 2799, 'batch_loss/train': 0.8490456156432629}
+12/21/2021 23:46:12 - INFO - codeparrot_training - Step 2800: {'lr': 0.0004965834947545128, 'samples': 1434112, 'steps': 2800, 'batch_loss/train': 0.9143759487196803}
+12/21/2021 23:46:23 - INFO - codeparrot_training - Step 2801: {'lr': 0.000496580897157899, 'samples': 1434624, 'steps': 2801, 'batch_loss/train': 0.8197619970887899}
+12/21/2021 23:46:36 - INFO - codeparrot_training - Step 2802: {'lr': 0.0004965782985809726, 'samples': 1435136, 'steps': 2802, 'batch_loss/train': 0.8713466441258788}
+12/21/2021 23:46:46 - INFO - codeparrot_training - Step 2803: {'lr': 0.0004965756990237439, 'samples': 1435648, 'steps': 2803, 'batch_loss/train': 0.9801749223843217}
+12/21/2021 23:46:57 - INFO - codeparrot_training - Step 2804: {'lr': 0.0004965730984862233, 'samples': 1436160, 'steps': 2804, 'batch_loss/train': 0.8587969169020653}
+12/21/2021 23:47:07 - INFO - codeparrot_training - Step 2805: {'lr': 0.0004965704969684213, 'samples': 1436672, 'steps': 2805, 'batch_loss/train': 0.8538382276892662}
+12/21/2021 23:47:19 - INFO - codeparrot_training - Step 2806: {'lr': 0.0004965678944703481, 'samples': 1437184, 'steps': 2806, 'batch_loss/train': 0.9124665325507522}
+12/21/2021 23:47:30 - INFO - codeparrot_training - Step 2807: {'lr': 0.0004965652909920139, 'samples': 1437696, 'steps': 2807, 'batch_loss/train': 0.8945768615230918}
+12/21/2021 23:47:41 - INFO - codeparrot_training - Step 2808: {'lr': 0.0004965626865334294, 'samples': 1438208, 'steps': 2808, 'batch_loss/train': 0.9108815314248204}
+12/21/2021 23:47:53 - INFO - codeparrot_training - Step 2809: {'lr': 0.0004965600810946047, 'samples': 1438720, 'steps': 2809, 'batch_loss/train': 0.9295633239671588}
+12/21/2021 23:48:03 - INFO - codeparrot_training - Step 2810: {'lr': 0.0004965574746755502, 'samples': 1439232, 'steps': 2810, 'batch_loss/train': 0.9038051944226027}
+12/21/2021 23:48:14 - INFO - codeparrot_training - Step 2811: {'lr': 0.0004965548672762761, 'samples': 1439744, 'steps': 2811, 'batch_loss/train': 0.8813595036044717}
+12/21/2021 23:48:27 - INFO - codeparrot_training - Step 2812: {'lr': 0.0004965522588967933, 'samples': 1440256, 'steps': 2812, 'batch_loss/train': 0.8693674448877573}
+12/21/2021 23:48:37 - INFO - codeparrot_training - Step 2813: {'lr': 0.0004965496495371115, 'samples': 1440768, 'steps': 2813, 'batch_loss/train': 0.854512601159513}
+12/21/2021 23:48:48 - INFO - codeparrot_training - Step 2814: {'lr': 0.0004965470391972416, 'samples': 1441280, 'steps': 2814, 'batch_loss/train': 0.8857122138142586}
+12/21/2021 23:49:00 - INFO - codeparrot_training - Step 2815: {'lr': 0.0004965444278771936, 'samples': 1441792, 'steps': 2815, 'batch_loss/train': 0.9771657353267074}
+12/21/2021 23:49:11 - INFO - codeparrot_training - Step 2816: {'lr': 0.0004965418155769781, 'samples': 1442304, 'steps': 2816, 'batch_loss/train': 0.8739115702919662}
+12/21/2021 23:49:21 - INFO - codeparrot_training - Step 2817: {'lr': 0.0004965392022966054, 'samples': 1442816, 'steps': 2817, 'batch_loss/train': 0.916544396430254}
+12/21/2021 23:49:32 - INFO - codeparrot_training - Step 2818: {'lr': 0.0004965365880360861, 'samples': 1443328, 'steps': 2818, 'batch_loss/train': 0.8176784424576908}
+12/21/2021 23:49:44 - INFO - codeparrot_training - Step 2819: {'lr': 0.0004965339727954302, 'samples': 1443840, 'steps': 2819, 'batch_loss/train': 0.7750601591542363}
+12/21/2021 23:49:55 - INFO - codeparrot_training - Step 2820: {'lr': 0.0004965313565746484, 'samples': 1444352, 'steps': 2820, 'batch_loss/train': 0.9488355049397796}
+12/21/2021 23:50:05 - INFO - codeparrot_training - Step 2821: {'lr': 0.000496528739373751, 'samples': 1444864, 'steps': 2821, 'batch_loss/train': 0.7964668245986104}
+12/21/2021 23:50:17 - INFO - codeparrot_training - Step 2822: {'lr': 0.0004965261211927484, 'samples': 1445376, 'steps': 2822, 'batch_loss/train': 0.9484735019505024}
+12/21/2021 23:50:28 - INFO - codeparrot_training - Step 2823: {'lr': 0.0004965235020316511, 'samples': 1445888, 'steps': 2823, 'batch_loss/train': 0.7780307899229228}
+12/21/2021 23:50:39 - INFO - codeparrot_training - Step 2824: {'lr': 0.0004965208818904694, 'samples': 1446400, 'steps': 2824, 'batch_loss/train': 0.7593808164820075}
+12/21/2021 23:50:52 - INFO - codeparrot_training - Step 2825: {'lr': 0.0004965182607692137, 'samples': 1446912, 'steps': 2825, 'batch_loss/train': 1.2515212474390864}
+12/21/2021 23:51:02 - INFO - codeparrot_training - Step 2826: {'lr': 0.0004965156386678945, 'samples': 1447424, 'steps': 2826, 'batch_loss/train': 0.8807951798662543}
+12/21/2021 23:51:13 - INFO - codeparrot_training - Step 2827: {'lr': 0.0004965130155865223, 'samples': 1447936, 'steps': 2827, 'batch_loss/train': 0.8640672229230404}
+12/21/2021 23:51:23 - INFO - codeparrot_training - Step 2828: {'lr': 0.0004965103915251073, 'samples': 1448448, 'steps': 2828, 'batch_loss/train': 0.9924935344606638}
+12/21/2021 23:51:36 - INFO - codeparrot_training - Step 2829: {'lr': 0.0004965077664836602, 'samples': 1448960, 'steps': 2829, 'batch_loss/train': 0.8473209850490093}
+12/21/2021 23:51:46 - INFO - codeparrot_training - Step 2830: {'lr': 0.0004965051404621911, 'samples': 1449472, 'steps': 2830, 'batch_loss/train': 0.8569857375696301}
+12/21/2021 23:51:57 - INFO - codeparrot_training - Step 2831: {'lr': 0.0004965025134607107, 'samples': 1449984, 'steps': 2831, 'batch_loss/train': 0.8988811438903213}
+12/21/2021 23:52:09 - INFO - codeparrot_training - Step 2832: {'lr': 0.0004964998854792295, 'samples': 1450496, 'steps': 2832, 'batch_loss/train': 0.84225017670542}
+12/21/2021 23:52:20 - INFO - codeparrot_training - Step 2833: {'lr': 0.0004964972565177578, 'samples': 1451008, 'steps': 2833, 'batch_loss/train': 0.9077969556674361}
+12/21/2021 23:52:30 - INFO - codeparrot_training - Step 2834: {'lr': 0.000496494626576306, 'samples': 1451520, 'steps': 2834, 'batch_loss/train': 0.9489975296892226}
+12/21/2021 23:52:43 - INFO - codeparrot_training - Step 2835: {'lr': 0.0004964919956548847, 'samples': 1452032, 'steps': 2835, 'batch_loss/train': 0.8240236695855856}
+12/21/2021 23:52:54 - INFO - codeparrot_training - Step 2836: {'lr': 0.0004964893637535043, 'samples': 1452544, 'steps': 2836, 'batch_loss/train': 0.9654202740639448}
+12/21/2021 23:53:04 - INFO - codeparrot_training - Step 2837: {'lr': 0.0004964867308721753, 'samples': 1453056, 'steps': 2837, 'batch_loss/train': 0.852312111761421}
+12/21/2021 23:53:15 - INFO - codeparrot_training - Step 2838: {'lr': 0.000496484097010908, 'samples': 1453568, 'steps': 2838, 'batch_loss/train': 0.8109756391495466}
+12/21/2021 23:53:27 - INFO - codeparrot_training - Step 2839: {'lr': 0.000496481462169713, 'samples': 1454080, 'steps': 2839, 'batch_loss/train': 0.8806477729231119}
+12/21/2021 23:53:38 - INFO - codeparrot_training - Step 2840: {'lr': 0.0004964788263486008, 'samples': 1454592, 'steps': 2840, 'batch_loss/train': 0.8800964802503586}
+12/21/2021 23:53:48 - INFO - codeparrot_training - Step 2841: {'lr': 0.000496476189547582, 'samples': 1455104, 'steps': 2841, 'batch_loss/train': 0.9086245694197714}
+12/21/2021 23:54:01 - INFO - codeparrot_training - Step 2842: {'lr': 0.0004964735517666668, 'samples': 1455616, 'steps': 2842, 'batch_loss/train': 0.8611039528623223}
+12/21/2021 23:54:12 - INFO - codeparrot_training - Step 2843: {'lr': 0.0004964709130058658, 'samples': 1456128, 'steps': 2843, 'batch_loss/train': 0.885093062184751}
+12/21/2021 23:54:22 - INFO - codeparrot_training - Step 2844: {'lr': 0.0004964682732651896, 'samples': 1456640, 'steps': 2844, 'batch_loss/train': 0.9418956665322185}
+12/21/2021 23:54:34 - INFO - codeparrot_training - Step 2845: {'lr': 0.0004964656325446486, 'samples': 1457152, 'steps': 2845, 'batch_loss/train': 0.8936934070661664}
+12/21/2021 23:54:45 - INFO - codeparrot_training - Step 2846: {'lr': 0.0004964629908442532, 'samples': 1457664, 'steps': 2846, 'batch_loss/train': 0.8727347794920206}
+12/21/2021 23:54:55 - INFO - codeparrot_training - Step 2847: {'lr': 0.0004964603481640142, 'samples': 1458176, 'steps': 2847, 'batch_loss/train': 0.9256553370505571}
+12/21/2021 23:55:07 - INFO - codeparrot_training - Step 2848: {'lr': 0.0004964577045039418, 'samples': 1458688, 'steps': 2848, 'batch_loss/train': 0.9007095694541931}
+12/21/2021 23:55:18 - INFO - codeparrot_training - Step 2849: {'lr': 0.0004964550598640466, 'samples': 1459200, 'steps': 2849, 'batch_loss/train': 0.9398393807932734}
+12/21/2021 23:55:29 - INFO - codeparrot_training - Step 2850: {'lr': 0.0004964524142443392, 'samples': 1459712, 'steps': 2850, 'batch_loss/train': 0.8468107334338129}
+12/21/2021 23:55:39 - INFO - codeparrot_training - Step 2851: {'lr': 0.0004964497676448301, 'samples': 1460224, 'steps': 2851, 'batch_loss/train': 0.9058442609384656}
+12/21/2021 23:55:52 - INFO - codeparrot_training - Step 2852: {'lr': 0.0004964471200655296, 'samples': 1460736, 'steps': 2852, 'batch_loss/train': 0.8936695717275143}
+12/21/2021 23:56:03 - INFO - codeparrot_training - Step 2853: {'lr': 0.0004964444715064485, 'samples': 1461248, 'steps': 2853, 'batch_loss/train': 0.8698366414755583}
+12/21/2021 23:56:13 - INFO - codeparrot_training - Step 2854: {'lr': 0.0004964418219675973, 'samples': 1461760, 'steps': 2854, 'batch_loss/train': 0.8841481376439333}
+12/21/2021 23:56:26 - INFO - codeparrot_training - Step 2855: {'lr': 0.0004964391714489864, 'samples': 1462272, 'steps': 2855, 'batch_loss/train': 0.9602138102054596}
+12/21/2021 23:56:37 - INFO - codeparrot_training - Step 2856: {'lr': 0.0004964365199506264, 'samples': 1462784, 'steps': 2856, 'batch_loss/train': 1.2038272619247437}
+12/21/2021 23:56:47 - INFO - codeparrot_training - Step 2857: {'lr': 0.000496433867472528, 'samples': 1463296, 'steps': 2857, 'batch_loss/train': 1.0564644867554307}
+12/21/2021 23:56:58 - INFO - codeparrot_training - Step 2858: {'lr': 0.0004964312140147013, 'samples': 1463808, 'steps': 2858, 'batch_loss/train': 0.9190641529858112}
+12/21/2021 23:57:10 - INFO - codeparrot_training - Step 2859: {'lr': 0.0004964285595771573, 'samples': 1464320, 'steps': 2859, 'batch_loss/train': 0.8868136648088694}
+12/21/2021 23:57:21 - INFO - codeparrot_training - Step 2860: {'lr': 0.0004964259041599066, 'samples': 1464832, 'steps': 2860, 'batch_loss/train': 0.8466164115816355}
+12/21/2021 23:57:31 - INFO - codeparrot_training - Step 2861: {'lr': 0.0004964232477629593, 'samples': 1465344, 'steps': 2861, 'batch_loss/train': 0.7719985288567841}
+12/21/2021 23:57:45 - INFO - codeparrot_training - Step 2862: {'lr': 0.0004964205903863262, 'samples': 1465856, 'steps': 2862, 'batch_loss/train': 0.915548182092607}
+12/21/2021 23:57:55 - INFO - codeparrot_training - Step 2863: {'lr': 0.0004964179320300179, 'samples': 1466368, 'steps': 2863, 'batch_loss/train': 0.8909932738170028}
+12/21/2021 23:58:06 - INFO - codeparrot_training - Step 2864: {'lr': 0.000496415272694045, 'samples': 1466880, 'steps': 2864, 'batch_loss/train': 0.765384775120765}
+12/21/2021 23:58:18 - INFO - codeparrot_training - Step 2865: {'lr': 0.000496412612378418, 'samples': 1467392, 'steps': 2865, 'batch_loss/train': 0.8376013990491629}
+12/21/2021 23:58:29 - INFO - codeparrot_training - Step 2866: {'lr': 0.0004964099510831475, 'samples': 1467904, 'steps': 2866, 'batch_loss/train': 0.8705869084224105}
+12/21/2021 23:58:39 - INFO - codeparrot_training - Step 2867: {'lr': 0.0004964072888082442, 'samples': 1468416, 'steps': 2867, 'batch_loss/train': 0.9318092977628112}
+12/21/2021 23:58:50 - INFO - codeparrot_training - Step 2868: {'lr': 0.0004964046255537184, 'samples': 1468928, 'steps': 2868, 'batch_loss/train': 0.8997740289196372}
+12/21/2021 23:59:02 - INFO - codeparrot_training - Step 2869: {'lr': 0.000496401961319581, 'samples': 1469440, 'steps': 2869, 'batch_loss/train': 1.031172463670373}
+12/21/2021 23:59:13 - INFO - codeparrot_training - Step 2870: {'lr': 0.0004963992961058422, 'samples': 1469952, 'steps': 2870, 'batch_loss/train': 0.8672622283920646}
+12/21/2021 23:59:23 - INFO - codeparrot_training - Step 2871: {'lr': 0.000496396629912513, 'samples': 1470464, 'steps': 2871, 'batch_loss/train': 1.049331195652485}
+12/21/2021 23:59:36 - INFO - codeparrot_training - Step 2872: {'lr': 0.0004963939627396038, 'samples': 1470976, 'steps': 2872, 'batch_loss/train': 1.3430225565098226}
+12/21/2021 23:59:47 - INFO - codeparrot_training - Step 2873: {'lr': 0.0004963912945871252, 'samples': 1471488, 'steps': 2873, 'batch_loss/train': 0.8312508948147297}
+12/21/2021 23:59:57 - INFO - codeparrot_training - Step 2874: {'lr': 0.0004963886254550878, 'samples': 1472000, 'steps': 2874, 'batch_loss/train': 0.8993829181417823}
+12/22/2021 00:00:09 - INFO - codeparrot_training - Step 2875: {'lr': 0.0004963859553435025, 'samples': 1472512, 'steps': 2875, 'batch_loss/train': 0.8733553243800998}
+12/22/2021 00:00:20 - INFO - codeparrot_training - Step 2876: {'lr': 0.0004963832842523794, 'samples': 1473024, 'steps': 2876, 'batch_loss/train': 0.9229561807587743}
+12/22/2021 00:00:31 - INFO - codeparrot_training - Step 2877: {'lr': 0.0004963806121817296, 'samples': 1473536, 'steps': 2877, 'batch_loss/train': 0.8684650948271155}
+12/22/2021 00:00:41 - INFO - codeparrot_training - Step 2878: {'lr': 0.0004963779391315634, 'samples': 1474048, 'steps': 2878, 'batch_loss/train': 0.929153410717845}
+12/22/2021 00:00:54 - INFO - codeparrot_training - Step 2879: {'lr': 0.0004963752651018916, 'samples': 1474560, 'steps': 2879, 'batch_loss/train': 0.9285211749374866}
+12/22/2021 00:01:04 - INFO - codeparrot_training - Step 2880: {'lr': 0.0004963725900927247, 'samples': 1475072, 'steps': 2880, 'batch_loss/train': 0.9373218063265085}
+12/22/2021 00:01:15 - INFO - codeparrot_training - Step 2881: {'lr': 0.0004963699141040734, 'samples': 1475584, 'steps': 2881, 'batch_loss/train': 0.7236965104239061}
+12/22/2021 00:01:28 - INFO - codeparrot_training - Step 2882: {'lr': 0.0004963672371359484, 'samples': 1476096, 'steps': 2882, 'batch_loss/train': 0.9335309453308582}
+12/22/2021 00:01:38 - INFO - codeparrot_training - Step 2883: {'lr': 0.0004963645591883603, 'samples': 1476608, 'steps': 2883, 'batch_loss/train': 0.9433216033503413}
+12/22/2021 00:01:49 - INFO - codeparrot_training - Step 2884: {'lr': 0.0004963618802613197, 'samples': 1477120, 'steps': 2884, 'batch_loss/train': 1.0087015088647604}
+12/22/2021 00:02:01 - INFO - codeparrot_training - Step 2885: {'lr': 0.0004963592003548374, 'samples': 1477632, 'steps': 2885, 'batch_loss/train': 0.6383123500272632}
+12/22/2021 00:02:12 - INFO - codeparrot_training - Step 2886: {'lr': 0.0004963565194689238, 'samples': 1478144, 'steps': 2886, 'batch_loss/train': 0.8915530694648623}
+12/22/2021 00:02:22 - INFO - codeparrot_training - Step 2887: {'lr': 0.0004963538376035897, 'samples': 1478656, 'steps': 2887, 'batch_loss/train': 0.8105394979938865}
+12/22/2021 00:02:34 - INFO - codeparrot_training - Step 2888: {'lr': 0.0004963511547588458, 'samples': 1479168, 'steps': 2888, 'batch_loss/train': 0.9146529901772738}
+12/22/2021 00:02:45 - INFO - codeparrot_training - Step 2889: {'lr': 0.0004963484709347028, 'samples': 1479680, 'steps': 2889, 'batch_loss/train': 0.9707105793058872}
+12/22/2021 00:02:56 - INFO - codeparrot_training - Step 2890: {'lr': 0.0004963457861311713, 'samples': 1480192, 'steps': 2890, 'batch_loss/train': 0.7517307370435447}
+12/22/2021 00:03:06 - INFO - codeparrot_training - Step 2891: {'lr': 0.0004963431003482618, 'samples': 1480704, 'steps': 2891, 'batch_loss/train': 0.8765983311459422}
+12/22/2021 00:03:19 - INFO - codeparrot_training - Step 2892: {'lr': 0.0004963404135859853, 'samples': 1481216, 'steps': 2892, 'batch_loss/train': 0.7453456418588758}
+12/22/2021 00:03:30 - INFO - codeparrot_training - Step 2893: {'lr': 0.0004963377258443522, 'samples': 1481728, 'steps': 2893, 'batch_loss/train': 0.9584305575117469}
+12/22/2021 00:03:40 - INFO - codeparrot_training - Step 2894: {'lr': 0.0004963350371233735, 'samples': 1482240, 'steps': 2894, 'batch_loss/train': 0.8540538772940636}
+12/22/2021 00:03:53 - INFO - codeparrot_training - Step 2895: {'lr': 0.0004963323474230596, 'samples': 1482752, 'steps': 2895, 'batch_loss/train': 0.8443974177353084}
+12/22/2021 00:04:03 - INFO - codeparrot_training - Step 2896: {'lr': 0.0004963296567434213, 'samples': 1483264, 'steps': 2896, 'batch_loss/train': 0.800471568480134}
+12/22/2021 00:04:14 - INFO - codeparrot_training - Step 2897: {'lr': 0.0004963269650844692, 'samples': 1483776, 'steps': 2897, 'batch_loss/train': 0.8654970473144203}
+12/22/2021 00:04:27 - INFO - codeparrot_training - Step 2898: {'lr': 0.0004963242724462143, 'samples': 1484288, 'steps': 2898, 'batch_loss/train': 0.8327738051302731}
+12/22/2021 00:04:37 - INFO - codeparrot_training - Step 2899: {'lr': 0.0004963215788286669, 'samples': 1484800, 'steps': 2899, 'batch_loss/train': 0.8541070362553}
+12/22/2021 00:04:48 - INFO - codeparrot_training - Step 2900: {'lr': 0.0004963188842318381, 'samples': 1485312, 'steps': 2900, 'batch_loss/train': 0.8433470204472542}
+12/22/2021 00:04:59 - INFO - codeparrot_training - Step 2901: {'lr': 0.0004963161886557383, 'samples': 1485824, 'steps': 2901, 'batch_loss/train': 0.8325515834148973}
+12/22/2021 00:05:11 - INFO - codeparrot_training - Step 2902: {'lr': 0.0004963134921003783, 'samples': 1486336, 'steps': 2902, 'batch_loss/train': 0.9418292930349708}
+12/22/2021 00:05:21 - INFO - codeparrot_training - Step 2903: {'lr': 0.0004963107945657689, 'samples': 1486848, 'steps': 2903, 'batch_loss/train': 0.7670798851177096}
+12/22/2021 00:05:32 - INFO - codeparrot_training - Step 2904: {'lr': 0.0004963080960519209, 'samples': 1487360, 'steps': 2904, 'batch_loss/train': 0.8767623296007514}
+12/22/2021 00:05:44 - INFO - codeparrot_training - Step 2905: {'lr': 0.0004963053965588447, 'samples': 1487872, 'steps': 2905, 'batch_loss/train': 0.9281723168678582}
+12/22/2021 00:05:54 - INFO - codeparrot_training - Step 2906: {'lr': 0.0004963026960865515, 'samples': 1488384, 'steps': 2906, 'batch_loss/train': 0.8888087114319205}
+12/22/2021 00:06:05 - INFO - codeparrot_training - Step 2907: {'lr': 0.0004962999946350516, 'samples': 1488896, 'steps': 2907, 'batch_loss/train': 0.8760175798088312}
+12/22/2021 00:06:17 - INFO - codeparrot_training - Step 2908: {'lr': 0.0004962972922043559, 'samples': 1489408, 'steps': 2908, 'batch_loss/train': 0.9299073615111411}
+12/22/2021 00:06:28 - INFO - codeparrot_training - Step 2909: {'lr': 0.0004962945887944753, 'samples': 1489920, 'steps': 2909, 'batch_loss/train': 0.7910862183198333}
+12/22/2021 00:06:39 - INFO - codeparrot_training - Step 2910: {'lr': 0.0004962918844054204, 'samples': 1490432, 'steps': 2910, 'batch_loss/train': 0.872055065818131}
+12/22/2021 00:06:49 - INFO - codeparrot_training - Step 2911: {'lr': 0.0004962891790372019, 'samples': 1490944, 'steps': 2911, 'batch_loss/train': 0.8696145731955767}
+12/22/2021 00:07:02 - INFO - codeparrot_training - Step 2912: {'lr': 0.0004962864726898306, 'samples': 1491456, 'steps': 2912, 'batch_loss/train': 0.8794516469351947}
+12/22/2021 00:07:13 - INFO - codeparrot_training - Step 2913: {'lr': 0.0004962837653633174, 'samples': 1491968, 'steps': 2913, 'batch_loss/train': 0.7723189720418304}
+12/22/2021 00:07:23 - INFO - codeparrot_training - Step 2914: {'lr': 0.0004962810570576727, 'samples': 1492480, 'steps': 2914, 'batch_loss/train': 0.9134014174342155}
+12/22/2021 00:07:35 - INFO - codeparrot_training - Step 2915: {'lr': 0.0004962783477729076, 'samples': 1492992, 'steps': 2915, 'batch_loss/train': 0.8580280332826078}
+12/22/2021 00:07:46 - INFO - codeparrot_training - Step 2916: {'lr': 0.0004962756375090329, 'samples': 1493504, 'steps': 2916, 'batch_loss/train': 0.832851410843432}
+12/22/2021 00:07:57 - INFO - codeparrot_training - Step 2917: {'lr': 0.0004962729262660593, 'samples': 1494016, 'steps': 2917, 'batch_loss/train': 1.0168451061472297}
+12/22/2021 00:08:09 - INFO - codeparrot_training - Step 2918: {'lr': 0.0004962702140439973, 'samples': 1494528, 'steps': 2918, 'batch_loss/train': 0.852037301287055}
+12/22/2021 00:08:19 - INFO - codeparrot_training - Step 2919: {'lr': 0.0004962675008428581, 'samples': 1495040, 'steps': 2919, 'batch_loss/train': 0.8455076892860234}
+12/22/2021 00:08:30 - INFO - codeparrot_training - Step 2920: {'lr': 0.0004962647866626523, 'samples': 1495552, 'steps': 2920, 'batch_loss/train': 0.871443840675056}
+12/22/2021 00:08:42 - INFO - codeparrot_training - Step 2921: {'lr': 0.0004962620715033906, 'samples': 1496064, 'steps': 2921, 'batch_loss/train': 0.7829725155606866}
+12/22/2021 00:08:53 - INFO - codeparrot_training - Step 2922: {'lr': 0.0004962593553650839, 'samples': 1496576, 'steps': 2922, 'batch_loss/train': 0.8813907615840435}
+12/22/2021 00:09:04 - INFO - codeparrot_training - Step 2923: {'lr': 0.000496256638247743, 'samples': 1497088, 'steps': 2923, 'batch_loss/train': 0.8756352197378874}
+12/22/2021 00:09:14 - INFO - codeparrot_training - Step 2924: {'lr': 0.0004962539201513787, 'samples': 1497600, 'steps': 2924, 'batch_loss/train': 0.8332637073472142}
+12/22/2021 00:09:27 - INFO - codeparrot_training - Step 2925: {'lr': 0.0004962512010760018, 'samples': 1498112, 'steps': 2925, 'batch_loss/train': 0.8550588954240084}
+12/22/2021 00:09:38 - INFO - codeparrot_training - Step 2926: {'lr': 0.0004962484810216232, 'samples': 1498624, 'steps': 2926, 'batch_loss/train': 0.8066789982840419}
+12/22/2021 00:09:48 - INFO - codeparrot_training - Step 2927: {'lr': 0.0004962457599882535, 'samples': 1499136, 'steps': 2927, 'batch_loss/train': 0.7762155579403043}
+12/22/2021 00:10:01 - INFO - codeparrot_training - Step 2928: {'lr': 0.0004962430379759036, 'samples': 1499648, 'steps': 2928, 'batch_loss/train': 0.8517991006374359}
+12/22/2021 00:10:12 - INFO - codeparrot_training - Step 2929: {'lr': 0.0004962403149845844, 'samples': 1500160, 'steps': 2929, 'batch_loss/train': 0.786177865229547}
+12/22/2021 00:10:22 - INFO - codeparrot_training - Step 2930: {'lr': 0.0004962375910143068, 'samples': 1500672, 'steps': 2930, 'batch_loss/train': 0.7200079159811139}
+12/22/2021 00:10:34 - INFO - codeparrot_training - Step 2931: {'lr': 0.0004962348660650814, 'samples': 1501184, 'steps': 2931, 'batch_loss/train': 0.8562792930752039}
+12/22/2021 00:10:45 - INFO - codeparrot_training - Step 2932: {'lr': 0.0004962321401369192, 'samples': 1501696, 'steps': 2932, 'batch_loss/train': 0.8072061110287905}
+12/22/2021 00:10:56 - INFO - codeparrot_training - Step 2933: {'lr': 0.0004962294132298309, 'samples': 1502208, 'steps': 2933, 'batch_loss/train': 0.8849640721455216}
+12/22/2021 00:11:06 - INFO - codeparrot_training - Step 2934: {'lr': 0.0004962266853438275, 'samples': 1502720, 'steps': 2934, 'batch_loss/train': 0.9049284048378468}
+12/22/2021 00:11:18 - INFO - codeparrot_training - Step 2935: {'lr': 0.0004962239564789197, 'samples': 1503232, 'steps': 2935, 'batch_loss/train': 0.9346189349889755}
+12/22/2021 00:11:29 - INFO - codeparrot_training - Step 2936: {'lr': 0.0004962212266351185, 'samples': 1503744, 'steps': 2936, 'batch_loss/train': 1.0462322980165482}
+12/22/2021 00:11:40 - INFO - codeparrot_training - Step 2937: {'lr': 0.0004962184958124346, 'samples': 1504256, 'steps': 2937, 'batch_loss/train': 0.88956314092502}
+12/22/2021 00:11:52 - INFO - codeparrot_training - Step 2938: {'lr': 0.000496215764010879, 'samples': 1504768, 'steps': 2938, 'batch_loss/train': 0.8482174808159471}
+12/22/2021 00:12:03 - INFO - codeparrot_training - Step 2939: {'lr': 0.0004962130312304625, 'samples': 1505280, 'steps': 2939, 'batch_loss/train': 0.8539789877831936}
+12/22/2021 00:12:14 - INFO - codeparrot_training - Step 2940: {'lr': 0.0004962102974711959, 'samples': 1505792, 'steps': 2940, 'batch_loss/train': 0.8022037263726816}
+12/22/2021 00:12:26 - INFO - codeparrot_training - Step 2941: {'lr': 0.0004962075627330901, 'samples': 1506304, 'steps': 2941, 'batch_loss/train': 0.9581134002655745}
+12/22/2021 00:12:37 - INFO - codeparrot_training - Step 2942: {'lr': 0.0004962048270161561, 'samples': 1506816, 'steps': 2942, 'batch_loss/train': 0.8410080634057522}
+12/22/2021 00:12:48 - INFO - codeparrot_training - Step 2943: {'lr': 0.0004962020903204045, 'samples': 1507328, 'steps': 2943, 'batch_loss/train': 0.8268013931810856}
+12/22/2021 00:12:58 - INFO - codeparrot_training - Step 2944: {'lr': 0.0004961993526458465, 'samples': 1507840, 'steps': 2944, 'batch_loss/train': 0.7475924706086516}
+12/22/2021 00:13:10 - INFO - codeparrot_training - Step 2945: {'lr': 0.0004961966139924929, 'samples': 1508352, 'steps': 2945, 'batch_loss/train': 0.8386268308386207}
+12/22/2021 00:13:21 - INFO - codeparrot_training - Step 2946: {'lr': 0.0004961938743603543, 'samples': 1508864, 'steps': 2946, 'batch_loss/train': 0.8953671613708138}
+12/22/2021 00:13:32 - INFO - codeparrot_training - Step 2947: {'lr': 0.000496191133749442, 'samples': 1509376, 'steps': 2947, 'batch_loss/train': 0.9012109395116568}
+12/22/2021 00:13:44 - INFO - codeparrot_training - Step 2948: {'lr': 0.0004961883921597666, 'samples': 1509888, 'steps': 2948, 'batch_loss/train': 0.9005736131221056}
+12/22/2021 00:13:54 - INFO - codeparrot_training - Step 2949: {'lr': 0.0004961856495913392, 'samples': 1510400, 'steps': 2949, 'batch_loss/train': 1.0169416833668947}
+12/22/2021 00:14:05 - INFO - codeparrot_training - Step 2950: {'lr': 0.0004961829060441705, 'samples': 1510912, 'steps': 2950, 'batch_loss/train': 1.0916631098371}
+12/22/2021 00:14:18 - INFO - codeparrot_training - Step 2951: {'lr': 0.0004961801615182716, 'samples': 1511424, 'steps': 2951, 'batch_loss/train': 0.7530182292684913}
+12/22/2021 00:14:29 - INFO - codeparrot_training - Step 2952: {'lr': 0.0004961774160136533, 'samples': 1511936, 'steps': 2952, 'batch_loss/train': 0.8072453094646335}
+12/22/2021 00:14:39 - INFO - codeparrot_training - Step 2953: {'lr': 0.0004961746695303265, 'samples': 1512448, 'steps': 2953, 'batch_loss/train': 0.8104291008785367}
+12/22/2021 00:14:50 - INFO - codeparrot_training - Step 2954: {'lr': 0.0004961719220683024, 'samples': 1512960, 'steps': 2954, 'batch_loss/train': 0.8152489559724927}
+12/22/2021 00:15:02 - INFO - codeparrot_training - Step 2955: {'lr': 0.0004961691736275914, 'samples': 1513472, 'steps': 2955, 'batch_loss/train': 0.8046854101121426}
+12/22/2021 00:15:13 - INFO - codeparrot_training - Step 2956: {'lr': 0.0004961664242082048, 'samples': 1513984, 'steps': 2956, 'batch_loss/train': 0.8412078423425555}
+12/22/2021 00:15:23 - INFO - codeparrot_training - Step 2957: {'lr': 0.0004961636738101535, 'samples': 1514496, 'steps': 2957, 'batch_loss/train': 0.9023262448608875}
+12/22/2021 00:15:36 - INFO - codeparrot_training - Step 2958: {'lr': 0.0004961609224334484, 'samples': 1515008, 'steps': 2958, 'batch_loss/train': 0.8240511417388916}
+12/22/2021 00:15:47 - INFO - codeparrot_training - Step 2959: {'lr': 0.0004961581700781003, 'samples': 1515520, 'steps': 2959, 'batch_loss/train': 0.9120802539400756}
+12/22/2021 00:15:57 - INFO - codeparrot_training - Step 2960: {'lr': 0.0004961554167441203, 'samples': 1516032, 'steps': 2960, 'batch_loss/train': 0.8870995547622442}
+12/22/2021 00:16:09 - INFO - codeparrot_training - Step 2961: {'lr': 0.0004961526624315194, 'samples': 1516544, 'steps': 2961, 'batch_loss/train': 0.9367961045354605}
+12/22/2021 00:16:20 - INFO - codeparrot_training - Step 2962: {'lr': 0.0004961499071403084, 'samples': 1517056, 'steps': 2962, 'batch_loss/train': 0.8567962287925184}
+12/22/2021 00:16:31 - INFO - codeparrot_training - Step 2963: {'lr': 0.0004961471508704983, 'samples': 1517568, 'steps': 2963, 'batch_loss/train': 0.960740964859724}
+12/22/2021 00:16:43 - INFO - codeparrot_training - Step 2964: {'lr': 0.0004961443936221001, 'samples': 1518080, 'steps': 2964, 'batch_loss/train': 0.8646677490323782}
+12/22/2021 00:16:53 - INFO - codeparrot_training - Step 2965: {'lr': 0.0004961416353951247, 'samples': 1518592, 'steps': 2965, 'batch_loss/train': 0.9682387188076973}
+12/22/2021 00:17:04 - INFO - codeparrot_training - Step 2966: {'lr': 0.0004961388761895832, 'samples': 1519104, 'steps': 2966, 'batch_loss/train': 0.9413503743708134}
+12/22/2021 00:17:14 - INFO - codeparrot_training - Step 2967: {'lr': 0.0004961361160054864, 'samples': 1519616, 'steps': 2967, 'batch_loss/train': 0.9703543996438384}
+12/22/2021 00:17:27 - INFO - codeparrot_training - Step 2968: {'lr': 0.0004961333548428453, 'samples': 1520128, 'steps': 2968, 'batch_loss/train': 0.8507348503917456}
+12/22/2021 00:17:38 - INFO - codeparrot_training - Step 2969: {'lr': 0.0004961305927016708, 'samples': 1520640, 'steps': 2969, 'batch_loss/train': 0.8701075608842075}
+12/22/2021 00:17:48 - INFO - codeparrot_training - Step 2970: {'lr': 0.0004961278295819743, 'samples': 1521152, 'steps': 2970, 'batch_loss/train': 0.8559769433923066}
+12/22/2021 00:18:01 - INFO - codeparrot_training - Step 2971: {'lr': 0.0004961250654837662, 'samples': 1521664, 'steps': 2971, 'batch_loss/train': 0.8931840006262064}
+12/22/2021 00:18:11 - INFO - codeparrot_training - Step 2972: {'lr': 0.0004961223004070579, 'samples': 1522176, 'steps': 2972, 'batch_loss/train': 0.8695220556110144}
+12/22/2021 00:18:22 - INFO - codeparrot_training - Step 2973: {'lr': 0.0004961195343518603, 'samples': 1522688, 'steps': 2973, 'batch_loss/train': 0.9247833495028317}
+12/22/2021 00:18:35 - INFO - codeparrot_training - Step 2974: {'lr': 0.0004961167673181844, 'samples': 1523200, 'steps': 2974, 'batch_loss/train': 0.754037200473249}
+12/22/2021 00:18:45 - INFO - codeparrot_training - Step 2975: {'lr': 0.000496113999306041, 'samples': 1523712, 'steps': 2975, 'batch_loss/train': 0.9668109491467476}
+12/22/2021 00:18:56 - INFO - codeparrot_training - Step 2976: {'lr': 0.0004961112303154413, 'samples': 1524224, 'steps': 2976, 'batch_loss/train': 0.8115405943244696}
+12/22/2021 00:19:06 - INFO - codeparrot_training - Step 2977: {'lr': 0.0004961084603463963, 'samples': 1524736, 'steps': 2977, 'batch_loss/train': 0.5788128701969981}
+12/22/2021 00:19:19 - INFO - codeparrot_training - Step 2978: {'lr': 0.0004961056893989171, 'samples': 1525248, 'steps': 2978, 'batch_loss/train': 0.7695569433271885}
+12/22/2021 00:19:30 - INFO - codeparrot_training - Step 2979: {'lr': 0.0004961029174730146, 'samples': 1525760, 'steps': 2979, 'batch_loss/train': 0.8036586173111573}
+12/22/2021 00:19:40 - INFO - codeparrot_training - Step 2980: {'lr': 0.0004961001445686996, 'samples': 1526272, 'steps': 2980, 'batch_loss/train': 0.7599600348621607}
+12/22/2021 00:19:53 - INFO - codeparrot_training - Step 2981: {'lr': 0.0004960973706859836, 'samples': 1526784, 'steps': 2981, 'batch_loss/train': 0.8249022495001554}
+12/22/2021 00:20:03 - INFO - codeparrot_training - Step 2982: {'lr': 0.0004960945958248773, 'samples': 1527296, 'steps': 2982, 'batch_loss/train': 0.9340034928172827}
+12/22/2021 00:20:14 - INFO - codeparrot_training - Step 2983: {'lr': 0.0004960918199853917, 'samples': 1527808, 'steps': 2983, 'batch_loss/train': 0.9259119182825089}
+12/22/2021 00:20:26 - INFO - codeparrot_training - Step 2984: {'lr': 0.000496089043167538, 'samples': 1528320, 'steps': 2984, 'batch_loss/train': 0.965371448546648}
+12/22/2021 00:20:37 - INFO - codeparrot_training - Step 2985: {'lr': 0.0004960862653713273, 'samples': 1528832, 'steps': 2985, 'batch_loss/train': 0.963838517665863}
+12/22/2021 00:20:47 - INFO - codeparrot_training - Step 2986: {'lr': 0.0004960834865967704, 'samples': 1529344, 'steps': 2986, 'batch_loss/train': 0.861060225404799}
+12/22/2021 00:20:58 - INFO - codeparrot_training - Step 2987: {'lr': 0.0004960807068438785, 'samples': 1529856, 'steps': 2987, 'batch_loss/train': 0.9171348242089152}
+12/22/2021 00:21:10 - INFO - codeparrot_training - Step 2988: {'lr': 0.0004960779261126626, 'samples': 1530368, 'steps': 2988, 'batch_loss/train': 0.7605819683521986}
+12/22/2021 00:21:21 - INFO - codeparrot_training - Step 2989: {'lr': 0.0004960751444031339, 'samples': 1530880, 'steps': 2989, 'batch_loss/train': 0.7838842070195824}
+12/22/2021 00:21:31 - INFO - codeparrot_training - Step 2990: {'lr': 0.0004960723617153032, 'samples': 1531392, 'steps': 2990, 'batch_loss/train': 0.8764848709106445}
+12/22/2021 00:21:44 - INFO - codeparrot_training - Step 2991: {'lr': 0.0004960695780491818, 'samples': 1531904, 'steps': 2991, 'batch_loss/train': 0.8022947888821363}
+12/22/2021 00:21:55 - INFO - codeparrot_training - Step 2992: {'lr': 0.0004960667934047807, 'samples': 1532416, 'steps': 2992, 'batch_loss/train': 0.8532500602304935}
+12/22/2021 00:22:05 - INFO - codeparrot_training - Step 2993: {'lr': 0.0004960640077821108, 'samples': 1532928, 'steps': 2993, 'batch_loss/train': 0.8128378102555871}
+12/22/2021 00:22:17 - INFO - codeparrot_training - Step 2994: {'lr': 0.0004960612211811834, 'samples': 1533440, 'steps': 2994, 'batch_loss/train': 0.8611951814964414}
+12/22/2021 00:22:28 - INFO - codeparrot_training - Step 2995: {'lr': 0.0004960584336020095, 'samples': 1533952, 'steps': 2995, 'batch_loss/train': 0.8225822672247887}
+12/22/2021 00:22:38 - INFO - codeparrot_training - Step 2996: {'lr': 0.0004960556450446001, 'samples': 1534464, 'steps': 2996, 'batch_loss/train': 0.8130850829184055}
+12/22/2021 00:22:49 - INFO - codeparrot_training - Step 2997: {'lr': 0.0004960528555089665, 'samples': 1534976, 'steps': 2997, 'batch_loss/train': 0.8801628071814775}
+12/22/2021 00:23:02 - INFO - codeparrot_training - Step 2998: {'lr': 0.0004960500649951195, 'samples': 1535488, 'steps': 2998, 'batch_loss/train': 0.9043007805012167}
+12/22/2021 00:23:12 - INFO - codeparrot_training - Step 2999: {'lr': 0.0004960472735030705, 'samples': 1536000, 'steps': 2999, 'batch_loss/train': 1.0239335969090462}
+12/22/2021 00:23:23 - INFO - codeparrot_training - Step 3000: {'lr': 0.0004960444810328303, 'samples': 1536512, 'steps': 3000, 'batch_loss/train': 0.845787356607616}
+12/22/2021 00:23:35 - INFO - codeparrot_training - Step 3001: {'lr': 0.0004960416875844102, 'samples': 1537024, 'steps': 3001, 'batch_loss/train': 0.8958561411127448}
+12/22/2021 00:23:46 - INFO - codeparrot_training - Step 3002: {'lr': 0.0004960388931578212, 'samples': 1537536, 'steps': 3002, 'batch_loss/train': 0.8389314515516162}
+12/22/2021 00:23:57 - INFO - codeparrot_training - Step 3003: {'lr': 0.0004960360977530746, 'samples': 1538048, 'steps': 3003, 'batch_loss/train': 0.7584452927112579}
+12/22/2021 00:24:09 - INFO - codeparrot_training - Step 3004: {'lr': 0.0004960333013701813, 'samples': 1538560, 'steps': 3004, 'batch_loss/train': 0.8678699880838394}
+12/22/2021 00:24:19 - INFO - codeparrot_training - Step 3005: {'lr': 0.0004960305040091525, 'samples': 1539072, 'steps': 3005, 'batch_loss/train': 0.7375816283747554}
+12/22/2021 00:24:30 - INFO - codeparrot_training - Step 3006: {'lr': 0.0004960277056699993, 'samples': 1539584, 'steps': 3006, 'batch_loss/train': 0.9170281309634447}
+12/22/2021 00:24:43 - INFO - codeparrot_training - Step 3007: {'lr': 0.0004960249063527328, 'samples': 1540096, 'steps': 3007, 'batch_loss/train': 0.8138867886736989}
+12/22/2021 00:24:54 - INFO - codeparrot_training - Step 3008: {'lr': 0.0004960221060573642, 'samples': 1540608, 'steps': 3008, 'batch_loss/train': 0.8875448501203209}
+12/22/2021 00:25:04 - INFO - codeparrot_training - Step 3009: {'lr': 0.0004960193047839047, 'samples': 1541120, 'steps': 3009, 'batch_loss/train': 1.2428184300661087}
+12/22/2021 00:25:15 - INFO - codeparrot_training - Step 3010: {'lr': 0.0004960165025323652, 'samples': 1541632, 'steps': 3010, 'batch_loss/train': 1.5285909390076995}
+12/22/2021 00:25:27 - INFO - codeparrot_training - Step 3011: {'lr': 0.000496013699302757, 'samples': 1542144, 'steps': 3011, 'batch_loss/train': 0.926459682174027}
+12/22/2021 00:25:38 - INFO - codeparrot_training - Step 3012: {'lr': 0.0004960108950950913, 'samples': 1542656, 'steps': 3012, 'batch_loss/train': 0.7894781604409218}
+12/22/2021 00:25:48 - INFO - codeparrot_training - Step 3013: {'lr': 0.000496008089909379, 'samples': 1543168, 'steps': 3013, 'batch_loss/train': 0.9074496598914266}
+12/22/2021 00:26:01 - INFO - codeparrot_training - Step 3014: {'lr': 0.0004960052837456317, 'samples': 1543680, 'steps': 3014, 'batch_loss/train': 0.8952338602393866}
+12/22/2021 00:26:12 - INFO - codeparrot_training - Step 3015: {'lr': 0.0004960024766038601, 'samples': 1544192, 'steps': 3015, 'batch_loss/train': 0.7996892146766186}
+12/22/2021 00:26:23 - INFO - codeparrot_training - Step 3016: {'lr': 0.0004959996684840755, 'samples': 1544704, 'steps': 3016, 'batch_loss/train': 0.9057547110132873}
+12/22/2021 00:26:35 - INFO - codeparrot_training - Step 3017: {'lr': 0.0004959968593862892, 'samples': 1545216, 'steps': 3017, 'batch_loss/train': 0.9462001109495759}
+12/22/2021 00:26:45 - INFO - codeparrot_training - Step 3018: {'lr': 0.0004959940493105123, 'samples': 1545728, 'steps': 3018, 'batch_loss/train': 0.8366453787311912}
+12/22/2021 00:26:56 - INFO - codeparrot_training - Step 3019: {'lr': 0.0004959912382567559, 'samples': 1546240, 'steps': 3019, 'batch_loss/train': 0.8614417221397161}
+12/22/2021 00:27:07 - INFO - codeparrot_training - Step 3020: {'lr': 0.0004959884262250311, 'samples': 1546752, 'steps': 3020, 'batch_loss/train': 0.8534379992634058}
+12/22/2021 00:27:19 - INFO - codeparrot_training - Step 3021: {'lr': 0.0004959856132153493, 'samples': 1547264, 'steps': 3021, 'batch_loss/train': 0.7620975030586123}
+12/22/2021 00:27:29 - INFO - codeparrot_training - Step 3022: {'lr': 0.0004959827992277216, 'samples': 1547776, 'steps': 3022, 'batch_loss/train': 0.9459830988198519}
+12/22/2021 00:27:40 - INFO - codeparrot_training - Step 3023: {'lr': 0.0004959799842621592, 'samples': 1548288, 'steps': 3023, 'batch_loss/train': 0.8370558796450496}
+12/22/2021 00:27:52 - INFO - codeparrot_training - Step 3024: {'lr': 0.0004959771683186732, 'samples': 1548800, 'steps': 3024, 'batch_loss/train': 0.8837002348154783}
+12/22/2021 00:28:02 - INFO - codeparrot_training - Step 3025: {'lr': 0.0004959743513972748, 'samples': 1549312, 'steps': 3025, 'batch_loss/train': 0.884586906991899}
+12/22/2021 00:28:13 - INFO - codeparrot_training - Step 3026: {'lr': 0.0004959715334979754, 'samples': 1549824, 'steps': 3026, 'batch_loss/train': 0.8589917328208685}
+12/22/2021 00:28:26 - INFO - codeparrot_training - Step 3027: {'lr': 0.000495968714620786, 'samples': 1550336, 'steps': 3027, 'batch_loss/train': 0.8917285269126296}
+12/22/2021 00:28:36 - INFO - codeparrot_training - Step 3028: {'lr': 0.0004959658947657178, 'samples': 1550848, 'steps': 3028, 'batch_loss/train': 0.8786073978990316}
+12/22/2021 00:28:47 - INFO - codeparrot_training - Step 3029: {'lr': 0.0004959630739327822, 'samples': 1551360, 'steps': 3029, 'batch_loss/train': 0.8593123937025666}
+12/22/2021 00:28:58 - INFO - codeparrot_training - Step 3030: {'lr': 0.0004959602521219901, 'samples': 1551872, 'steps': 3030, 'batch_loss/train': 0.8191675832495093}
+12/22/2021 00:29:10 - INFO - codeparrot_training - Step 3031: {'lr': 0.000495957429333353, 'samples': 1552384, 'steps': 3031, 'batch_loss/train': 1.0185594484210014}
+12/22/2021 00:29:20 - INFO - codeparrot_training - Step 3032: {'lr': 0.0004959546055668822, 'samples': 1552896, 'steps': 3032, 'batch_loss/train': 0.8848305458668619}
+12/22/2021 00:29:31 - INFO - codeparrot_training - Step 3033: {'lr': 0.0004959517808225886, 'samples': 1553408, 'steps': 3033, 'batch_loss/train': 0.8473475202918053}
+12/22/2021 00:29:43 - INFO - codeparrot_training - Step 3034: {'lr': 0.0004959489551004836, 'samples': 1553920, 'steps': 3034, 'batch_loss/train': 0.8368791860993952}
+12/22/2021 00:29:54 - INFO - codeparrot_training - Step 3035: {'lr': 0.0004959461284005784, 'samples': 1554432, 'steps': 3035, 'batch_loss/train': 0.8726472007110715}
+12/22/2021 00:30:04 - INFO - codeparrot_training - Step 3036: {'lr': 0.0004959433007228843, 'samples': 1554944, 'steps': 3036, 'batch_loss/train': 0.877885733731091}
+12/22/2021 00:30:17 - INFO - codeparrot_training - Step 3037: {'lr': 0.0004959404720674124, 'samples': 1555456, 'steps': 3037, 'batch_loss/train': 0.8191741090267897}
+12/22/2021 00:30:28 - INFO - codeparrot_training - Step 3038: {'lr': 0.0004959376424341741, 'samples': 1555968, 'steps': 3038, 'batch_loss/train': 0.8256903504952788}
+12/22/2021 00:30:38 - INFO - codeparrot_training - Step 3039: {'lr': 0.0004959348118231807, 'samples': 1556480, 'steps': 3039, 'batch_loss/train': 0.7605213592760265}
+12/22/2021 00:30:50 - INFO - codeparrot_training - Step 3040: {'lr': 0.0004959319802344433, 'samples': 1556992, 'steps': 3040, 'batch_loss/train': 0.9237731462344527}
+12/22/2021 00:31:01 - INFO - codeparrot_training - Step 3041: {'lr': 0.0004959291476679731, 'samples': 1557504, 'steps': 3041, 'batch_loss/train': 0.8381185550242662}
+12/22/2021 00:31:12 - INFO - codeparrot_training - Step 3042: {'lr': 0.0004959263141237816, 'samples': 1558016, 'steps': 3042, 'batch_loss/train': 0.9697933858260512}
+12/22/2021 00:31:22 - INFO - codeparrot_training - Step 3043: {'lr': 0.0004959234796018799, 'samples': 1558528, 'steps': 3043, 'batch_loss/train': 0.9182802028954029}
+12/22/2021 00:31:35 - INFO - codeparrot_training - Step 3044: {'lr': 0.0004959206441022792, 'samples': 1559040, 'steps': 3044, 'batch_loss/train': 0.8922312278300524}
+12/22/2021 00:31:46 - INFO - codeparrot_training - Step 3045: {'lr': 0.000495917807624991, 'samples': 1559552, 'steps': 3045, 'batch_loss/train': 0.7025610520504415}
+12/22/2021 00:31:57 - INFO - codeparrot_training - Step 3046: {'lr': 0.0004959149701700264, 'samples': 1560064, 'steps': 3046, 'batch_loss/train': 0.8047926286235452}
+12/22/2021 00:32:09 - INFO - codeparrot_training - Step 3047: {'lr': 0.0004959121317373968, 'samples': 1560576, 'steps': 3047, 'batch_loss/train': 0.8515224056318402}
+12/22/2021 00:32:19 - INFO - codeparrot_training - Step 3048: {'lr': 0.0004959092923271134, 'samples': 1561088, 'steps': 3048, 'batch_loss/train': 0.8055978587362915}
+12/22/2021 00:32:30 - INFO - codeparrot_training - Step 3049: {'lr': 0.0004959064519391874, 'samples': 1561600, 'steps': 3049, 'batch_loss/train': 0.8483535428531468}
+12/22/2021 00:32:43 - INFO - codeparrot_training - Step 3050: {'lr': 0.0004959036105736303, 'samples': 1562112, 'steps': 3050, 'batch_loss/train': 0.88635613466613}
+12/22/2021 00:32:54 - INFO - codeparrot_training - Step 3051: {'lr': 0.0004959007682304532, 'samples': 1562624, 'steps': 3051, 'batch_loss/train': 0.7347767143510282}
+12/22/2021 00:33:04 - INFO - codeparrot_training - Step 3052: {'lr': 0.0004958979249096675, 'samples': 1563136, 'steps': 3052, 'batch_loss/train': 0.8436926156282425}
+12/22/2021 00:33:15 - INFO - codeparrot_training - Step 3053: {'lr': 0.0004958950806112847, 'samples': 1563648, 'steps': 3053, 'batch_loss/train': 1.223364321514964}
+12/22/2021 00:33:27 - INFO - codeparrot_training - Step 3054: {'lr': 0.0004958922353353156, 'samples': 1564160, 'steps': 3054, 'batch_loss/train': 0.9730399204418063}
+12/22/2021 00:33:38 - INFO - codeparrot_training - Step 3055: {'lr': 0.000495889389081772, 'samples': 1564672, 'steps': 3055, 'batch_loss/train': 0.7957408530637622}
+12/22/2021 00:33:49 - INFO - codeparrot_training - Step 3056: {'lr': 0.0004958865418506651, 'samples': 1565184, 'steps': 3056, 'batch_loss/train': 0.8656440395861864}
+12/22/2021 00:34:03 - INFO - codeparrot_training - Step 3057: {'lr': 0.000495883693642006, 'samples': 1565696, 'steps': 3057, 'batch_loss/train': 0.9476745035499334}
+12/22/2021 00:34:13 - INFO - codeparrot_training - Step 3058: {'lr': 0.0004958808444558063, 'samples': 1566208, 'steps': 3058, 'batch_loss/train': 0.9414535304531455}
+12/22/2021 00:34:24 - INFO - codeparrot_training - Step 3059: {'lr': 0.0004958779942920771, 'samples': 1566720, 'steps': 3059, 'batch_loss/train': 0.9855457870289683}
+12/22/2021 00:34:34 - INFO - codeparrot_training - Step 3060: {'lr': 0.0004958751431508298, 'samples': 1567232, 'steps': 3060, 'batch_loss/train': 0.804049733094871}
+12/22/2021 00:34:46 - INFO - codeparrot_training - Step 3061: {'lr': 0.0004958722910320759, 'samples': 1567744, 'steps': 3061, 'batch_loss/train': 0.8185342783108354}
+12/22/2021 00:34:57 - INFO - codeparrot_training - Step 3062: {'lr': 0.0004958694379358265, 'samples': 1568256, 'steps': 3062, 'batch_loss/train': 0.848387093283236}
+12/22/2021 00:35:08 - INFO - codeparrot_training - Step 3063: {'lr': 0.0004958665838620932, 'samples': 1568768, 'steps': 3063, 'batch_loss/train': 0.9590487708337605}
+12/22/2021 00:35:20 - INFO - codeparrot_training - Step 3064: {'lr': 0.000495863728810887, 'samples': 1569280, 'steps': 3064, 'batch_loss/train': 0.7944198246113956}
+12/22/2021 00:35:30 - INFO - codeparrot_training - Step 3065: {'lr': 0.0004958608727822196, 'samples': 1569792, 'steps': 3065, 'batch_loss/train': 0.8014315916225314}
+12/22/2021 00:35:41 - INFO - codeparrot_training - Step 3066: {'lr': 0.0004958580157761022, 'samples': 1570304, 'steps': 3066, 'batch_loss/train': 0.7802999187260866}
+12/22/2021 00:35:54 - INFO - codeparrot_training - Step 3067: {'lr': 0.0004958551577925461, 'samples': 1570816, 'steps': 3067, 'batch_loss/train': 0.8856266178190708}
+12/22/2021 00:36:04 - INFO - codeparrot_training - Step 3068: {'lr': 0.0004958522988315627, 'samples': 1571328, 'steps': 3068, 'batch_loss/train': 0.749654735904187}
+12/22/2021 00:36:15 - INFO - codeparrot_training - Step 3069: {'lr': 0.0004958494388931635, 'samples': 1571840, 'steps': 3069, 'batch_loss/train': 0.784135281573981}
+12/22/2021 00:36:27 - INFO - codeparrot_training - Step 3070: {'lr': 0.0004958465779773596, 'samples': 1572352, 'steps': 3070, 'batch_loss/train': 0.899507686495781}
+12/22/2021 00:36:38 - INFO - codeparrot_training - Step 3071: {'lr': 0.0004958437160841627, 'samples': 1572864, 'steps': 3071, 'batch_loss/train': 0.8792612408287823}
+12/22/2021 00:36:48 - INFO - codeparrot_training - Step 3072: {'lr': 0.0004958408532135839, 'samples': 1573376, 'steps': 3072, 'batch_loss/train': 0.8825881537050009}
+12/22/2021 00:36:59 - INFO - codeparrot_training - Step 3073: {'lr': 0.0004958379893656347, 'samples': 1573888, 'steps': 3073, 'batch_loss/train': 0.5988505707355216}
+12/22/2021 00:37:12 - INFO - codeparrot_training - Step 3074: {'lr': 0.0004958351245403265, 'samples': 1574400, 'steps': 3074, 'batch_loss/train': 0.8611243199557066}
+12/22/2021 00:37:23 - INFO - codeparrot_training - Step 3075: {'lr': 0.0004958322587376707, 'samples': 1574912, 'steps': 3075, 'batch_loss/train': 0.8500094041228294}
+12/22/2021 00:37:33 - INFO - codeparrot_training - Step 3076: {'lr': 0.0004958293919576786, 'samples': 1575424, 'steps': 3076, 'batch_loss/train': 0.8364934409037232}
+12/22/2021 00:37:45 - INFO - codeparrot_training - Step 3077: {'lr': 0.0004958265242003617, 'samples': 1575936, 'steps': 3077, 'batch_loss/train': 0.8479018164798617}
+12/22/2021 00:37:56 - INFO - codeparrot_training - Step 3078: {'lr': 0.0004958236554657313, 'samples': 1576448, 'steps': 3078, 'batch_loss/train': 0.8614955022931099}
+12/22/2021 00:38:07 - INFO - codeparrot_training - Step 3079: {'lr': 0.000495820785753799, 'samples': 1576960, 'steps': 3079, 'batch_loss/train': 0.8291443753987551}
+12/22/2021 00:38:20 - INFO - codeparrot_training - Step 3080: {'lr': 0.0004958179150645759, 'samples': 1577472, 'steps': 3080, 'batch_loss/train': 0.8062189901247621}
+12/22/2021 00:38:30 - INFO - codeparrot_training - Step 3081: {'lr': 0.0004958150433980738, 'samples': 1577984, 'steps': 3081, 'batch_loss/train': 1.0027417140081525}
+12/22/2021 00:38:41 - INFO - codeparrot_training - Step 3082: {'lr': 0.0004958121707543037, 'samples': 1578496, 'steps': 3082, 'batch_loss/train': 0.8559663305059075}
+12/22/2021 00:38:51 - INFO - codeparrot_training - Step 3083: {'lr': 0.0004958092971332773, 'samples': 1579008, 'steps': 3083, 'batch_loss/train': 0.9047391004860401}
+12/22/2021 00:39:03 - INFO - codeparrot_training - Step 3084: {'lr': 0.0004958064225350061, 'samples': 1579520, 'steps': 3084, 'batch_loss/train': 0.8246345072984695}
+12/22/2021 00:39:14 - INFO - codeparrot_training - Step 3085: {'lr': 0.0004958035469595012, 'samples': 1580032, 'steps': 3085, 'batch_loss/train': 0.7823211150243878}
+12/22/2021 00:39:25 - INFO - codeparrot_training - Step 3086: {'lr': 0.0004958006704067743, 'samples': 1580544, 'steps': 3086, 'batch_loss/train': 0.8490783916786313}
+12/22/2021 00:39:37 - INFO - codeparrot_training - Step 3087: {'lr': 0.0004957977928768366, 'samples': 1581056, 'steps': 3087, 'batch_loss/train': 0.9028349558357149}
+12/22/2021 00:39:48 - INFO - codeparrot_training - Step 3088: {'lr': 0.0004957949143696998, 'samples': 1581568, 'steps': 3088, 'batch_loss/train': 0.8764702859334648}
+12/22/2021 00:39:58 - INFO - codeparrot_training - Step 3089: {'lr': 0.0004957920348853752, 'samples': 1582080, 'steps': 3089, 'batch_loss/train': 0.7288846196606755}
+12/22/2021 00:40:10 - INFO - codeparrot_training - Step 3090: {'lr': 0.0004957891544238742, 'samples': 1582592, 'steps': 3090, 'batch_loss/train': 0.8401413289830089}
+12/22/2021 00:40:21 - INFO - codeparrot_training - Step 3091: {'lr': 0.0004957862729852086, 'samples': 1583104, 'steps': 3091, 'batch_loss/train': 0.9385048374533653}
+12/22/2021 00:40:31 - INFO - codeparrot_training - Step 3092: {'lr': 0.0004957833905693893, 'samples': 1583616, 'steps': 3092, 'batch_loss/train': 0.8192966913338751}
+12/22/2021 00:40:42 - INFO - codeparrot_training - Step 3093: {'lr': 0.000495780507176428, 'samples': 1584128, 'steps': 3093, 'batch_loss/train': 0.8873361181467772}
+12/22/2021 00:40:54 - INFO - codeparrot_training - Step 3094: {'lr': 0.0004957776228063364, 'samples': 1584640, 'steps': 3094, 'batch_loss/train': 0.8343557557091117}
+12/22/2021 00:41:05 - INFO - codeparrot_training - Step 3095: {'lr': 0.0004957747374591258, 'samples': 1585152, 'steps': 3095, 'batch_loss/train': 0.8645121119916439}
+12/22/2021 00:41:16 - INFO - codeparrot_training - Step 3096: {'lr': 0.0004957718511348076, 'samples': 1585664, 'steps': 3096, 'batch_loss/train': 0.9243402648717165}
+12/22/2021 00:41:29 - INFO - codeparrot_training - Step 3097: {'lr': 0.0004957689638333933, 'samples': 1586176, 'steps': 3097, 'batch_loss/train': 0.8603623956441879}
+12/22/2021 00:41:39 - INFO - codeparrot_training - Step 3098: {'lr': 0.0004957660755548943, 'samples': 1586688, 'steps': 3098, 'batch_loss/train': 0.9453988280147314}
+12/22/2021 00:41:50 - INFO - codeparrot_training - Step 3099: {'lr': 0.0004957631862993223, 'samples': 1587200, 'steps': 3099, 'batch_loss/train': 0.8779096202924848}
+12/22/2021 00:42:02 - INFO - codeparrot_training - Step 3100: {'lr': 0.0004957602960666886, 'samples': 1587712, 'steps': 3100, 'batch_loss/train': 0.851197361946106}
+12/22/2021 00:42:13 - INFO - codeparrot_training - Step 3101: {'lr': 0.0004957574048570048, 'samples': 1588224, 'steps': 3101, 'batch_loss/train': 0.8761541591957211}
+12/22/2021 00:42:23 - INFO - codeparrot_training - Step 3102: {'lr': 0.0004957545126702824, 'samples': 1588736, 'steps': 3102, 'batch_loss/train': 0.8260644427500665}
+12/22/2021 00:42:34 - INFO - codeparrot_training - Step 3103: {'lr': 0.0004957516195065327, 'samples': 1589248, 'steps': 3103, 'batch_loss/train': 0.8532250113785267}
+12/22/2021 00:42:47 - INFO - codeparrot_training - Step 3104: {'lr': 0.0004957487253657674, 'samples': 1589760, 'steps': 3104, 'batch_loss/train': 0.9954732721671462}
+12/22/2021 00:42:57 - INFO - codeparrot_training - Step 3105: {'lr': 0.0004957458302479981, 'samples': 1590272, 'steps': 3105, 'batch_loss/train': 0.8254889557138085}
+12/22/2021 00:43:08 - INFO - codeparrot_training - Step 3106: {'lr': 0.000495742934153236, 'samples': 1590784, 'steps': 3106, 'batch_loss/train': 0.8195729069411755}
+12/22/2021 00:43:20 - INFO - codeparrot_training - Step 3107: {'lr': 0.0004957400370814929, 'samples': 1591296, 'steps': 3107, 'batch_loss/train': 0.8999533872120082}
+12/22/2021 00:43:30 - INFO - codeparrot_training - Step 3108: {'lr': 0.0004957371390327802, 'samples': 1591808, 'steps': 3108, 'batch_loss/train': 0.8271447294391692}
+12/22/2021 00:43:41 - INFO - codeparrot_training - Step 3109: {'lr': 0.0004957342400071093, 'samples': 1592320, 'steps': 3109, 'batch_loss/train': 1.0253043249249458}
+12/22/2021 00:43:53 - INFO - codeparrot_training - Step 3110: {'lr': 0.0004957313400044919, 'samples': 1592832, 'steps': 3110, 'batch_loss/train': 0.8345599882304668}
+12/22/2021 00:44:04 - INFO - codeparrot_training - Step 3111: {'lr': 0.0004957284390249396, 'samples': 1593344, 'steps': 3111, 'batch_loss/train': 0.8806321583688259}
+12/22/2021 00:44:14 - INFO - codeparrot_training - Step 3112: {'lr': 0.0004957255370684637, 'samples': 1593856, 'steps': 3112, 'batch_loss/train': 0.9513812442310154}
+12/22/2021 00:44:25 - INFO - codeparrot_training - Step 3113: {'lr': 0.0004957226341350758, 'samples': 1594368, 'steps': 3113, 'batch_loss/train': 0.9449809119105339}
+12/22/2021 00:44:38 - INFO - codeparrot_training - Step 3114: {'lr': 0.0004957197302247876, 'samples': 1594880, 'steps': 3114, 'batch_loss/train': 1.0237303017638624}
+12/22/2021 00:44:48 - INFO - codeparrot_training - Step 3115: {'lr': 0.0004957168253376104, 'samples': 1595392, 'steps': 3115, 'batch_loss/train': 0.9327936503104866}
+12/22/2021 00:44:59 - INFO - codeparrot_training - Step 3116: {'lr': 0.000495713919473556, 'samples': 1595904, 'steps': 3116, 'batch_loss/train': 0.8291188208386302}
+12/22/2021 00:45:11 - INFO - codeparrot_training - Step 3117: {'lr': 0.0004957110126326358, 'samples': 1596416, 'steps': 3117, 'batch_loss/train': 0.894895819015801}
+12/22/2021 00:45:22 - INFO - codeparrot_training - Step 3118: {'lr': 0.0004957081048148614, 'samples': 1596928, 'steps': 3118, 'batch_loss/train': 0.9036348462104797}
+12/22/2021 00:45:32 - INFO - codeparrot_training - Step 3119: {'lr': 0.0004957051960202443, 'samples': 1597440, 'steps': 3119, 'batch_loss/train': 0.913657296448946}
+12/22/2021 00:45:45 - INFO - codeparrot_training - Step 3120: {'lr': 0.0004957022862487963, 'samples': 1597952, 'steps': 3120, 'batch_loss/train': 0.9887194253969938}
+12/22/2021 00:45:55 - INFO - codeparrot_training - Step 3121: {'lr': 0.0004956993755005285, 'samples': 1598464, 'steps': 3121, 'batch_loss/train': 0.8462177379988134}
+12/22/2021 00:46:06 - INFO - codeparrot_training - Step 3122: {'lr': 0.0004956964637754529, 'samples': 1598976, 'steps': 3122, 'batch_loss/train': 0.8642888115718961}
+12/22/2021 00:46:18 - INFO - codeparrot_training - Step 3123: {'lr': 0.0004956935510735809, 'samples': 1599488, 'steps': 3123, 'batch_loss/train': 0.947129082866013}
+12/22/2021 00:46:29 - INFO - codeparrot_training - Step 3124: {'lr': 0.0004956906373949242, 'samples': 1600000, 'steps': 3124, 'batch_loss/train': 0.8488472178578377}
+12/22/2021 00:46:39 - INFO - codeparrot_training - Step 3125: {'lr': 0.0004956877227394942, 'samples': 1600512, 'steps': 3125, 'batch_loss/train': 0.8660394959151745}
+12/22/2021 00:46:50 - INFO - codeparrot_training - Step 3126: {'lr': 0.0004956848071073026, 'samples': 1601024, 'steps': 3126, 'batch_loss/train': 0.937318030744791}
+12/22/2021 00:47:02 - INFO - codeparrot_training - Step 3127: {'lr': 0.000495681890498361, 'samples': 1601536, 'steps': 3127, 'batch_loss/train': 0.9434640668332577}
+12/22/2021 00:47:13 - INFO - codeparrot_training - Step 3128: {'lr': 0.0004956789729126809, 'samples': 1602048, 'steps': 3128, 'batch_loss/train': 0.9394240211695433}
+12/22/2021 00:47:23 - INFO - codeparrot_training - Step 3129: {'lr': 0.0004956760543502741, 'samples': 1602560, 'steps': 3129, 'batch_loss/train': 0.9542834351304919}
+12/22/2021 00:47:35 - INFO - codeparrot_training - Step 3130: {'lr': 0.0004956731348111519, 'samples': 1603072, 'steps': 3130, 'batch_loss/train': 0.932606253772974}
+12/22/2021 00:47:46 - INFO - codeparrot_training - Step 3131: {'lr': 0.0004956702142953262, 'samples': 1603584, 'steps': 3131, 'batch_loss/train': 0.8273211540654302}
+12/22/2021 00:47:56 - INFO - codeparrot_training - Step 3132: {'lr': 0.0004956672928028086, 'samples': 1604096, 'steps': 3132, 'batch_loss/train': 0.7796893659979105}
+12/22/2021 00:48:09 - INFO - codeparrot_training - Step 3133: {'lr': 0.0004956643703336103, 'samples': 1604608, 'steps': 3133, 'batch_loss/train': 0.9116971455514431}
+12/22/2021 00:48:20 - INFO - codeparrot_training - Step 3134: {'lr': 0.0004956614468877435, 'samples': 1605120, 'steps': 3134, 'batch_loss/train': 1.1251118397340178}
+12/22/2021 00:48:31 - INFO - codeparrot_training - Step 3135: {'lr': 0.0004956585224652194, 'samples': 1605632, 'steps': 3135, 'batch_loss/train': 0.6840076111257076}
+12/22/2021 00:48:41 - INFO - codeparrot_training - Step 3136: {'lr': 0.0004956555970660498, 'samples': 1606144, 'steps': 3136, 'batch_loss/train': 0.8798742722719908}
+12/22/2021 00:48:53 - INFO - codeparrot_training - Step 3137: {'lr': 0.0004956526706902464, 'samples': 1606656, 'steps': 3137, 'batch_loss/train': 0.9323478145524859}
+12/22/2021 00:49:04 - INFO - codeparrot_training - Step 3138: {'lr': 0.0004956497433378206, 'samples': 1607168, 'steps': 3138, 'batch_loss/train': 0.8929630997590721}
+12/22/2021 00:49:15 - INFO - codeparrot_training - Step 3139: {'lr': 0.0004956468150087842, 'samples': 1607680, 'steps': 3139, 'batch_loss/train': 0.8258349057286978}
+12/22/2021 00:49:27 - INFO - codeparrot_training - Step 3140: {'lr': 0.0004956438857031488, 'samples': 1608192, 'steps': 3140, 'batch_loss/train': 0.8580984491854906}
+12/22/2021 00:49:37 - INFO - codeparrot_training - Step 3141: {'lr': 0.0004956409554209262, 'samples': 1608704, 'steps': 3141, 'batch_loss/train': 0.708816030761227}
+12/22/2021 00:49:48 - INFO - codeparrot_training - Step 3142: {'lr': 0.0004956380241621278, 'samples': 1609216, 'steps': 3142, 'batch_loss/train': 0.8920195316895843}
+12/22/2021 00:50:01 - INFO - codeparrot_training - Step 3143: {'lr': 0.0004956350919267653, 'samples': 1609728, 'steps': 3143, 'batch_loss/train': 0.8528318586759269}
+12/22/2021 00:50:12 - INFO - codeparrot_training - Step 3144: {'lr': 0.0004956321587148505, 'samples': 1610240, 'steps': 3144, 'batch_loss/train': 0.879759943112731}
+12/22/2021 00:50:22 - INFO - codeparrot_training - Step 3145: {'lr': 0.000495629224526395, 'samples': 1610752, 'steps': 3145, 'batch_loss/train': 0.7971174586564302}
+12/22/2021 00:50:33 - INFO - codeparrot_training - Step 3146: {'lr': 0.0004956262893614104, 'samples': 1611264, 'steps': 3146, 'batch_loss/train': 0.6952160979853943}
+12/22/2021 00:50:45 - INFO - codeparrot_training - Step 3147: {'lr': 0.0004956233532199084, 'samples': 1611776, 'steps': 3147, 'batch_loss/train': 0.8164999010041356}
+12/22/2021 00:50:55 - INFO - codeparrot_training - Step 3148: {'lr': 0.0004956204161019008, 'samples': 1612288, 'steps': 3148, 'batch_loss/train': 0.8433505753055215}
+12/22/2021 00:51:06 - INFO - codeparrot_training - Step 3149: {'lr': 0.0004956174780073991, 'samples': 1612800, 'steps': 3149, 'batch_loss/train': 0.8666272582486272}
+12/22/2021 00:51:19 - INFO - codeparrot_training - Step 3150: {'lr': 0.000495614538936415, 'samples': 1613312, 'steps': 3150, 'batch_loss/train': 1.1471748743206263}
+12/22/2021 00:51:30 - INFO - codeparrot_training - Step 3151: {'lr': 0.0004956115988889603, 'samples': 1613824, 'steps': 3151, 'batch_loss/train': 0.9273092318326235}
+12/22/2021 00:51:40 - INFO - codeparrot_training - Step 3152: {'lr': 0.0004956086578650466, 'samples': 1614336, 'steps': 3152, 'batch_loss/train': 0.8708318891003728}
+12/22/2021 00:51:52 - INFO - codeparrot_training - Step 3153: {'lr': 0.0004956057158646858, 'samples': 1614848, 'steps': 3153, 'batch_loss/train': 0.9029769892804325}
+12/22/2021 00:52:03 - INFO - codeparrot_training - Step 3154: {'lr': 0.0004956027728878891, 'samples': 1615360, 'steps': 3154, 'batch_loss/train': 0.6747975691687316}
+12/22/2021 00:52:14 - INFO - codeparrot_training - Step 3155: {'lr': 0.0004955998289346687, 'samples': 1615872, 'steps': 3155, 'batch_loss/train': 0.7828514622524381}
+12/22/2021 00:52:24 - INFO - codeparrot_training - Step 3156: {'lr': 0.000495596884005036, 'samples': 1616384, 'steps': 3156, 'batch_loss/train': 0.8458865177817643}
+12/22/2021 00:52:37 - INFO - codeparrot_training - Step 3157: {'lr': 0.0004955939380990029, 'samples': 1616896, 'steps': 3157, 'batch_loss/train': 0.8477370543405414}
+12/22/2021 00:52:47 - INFO - codeparrot_training - Step 3158: {'lr': 0.000495590991216581, 'samples': 1617408, 'steps': 3158, 'batch_loss/train': 0.9276319891214371}
+12/22/2021 00:52:58 - INFO - codeparrot_training - Step 3159: {'lr': 0.0004955880433577821, 'samples': 1617920, 'steps': 3159, 'batch_loss/train': 0.8668582211248577}
+12/22/2021 00:53:11 - INFO - codeparrot_training - Step 3160: {'lr': 0.0004955850945226179, 'samples': 1618432, 'steps': 3160, 'batch_loss/train': 0.8766002906486392}
+12/22/2021 00:53:21 - INFO - codeparrot_training - Step 3161: {'lr': 0.0004955821447110999, 'samples': 1618944, 'steps': 3161, 'batch_loss/train': 0.8407662138342857}
+12/22/2021 00:53:32 - INFO - codeparrot_training - Step 3162: {'lr': 0.0004955791939232402, 'samples': 1619456, 'steps': 3162, 'batch_loss/train': 0.9558550100773573}
+12/22/2021 00:53:44 - INFO - codeparrot_training - Step 3163: {'lr': 0.0004955762421590504, 'samples': 1619968, 'steps': 3163, 'batch_loss/train': 0.8579746903851628}
+12/22/2021 00:53:55 - INFO - codeparrot_training - Step 3164: {'lr': 0.0004955732894185421, 'samples': 1620480, 'steps': 3164, 'batch_loss/train': 0.8738546902313828}
+12/22/2021 00:54:05 - INFO - codeparrot_training - Step 3165: {'lr': 0.0004955703357017271, 'samples': 1620992, 'steps': 3165, 'batch_loss/train': 0.8202944239601493}
+12/22/2021 00:54:16 - INFO - codeparrot_training - Step 3166: {'lr': 0.0004955673810086172, 'samples': 1621504, 'steps': 3166, 'batch_loss/train': 0.9381919177249074}
+12/22/2021 00:54:28 - INFO - codeparrot_training - Step 3167: {'lr': 0.0004955644253392241, 'samples': 1622016, 'steps': 3167, 'batch_loss/train': 0.8512092921882868}
+12/22/2021 00:54:38 - INFO - codeparrot_training - Step 3168: {'lr': 0.0004955614686935596, 'samples': 1622528, 'steps': 3168, 'batch_loss/train': 0.7866478050127625}
+12/22/2021 00:54:49 - INFO - codeparrot_training - Step 3169: {'lr': 0.0004955585110716353, 'samples': 1623040, 'steps': 3169, 'batch_loss/train': 0.8045298187062144}
+12/22/2021 00:55:01 - INFO - codeparrot_training - Step 3170: {'lr': 0.0004955555524734632, 'samples': 1623552, 'steps': 3170, 'batch_loss/train': 0.9548365105874836}
+12/22/2021 00:55:12 - INFO - codeparrot_training - Step 3171: {'lr': 0.000495552592899055, 'samples': 1624064, 'steps': 3171, 'batch_loss/train': 0.8311224840581417}
+12/22/2021 00:55:22 - INFO - codeparrot_training - Step 3172: {'lr': 0.0004955496323484223, 'samples': 1624576, 'steps': 3172, 'batch_loss/train': 0.9350264267995954}
+12/22/2021 00:55:35 - INFO - codeparrot_training - Step 3173: {'lr': 0.000495546670821577, 'samples': 1625088, 'steps': 3173, 'batch_loss/train': 0.8304752875119448}
+12/22/2021 00:55:46 - INFO - codeparrot_training - Step 3174: {'lr': 0.0004955437083185308, 'samples': 1625600, 'steps': 3174, 'batch_loss/train': 0.9179609259590507}
+12/22/2021 00:55:56 - INFO - codeparrot_training - Step 3175: {'lr': 0.0004955407448392955, 'samples': 1626112, 'steps': 3175, 'batch_loss/train': 0.8328950349241495}
+12/22/2021 00:56:08 - INFO - codeparrot_training - Step 3176: {'lr': 0.000495537780383883, 'samples': 1626624, 'steps': 3176, 'batch_loss/train': 0.9142196793109179}
+12/22/2021 00:56:19 - INFO - codeparrot_training - Step 3177: {'lr': 0.0004955348149523051, 'samples': 1627136, 'steps': 3177, 'batch_loss/train': 0.892035293392837}
+12/22/2021 00:56:30 - INFO - codeparrot_training - Step 3178: {'lr': 0.0004955318485445734, 'samples': 1627648, 'steps': 3178, 'batch_loss/train': 0.9108480010181665}
+12/22/2021 00:56:40 - INFO - codeparrot_training - Step 3179: {'lr': 0.0004955288811606997, 'samples': 1628160, 'steps': 3179, 'batch_loss/train': 0.899305091239512}
+12/22/2021 00:56:52 - INFO - codeparrot_training - Step 3180: {'lr': 0.000495525912800696, 'samples': 1628672, 'steps': 3180, 'batch_loss/train': 0.8560072919353843}
+12/22/2021 00:57:03 - INFO - codeparrot_training - Step 3181: {'lr': 0.0004955229434645738, 'samples': 1629184, 'steps': 3181, 'batch_loss/train': 0.8620474515482783}
+12/22/2021 00:57:14 - INFO - codeparrot_training - Step 3182: {'lr': 0.0004955199731523453, 'samples': 1629696, 'steps': 3182, 'batch_loss/train': 0.8335727546364069}
+12/22/2021 00:57:26 - INFO - codeparrot_training - Step 3183: {'lr': 0.000495517001864022, 'samples': 1630208, 'steps': 3183, 'batch_loss/train': 0.7653261162340641}
+12/22/2021 00:57:37 - INFO - codeparrot_training - Step 3184: {'lr': 0.0004955140295996157, 'samples': 1630720, 'steps': 3184, 'batch_loss/train': 0.8150523398071527}
+12/22/2021 00:57:48 - INFO - codeparrot_training - Step 3185: {'lr': 0.0004955110563591384, 'samples': 1631232, 'steps': 3185, 'batch_loss/train': 0.9723459994420409}
+12/22/2021 00:58:00 - INFO - codeparrot_training - Step 3186: {'lr': 0.0004955080821426019, 'samples': 1631744, 'steps': 3186, 'batch_loss/train': 0.8903674529865384}
+12/22/2021 00:58:10 - INFO - codeparrot_training - Step 3187: {'lr': 0.0004955051069500179, 'samples': 1632256, 'steps': 3187, 'batch_loss/train': 0.9380496283993125}
+12/22/2021 00:58:21 - INFO - codeparrot_training - Step 3188: {'lr': 0.0004955021307813983, 'samples': 1632768, 'steps': 3188, 'batch_loss/train': 0.8543719546869397}
+12/22/2021 00:58:31 - INFO - codeparrot_training - Step 3189: {'lr': 0.000495499153636755, 'samples': 1633280, 'steps': 3189, 'batch_loss/train': 0.8932953625917435}
+12/22/2021 00:58:44 - INFO - codeparrot_training - Step 3190: {'lr': 0.0004954961755160996, 'samples': 1633792, 'steps': 3190, 'batch_loss/train': 0.8710927246138453}
+12/22/2021 00:58:55 - INFO - codeparrot_training - Step 3191: {'lr': 0.0004954931964194442, 'samples': 1634304, 'steps': 3191, 'batch_loss/train': 0.8828936778008938}
+12/22/2021 00:59:05 - INFO - codeparrot_training - Step 3192: {'lr': 0.0004954902163468006, 'samples': 1634816, 'steps': 3192, 'batch_loss/train': 0.9056357750669122}
+12/22/2021 00:59:17 - INFO - codeparrot_training - Step 3193: {'lr': 0.0004954872352981805, 'samples': 1635328, 'steps': 3193, 'batch_loss/train': 0.8068346404470503}
+12/22/2021 00:59:28 - INFO - codeparrot_training - Step 3194: {'lr': 0.0004954842532735959, 'samples': 1635840, 'steps': 3194, 'batch_loss/train': 0.8595417821779847}
+12/22/2021 00:59:39 - INFO - codeparrot_training - Step 3195: {'lr': 0.0004954812702730586, 'samples': 1636352, 'steps': 3195, 'batch_loss/train': 0.852472176309675}
+12/22/2021 00:59:51 - INFO - codeparrot_training - Step 3196: {'lr': 0.0004954782862965805, 'samples': 1636864, 'steps': 3196, 'batch_loss/train': 0.8074733950197697}
+12/22/2021 01:00:01 - INFO - codeparrot_training - Step 3197: {'lr': 0.0004954753013441732, 'samples': 1637376, 'steps': 3197, 'batch_loss/train': 0.8092804551124573}
+12/22/2021 01:00:12 - INFO - codeparrot_training - Step 3198: {'lr': 0.000495472315415849, 'samples': 1637888, 'steps': 3198, 'batch_loss/train': 0.8897005319595337}
+12/22/2021 01:00:22 - INFO - codeparrot_training - Step 3199: {'lr': 0.0004954693285116196, 'samples': 1638400, 'steps': 3199, 'batch_loss/train': 0.9762557428330183}
+12/22/2021 01:00:35 - INFO - codeparrot_training - Step 3200: {'lr': 0.0004954663406314967, 'samples': 1638912, 'steps': 3200, 'batch_loss/train': 0.8925016354769468}
+12/22/2021 01:00:46 - INFO - codeparrot_training - Step 3201: {'lr': 0.0004954633517754924, 'samples': 1639424, 'steps': 3201, 'batch_loss/train': 0.9250837806612253}
+12/22/2021 01:00:56 - INFO - codeparrot_training - Step 3202: {'lr': 0.0004954603619436184, 'samples': 1639936, 'steps': 3202, 'batch_loss/train': 0.940974947065115}
+12/22/2021 01:01:08 - INFO - codeparrot_training - Step 3203: {'lr': 0.0004954573711358868, 'samples': 1640448, 'steps': 3203, 'batch_loss/train': 0.7833749856799841}
+12/22/2021 01:01:19 - INFO - codeparrot_training - Step 3204: {'lr': 0.0004954543793523093, 'samples': 1640960, 'steps': 3204, 'batch_loss/train': 0.6777229853905737}
+12/22/2021 01:01:30 - INFO - codeparrot_training - Step 3205: {'lr': 0.0004954513865928979, 'samples': 1641472, 'steps': 3205, 'batch_loss/train': 0.8670973004773259}
+12/22/2021 01:01:42 - INFO - codeparrot_training - Step 3206: {'lr': 0.0004954483928576645, 'samples': 1641984, 'steps': 3206, 'batch_loss/train': 0.8695839610882103}
+12/22/2021 01:01:52 - INFO - codeparrot_training - Step 3207: {'lr': 0.0004954453981466209, 'samples': 1642496, 'steps': 3207, 'batch_loss/train': 0.9005298353731632}
+12/22/2021 01:02:03 - INFO - codeparrot_training - Step 3208: {'lr': 0.0004954424024597791, 'samples': 1643008, 'steps': 3208, 'batch_loss/train': 0.8060500612482429}
+12/22/2021 01:02:13 - INFO - codeparrot_training - Step 3209: {'lr': 0.000495439405797151, 'samples': 1643520, 'steps': 3209, 'batch_loss/train': 0.8038836251944304}
+12/22/2021 01:02:25 - INFO - codeparrot_training - Step 3210: {'lr': 0.0004954364081587484, 'samples': 1644032, 'steps': 3210, 'batch_loss/train': 0.8096551196649671}
+12/22/2021 01:02:36 - INFO - codeparrot_training - Step 3211: {'lr': 0.0004954334095445833, 'samples': 1644544, 'steps': 3211, 'batch_loss/train': 0.8127144649624825}
+12/22/2021 01:02:47 - INFO - codeparrot_training - Step 3212: {'lr': 0.0004954304099546678, 'samples': 1645056, 'steps': 3212, 'batch_loss/train': 0.9686018507927656}
+12/22/2021 01:03:00 - INFO - codeparrot_training - Step 3213: {'lr': 0.0004954274093890137, 'samples': 1645568, 'steps': 3213, 'batch_loss/train': 0.7230539321899414}
+12/22/2021 01:03:10 - INFO - codeparrot_training - Step 3214: {'lr': 0.0004954244078476327, 'samples': 1646080, 'steps': 3214, 'batch_loss/train': 0.8607652503997087}
+12/22/2021 01:03:21 - INFO - codeparrot_training - Step 3215: {'lr': 0.0004954214053305369, 'samples': 1646592, 'steps': 3215, 'batch_loss/train': 0.8517503682523966}
+12/22/2021 01:03:33 - INFO - codeparrot_training - Step 3216: {'lr': 0.0004954184018377385, 'samples': 1647104, 'steps': 3216, 'batch_loss/train': 0.9722456829622388}
+12/22/2021 01:03:43 - INFO - codeparrot_training - Step 3217: {'lr': 0.000495415397369249, 'samples': 1647616, 'steps': 3217, 'batch_loss/train': 0.9117504945024848}
+12/22/2021 01:03:54 - INFO - codeparrot_training - Step 3218: {'lr': 0.0004954123919250806, 'samples': 1648128, 'steps': 3218, 'batch_loss/train': 0.8294601608067751}
+12/22/2021 01:04:05 - INFO - codeparrot_training - Step 3219: {'lr': 0.0004954093855052452, 'samples': 1648640, 'steps': 3219, 'batch_loss/train': 0.8942053578794003}
+12/22/2021 01:04:18 - INFO - codeparrot_training - Step 3220: {'lr': 0.0004954063781097548, 'samples': 1649152, 'steps': 3220, 'batch_loss/train': 0.7798873065039515}
+12/22/2021 01:04:29 - INFO - codeparrot_training - Step 3221: {'lr': 0.0004954033697386212, 'samples': 1649664, 'steps': 3221, 'batch_loss/train': 1.4414020013064146}
+12/22/2021 01:04:39 - INFO - codeparrot_training - Step 3222: {'lr': 0.0004954003603918566, 'samples': 1650176, 'steps': 3222, 'batch_loss/train': 1.008320851251483}
+12/22/2021 01:04:52 - INFO - codeparrot_training - Step 3223: {'lr': 0.0004953973500694726, 'samples': 1650688, 'steps': 3223, 'batch_loss/train': 0.7174558758269995}
+12/22/2021 01:05:02 - INFO - codeparrot_training - Step 3224: {'lr': 0.0004953943387714816, 'samples': 1651200, 'steps': 3224, 'batch_loss/train': 0.7632359374547377}
+12/22/2021 01:05:13 - INFO - codeparrot_training - Step 3225: {'lr': 0.0004953913264978953, 'samples': 1651712, 'steps': 3225, 'batch_loss/train': 0.7568937296746299}
+12/22/2021 01:05:25 - INFO - codeparrot_training - Step 3226: {'lr': 0.0004953883132487257, 'samples': 1652224, 'steps': 3226, 'batch_loss/train': 0.8296248037368059}
+12/22/2021 01:05:36 - INFO - codeparrot_training - Step 3227: {'lr': 0.0004953852990239849, 'samples': 1652736, 'steps': 3227, 'batch_loss/train': 1.025816055946052}
+12/22/2021 01:05:46 - INFO - codeparrot_training - Step 3228: {'lr': 0.0004953822838236848, 'samples': 1653248, 'steps': 3228, 'batch_loss/train': 0.8397544547915459}
+12/22/2021 01:05:57 - INFO - codeparrot_training - Step 3229: {'lr': 0.0004953792676478373, 'samples': 1653760, 'steps': 3229, 'batch_loss/train': 0.9426050530746579}
+12/22/2021 01:06:10 - INFO - codeparrot_training - Step 3230: {'lr': 0.0004953762504964545, 'samples': 1654272, 'steps': 3230, 'batch_loss/train': 0.8729694799985737}
+12/22/2021 01:06:20 - INFO - codeparrot_training - Step 3231: {'lr': 0.0004953732323695484, 'samples': 1654784, 'steps': 3231, 'batch_loss/train': 1.198142415145412}
+12/22/2021 01:06:31 - INFO - codeparrot_training - Step 3232: {'lr': 0.000495370213267131, 'samples': 1655296, 'steps': 3232, 'batch_loss/train': 1.3036359138786793}
+12/22/2021 01:06:43 - INFO - codeparrot_training - Step 3233: {'lr': 0.0004953671931892143, 'samples': 1655808, 'steps': 3233, 'batch_loss/train': 0.8891704445704818}
+12/22/2021 01:06:54 - INFO - codeparrot_training - Step 3234: {'lr': 0.0004953641721358104, 'samples': 1656320, 'steps': 3234, 'batch_loss/train': 0.8976704366505146}
+12/22/2021 01:07:05 - INFO - codeparrot_training - Step 3235: {'lr': 0.0004953611501069309, 'samples': 1656832, 'steps': 3235, 'batch_loss/train': 0.8161741960793734}
+12/22/2021 01:07:15 - INFO - codeparrot_training - Step 3236: {'lr': 0.0004953581271025883, 'samples': 1657344, 'steps': 3236, 'batch_loss/train': 0.7266395227052271}
+12/22/2021 01:07:28 - INFO - codeparrot_training - Step 3237: {'lr': 0.0004953551031227944, 'samples': 1657856, 'steps': 3237, 'batch_loss/train': 0.8324987096711993}
+12/22/2021 01:07:38 - INFO - codeparrot_training - Step 3238: {'lr': 0.0004953520781675613, 'samples': 1658368, 'steps': 3238, 'batch_loss/train': 0.880282562226057}
+12/22/2021 01:07:49 - INFO - codeparrot_training - Step 3239: {'lr': 0.0004953490522369009, 'samples': 1658880, 'steps': 3239, 'batch_loss/train': 0.895488828420639}
+12/22/2021 01:08:01 - INFO - codeparrot_training - Step 3240: {'lr': 0.0004953460253308254, 'samples': 1659392, 'steps': 3240, 'batch_loss/train': 0.998632880859077}
+12/22/2021 01:08:12 - INFO - codeparrot_training - Step 3241: {'lr': 0.0004953429974493466, 'samples': 1659904, 'steps': 3241, 'batch_loss/train': 0.9156677424907684}
+12/22/2021 01:08:22 - INFO - codeparrot_training - Step 3242: {'lr': 0.0004953399685924769, 'samples': 1660416, 'steps': 3242, 'batch_loss/train': 0.8671466996893287}
+12/22/2021 01:08:34 - INFO - codeparrot_training - Step 3243: {'lr': 0.000495336938760228, 'samples': 1660928, 'steps': 3243, 'batch_loss/train': 0.800285778939724}
+12/22/2021 01:08:45 - INFO - codeparrot_training - Step 3244: {'lr': 0.000495333907952612, 'samples': 1661440, 'steps': 3244, 'batch_loss/train': 0.815495758317411}
+12/22/2021 01:08:55 - INFO - codeparrot_training - Step 3245: {'lr': 0.0004953308761696411, 'samples': 1661952, 'steps': 3245, 'batch_loss/train': 0.9219830073416233}
+12/22/2021 01:09:07 - INFO - codeparrot_training - Step 3246: {'lr': 0.0004953278434113272, 'samples': 1662464, 'steps': 3246, 'batch_loss/train': 0.8454957623034716}
+12/22/2021 01:09:18 - INFO - codeparrot_training - Step 3247: {'lr': 0.0004953248096776824, 'samples': 1662976, 'steps': 3247, 'batch_loss/train': 0.8319892371073365}
+12/22/2021 01:09:29 - INFO - codeparrot_training - Step 3248: {'lr': 0.0004953217749687189, 'samples': 1663488, 'steps': 3248, 'batch_loss/train': 0.8952219849452376}
+12/22/2021 01:09:39 - INFO - codeparrot_training - Step 3249: {'lr': 0.0004953187392844486, 'samples': 1664000, 'steps': 3249, 'batch_loss/train': 0.8613059027120471}
+12/22/2021 01:09:52 - INFO - codeparrot_training - Step 3250: {'lr': 0.0004953157026248836, 'samples': 1664512, 'steps': 3250, 'batch_loss/train': 0.9219053657725453}
+12/22/2021 01:10:03 - INFO - codeparrot_training - Step 3251: {'lr': 0.000495312664990036, 'samples': 1665024, 'steps': 3251, 'batch_loss/train': 0.9366052150726318}
+12/22/2021 01:10:13 - INFO - codeparrot_training - Step 3252: {'lr': 0.000495309626379918, 'samples': 1665536, 'steps': 3252, 'batch_loss/train': 0.811802089214325}
+12/22/2021 01:10:26 - INFO - codeparrot_training - Step 3253: {'lr': 0.0004953065867945414, 'samples': 1666048, 'steps': 3253, 'batch_loss/train': 0.8236198360100389}
+12/22/2021 01:10:36 - INFO - codeparrot_training - Step 3254: {'lr': 0.0004953035462339184, 'samples': 1666560, 'steps': 3254, 'batch_loss/train': 0.9514868892729282}
+12/22/2021 01:10:47 - INFO - codeparrot_training - Step 3255: {'lr': 0.0004953005046980613, 'samples': 1667072, 'steps': 3255, 'batch_loss/train': 0.7828476364957169}
+12/22/2021 01:10:59 - INFO - codeparrot_training - Step 3256: {'lr': 0.000495297462186982, 'samples': 1667584, 'steps': 3256, 'batch_loss/train': 0.7857782924547791}
+12/22/2021 01:11:10 - INFO - codeparrot_training - Step 3257: {'lr': 0.0004952944187006925, 'samples': 1668096, 'steps': 3257, 'batch_loss/train': 0.8527895710431039}
+12/22/2021 01:11:20 - INFO - codeparrot_training - Step 3258: {'lr': 0.000495291374239205, 'samples': 1668608, 'steps': 3258, 'batch_loss/train': 0.8169447779655457}
+12/22/2021 01:11:31 - INFO - codeparrot_training - Step 3259: {'lr': 0.0004952883288025316, 'samples': 1669120, 'steps': 3259, 'batch_loss/train': 0.993160692974925}
+12/22/2021 01:11:44 - INFO - codeparrot_training - Step 3260: {'lr': 0.0004952852823906844, 'samples': 1669632, 'steps': 3260, 'batch_loss/train': 0.8077951131854206}
+12/22/2021 01:11:54 - INFO - codeparrot_training - Step 3261: {'lr': 0.0004952822350036757, 'samples': 1670144, 'steps': 3261, 'batch_loss/train': 0.8177419197745621}
+12/22/2021 01:12:05 - INFO - codeparrot_training - Step 3262: {'lr': 0.0004952791866415174, 'samples': 1670656, 'steps': 3262, 'batch_loss/train': 0.8868386670947075}
+12/22/2021 01:12:17 - INFO - codeparrot_training - Step 3263: {'lr': 0.0004952761373042216, 'samples': 1671168, 'steps': 3263, 'batch_loss/train': 0.7827025903388858}
+12/22/2021 01:12:28 - INFO - codeparrot_training - Step 3264: {'lr': 0.0004952730869918005, 'samples': 1671680, 'steps': 3264, 'batch_loss/train': 0.8612278525251895}
+12/22/2021 01:12:38 - INFO - codeparrot_training - Step 3265: {'lr': 0.0004952700357042662, 'samples': 1672192, 'steps': 3265, 'batch_loss/train': 0.8218933547614142}
+12/22/2021 01:12:51 - INFO - codeparrot_training - Step 3266: {'lr': 0.0004952669834416309, 'samples': 1672704, 'steps': 3266, 'batch_loss/train': 0.820244312286377}
+12/22/2021 01:13:02 - INFO - codeparrot_training - Step 3267: {'lr': 0.0004952639302039067, 'samples': 1673216, 'steps': 3267, 'batch_loss/train': 0.8839958850294352}
+12/22/2021 01:13:12 - INFO - codeparrot_training - Step 3268: {'lr': 0.0004952608759911057, 'samples': 1673728, 'steps': 3268, 'batch_loss/train': 0.9420266337692738}
+12/22/2021 01:13:23 - INFO - codeparrot_training - Step 3269: {'lr': 0.00049525782080324, 'samples': 1674240, 'steps': 3269, 'batch_loss/train': 0.9000209402292967}
+12/22/2021 01:13:35 - INFO - codeparrot_training - Step 3270: {'lr': 0.0004952547646403219, 'samples': 1674752, 'steps': 3270, 'batch_loss/train': 0.9081681515090168}
+12/22/2021 01:13:46 - INFO - codeparrot_training - Step 3271: {'lr': 0.0004952517075023634, 'samples': 1675264, 'steps': 3271, 'batch_loss/train': 0.8225785752292722}
+12/22/2021 01:13:56 - INFO - codeparrot_training - Step 3272: {'lr': 0.0004952486493893768, 'samples': 1675776, 'steps': 3272, 'batch_loss/train': 0.9075093939900398}
+12/22/2021 01:14:08 - INFO - codeparrot_training - Step 3273: {'lr': 0.000495245590301374, 'samples': 1676288, 'steps': 3273, 'batch_loss/train': 0.8571320325136185}
+12/22/2021 01:14:19 - INFO - codeparrot_training - Step 3274: {'lr': 0.0004952425302383675, 'samples': 1676800, 'steps': 3274, 'batch_loss/train': 0.742012869566679}
+12/22/2021 01:14:30 - INFO - codeparrot_training - Step 3275: {'lr': 0.0004952394692003692, 'samples': 1677312, 'steps': 3275, 'batch_loss/train': 0.8040602137334645}
+12/22/2021 01:14:42 - INFO - codeparrot_training - Step 3276: {'lr': 0.0004952364071873915, 'samples': 1677824, 'steps': 3276, 'batch_loss/train': 0.8436339679174125}
+12/22/2021 01:14:52 - INFO - codeparrot_training - Step 3277: {'lr': 0.0004952333441994464, 'samples': 1678336, 'steps': 3277, 'batch_loss/train': 0.883572404505685}
+12/22/2021 01:15:03 - INFO - codeparrot_training - Step 3278: {'lr': 0.000495230280236546, 'samples': 1678848, 'steps': 3278, 'batch_loss/train': 0.8778392914682627}
+12/22/2021 01:15:16 - INFO - codeparrot_training - Step 3279: {'lr': 0.0004952272152987026, 'samples': 1679360, 'steps': 3279, 'batch_loss/train': 0.8123840838670731}
+12/22/2021 01:15:26 - INFO - codeparrot_training - Step 3280: {'lr': 0.0004952241493859285, 'samples': 1679872, 'steps': 3280, 'batch_loss/train': 0.7877422538585961}
+12/22/2021 01:15:37 - INFO - codeparrot_training - Step 3281: {'lr': 0.0004952210824982357, 'samples': 1680384, 'steps': 3281, 'batch_loss/train': 0.9263921580277383}
+12/22/2021 01:15:48 - INFO - codeparrot_training - Step 3282: {'lr': 0.0004952180146356365, 'samples': 1680896, 'steps': 3282, 'batch_loss/train': 1.0066408598795533}
+12/22/2021 01:16:00 - INFO - codeparrot_training - Step 3283: {'lr': 0.0004952149457981432, 'samples': 1681408, 'steps': 3283, 'batch_loss/train': 0.7316201319918036}
+12/22/2021 01:16:10 - INFO - codeparrot_training - Step 3284: {'lr': 0.0004952118759857677, 'samples': 1681920, 'steps': 3284, 'batch_loss/train': 0.8549640281125903}
+12/22/2021 01:16:21 - INFO - codeparrot_training - Step 3285: {'lr': 0.0004952088051985224, 'samples': 1682432, 'steps': 3285, 'batch_loss/train': 0.827948659658432}
+12/22/2021 01:16:33 - INFO - codeparrot_training - Step 3286: {'lr': 0.0004952057334364194, 'samples': 1682944, 'steps': 3286, 'batch_loss/train': 0.8094743508845568}
+12/22/2021 01:16:43 - INFO - codeparrot_training - Step 3287: {'lr': 0.0004952026606994711, 'samples': 1683456, 'steps': 3287, 'batch_loss/train': 0.8417792990803719}
+12/22/2021 01:16:54 - INFO - codeparrot_training - Step 3288: {'lr': 0.0004951995869876897, 'samples': 1683968, 'steps': 3288, 'batch_loss/train': 0.9162263749167323}
+12/22/2021 01:17:07 - INFO - codeparrot_training - Step 3289: {'lr': 0.0004951965123010871, 'samples': 1684480, 'steps': 3289, 'batch_loss/train': 0.8527079345658422}
+12/22/2021 01:17:17 - INFO - codeparrot_training - Step 3290: {'lr': 0.0004951934366396759, 'samples': 1684992, 'steps': 3290, 'batch_loss/train': 0.848004000261426}
+12/22/2021 01:17:28 - INFO - codeparrot_training - Step 3291: {'lr': 0.0004951903600034681, 'samples': 1685504, 'steps': 3291, 'batch_loss/train': 0.8483575042337179}
+12/22/2021 01:17:38 - INFO - codeparrot_training - Step 3292: {'lr': 0.0004951872823924761, 'samples': 1686016, 'steps': 3292, 'batch_loss/train': 0.9069962371140718}
+12/22/2021 01:17:51 - INFO - codeparrot_training - Step 3293: {'lr': 0.0004951842038067119, 'samples': 1686528, 'steps': 3293, 'batch_loss/train': 0.8679569992236793}
+12/22/2021 01:18:01 - INFO - codeparrot_training - Step 3294: {'lr': 0.000495181124246188, 'samples': 1687040, 'steps': 3294, 'batch_loss/train': 0.9147716956213117}
+12/22/2021 01:18:12 - INFO - codeparrot_training - Step 3295: {'lr': 0.0004951780437109165, 'samples': 1687552, 'steps': 3295, 'batch_loss/train': 0.9453265117481351}
+12/22/2021 01:18:25 - INFO - codeparrot_training - Step 3296: {'lr': 0.0004951749622009096, 'samples': 1688064, 'steps': 3296, 'batch_loss/train': 0.8698658663779497}
+12/22/2021 01:18:35 - INFO - codeparrot_training - Step 3297: {'lr': 0.0004951718797161798, 'samples': 1688576, 'steps': 3297, 'batch_loss/train': 1.720781633630395}
+12/22/2021 01:18:46 - INFO - codeparrot_training - Step 3298: {'lr': 0.000495168796256739, 'samples': 1689088, 'steps': 3298, 'batch_loss/train': 1.0057665100321174}
+12/22/2021 01:18:58 - INFO - codeparrot_training - Step 3299: {'lr': 0.0004951657118225998, 'samples': 1689600, 'steps': 3299, 'batch_loss/train': 0.9691520966589451}
+12/22/2021 01:19:09 - INFO - codeparrot_training - Step 3300: {'lr': 0.0004951626264137741, 'samples': 1690112, 'steps': 3300, 'batch_loss/train': 0.9822781444527209}
+12/22/2021 01:19:19 - INFO - codeparrot_training - Step 3301: {'lr': 0.0004951595400302745, 'samples': 1690624, 'steps': 3301, 'batch_loss/train': 0.9080630950629711}
+12/22/2021 01:19:30 - INFO - codeparrot_training - Step 3302: {'lr': 0.0004951564526721131, 'samples': 1691136, 'steps': 3302, 'batch_loss/train': 0.8833744712173939}
+12/22/2021 01:19:42 - INFO - codeparrot_training - Step 3303: {'lr': 0.0004951533643393022, 'samples': 1691648, 'steps': 3303, 'batch_loss/train': 0.8311827890574932}
+12/22/2021 01:19:53 - INFO - codeparrot_training - Step 3304: {'lr': 0.0004951502750318541, 'samples': 1692160, 'steps': 3304, 'batch_loss/train': 0.8668560776859522}
+12/22/2021 01:20:03 - INFO - codeparrot_training - Step 3305: {'lr': 0.0004951471847497812, 'samples': 1692672, 'steps': 3305, 'batch_loss/train': 0.8658565212972462}
+12/22/2021 01:20:16 - INFO - codeparrot_training - Step 3306: {'lr': 0.0004951440934930955, 'samples': 1693184, 'steps': 3306, 'batch_loss/train': 0.9992596823722124}
+12/22/2021 01:20:27 - INFO - codeparrot_training - Step 3307: {'lr': 0.0004951410012618095, 'samples': 1693696, 'steps': 3307, 'batch_loss/train': 0.9248998183757067}
+12/22/2021 01:20:37 - INFO - codeparrot_training - Step 3308: {'lr': 0.0004951379080559354, 'samples': 1694208, 'steps': 3308, 'batch_loss/train': 0.9645476881414652}
+12/22/2021 01:20:49 - INFO - codeparrot_training - Step 3309: {'lr': 0.0004951348138754856, 'samples': 1694720, 'steps': 3309, 'batch_loss/train': 0.8214915383141488}
+12/22/2021 01:21:00 - INFO - codeparrot_training - Step 3310: {'lr': 0.0004951317187204724, 'samples': 1695232, 'steps': 3310, 'batch_loss/train': 0.9077181573957205}
+12/22/2021 01:21:11 - INFO - codeparrot_training - Step 3311: {'lr': 0.0004951286225909078, 'samples': 1695744, 'steps': 3311, 'batch_loss/train': 0.8042204430093989}
+12/22/2021 01:21:21 - INFO - codeparrot_training - Step 3312: {'lr': 0.0004951255254868046, 'samples': 1696256, 'steps': 3312, 'batch_loss/train': 0.7171985658351332}
+12/22/2021 01:21:33 - INFO - codeparrot_training - Step 3313: {'lr': 0.0004951224274081748, 'samples': 1696768, 'steps': 3313, 'batch_loss/train': 0.913719198666513}
+12/22/2021 01:21:44 - INFO - codeparrot_training - Step 3314: {'lr': 0.0004951193283550307, 'samples': 1697280, 'steps': 3314, 'batch_loss/train': 0.7739215805195272}
+12/22/2021 01:21:55 - INFO - codeparrot_training - Step 3315: {'lr': 0.0004951162283273848, 'samples': 1697792, 'steps': 3315, 'batch_loss/train': 0.8415600573644042}
+12/22/2021 01:22:08 - INFO - codeparrot_training - Step 3316: {'lr': 0.0004951131273252492, 'samples': 1698304, 'steps': 3316, 'batch_loss/train': 0.8914443589746952}
+12/22/2021 01:22:18 - INFO - codeparrot_training - Step 3317: {'lr': 0.0004951100253486365, 'samples': 1698816, 'steps': 3317, 'batch_loss/train': 0.8173208148218691}
+12/22/2021 01:22:29 - INFO - codeparrot_training - Step 3318: {'lr': 0.0004951069223975589, 'samples': 1699328, 'steps': 3318, 'batch_loss/train': 0.9111671587452292}
+12/22/2021 01:22:41 - INFO - codeparrot_training - Step 3319: {'lr': 0.0004951038184720286, 'samples': 1699840, 'steps': 3319, 'batch_loss/train': 0.8911869488656521}
+12/22/2021 01:22:52 - INFO - codeparrot_training - Step 3320: {'lr': 0.0004951007135720582, 'samples': 1700352, 'steps': 3320, 'batch_loss/train': 0.9127333955839276}
+12/22/2021 01:23:02 - INFO - codeparrot_training - Step 3321: {'lr': 0.0004950976076976598, 'samples': 1700864, 'steps': 3321, 'batch_loss/train': 0.8426312864758074}
+12/22/2021 01:23:14 - INFO - codeparrot_training - Step 3322: {'lr': 0.0004950945008488459, 'samples': 1701376, 'steps': 3322, 'batch_loss/train': 0.8474989314563572}
+12/22/2021 01:23:25 - INFO - codeparrot_training - Step 3323: {'lr': 0.0004950913930256288, 'samples': 1701888, 'steps': 3323, 'batch_loss/train': 0.7600602176971734}
+12/22/2021 01:23:36 - INFO - codeparrot_training - Step 3324: {'lr': 0.0004950882842280209, 'samples': 1702400, 'steps': 3324, 'batch_loss/train': 0.8494994239881635}
+12/22/2021 01:23:46 - INFO - codeparrot_training - Step 3325: {'lr': 0.0004950851744560345, 'samples': 1702912, 'steps': 3325, 'batch_loss/train': 0.8507796199992299}
+12/22/2021 01:23:59 - INFO - codeparrot_training - Step 3326: {'lr': 0.0004950820637096819, 'samples': 1703424, 'steps': 3326, 'batch_loss/train': 0.8060475625097752}
+12/22/2021 01:24:10 - INFO - codeparrot_training - Step 3327: {'lr': 0.0004950789519889756, 'samples': 1703936, 'steps': 3327, 'batch_loss/train': 0.7596516348421574}
+12/22/2021 01:24:20 - INFO - codeparrot_training - Step 3328: {'lr': 0.0004950758392939281, 'samples': 1704448, 'steps': 3328, 'batch_loss/train': 0.8100775023922324}
+12/22/2021 01:24:32 - INFO - codeparrot_training - Step 3329: {'lr': 0.0004950727256245514, 'samples': 1704960, 'steps': 3329, 'batch_loss/train': 0.8798440617974848}
+12/22/2021 01:24:43 - INFO - codeparrot_training - Step 3330: {'lr': 0.0004950696109808581, 'samples': 1705472, 'steps': 3330, 'batch_loss/train': 0.9333367650397122}
+12/22/2021 01:24:54 - INFO - codeparrot_training - Step 3331: {'lr': 0.0004950664953628606, 'samples': 1705984, 'steps': 3331, 'batch_loss/train': 0.8974853558465838}
+12/22/2021 01:25:06 - INFO - codeparrot_training - Step 3332: {'lr': 0.0004950633787705712, 'samples': 1706496, 'steps': 3332, 'batch_loss/train': 0.9606946017593145}
+12/22/2021 01:25:16 - INFO - codeparrot_training - Step 3333: {'lr': 0.0004950602612040024, 'samples': 1707008, 'steps': 3333, 'batch_loss/train': 0.7826344245113432}
+12/22/2021 01:25:27 - INFO - codeparrot_training - Step 3334: {'lr': 0.0004950571426631666, 'samples': 1707520, 'steps': 3334, 'batch_loss/train': 0.7861535400152206}
+12/22/2021 01:25:38 - INFO - codeparrot_training - Step 3335: {'lr': 0.000495054023148076, 'samples': 1708032, 'steps': 3335, 'batch_loss/train': 0.8086537765339017}
+12/22/2021 01:25:50 - INFO - codeparrot_training - Step 3336: {'lr': 0.0004950509026587432, 'samples': 1708544, 'steps': 3336, 'batch_loss/train': 0.8678730884566903}
+12/22/2021 01:26:01 - INFO - codeparrot_training - Step 3337: {'lr': 0.0004950477811951805, 'samples': 1709056, 'steps': 3337, 'batch_loss/train': 0.7900496572256088}
+12/22/2021 01:26:11 - INFO - codeparrot_training - Step 3338: {'lr': 0.0004950446587574003, 'samples': 1709568, 'steps': 3338, 'batch_loss/train': 0.8214613827876747}
+12/22/2021 01:26:24 - INFO - codeparrot_training - Step 3339: {'lr': 0.0004950415353454152, 'samples': 1710080, 'steps': 3339, 'batch_loss/train': 0.8419863726012409}
+12/22/2021 01:26:35 - INFO - codeparrot_training - Step 3340: {'lr': 0.0004950384109592374, 'samples': 1710592, 'steps': 3340, 'batch_loss/train': 0.7351262625306845}
+12/22/2021 01:26:45 - INFO - codeparrot_training - Step 3341: {'lr': 0.0004950352855988794, 'samples': 1711104, 'steps': 3341, 'batch_loss/train': 0.823459388804622}
+12/22/2021 01:26:57 - INFO - codeparrot_training - Step 3342: {'lr': 0.0004950321592643536, 'samples': 1711616, 'steps': 3342, 'batch_loss/train': 0.8006290141493082}
+12/22/2021 01:27:08 - INFO - codeparrot_training - Step 3343: {'lr': 0.0004950290319556726, 'samples': 1712128, 'steps': 3343, 'batch_loss/train': 0.9133477415889502}
+12/22/2021 01:27:18 - INFO - codeparrot_training - Step 3344: {'lr': 0.0004950259036728485, 'samples': 1712640, 'steps': 3344, 'batch_loss/train': 0.8628484271466732}
+12/22/2021 01:27:29 - INFO - codeparrot_training - Step 3345: {'lr': 0.0004950227744158941, 'samples': 1713152, 'steps': 3345, 'batch_loss/train': 0.832843164447695}
+12/22/2021 01:27:42 - INFO - codeparrot_training - Step 3346: {'lr': 0.0004950196441848215, 'samples': 1713664, 'steps': 3346, 'batch_loss/train': 0.8937053717672825}
+12/22/2021 01:27:52 - INFO - codeparrot_training - Step 3347: {'lr': 0.0004950165129796434, 'samples': 1714176, 'steps': 3347, 'batch_loss/train': 0.9066405529156327}
+12/22/2021 01:28:03 - INFO - codeparrot_training - Step 3348: {'lr': 0.0004950133808003721, 'samples': 1714688, 'steps': 3348, 'batch_loss/train': 0.8267844850197434}
+12/22/2021 01:28:15 - INFO - codeparrot_training - Step 3349: {'lr': 0.0004950102476470202, 'samples': 1715200, 'steps': 3349, 'batch_loss/train': 0.8786013047210872}
+12/22/2021 01:28:26 - INFO - codeparrot_training - Step 3350: {'lr': 0.0004950071135196001, 'samples': 1715712, 'steps': 3350, 'batch_loss/train': 0.8179828943684697}
+12/22/2021 01:28:36 - INFO - codeparrot_training - Step 3351: {'lr': 0.000495003978418124, 'samples': 1716224, 'steps': 3351, 'batch_loss/train': 0.8873338755220175}
+12/22/2021 01:28:48 - INFO - codeparrot_training - Step 3352: {'lr': 0.0004950008423426047, 'samples': 1716736, 'steps': 3352, 'batch_loss/train': 0.8418361209332943}
+12/22/2021 01:28:59 - INFO - codeparrot_training - Step 3353: {'lr': 0.0004949977052930547, 'samples': 1717248, 'steps': 3353, 'batch_loss/train': 0.8470705589279532}
+12/22/2021 01:29:10 - INFO - codeparrot_training - Step 3354: {'lr': 0.0004949945672694862, 'samples': 1717760, 'steps': 3354, 'batch_loss/train': 0.9693102296441793}
+12/22/2021 01:29:20 - INFO - codeparrot_training - Step 3355: {'lr': 0.0004949914282719118, 'samples': 1718272, 'steps': 3355, 'batch_loss/train': 0.8353178454563022}
+12/22/2021 01:29:33 - INFO - codeparrot_training - Step 3356: {'lr': 0.000494988288300344, 'samples': 1718784, 'steps': 3356, 'batch_loss/train': 1.6879682741127908}
+12/22/2021 01:29:43 - INFO - codeparrot_training - Step 3357: {'lr': 0.0004949851473547953, 'samples': 1719296, 'steps': 3357, 'batch_loss/train': 0.8219684339128435}
+12/22/2021 01:29:54 - INFO - codeparrot_training - Step 3358: {'lr': 0.0004949820054352782, 'samples': 1719808, 'steps': 3358, 'batch_loss/train': 0.886695166118443}
+12/22/2021 01:30:07 - INFO - codeparrot_training - Step 3359: {'lr': 0.0004949788625418051, 'samples': 1720320, 'steps': 3359, 'batch_loss/train': 0.8939358908683062}
+12/22/2021 01:30:17 - INFO - codeparrot_training - Step 3360: {'lr': 0.0004949757186743886, 'samples': 1720832, 'steps': 3360, 'batch_loss/train': 0.8564875368028879}
+12/22/2021 01:30:28 - INFO - codeparrot_training - Step 3361: {'lr': 0.0004949725738330411, 'samples': 1721344, 'steps': 3361, 'batch_loss/train': 0.8089627851732075}
+12/22/2021 01:30:40 - INFO - codeparrot_training - Step 3362: {'lr': 0.000494969428017775, 'samples': 1721856, 'steps': 3362, 'batch_loss/train': 0.8794811833649874}
+12/22/2021 01:30:51 - INFO - codeparrot_training - Step 3363: {'lr': 0.0004949662812286031, 'samples': 1722368, 'steps': 3363, 'batch_loss/train': 0.8640848947688937}
+12/22/2021 01:31:01 - INFO - codeparrot_training - Step 3364: {'lr': 0.0004949631334655377, 'samples': 1722880, 'steps': 3364, 'batch_loss/train': 0.9145896658301353}
+12/22/2021 01:31:12 - INFO - codeparrot_training - Step 3365: {'lr': 0.0004949599847285915, 'samples': 1723392, 'steps': 3365, 'batch_loss/train': 0.7617625597631559}
+12/22/2021 01:31:25 - INFO - codeparrot_training - Step 3366: {'lr': 0.0004949568350177768, 'samples': 1723904, 'steps': 3366, 'batch_loss/train': 0.9003536608070135}
+12/22/2021 01:31:36 - INFO - codeparrot_training - Step 3367: {'lr': 0.0004949536843331063, 'samples': 1724416, 'steps': 3367, 'batch_loss/train': 0.8585276575759053}
+12/22/2021 01:31:47 - INFO - codeparrot_training - Step 3368: {'lr': 0.0004949505326745923, 'samples': 1724928, 'steps': 3368, 'batch_loss/train': 0.7112729009240866}
+12/22/2021 01:31:59 - INFO - codeparrot_training - Step 3369: {'lr': 0.0004949473800422476, 'samples': 1725440, 'steps': 3369, 'batch_loss/train': 0.7274879766628146}
+12/22/2021 01:32:09 - INFO - codeparrot_training - Step 3370: {'lr': 0.0004949442264360845, 'samples': 1725952, 'steps': 3370, 'batch_loss/train': 0.9315635552629828}
+12/22/2021 01:32:20 - INFO - codeparrot_training - Step 3371: {'lr': 0.0004949410718561157, 'samples': 1726464, 'steps': 3371, 'batch_loss/train': 0.7658983878791332}
+12/22/2021 01:32:32 - INFO - codeparrot_training - Step 3372: {'lr': 0.0004949379163023536, 'samples': 1726976, 'steps': 3372, 'batch_loss/train': 0.9245859263464808}
+12/22/2021 01:32:43 - INFO - codeparrot_training - Step 3373: {'lr': 0.0004949347597748109, 'samples': 1727488, 'steps': 3373, 'batch_loss/train': 0.9659429499879479}
+12/22/2021 01:32:53 - INFO - codeparrot_training - Step 3374: {'lr': 0.0004949316022735001, 'samples': 1728000, 'steps': 3374, 'batch_loss/train': 0.9042179335374385}
+12/22/2021 01:33:04 - INFO - codeparrot_training - Step 3375: {'lr': 0.0004949284437984337, 'samples': 1728512, 'steps': 3375, 'batch_loss/train': 0.830235549248755}
+12/22/2021 01:33:17 - INFO - codeparrot_training - Step 3376: {'lr': 0.0004949252843496244, 'samples': 1729024, 'steps': 3376, 'batch_loss/train': 0.7931954357773066}
+12/22/2021 01:33:27 - INFO - codeparrot_training - Step 3377: {'lr': 0.0004949221239270845, 'samples': 1729536, 'steps': 3377, 'batch_loss/train': 0.8651972180232406}
+12/22/2021 01:33:38 - INFO - codeparrot_training - Step 3378: {'lr': 0.0004949189625308268, 'samples': 1730048, 'steps': 3378, 'batch_loss/train': 0.8280920311808586}
+12/22/2021 01:33:50 - INFO - codeparrot_training - Step 3379: {'lr': 0.0004949158001608636, 'samples': 1730560, 'steps': 3379, 'batch_loss/train': 0.8807862750254571}
+12/22/2021 01:34:01 - INFO - codeparrot_training - Step 3380: {'lr': 0.0004949126368172079, 'samples': 1731072, 'steps': 3380, 'batch_loss/train': 0.9043366210535169}
+12/22/2021 01:34:11 - INFO - codeparrot_training - Step 3381: {'lr': 0.000494909472499872, 'samples': 1731584, 'steps': 3381, 'batch_loss/train': 0.797097334638238}
+12/22/2021 01:34:24 - INFO - codeparrot_training - Step 3382: {'lr': 0.0004949063072088684, 'samples': 1732096, 'steps': 3382, 'batch_loss/train': 0.8598443325608969}
+12/22/2021 01:34:35 - INFO - codeparrot_training - Step 3383: {'lr': 0.0004949031409442099, 'samples': 1732608, 'steps': 3383, 'batch_loss/train': 0.8089424767531455}
+12/22/2021 01:34:45 - INFO - codeparrot_training - Step 3384: {'lr': 0.0004948999737059089, 'samples': 1733120, 'steps': 3384, 'batch_loss/train': 0.9327204441651702}
+12/22/2021 01:34:56 - INFO - codeparrot_training - Step 3385: {'lr': 0.000494896805493978, 'samples': 1733632, 'steps': 3385, 'batch_loss/train': 0.927832999266684}
+12/22/2021 01:35:08 - INFO - codeparrot_training - Step 3386: {'lr': 0.00049489363630843, 'samples': 1734144, 'steps': 3386, 'batch_loss/train': 0.8636948452331126}
+12/22/2021 01:35:19 - INFO - codeparrot_training - Step 3387: {'lr': 0.0004948904661492774, 'samples': 1734656, 'steps': 3387, 'batch_loss/train': 0.9479699833318591}
+12/22/2021 01:35:29 - INFO - codeparrot_training - Step 3388: {'lr': 0.0004948872950165326, 'samples': 1735168, 'steps': 3388, 'batch_loss/train': 0.7856004713103175}
+12/22/2021 01:35:41 - INFO - codeparrot_training - Step 3389: {'lr': 0.0004948841229102086, 'samples': 1735680, 'steps': 3389, 'batch_loss/train': 0.8151787873357534}
+12/22/2021 01:35:52 - INFO - codeparrot_training - Step 3390: {'lr': 0.0004948809498303176, 'samples': 1736192, 'steps': 3390, 'batch_loss/train': 0.8436945173889399}
+12/22/2021 01:36:03 - INFO - codeparrot_training - Step 3391: {'lr': 0.0004948777757768725, 'samples': 1736704, 'steps': 3391, 'batch_loss/train': 0.8598989369347692}
+12/22/2021 01:36:15 - INFO - codeparrot_training - Step 3392: {'lr': 0.0004948746007498859, 'samples': 1737216, 'steps': 3392, 'batch_loss/train': 0.9182702000252903}
+12/22/2021 01:36:25 - INFO - codeparrot_training - Step 3393: {'lr': 0.0004948714247493703, 'samples': 1737728, 'steps': 3393, 'batch_loss/train': 0.8036752948537469}
+12/22/2021 01:36:36 - INFO - codeparrot_training - Step 3394: {'lr': 0.0004948682477753383, 'samples': 1738240, 'steps': 3394, 'batch_loss/train': 0.8835043162107468}
+12/22/2021 01:36:47 - INFO - codeparrot_training - Step 3395: {'lr': 0.0004948650698278027, 'samples': 1738752, 'steps': 3395, 'batch_loss/train': 0.9211112689226866}
+12/22/2021 01:37:00 - INFO - codeparrot_training - Step 3396: {'lr': 0.000494861890906776, 'samples': 1739264, 'steps': 3396, 'batch_loss/train': 0.610370030393824}
+12/22/2021 01:37:10 - INFO - codeparrot_training - Step 3397: {'lr': 0.0004948587110122708, 'samples': 1739776, 'steps': 3397, 'batch_loss/train': 0.8418231131508946}
+12/22/2021 01:37:21 - INFO - codeparrot_training - Step 3398: {'lr': 0.0004948555301442999, 'samples': 1740288, 'steps': 3398, 'batch_loss/train': 0.8670580238103867}
+12/22/2021 01:37:33 - INFO - codeparrot_training - Step 3399: {'lr': 0.0004948523483028759, 'samples': 1740800, 'steps': 3399, 'batch_loss/train': 0.8117843121290207}
+12/22/2021 01:37:44 - INFO - codeparrot_training - Step 3400: {'lr': 0.0004948491654880113, 'samples': 1741312, 'steps': 3400, 'batch_loss/train': 0.7641113931313157}
+12/22/2021 01:37:54 - INFO - codeparrot_training - Step 3401: {'lr': 0.000494845981699719, 'samples': 1741824, 'steps': 3401, 'batch_loss/train': 0.748710936284624}
+12/22/2021 01:38:06 - INFO - codeparrot_training - Step 3402: {'lr': 0.0004948427969380115, 'samples': 1742336, 'steps': 3402, 'batch_loss/train': 0.9423190783709288}
+12/22/2021 01:38:17 - INFO - codeparrot_training - Step 3403: {'lr': 0.0004948396112029014, 'samples': 1742848, 'steps': 3403, 'batch_loss/train': 0.8834946695715189}
+12/22/2021 01:38:28 - INFO - codeparrot_training - Step 3404: {'lr': 0.0004948364244944015, 'samples': 1743360, 'steps': 3404, 'batch_loss/train': 0.8975165830925107}
+12/22/2021 01:38:40 - INFO - codeparrot_training - Step 3405: {'lr': 0.0004948332368125244, 'samples': 1743872, 'steps': 3405, 'batch_loss/train': 0.8442022111266851}
+12/22/2021 01:38:51 - INFO - codeparrot_training - Step 3406: {'lr': 0.0004948300481572829, 'samples': 1744384, 'steps': 3406, 'batch_loss/train': 1.59714859072119}
+12/22/2021 01:39:02 - INFO - codeparrot_training - Step 3407: {'lr': 0.0004948268585286895, 'samples': 1744896, 'steps': 3407, 'batch_loss/train': 0.5950370144564658}
+12/22/2021 01:39:12 - INFO - codeparrot_training - Step 3408: {'lr': 0.0004948236679267569, 'samples': 1745408, 'steps': 3408, 'batch_loss/train': 0.7973870933055878}
+12/22/2021 01:39:24 - INFO - codeparrot_training - Step 3409: {'lr': 0.0004948204763514979, 'samples': 1745920, 'steps': 3409, 'batch_loss/train': 0.7612559555564076}
+12/22/2021 01:39:35 - INFO - codeparrot_training - Step 3410: {'lr': 0.0004948172838029251, 'samples': 1746432, 'steps': 3410, 'batch_loss/train': 0.9103408735245466}
+12/22/2021 01:39:46 - INFO - codeparrot_training - Step 3411: {'lr': 0.0004948140902810513, 'samples': 1746944, 'steps': 3411, 'batch_loss/train': 0.8794205598533154}
+12/22/2021 01:39:58 - INFO - codeparrot_training - Step 3412: {'lr': 0.000494810895785889, 'samples': 1747456, 'steps': 3412, 'batch_loss/train': 0.8798856721259654}
+12/22/2021 01:40:09 - INFO - codeparrot_training - Step 3413: {'lr': 0.000494807700317451, 'samples': 1747968, 'steps': 3413, 'batch_loss/train': 0.8439251352101564}
+12/22/2021 01:40:19 - INFO - codeparrot_training - Step 3414: {'lr': 0.0004948045038757502, 'samples': 1748480, 'steps': 3414, 'batch_loss/train': 0.865317358635366}
+12/22/2021 01:40:32 - INFO - codeparrot_training - Step 3415: {'lr': 0.000494801306460799, 'samples': 1748992, 'steps': 3415, 'batch_loss/train': 0.7499922765418887}
+12/22/2021 01:40:43 - INFO - codeparrot_training - Step 3416: {'lr': 0.0004947981080726102, 'samples': 1749504, 'steps': 3416, 'batch_loss/train': 0.8782188044860959}
+12/22/2021 01:40:53 - INFO - codeparrot_training - Step 3417: {'lr': 0.0004947949087111967, 'samples': 1750016, 'steps': 3417, 'batch_loss/train': 0.8633600249886513}
+12/22/2021 01:41:04 - INFO - codeparrot_training - Step 3418: {'lr': 0.0004947917083765709, 'samples': 1750528, 'steps': 3418, 'batch_loss/train': 0.8563424134626985}
+12/22/2021 01:41:16 - INFO - codeparrot_training - Step 3419: {'lr': 0.0004947885070687457, 'samples': 1751040, 'steps': 3419, 'batch_loss/train': 0.8643941758200526}
+12/22/2021 01:41:27 - INFO - codeparrot_training - Step 3420: {'lr': 0.000494785304787734, 'samples': 1751552, 'steps': 3420, 'batch_loss/train': 0.8091750051826239}
+12/22/2021 01:41:37 - INFO - codeparrot_training - Step 3421: {'lr': 0.0004947821015335483, 'samples': 1752064, 'steps': 3421, 'batch_loss/train': 0.9128811741247773}
+12/22/2021 01:41:50 - INFO - codeparrot_training - Step 3422: {'lr': 0.0004947788973062013, 'samples': 1752576, 'steps': 3422, 'batch_loss/train': 0.9143862789496779}
+12/22/2021 01:42:01 - INFO - codeparrot_training - Step 3423: {'lr': 0.0004947756921057059, 'samples': 1753088, 'steps': 3423, 'batch_loss/train': 0.9567630970850587}
+12/22/2021 01:42:11 - INFO - codeparrot_training - Step 3424: {'lr': 0.0004947724859320747, 'samples': 1753600, 'steps': 3424, 'batch_loss/train': 0.865407002158463}
+12/22/2021 01:42:23 - INFO - codeparrot_training - Step 3425: {'lr': 0.0004947692787853206, 'samples': 1754112, 'steps': 3425, 'batch_loss/train': 0.9021863555535674}
+12/22/2021 01:42:34 - INFO - codeparrot_training - Step 3426: {'lr': 0.0004947660706654562, 'samples': 1754624, 'steps': 3426, 'batch_loss/train': 0.8894019816070795}
+12/22/2021 01:42:45 - INFO - codeparrot_training - Step 3427: {'lr': 0.0004947628615724944, 'samples': 1755136, 'steps': 3427, 'batch_loss/train': 0.8438635151833296}
+12/22/2021 01:42:55 - INFO - codeparrot_training - Step 3428: {'lr': 0.0004947596515064479, 'samples': 1755648, 'steps': 3428, 'batch_loss/train': 0.7859973236918449}
+12/22/2021 01:43:08 - INFO - codeparrot_training - Step 3429: {'lr': 0.0004947564404673293, 'samples': 1756160, 'steps': 3429, 'batch_loss/train': 0.9809649474918842}
+12/22/2021 01:43:18 - INFO - codeparrot_training - Step 3430: {'lr': 0.0004947532284551516, 'samples': 1756672, 'steps': 3430, 'batch_loss/train': 0.7754708230495453}
+12/22/2021 01:43:29 - INFO - codeparrot_training - Step 3431: {'lr': 0.0004947500154699275, 'samples': 1757184, 'steps': 3431, 'batch_loss/train': 0.8452319046482444}
+12/22/2021 01:43:41 - INFO - codeparrot_training - Step 3432: {'lr': 0.0004947468015116698, 'samples': 1757696, 'steps': 3432, 'batch_loss/train': 0.8546511121094227}
+12/22/2021 01:43:51 - INFO - codeparrot_training - Step 3433: {'lr': 0.0004947435865803911, 'samples': 1758208, 'steps': 3433, 'batch_loss/train': 0.8639962105080485}
+12/22/2021 01:44:02 - INFO - codeparrot_training - Step 3434: {'lr': 0.0004947403706761043, 'samples': 1758720, 'steps': 3434, 'batch_loss/train': 0.9540189248509705}
+12/22/2021 01:44:15 - INFO - codeparrot_training - Step 3435: {'lr': 0.0004947371537988223, 'samples': 1759232, 'steps': 3435, 'batch_loss/train': 0.9038183055818081}
+12/22/2021 01:44:25 - INFO - codeparrot_training - Step 3436: {'lr': 0.0004947339359485577, 'samples': 1759744, 'steps': 3436, 'batch_loss/train': 0.7885990324430168}
+12/22/2021 01:44:36 - INFO - codeparrot_training - Step 3437: {'lr': 0.0004947307171253235, 'samples': 1760256, 'steps': 3437, 'batch_loss/train': 0.8729413943365216}
+12/22/2021 01:44:48 - INFO - codeparrot_training - Step 3438: {'lr': 0.0004947274973291323, 'samples': 1760768, 'steps': 3438, 'batch_loss/train': 0.8978551314212382}
+12/22/2021 01:44:59 - INFO - codeparrot_training - Step 3439: {'lr': 0.000494724276559997, 'samples': 1761280, 'steps': 3439, 'batch_loss/train': 0.8837389647960663}
+12/22/2021 01:45:09 - INFO - codeparrot_training - Step 3440: {'lr': 0.0004947210548179303, 'samples': 1761792, 'steps': 3440, 'batch_loss/train': 0.8333333535119891}
+12/22/2021 01:45:20 - INFO - codeparrot_training - Step 3441: {'lr': 0.0004947178321029452, 'samples': 1762304, 'steps': 3441, 'batch_loss/train': 0.7598433429375291}
+12/22/2021 01:45:32 - INFO - codeparrot_training - Step 3442: {'lr': 0.0004947146084150544, 'samples': 1762816, 'steps': 3442, 'batch_loss/train': 0.92936583282426}
+12/22/2021 01:45:42 - INFO - codeparrot_training - Step 3443: {'lr': 0.0004947113837542707, 'samples': 1763328, 'steps': 3443, 'batch_loss/train': 0.8570017539896071}
+12/22/2021 01:45:53 - INFO - codeparrot_training - Step 3444: {'lr': 0.0004947081581206068, 'samples': 1763840, 'steps': 3444, 'batch_loss/train': 0.735582840628922}
+12/22/2021 01:46:06 - INFO - codeparrot_training - Step 3445: {'lr': 0.0004947049315140758, 'samples': 1764352, 'steps': 3445, 'batch_loss/train': 0.8245374895632267}
+12/22/2021 01:46:16 - INFO - codeparrot_training - Step 3446: {'lr': 0.0004947017039346904, 'samples': 1764864, 'steps': 3446, 'batch_loss/train': 0.7546464260667562}
+12/22/2021 01:46:27 - INFO - codeparrot_training - Step 3447: {'lr': 0.0004946984753824633, 'samples': 1765376, 'steps': 3447, 'batch_loss/train': 0.8289693417027593}
+12/22/2021 01:46:39 - INFO - codeparrot_training - Step 3448: {'lr': 0.0004946952458574075, 'samples': 1765888, 'steps': 3448, 'batch_loss/train': 0.8947907940018922}
+12/22/2021 01:46:50 - INFO - codeparrot_training - Step 3449: {'lr': 0.0004946920153595359, 'samples': 1766400, 'steps': 3449, 'batch_loss/train': 0.8471428910270333}
+12/22/2021 01:47:00 - INFO - codeparrot_training - Step 3450: {'lr': 0.0004946887838888612, 'samples': 1766912, 'steps': 3450, 'batch_loss/train': 0.9065291732549667}
+12/22/2021 01:47:11 - INFO - codeparrot_training - Step 3451: {'lr': 0.0004946855514453962, 'samples': 1767424, 'steps': 3451, 'batch_loss/train': 0.8795671816915274}
+12/22/2021 01:47:24 - INFO - codeparrot_training - Step 3452: {'lr': 0.0004946823180291539, 'samples': 1767936, 'steps': 3452, 'batch_loss/train': 0.8072973852977157}
+12/22/2021 01:47:34 - INFO - codeparrot_training - Step 3453: {'lr': 0.000494679083640147, 'samples': 1768448, 'steps': 3453, 'batch_loss/train': 0.7879467578604817}
+12/22/2021 01:47:45 - INFO - codeparrot_training - Step 3454: {'lr': 0.0004946758482783886, 'samples': 1768960, 'steps': 3454, 'batch_loss/train': 0.9275901149958372}
+12/22/2021 01:47:57 - INFO - codeparrot_training - Step 3455: {'lr': 0.0004946726119438913, 'samples': 1769472, 'steps': 3455, 'batch_loss/train': 0.7924302471801639}
+12/22/2021 01:48:08 - INFO - codeparrot_training - Step 3456: {'lr': 0.0004946693746366681, 'samples': 1769984, 'steps': 3456, 'batch_loss/train': 0.8475770372897387}
+12/22/2021 01:48:18 - INFO - codeparrot_training - Step 3457: {'lr': 0.000494666136356732, 'samples': 1770496, 'steps': 3457, 'batch_loss/train': 0.9338865922763944}
+12/22/2021 01:48:30 - INFO - codeparrot_training - Step 3458: {'lr': 0.0004946628971040956, 'samples': 1771008, 'steps': 3458, 'batch_loss/train': 0.7618992370553315}
+12/22/2021 01:48:41 - INFO - codeparrot_training - Step 3459: {'lr': 0.0004946596568787719, 'samples': 1771520, 'steps': 3459, 'batch_loss/train': 0.8476750357076526}
+12/22/2021 01:48:52 - INFO - codeparrot_training - Step 3460: {'lr': 0.0004946564156807738, 'samples': 1772032, 'steps': 3460, 'batch_loss/train': 0.8062706240452826}
+12/22/2021 01:49:02 - INFO - codeparrot_training - Step 3461: {'lr': 0.0004946531735101141, 'samples': 1772544, 'steps': 3461, 'batch_loss/train': 0.9660002440214157}
+12/22/2021 01:49:15 - INFO - codeparrot_training - Step 3462: {'lr': 0.0004946499303668058, 'samples': 1773056, 'steps': 3462, 'batch_loss/train': 0.9085809281095862}
+12/22/2021 01:49:26 - INFO - codeparrot_training - Step 3463: {'lr': 0.0004946466862508619, 'samples': 1773568, 'steps': 3463, 'batch_loss/train': 0.857090204488486}
+12/22/2021 01:49:36 - INFO - codeparrot_training - Step 3464: {'lr': 0.000494643441162295, 'samples': 1774080, 'steps': 3464, 'batch_loss/train': 0.943649560213089}
+12/22/2021 01:49:48 - INFO - codeparrot_training - Step 3465: {'lr': 0.0004946401951011182, 'samples': 1774592, 'steps': 3465, 'batch_loss/train': 0.6680805434007198}
+12/22/2021 01:49:59 - INFO - codeparrot_training - Step 3466: {'lr': 0.0004946369480673443, 'samples': 1775104, 'steps': 3466, 'batch_loss/train': 0.8659596741199493}
+12/22/2021 01:50:10 - INFO - codeparrot_training - Step 3467: {'lr': 0.0004946337000609863, 'samples': 1775616, 'steps': 3467, 'batch_loss/train': 0.8596974331885576}
+12/22/2021 01:50:22 - INFO - codeparrot_training - Step 3468: {'lr': 0.000494630451082057, 'samples': 1776128, 'steps': 3468, 'batch_loss/train': 0.8380794748663902}
+12/22/2021 01:50:33 - INFO - codeparrot_training - Step 3469: {'lr': 0.0004946272011305694, 'samples': 1776640, 'steps': 3469, 'batch_loss/train': 0.5856748193036765}
+12/22/2021 01:50:44 - INFO - codeparrot_training - Step 3470: {'lr': 0.0004946239502065366, 'samples': 1777152, 'steps': 3470, 'batch_loss/train': 0.7223432927858084}
+12/22/2021 01:50:54 - INFO - codeparrot_training - Step 3471: {'lr': 0.0004946206983099712, 'samples': 1777664, 'steps': 3471, 'batch_loss/train': 0.8448981121182442}
+12/22/2021 01:51:06 - INFO - codeparrot_training - Step 3472: {'lr': 0.0004946174454408863, 'samples': 1778176, 'steps': 3472, 'batch_loss/train': 1.04445660719648}
+12/22/2021 01:51:17 - INFO - codeparrot_training - Step 3473: {'lr': 0.0004946141915992948, 'samples': 1778688, 'steps': 3473, 'batch_loss/train': 0.9172955797985196}
+12/22/2021 01:51:27 - INFO - codeparrot_training - Step 3474: {'lr': 0.0004946109367852097, 'samples': 1779200, 'steps': 3474, 'batch_loss/train': 1.0339185260236263}
+12/22/2021 01:51:41 - INFO - codeparrot_training - Step 3475: {'lr': 0.0004946076809986438, 'samples': 1779712, 'steps': 3475, 'batch_loss/train': 0.8509270157665014}
+12/22/2021 01:51:51 - INFO - codeparrot_training - Step 3476: {'lr': 0.0004946044242396101, 'samples': 1780224, 'steps': 3476, 'batch_loss/train': 1.1049997832160443}
+12/22/2021 01:52:02 - INFO - codeparrot_training - Step 3477: {'lr': 0.0004946011665081216, 'samples': 1780736, 'steps': 3477, 'batch_loss/train': 0.9175719609484076}
+12/22/2021 01:52:14 - INFO - codeparrot_training - Step 3478: {'lr': 0.0004945979078041912, 'samples': 1781248, 'steps': 3478, 'batch_loss/train': 0.9563420200720429}
+12/22/2021 01:52:25 - INFO - codeparrot_training - Step 3479: {'lr': 0.0004945946481278319, 'samples': 1781760, 'steps': 3479, 'batch_loss/train': 0.8762904442846775}
+12/22/2021 01:52:35 - INFO - codeparrot_training - Step 3480: {'lr': 0.0004945913874790566, 'samples': 1782272, 'steps': 3480, 'batch_loss/train': 0.8808010555803776}
+12/22/2021 01:52:46 - INFO - codeparrot_training - Step 3481: {'lr': 0.0004945881258578783, 'samples': 1782784, 'steps': 3481, 'batch_loss/train': 0.8639015620574355}
+12/22/2021 01:52:58 - INFO - codeparrot_training - Step 3482: {'lr': 0.00049458486326431, 'samples': 1783296, 'steps': 3482, 'batch_loss/train': 0.822933750692755}
+12/22/2021 01:53:09 - INFO - codeparrot_training - Step 3483: {'lr': 0.0004945815996983647, 'samples': 1783808, 'steps': 3483, 'batch_loss/train': 0.8456965144723654}
+12/22/2021 01:53:20 - INFO - codeparrot_training - Step 3484: {'lr': 0.0004945783351600552, 'samples': 1784320, 'steps': 3484, 'batch_loss/train': 0.8831368796527386}
+12/22/2021 01:53:32 - INFO - codeparrot_training - Step 3485: {'lr': 0.0004945750696493946, 'samples': 1784832, 'steps': 3485, 'batch_loss/train': 0.9064144417643547}
+12/22/2021 01:53:42 - INFO - codeparrot_training - Step 3486: {'lr': 0.000494571803166396, 'samples': 1785344, 'steps': 3486, 'batch_loss/train': 0.8073588674888015}
+12/22/2021 01:53:53 - INFO - codeparrot_training - Step 3487: {'lr': 0.0004945685357110721, 'samples': 1785856, 'steps': 3487, 'batch_loss/train': 0.9321060562506318}
+12/22/2021 01:54:05 - INFO - codeparrot_training - Step 3488: {'lr': 0.0004945652672834361, 'samples': 1786368, 'steps': 3488, 'batch_loss/train': 0.8714982904493809}
+12/22/2021 01:54:16 - INFO - codeparrot_training - Step 3489: {'lr': 0.0004945619978835009, 'samples': 1786880, 'steps': 3489, 'batch_loss/train': 0.8427813844755292}
+12/22/2021 01:54:26 - INFO - codeparrot_training - Step 3490: {'lr': 0.0004945587275112796, 'samples': 1787392, 'steps': 3490, 'batch_loss/train': 0.8943967996165156}
+12/22/2021 01:54:39 - INFO - codeparrot_training - Step 3491: {'lr': 0.000494555456166785, 'samples': 1787904, 'steps': 3491, 'batch_loss/train': 0.9104488557204604}
+12/22/2021 01:54:49 - INFO - codeparrot_training - Step 3492: {'lr': 0.0004945521838500305, 'samples': 1788416, 'steps': 3492, 'batch_loss/train': 0.8866565618664026}
+12/22/2021 01:55:00 - INFO - codeparrot_training - Step 3493: {'lr': 0.0004945489105610287, 'samples': 1788928, 'steps': 3493, 'batch_loss/train': 0.8301026145927608}
+12/22/2021 01:55:11 - INFO - codeparrot_training - Step 3494: {'lr': 0.0004945456362997928, 'samples': 1789440, 'steps': 3494, 'batch_loss/train': 0.864351318217814}
+12/22/2021 01:55:24 - INFO - codeparrot_training - Step 3495: {'lr': 0.0004945423610663357, 'samples': 1789952, 'steps': 3495, 'batch_loss/train': 0.7974714837037027}
+12/22/2021 01:55:35 - INFO - codeparrot_training - Step 3496: {'lr': 0.0004945390848606707, 'samples': 1790464, 'steps': 3496, 'batch_loss/train': 0.9848687676712871}
+12/22/2021 01:55:45 - INFO - codeparrot_training - Step 3497: {'lr': 0.0004945358076828104, 'samples': 1790976, 'steps': 3497, 'batch_loss/train': 0.9001434613019228}
+12/22/2021 01:55:57 - INFO - codeparrot_training - Step 3498: {'lr': 0.0004945325295327683, 'samples': 1791488, 'steps': 3498, 'batch_loss/train': 0.9471545265987515}
+12/22/2021 01:56:08 - INFO - codeparrot_training - Step 3499: {'lr': 0.000494529250410557, 'samples': 1792000, 'steps': 3499, 'batch_loss/train': 0.8704524664208293}
+12/22/2021 01:56:19 - INFO - codeparrot_training - Step 3500: {'lr': 0.0004945259703161898, 'samples': 1792512, 'steps': 3500, 'batch_loss/train': 0.8676300197839737}
+12/22/2021 01:56:31 - INFO - codeparrot_training - Step 3501: {'lr': 0.0004945226892496797, 'samples': 1793024, 'steps': 3501, 'batch_loss/train': 0.8452836577780545}
+12/22/2021 01:56:41 - INFO - codeparrot_training - Step 3502: {'lr': 0.0004945194072110397, 'samples': 1793536, 'steps': 3502, 'batch_loss/train': 0.8925215350463986}
+12/22/2021 01:56:52 - INFO - codeparrot_training - Step 3503: {'lr': 0.0004945161242002829, 'samples': 1794048, 'steps': 3503, 'batch_loss/train': 0.8552897032350302}
+12/22/2021 01:57:02 - INFO - codeparrot_training - Step 3504: {'lr': 0.0004945128402174222, 'samples': 1794560, 'steps': 3504, 'batch_loss/train': 1.0117326541803777}
+12/22/2021 01:57:15 - INFO - codeparrot_training - Step 3505: {'lr': 0.000494509555262471, 'samples': 1795072, 'steps': 3505, 'batch_loss/train': 0.883851895108819}
+12/22/2021 01:57:26 - INFO - codeparrot_training - Step 3506: {'lr': 0.0004945062693354419, 'samples': 1795584, 'steps': 3506, 'batch_loss/train': 0.9263391690328717}
+12/22/2021 01:57:36 - INFO - codeparrot_training - Step 3507: {'lr': 0.0004945029824363483, 'samples': 1796096, 'steps': 3507, 'batch_loss/train': 0.8215256440453231}
+12/22/2021 01:57:49 - INFO - codeparrot_training - Step 3508: {'lr': 0.0004944996945652031, 'samples': 1796608, 'steps': 3508, 'batch_loss/train': 0.7772551644593477}
+12/22/2021 01:57:59 - INFO - codeparrot_training - Step 3509: {'lr': 0.0004944964057220194, 'samples': 1797120, 'steps': 3509, 'batch_loss/train': 0.8318264717236161}
+12/22/2021 01:58:10 - INFO - codeparrot_training - Step 3510: {'lr': 0.0004944931159068104, 'samples': 1797632, 'steps': 3510, 'batch_loss/train': 0.9086710996925831}
+12/22/2021 01:58:22 - INFO - codeparrot_training - Step 3511: {'lr': 0.0004944898251195892, 'samples': 1798144, 'steps': 3511, 'batch_loss/train': 0.9272334445267916}
+12/22/2021 01:58:32 - INFO - codeparrot_training - Step 3512: {'lr': 0.0004944865333603686, 'samples': 1798656, 'steps': 3512, 'batch_loss/train': 0.9310260312631726}
+12/22/2021 01:58:43 - INFO - codeparrot_training - Step 3513: {'lr': 0.0004944832406291619, 'samples': 1799168, 'steps': 3513, 'batch_loss/train': 0.9598990902304649}
+12/22/2021 01:58:56 - INFO - codeparrot_training - Step 3514: {'lr': 0.0004944799469259821, 'samples': 1799680, 'steps': 3514, 'batch_loss/train': 0.8060433105565608}
+12/22/2021 01:59:06 - INFO - codeparrot_training - Step 3515: {'lr': 0.0004944766522508424, 'samples': 1800192, 'steps': 3515, 'batch_loss/train': 0.8312797234393656}
+12/22/2021 01:59:17 - INFO - codeparrot_training - Step 3516: {'lr': 0.0004944733566037559, 'samples': 1800704, 'steps': 3516, 'batch_loss/train': 0.8710194202139974}
+12/22/2021 01:59:27 - INFO - codeparrot_training - Step 3517: {'lr': 0.0004944700599847355, 'samples': 1801216, 'steps': 3517, 'batch_loss/train': 0.8407049275701866}
+12/22/2021 01:59:40 - INFO - codeparrot_training - Step 3518: {'lr': 0.0004944667623937945, 'samples': 1801728, 'steps': 3518, 'batch_loss/train': 2.8580757966265082}
+12/22/2021 01:59:51 - INFO - codeparrot_training - Step 3519: {'lr': 0.0004944634638309461, 'samples': 1802240, 'steps': 3519, 'batch_loss/train': 0.9616761561483145}
+12/22/2021 02:00:01 - INFO - codeparrot_training - Step 3520: {'lr': 0.0004944601642962031, 'samples': 1802752, 'steps': 3520, 'batch_loss/train': 0.9264923417940736}
+12/22/2021 02:00:14 - INFO - codeparrot_training - Step 3521: {'lr': 0.0004944568637895789, 'samples': 1803264, 'steps': 3521, 'batch_loss/train': 0.969231927767396}
+12/22/2021 02:00:25 - INFO - codeparrot_training - Step 3522: {'lr': 0.0004944535623110864, 'samples': 1803776, 'steps': 3522, 'batch_loss/train': 0.9023872278630733}
+12/22/2021 02:00:35 - INFO - codeparrot_training - Step 3523: {'lr': 0.0004944502598607388, 'samples': 1804288, 'steps': 3523, 'batch_loss/train': 0.8764679087325931}
+12/22/2021 02:00:46 - INFO - codeparrot_training - Step 3524: {'lr': 0.0004944469564385495, 'samples': 1804800, 'steps': 3524, 'batch_loss/train': 0.8167861038818955}
+12/22/2021 02:00:58 - INFO - codeparrot_training - Step 3525: {'lr': 0.0004944436520445312, 'samples': 1805312, 'steps': 3525, 'batch_loss/train': 0.9607346630655229}
+12/22/2021 02:01:09 - INFO - codeparrot_training - Step 3526: {'lr': 0.0004944403466786973, 'samples': 1805824, 'steps': 3526, 'batch_loss/train': 0.9265015041455626}
+12/22/2021 02:01:19 - INFO - codeparrot_training - Step 3527: {'lr': 0.0004944370403410609, 'samples': 1806336, 'steps': 3527, 'batch_loss/train': 0.8194585470482707}
+12/22/2021 02:01:31 - INFO - codeparrot_training - Step 3528: {'lr': 0.0004944337330316352, 'samples': 1806848, 'steps': 3528, 'batch_loss/train': 0.8380950358696282}
+12/22/2021 02:01:42 - INFO - codeparrot_training - Step 3529: {'lr': 0.0004944304247504332, 'samples': 1807360, 'steps': 3529, 'batch_loss/train': 0.8413641154766083}
+12/22/2021 02:01:52 - INFO - codeparrot_training - Step 3530: {'lr': 0.000494427115497468, 'samples': 1807872, 'steps': 3530, 'batch_loss/train': 0.9342019772157073}
+12/22/2021 02:02:05 - INFO - codeparrot_training - Step 3531: {'lr': 0.000494423805272753, 'samples': 1808384, 'steps': 3531, 'batch_loss/train': 2.0119240302592516}
+12/22/2021 02:02:16 - INFO - codeparrot_training - Step 3532: {'lr': 0.0004944204940763013, 'samples': 1808896, 'steps': 3532, 'batch_loss/train': 0.816680911462754}
+12/22/2021 02:02:27 - INFO - codeparrot_training - Step 3533: {'lr': 0.0004944171819081259, 'samples': 1809408, 'steps': 3533, 'batch_loss/train': 0.9404733330011368}
+12/22/2021 02:02:37 - INFO - codeparrot_training - Step 3534: {'lr': 0.0004944138687682402, 'samples': 1809920, 'steps': 3534, 'batch_loss/train': 0.834939862601459}
+12/22/2021 02:02:49 - INFO - codeparrot_training - Step 3535: {'lr': 0.0004944105546566571, 'samples': 1810432, 'steps': 3535, 'batch_loss/train': 0.9229628471657634}
+12/22/2021 02:03:00 - INFO - codeparrot_training - Step 3536: {'lr': 0.00049440723957339, 'samples': 1810944, 'steps': 3536, 'batch_loss/train': 0.912520335521549}
+12/22/2021 02:03:11 - INFO - codeparrot_training - Step 3537: {'lr': 0.0004944039235184518, 'samples': 1811456, 'steps': 3537, 'batch_loss/train': 0.8837254727259278}
+12/22/2021 02:03:23 - INFO - codeparrot_training - Step 3538: {'lr': 0.0004944006064918562, 'samples': 1811968, 'steps': 3538, 'batch_loss/train': 0.9516239296644926}
+12/22/2021 02:03:34 - INFO - codeparrot_training - Step 3539: {'lr': 0.0004943972884936159, 'samples': 1812480, 'steps': 3539, 'batch_loss/train': 0.9229928832501173}
+12/22/2021 02:03:44 - INFO - codeparrot_training - Step 3540: {'lr': 0.0004943939695237443, 'samples': 1812992, 'steps': 3540, 'batch_loss/train': 0.8192246803082526}
+12/22/2021 02:03:57 - INFO - codeparrot_training - Step 3541: {'lr': 0.0004943906495822545, 'samples': 1813504, 'steps': 3541, 'batch_loss/train': 0.8373703854158521}
+12/22/2021 02:04:07 - INFO - codeparrot_training - Step 3542: {'lr': 0.0004943873286691598, 'samples': 1814016, 'steps': 3542, 'batch_loss/train': 0.8835948491469026}
+12/22/2021 02:04:18 - INFO - codeparrot_training - Step 3543: {'lr': 0.0004943840067844733, 'samples': 1814528, 'steps': 3543, 'batch_loss/train': 0.5543482950888574}
+12/22/2021 02:04:31 - INFO - codeparrot_training - Step 3544: {'lr': 0.0004943806839282084, 'samples': 1815040, 'steps': 3544, 'batch_loss/train': 0.973328361287713}
+12/22/2021 02:04:41 - INFO - codeparrot_training - Step 3545: {'lr': 0.0004943773601003781, 'samples': 1815552, 'steps': 3545, 'batch_loss/train': 0.8416095515713096}
+12/22/2021 02:04:52 - INFO - codeparrot_training - Step 3546: {'lr': 0.0004943740353009956, 'samples': 1816064, 'steps': 3546, 'batch_loss/train': 0.8184488546103239}
+12/22/2021 02:05:03 - INFO - codeparrot_training - Step 3547: {'lr': 0.0004943707095300744, 'samples': 1816576, 'steps': 3547, 'batch_loss/train': 0.8637743787840009}
+12/22/2021 02:05:15 - INFO - codeparrot_training - Step 3548: {'lr': 0.0004943673827876273, 'samples': 1817088, 'steps': 3548, 'batch_loss/train': 0.815297300927341}
+12/22/2021 02:05:25 - INFO - codeparrot_training - Step 3549: {'lr': 0.000494364055073668, 'samples': 1817600, 'steps': 3549, 'batch_loss/train': 0.8656611237674952}
+12/22/2021 02:05:36 - INFO - codeparrot_training - Step 3550: {'lr': 0.0004943607263882094, 'samples': 1818112, 'steps': 3550, 'batch_loss/train': 0.8853835673071444}
+12/22/2021 02:05:49 - INFO - codeparrot_training - Step 3551: {'lr': 0.0004943573967312648, 'samples': 1818624, 'steps': 3551, 'batch_loss/train': 0.9265786493197083}
+12/22/2021 02:05:59 - INFO - codeparrot_training - Step 3552: {'lr': 0.0004943540661028474, 'samples': 1819136, 'steps': 3552, 'batch_loss/train': 0.8892348720692098}
+12/22/2021 02:06:10 - INFO - codeparrot_training - Step 3553: {'lr': 0.0004943507345029706, 'samples': 1819648, 'steps': 3553, 'batch_loss/train': 0.9021750576794147}
+12/22/2021 02:06:22 - INFO - codeparrot_training - Step 3554: {'lr': 0.0004943474019316474, 'samples': 1820160, 'steps': 3554, 'batch_loss/train': 0.7938539409078658}
+12/22/2021 02:06:32 - INFO - codeparrot_training - Step 3555: {'lr': 0.0004943440683888912, 'samples': 1820672, 'steps': 3555, 'batch_loss/train': 0.7603551298379898}
+12/22/2021 02:06:43 - INFO - codeparrot_training - Step 3556: {'lr': 0.0004943407338747154, 'samples': 1821184, 'steps': 3556, 'batch_loss/train': 0.9094089400023222}
+12/22/2021 02:06:54 - INFO - codeparrot_training - Step 3557: {'lr': 0.000494337398389133, 'samples': 1821696, 'steps': 3557, 'batch_loss/train': 0.8615685030817986}
+12/22/2021 02:07:06 - INFO - codeparrot_training - Step 3558: {'lr': 0.0004943340619321573, 'samples': 1822208, 'steps': 3558, 'batch_loss/train': 0.880504909902811}
+12/22/2021 02:07:16 - INFO - codeparrot_training - Step 3559: {'lr': 0.0004943307245038018, 'samples': 1822720, 'steps': 3559, 'batch_loss/train': 0.7891916492953897}
+12/22/2021 02:07:27 - INFO - codeparrot_training - Step 3560: {'lr': 0.0004943273861040795, 'samples': 1823232, 'steps': 3560, 'batch_loss/train': 0.8722427310422063}
+12/22/2021 02:07:40 - INFO - codeparrot_training - Step 3561: {'lr': 0.0004943240467330038, 'samples': 1823744, 'steps': 3561, 'batch_loss/train': 1.3392586950212717}
+12/22/2021 02:07:50 - INFO - codeparrot_training - Step 3562: {'lr': 0.0004943207063905879, 'samples': 1824256, 'steps': 3562, 'batch_loss/train': 0.8518108995631337}
+12/22/2021 02:08:01 - INFO - codeparrot_training - Step 3563: {'lr': 0.0004943173650768451, 'samples': 1824768, 'steps': 3563, 'batch_loss/train': 0.8585761766880751}
+12/22/2021 02:08:12 - INFO - codeparrot_training - Step 3564: {'lr': 0.0004943140227917888, 'samples': 1825280, 'steps': 3564, 'batch_loss/train': 0.8329691016115248}
+12/22/2021 02:08:24 - INFO - codeparrot_training - Step 3565: {'lr': 0.000494310679535432, 'samples': 1825792, 'steps': 3565, 'batch_loss/train': 0.824758957605809}
+12/22/2021 02:08:34 - INFO - codeparrot_training - Step 3566: {'lr': 0.0004943073353077884, 'samples': 1826304, 'steps': 3566, 'batch_loss/train': 0.8035524319857359}
+12/22/2021 02:08:45 - INFO - codeparrot_training - Step 3567: {'lr': 0.0004943039901088711, 'samples': 1826816, 'steps': 3567, 'batch_loss/train': 0.9234896302223206}
+12/22/2021 02:08:58 - INFO - codeparrot_training - Step 3568: {'lr': 0.0004943006439386932, 'samples': 1827328, 'steps': 3568, 'batch_loss/train': 0.8337323293089867}
+12/22/2021 02:09:08 - INFO - codeparrot_training - Step 3569: {'lr': 0.0004942972967972683, 'samples': 1827840, 'steps': 3569, 'batch_loss/train': 0.8427014593034983}
+12/22/2021 02:09:19 - INFO - codeparrot_training - Step 3570: {'lr': 0.0004942939486846095, 'samples': 1828352, 'steps': 3570, 'batch_loss/train': 0.9111682642251253}
+12/22/2021 02:09:32 - INFO - codeparrot_training - Step 3571: {'lr': 0.0004942905996007303, 'samples': 1828864, 'steps': 3571, 'batch_loss/train': 0.9075486836954951}
+12/22/2021 02:09:43 - INFO - codeparrot_training - Step 3572: {'lr': 0.000494287249545644, 'samples': 1829376, 'steps': 3572, 'batch_loss/train': 0.8511207697447389}
+12/22/2021 02:09:53 - INFO - codeparrot_training - Step 3573: {'lr': 0.0004942838985193636, 'samples': 1829888, 'steps': 3573, 'batch_loss/train': 0.9741732208058238}
+12/22/2021 02:10:04 - INFO - codeparrot_training - Step 3574: {'lr': 0.0004942805465219028, 'samples': 1830400, 'steps': 3574, 'batch_loss/train': 1.2674470040947199}
+12/22/2021 02:10:16 - INFO - codeparrot_training - Step 3575: {'lr': 0.0004942771935532748, 'samples': 1830912, 'steps': 3575, 'batch_loss/train': 0.9817301537841558}
+12/22/2021 02:10:26 - INFO - codeparrot_training - Step 3576: {'lr': 0.0004942738396134928, 'samples': 1831424, 'steps': 3576, 'batch_loss/train': 0.8651961451396346}
+12/22/2021 02:10:37 - INFO - codeparrot_training - Step 3577: {'lr': 0.0004942704847025704, 'samples': 1831936, 'steps': 3577, 'batch_loss/train': 0.8070804169401526}
+12/22/2021 02:10:49 - INFO - codeparrot_training - Step 3578: {'lr': 0.0004942671288205207, 'samples': 1832448, 'steps': 3578, 'batch_loss/train': 0.8615930192172527}
+12/22/2021 02:11:00 - INFO - codeparrot_training - Step 3579: {'lr': 0.0004942637719673571, 'samples': 1832960, 'steps': 3579, 'batch_loss/train': 0.8399009457789361}
+12/22/2021 02:11:10 - INFO - codeparrot_training - Step 3580: {'lr': 0.0004942604141430929, 'samples': 1833472, 'steps': 3580, 'batch_loss/train': 0.8758146241307259}
+12/22/2021 02:11:23 - INFO - codeparrot_training - Step 3581: {'lr': 0.0004942570553477417, 'samples': 1833984, 'steps': 3581, 'batch_loss/train': 0.768500764388591}
+12/22/2021 02:11:34 - INFO - codeparrot_training - Step 3582: {'lr': 0.0004942536955813166, 'samples': 1834496, 'steps': 3582, 'batch_loss/train': 0.7934064352884889}
+12/22/2021 02:11:44 - INFO - codeparrot_training - Step 3583: {'lr': 0.000494250334843831, 'samples': 1835008, 'steps': 3583, 'batch_loss/train': 0.8626810284331441}
+12/22/2021 02:11:55 - INFO - codeparrot_training - Step 3584: {'lr': 0.0004942469731352984, 'samples': 1835520, 'steps': 3584, 'batch_loss/train': 0.9239878803491592}
+12/22/2021 02:12:07 - INFO - codeparrot_training - Step 3585: {'lr': 0.000494243610455732, 'samples': 1836032, 'steps': 3585, 'batch_loss/train': 0.7879227800294757}
+12/22/2021 02:12:18 - INFO - codeparrot_training - Step 3586: {'lr': 0.0004942402468051452, 'samples': 1836544, 'steps': 3586, 'batch_loss/train': 0.9153551158960909}
+12/22/2021 02:12:28 - INFO - codeparrot_training - Step 3587: {'lr': 0.0004942368821835515, 'samples': 1837056, 'steps': 3587, 'batch_loss/train': 0.8310556160286069}
+12/22/2021 02:12:40 - INFO - codeparrot_training - Step 3588: {'lr': 0.0004942335165909641, 'samples': 1837568, 'steps': 3588, 'batch_loss/train': 0.8327822322025895}
+12/22/2021 02:12:51 - INFO - codeparrot_training - Step 3589: {'lr': 0.0004942301500273963, 'samples': 1838080, 'steps': 3589, 'batch_loss/train': 0.7075921571813524}
+12/22/2021 02:13:02 - INFO - codeparrot_training - Step 3590: {'lr': 0.0004942267824928619, 'samples': 1838592, 'steps': 3590, 'batch_loss/train': 0.9668259071186185}
+12/22/2021 02:13:14 - INFO - codeparrot_training - Step 3591: {'lr': 0.0004942234139873739, 'samples': 1839104, 'steps': 3591, 'batch_loss/train': 0.8692309316247702}
+12/22/2021 02:13:25 - INFO - codeparrot_training - Step 3592: {'lr': 0.0004942200445109458, 'samples': 1839616, 'steps': 3592, 'batch_loss/train': 0.9152122503146529}
+12/22/2021 02:13:35 - INFO - codeparrot_training - Step 3593: {'lr': 0.0004942166740635911, 'samples': 1840128, 'steps': 3593, 'batch_loss/train': 0.9167777337133884}
+12/22/2021 02:13:46 - INFO - codeparrot_training - Step 3594: {'lr': 0.0004942133026453232, 'samples': 1840640, 'steps': 3594, 'batch_loss/train': 0.8875272190198302}
+12/22/2021 02:13:58 - INFO - codeparrot_training - Step 3595: {'lr': 0.0004942099302561552, 'samples': 1841152, 'steps': 3595, 'batch_loss/train': 0.8295080633834004}
+12/22/2021 02:14:09 - INFO - codeparrot_training - Step 3596: {'lr': 0.0004942065568961008, 'samples': 1841664, 'steps': 3596, 'batch_loss/train': 0.8035096656531096}
+12/22/2021 02:14:19 - INFO - codeparrot_training - Step 3597: {'lr': 0.0004942031825651734, 'samples': 1842176, 'steps': 3597, 'batch_loss/train': 0.9165981682017446}
+12/22/2021 02:14:32 - INFO - codeparrot_training - Step 3598: {'lr': 0.0004941998072633863, 'samples': 1842688, 'steps': 3598, 'batch_loss/train': 1.048768994398415}
+12/22/2021 02:14:43 - INFO - codeparrot_training - Step 3599: {'lr': 0.000494196430990753, 'samples': 1843200, 'steps': 3599, 'batch_loss/train': 1.2040011070203036}
+12/22/2021 02:14:53 - INFO - codeparrot_training - Step 3600: {'lr': 0.0004941930537472869, 'samples': 1843712, 'steps': 3600, 'batch_loss/train': 0.807585927657783}
+12/22/2021 02:15:05 - INFO - codeparrot_training - Step 3601: {'lr': 0.0004941896755330014, 'samples': 1844224, 'steps': 3601, 'batch_loss/train': 0.7648380836471915}
+12/22/2021 02:15:16 - INFO - codeparrot_training - Step 3602: {'lr': 0.0004941862963479099, 'samples': 1844736, 'steps': 3602, 'batch_loss/train': 1.0362963839434087}
+12/22/2021 02:15:27 - INFO - codeparrot_training - Step 3603: {'lr': 0.000494182916192026, 'samples': 1845248, 'steps': 3603, 'batch_loss/train': 1.0919600976631045}
+12/22/2021 02:15:39 - INFO - codeparrot_training - Step 3604: {'lr': 0.000494179535065363, 'samples': 1845760, 'steps': 3604, 'batch_loss/train': 0.9153896253556013}
+12/22/2021 02:15:49 - INFO - codeparrot_training - Step 3605: {'lr': 0.0004941761529679343, 'samples': 1846272, 'steps': 3605, 'batch_loss/train': 1.2690646974369884}
+12/22/2021 02:16:00 - INFO - codeparrot_training - Step 3606: {'lr': 0.0004941727698997535, 'samples': 1846784, 'steps': 3606, 'batch_loss/train': 0.8726218547672033}
+12/22/2021 02:16:10 - INFO - codeparrot_training - Step 3607: {'lr': 0.0004941693858608339, 'samples': 1847296, 'steps': 3607, 'batch_loss/train': 0.8166847731918097}
+12/22/2021 02:16:24 - INFO - codeparrot_training - Step 3608: {'lr': 0.000494166000851189, 'samples': 1847808, 'steps': 3608, 'batch_loss/train': 0.8843117239885032}
+12/22/2021 02:16:34 - INFO - codeparrot_training - Step 3609: {'lr': 0.0004941626148708323, 'samples': 1848320, 'steps': 3609, 'batch_loss/train': 0.8140062503516674}
+12/22/2021 02:16:45 - INFO - codeparrot_training - Step 3610: {'lr': 0.0004941592279197772, 'samples': 1848832, 'steps': 3610, 'batch_loss/train': 0.8856231700628996}
+12/22/2021 02:16:57 - INFO - codeparrot_training - Step 3611: {'lr': 0.0004941558399980373, 'samples': 1849344, 'steps': 3611, 'batch_loss/train': 1.2615128380712122}
+12/22/2021 02:17:08 - INFO - codeparrot_training - Step 3612: {'lr': 0.0004941524511056259, 'samples': 1849856, 'steps': 3612, 'batch_loss/train': 0.9730823596473783}
+12/22/2021 02:17:18 - INFO - codeparrot_training - Step 3613: {'lr': 0.0004941490612425565, 'samples': 1850368, 'steps': 3613, 'batch_loss/train': 0.8517878665588796}
+12/22/2021 02:17:29 - INFO - codeparrot_training - Step 3614: {'lr': 0.0004941456704088427, 'samples': 1850880, 'steps': 3614, 'batch_loss/train': 0.8801688766106963}
+12/22/2021 02:17:42 - INFO - codeparrot_training - Step 3615: {'lr': 0.0004941422786044979, 'samples': 1851392, 'steps': 3615, 'batch_loss/train': 0.8270635297521949}
+12/22/2021 02:17:52 - INFO - codeparrot_training - Step 3616: {'lr': 0.0004941388858295356, 'samples': 1851904, 'steps': 3616, 'batch_loss/train': 0.8101574634201825}
+12/22/2021 02:18:03 - INFO - codeparrot_training - Step 3617: {'lr': 0.0004941354920839692, 'samples': 1852416, 'steps': 3617, 'batch_loss/train': 0.868084330111742}
+12/22/2021 02:18:15 - INFO - codeparrot_training - Step 3618: {'lr': 0.0004941320973678123, 'samples': 1852928, 'steps': 3618, 'batch_loss/train': 0.77992626093328}
+12/22/2021 02:18:26 - INFO - codeparrot_training - Step 3619: {'lr': 0.0004941287016810784, 'samples': 1853440, 'steps': 3619, 'batch_loss/train': 1.1729822349734604}
+12/22/2021 02:18:36 - INFO - codeparrot_training - Step 3620: {'lr': 0.0004941253050237809, 'samples': 1853952, 'steps': 3620, 'batch_loss/train': 0.841286982409656}
+12/22/2021 02:18:49 - INFO - codeparrot_training - Step 3621: {'lr': 0.0004941219073959334, 'samples': 1854464, 'steps': 3621, 'batch_loss/train': 0.8932104390114546}
+12/22/2021 02:19:00 - INFO - codeparrot_training - Step 3622: {'lr': 0.0004941185087975493, 'samples': 1854976, 'steps': 3622, 'batch_loss/train': 0.8765964093618095}
+12/22/2021 02:19:10 - INFO - codeparrot_training - Step 3623: {'lr': 0.0004941151092286422, 'samples': 1855488, 'steps': 3623, 'batch_loss/train': 0.7725192091893405}
+12/22/2021 02:19:22 - INFO - codeparrot_training - Step 3624: {'lr': 0.0004941117086892258, 'samples': 1856000, 'steps': 3624, 'batch_loss/train': 0.7387925083748996}
+12/22/2021 02:19:33 - INFO - codeparrot_training - Step 3625: {'lr': 0.0004941083071793132, 'samples': 1856512, 'steps': 3625, 'batch_loss/train': 0.7698519108816981}
+12/22/2021 02:19:44 - INFO - codeparrot_training - Step 3626: {'lr': 0.0004941049046989182, 'samples': 1857024, 'steps': 3626, 'batch_loss/train': 0.7716005090624094}
+12/22/2021 02:19:54 - INFO - codeparrot_training - Step 3627: {'lr': 0.0004941015012480543, 'samples': 1857536, 'steps': 3627, 'batch_loss/train': 0.930221838876605}
+12/22/2021 02:20:06 - INFO - codeparrot_training - Step 3628: {'lr': 0.0004940980968267349, 'samples': 1858048, 'steps': 3628, 'batch_loss/train': 0.8367686718702316}
+12/22/2021 02:20:17 - INFO - codeparrot_training - Step 3629: {'lr': 0.0004940946914349738, 'samples': 1858560, 'steps': 3629, 'batch_loss/train': 0.8119125356897712}
+12/22/2021 02:20:27 - INFO - codeparrot_training - Step 3630: {'lr': 0.0004940912850727843, 'samples': 1859072, 'steps': 3630, 'batch_loss/train': 0.867166300304234}
+12/22/2021 02:20:40 - INFO - codeparrot_training - Step 3631: {'lr': 0.00049408787774018, 'samples': 1859584, 'steps': 3631, 'batch_loss/train': 0.8659879714250565}
+12/22/2021 02:20:51 - INFO - codeparrot_training - Step 3632: {'lr': 0.0004940844694371743, 'samples': 1860096, 'steps': 3632, 'batch_loss/train': 0.8980640228837729}
+12/22/2021 02:21:01 - INFO - codeparrot_training - Step 3633: {'lr': 0.0004940810601637811, 'samples': 1860608, 'steps': 3633, 'batch_loss/train': 0.8157307635992765}
+12/22/2021 02:21:13 - INFO - codeparrot_training - Step 3634: {'lr': 0.0004940776499200138, 'samples': 1861120, 'steps': 3634, 'batch_loss/train': 0.8793178303167224}
+12/22/2021 02:21:24 - INFO - codeparrot_training - Step 3635: {'lr': 0.0004940742387058858, 'samples': 1861632, 'steps': 3635, 'batch_loss/train': 1.2891863882541656}
+12/22/2021 02:21:35 - INFO - codeparrot_training - Step 3636: {'lr': 0.0004940708265214109, 'samples': 1862144, 'steps': 3636, 'batch_loss/train': 0.8910515252500772}
+12/22/2021 02:21:45 - INFO - codeparrot_training - Step 3637: {'lr': 0.0004940674133666025, 'samples': 1862656, 'steps': 3637, 'batch_loss/train': 0.9146782271564007}
+12/22/2021 02:21:58 - INFO - codeparrot_training - Step 3638: {'lr': 0.0004940639992414743, 'samples': 1863168, 'steps': 3638, 'batch_loss/train': 0.9318164084106684}
+12/22/2021 02:22:08 - INFO - codeparrot_training - Step 3639: {'lr': 0.0004940605841460396, 'samples': 1863680, 'steps': 3639, 'batch_loss/train': 0.8962002722546458}
+12/22/2021 02:22:19 - INFO - codeparrot_training - Step 3640: {'lr': 0.0004940571680803124, 'samples': 1864192, 'steps': 3640, 'batch_loss/train': 0.7705502943135798}
+12/22/2021 02:22:31 - INFO - codeparrot_training - Step 3641: {'lr': 0.0004940537510443059, 'samples': 1864704, 'steps': 3641, 'batch_loss/train': 0.9080872964113951}
+12/22/2021 02:22:42 - INFO - codeparrot_training - Step 3642: {'lr': 0.0004940503330380339, 'samples': 1865216, 'steps': 3642, 'batch_loss/train': 0.9034329671412706}
+12/22/2021 02:22:52 - INFO - codeparrot_training - Step 3643: {'lr': 0.0004940469140615099, 'samples': 1865728, 'steps': 3643, 'batch_loss/train': 0.9537591021507978}
+12/22/2021 02:23:05 - INFO - codeparrot_training - Step 3644: {'lr': 0.0004940434941147475, 'samples': 1866240, 'steps': 3644, 'batch_loss/train': 0.7651811763644218}
+12/22/2021 02:23:15 - INFO - codeparrot_training - Step 3645: {'lr': 0.0004940400731977603, 'samples': 1866752, 'steps': 3645, 'batch_loss/train': 0.9020968480035663}
+12/22/2021 02:23:26 - INFO - codeparrot_training - Step 3646: {'lr': 0.000494036651310562, 'samples': 1867264, 'steps': 3646, 'batch_loss/train': 0.8872583769261837}
+12/22/2021 02:23:36 - INFO - codeparrot_training - Step 3647: {'lr': 0.0004940332284531661, 'samples': 1867776, 'steps': 3647, 'batch_loss/train': 1.2779811657965183}
+12/22/2021 02:23:49 - INFO - codeparrot_training - Step 3648: {'lr': 0.0004940298046255861, 'samples': 1868288, 'steps': 3648, 'batch_loss/train': 0.877135087735951}
+12/22/2021 02:24:00 - INFO - codeparrot_training - Step 3649: {'lr': 0.0004940263798278359, 'samples': 1868800, 'steps': 3649, 'batch_loss/train': 0.9365897988900542}
+12/22/2021 02:24:10 - INFO - codeparrot_training - Step 3650: {'lr': 0.0004940229540599288, 'samples': 1869312, 'steps': 3650, 'batch_loss/train': 0.8053650725632906}
+12/22/2021 02:24:23 - INFO - codeparrot_training - Step 3651: {'lr': 0.0004940195273218787, 'samples': 1869824, 'steps': 3651, 'batch_loss/train': 0.9111508382484317}
+12/22/2021 02:24:33 - INFO - codeparrot_training - Step 3652: {'lr': 0.0004940160996136991, 'samples': 1870336, 'steps': 3652, 'batch_loss/train': 0.8475642576813698}
+12/22/2021 02:24:44 - INFO - codeparrot_training - Step 3653: {'lr': 0.0004940126709354035, 'samples': 1870848, 'steps': 3653, 'batch_loss/train': 1.0278633758425713}
+12/22/2021 02:24:57 - INFO - codeparrot_training - Step 3654: {'lr': 0.0004940092412870058, 'samples': 1871360, 'steps': 3654, 'batch_loss/train': 0.8620964987203479}
+12/22/2021 02:25:07 - INFO - codeparrot_training - Step 3655: {'lr': 0.0004940058106685195, 'samples': 1871872, 'steps': 3655, 'batch_loss/train': 0.8140120171010494}
+12/22/2021 02:25:18 - INFO - codeparrot_training - Step 3656: {'lr': 0.0004940023790799582, 'samples': 1872384, 'steps': 3656, 'batch_loss/train': 0.6418354441411793}
+12/22/2021 02:25:29 - INFO - codeparrot_training - Step 3657: {'lr': 0.0004939989465213354, 'samples': 1872896, 'steps': 3657, 'batch_loss/train': 1.7412631381303072}
+12/22/2021 02:25:41 - INFO - codeparrot_training - Step 3658: {'lr': 0.0004939955129926651, 'samples': 1873408, 'steps': 3658, 'batch_loss/train': 0.8861029157415032}
+12/22/2021 02:25:51 - INFO - codeparrot_training - Step 3659: {'lr': 0.0004939920784939607, 'samples': 1873920, 'steps': 3659, 'batch_loss/train': 0.9573064064607024}
+12/22/2021 02:26:02 - INFO - codeparrot_training - Step 3660: {'lr': 0.0004939886430252359, 'samples': 1874432, 'steps': 3660, 'batch_loss/train': 0.9369873618707061}
+12/22/2021 02:26:14 - INFO - codeparrot_training - Step 3661: {'lr': 0.0004939852065865045, 'samples': 1874944, 'steps': 3661, 'batch_loss/train': 0.9306574715301394}
+12/22/2021 02:26:25 - INFO - codeparrot_training - Step 3662: {'lr': 0.00049398176917778, 'samples': 1875456, 'steps': 3662, 'batch_loss/train': 0.8630824033170938}
+12/22/2021 02:26:35 - INFO - codeparrot_training - Step 3663: {'lr': 0.000493978330799076, 'samples': 1875968, 'steps': 3663, 'batch_loss/train': 0.8511675326153636}
+12/22/2021 02:26:47 - INFO - codeparrot_training - Step 3664: {'lr': 0.0004939748914504064, 'samples': 1876480, 'steps': 3664, 'batch_loss/train': 0.9501930475234985}
+12/22/2021 02:26:58 - INFO - codeparrot_training - Step 3665: {'lr': 0.0004939714511317848, 'samples': 1876992, 'steps': 3665, 'batch_loss/train': 0.9063807829516008}
+12/22/2021 02:27:08 - INFO - codeparrot_training - Step 3666: {'lr': 0.0004939680098432247, 'samples': 1877504, 'steps': 3666, 'batch_loss/train': 0.8147152392193675}
+12/22/2021 02:27:21 - INFO - codeparrot_training - Step 3667: {'lr': 0.00049396456758474, 'samples': 1878016, 'steps': 3667, 'batch_loss/train': 0.9330359287559986}
+12/22/2021 02:27:32 - INFO - codeparrot_training - Step 3668: {'lr': 0.0004939611243563442, 'samples': 1878528, 'steps': 3668, 'batch_loss/train': 0.9242592337541282}
+12/22/2021 02:27:42 - INFO - codeparrot_training - Step 3669: {'lr': 0.0004939576801580511, 'samples': 1879040, 'steps': 3669, 'batch_loss/train': 0.8686613440513611}
+12/22/2021 02:27:53 - INFO - codeparrot_training - Step 3670: {'lr': 0.0004939542349898745, 'samples': 1879552, 'steps': 3670, 'batch_loss/train': 0.8887386941350996}
+12/22/2021 02:28:05 - INFO - codeparrot_training - Step 3671: {'lr': 0.0004939507888518279, 'samples': 1880064, 'steps': 3671, 'batch_loss/train': 0.8994757956825197}
+12/22/2021 02:28:16 - INFO - codeparrot_training - Step 3672: {'lr': 0.000493947341743925, 'samples': 1880576, 'steps': 3672, 'batch_loss/train': 0.8503441517241299}
+12/22/2021 02:28:26 - INFO - codeparrot_training - Step 3673: {'lr': 0.0004939438936661796, 'samples': 1881088, 'steps': 3673, 'batch_loss/train': 0.9394881743937731}
+12/22/2021 02:28:38 - INFO - codeparrot_training - Step 3674: {'lr': 0.0004939404446186055, 'samples': 1881600, 'steps': 3674, 'batch_loss/train': 0.8352928550448269}
+12/22/2021 02:28:49 - INFO - codeparrot_training - Step 3675: {'lr': 0.0004939369946012162, 'samples': 1882112, 'steps': 3675, 'batch_loss/train': 0.9431041590869427}
+12/22/2021 02:28:59 - INFO - codeparrot_training - Step 3676: {'lr': 0.0004939335436140255, 'samples': 1882624, 'steps': 3676, 'batch_loss/train': 1.0028809700161219}
+12/22/2021 02:29:12 - INFO - codeparrot_training - Step 3677: {'lr': 0.0004939300916570472, 'samples': 1883136, 'steps': 3677, 'batch_loss/train': 0.8926482358947396}
+12/22/2021 02:29:23 - INFO - codeparrot_training - Step 3678: {'lr': 0.000493926638730295, 'samples': 1883648, 'steps': 3678, 'batch_loss/train': 0.9580854177474976}
+12/22/2021 02:29:33 - INFO - codeparrot_training - Step 3679: {'lr': 0.0004939231848337826, 'samples': 1884160, 'steps': 3679, 'batch_loss/train': 0.8879381760489196}
+12/22/2021 02:29:46 - INFO - codeparrot_training - Step 3680: {'lr': 0.0004939197299675237, 'samples': 1884672, 'steps': 3680, 'batch_loss/train': 0.7806490198709071}
+12/22/2021 02:29:56 - INFO - codeparrot_training - Step 3681: {'lr': 0.000493916274131532, 'samples': 1885184, 'steps': 3681, 'batch_loss/train': 0.8014894425868988}
+12/22/2021 02:30:07 - INFO - codeparrot_training - Step 3682: {'lr': 0.0004939128173258213, 'samples': 1885696, 'steps': 3682, 'batch_loss/train': 0.7911846657516435}
+12/22/2021 02:30:17 - INFO - codeparrot_training - Step 3683: {'lr': 0.0004939093595504052, 'samples': 1886208, 'steps': 3683, 'batch_loss/train': 0.7792215831577778}
+12/22/2021 02:30:30 - INFO - codeparrot_training - Step 3684: {'lr': 0.0004939059008052979, 'samples': 1886720, 'steps': 3684, 'batch_loss/train': 0.9123597536236048}
+12/22/2021 02:30:41 - INFO - codeparrot_training - Step 3685: {'lr': 0.0004939024410905126, 'samples': 1887232, 'steps': 3685, 'batch_loss/train': 0.9013401214033365}
+12/22/2021 02:30:51 - INFO - codeparrot_training - Step 3686: {'lr': 0.0004938989804060633, 'samples': 1887744, 'steps': 3686, 'batch_loss/train': 0.9371725060045719}
+12/22/2021 02:31:03 - INFO - codeparrot_training - Step 3687: {'lr': 0.0004938955187519639, 'samples': 1888256, 'steps': 3687, 'batch_loss/train': 0.7906889840960503}
+12/22/2021 02:31:14 - INFO - codeparrot_training - Step 3688: {'lr': 0.0004938920561282278, 'samples': 1888768, 'steps': 3688, 'batch_loss/train': 0.9133713995106518}
+12/22/2021 02:31:25 - INFO - codeparrot_training - Step 3689: {'lr': 0.0004938885925348691, 'samples': 1889280, 'steps': 3689, 'batch_loss/train': 0.8408324522897601}
+12/22/2021 02:31:37 - INFO - codeparrot_training - Step 3690: {'lr': 0.0004938851279719014, 'samples': 1889792, 'steps': 3690, 'batch_loss/train': 0.902257933979854}
+12/22/2021 02:31:47 - INFO - codeparrot_training - Step 3691: {'lr': 0.0004938816624393386, 'samples': 1890304, 'steps': 3691, 'batch_loss/train': 0.7715837322175503}
+12/22/2021 02:31:58 - INFO - codeparrot_training - Step 3692: {'lr': 0.0004938781959371943, 'samples': 1890816, 'steps': 3692, 'batch_loss/train': 0.8506901357322931}
+12/22/2021 02:32:08 - INFO - codeparrot_training - Step 3693: {'lr': 0.0004938747284654824, 'samples': 1891328, 'steps': 3693, 'batch_loss/train': 0.875853581354022}
+12/22/2021 02:32:21 - INFO - codeparrot_training - Step 3694: {'lr': 0.0004938712600242167, 'samples': 1891840, 'steps': 3694, 'batch_loss/train': 0.8136497223749757}
+12/22/2021 02:32:32 - INFO - codeparrot_training - Step 3695: {'lr': 0.0004938677906134109, 'samples': 1892352, 'steps': 3695, 'batch_loss/train': 0.922045623883605}
+12/22/2021 02:32:43 - INFO - codeparrot_training - Step 3696: {'lr': 0.0004938643202330789, 'samples': 1892864, 'steps': 3696, 'batch_loss/train': 1.1267789769917727}
+12/22/2021 02:32:55 - INFO - codeparrot_training - Step 3697: {'lr': 0.0004938608488832344, 'samples': 1893376, 'steps': 3697, 'batch_loss/train': 0.944523161277175}
+12/22/2021 02:33:06 - INFO - codeparrot_training - Step 3698: {'lr': 0.0004938573765638913, 'samples': 1893888, 'steps': 3698, 'batch_loss/train': 0.9346029055304825}
+12/22/2021 02:33:16 - INFO - codeparrot_training - Step 3699: {'lr': 0.0004938539032750633, 'samples': 1894400, 'steps': 3699, 'batch_loss/train': 0.7726988680660725}
+12/22/2021 02:33:27 - INFO - codeparrot_training - Step 3700: {'lr': 0.0004938504290167643, 'samples': 1894912, 'steps': 3700, 'batch_loss/train': 0.8603280680254102}
+12/22/2021 02:33:39 - INFO - codeparrot_training - Step 3701: {'lr': 0.000493846953789008, 'samples': 1895424, 'steps': 3701, 'batch_loss/train': 0.8613020270131528}
+12/22/2021 02:33:49 - INFO - codeparrot_training - Step 3702: {'lr': 0.0004938434775918082, 'samples': 1895936, 'steps': 3702, 'batch_loss/train': 0.9788078777492046}
+12/22/2021 02:34:00 - INFO - codeparrot_training - Step 3703: {'lr': 0.000493840000425179, 'samples': 1896448, 'steps': 3703, 'batch_loss/train': 0.9022299209609628}
+12/22/2021 02:34:12 - INFO - codeparrot_training - Step 3704: {'lr': 0.0004938365222891339, 'samples': 1896960, 'steps': 3704, 'batch_loss/train': 0.7969147749245167}
+12/22/2021 02:34:23 - INFO - codeparrot_training - Step 3705: {'lr': 0.0004938330431836869, 'samples': 1897472, 'steps': 3705, 'batch_loss/train': 0.925512027926743}
+12/22/2021 02:34:34 - INFO - codeparrot_training - Step 3706: {'lr': 0.0004938295631088519, 'samples': 1897984, 'steps': 3706, 'batch_loss/train': 0.8370374981313944}
+12/22/2021 02:34:47 - INFO - codeparrot_training - Step 3707: {'lr': 0.0004938260820646426, 'samples': 1898496, 'steps': 3707, 'batch_loss/train': 1.066465531475842}
+12/22/2021 02:34:57 - INFO - codeparrot_training - Step 3708: {'lr': 0.0004938226000510726, 'samples': 1899008, 'steps': 3708, 'batch_loss/train': 0.867115480825305}
+12/22/2021 02:35:08 - INFO - codeparrot_training - Step 3709: {'lr': 0.0004938191170681562, 'samples': 1899520, 'steps': 3709, 'batch_loss/train': 0.9091820036992431}
+12/22/2021 02:35:19 - INFO - codeparrot_training - Step 3710: {'lr': 0.0004938156331159071, 'samples': 1900032, 'steps': 3710, 'batch_loss/train': 0.9045236324891448}
+12/22/2021 02:35:31 - INFO - codeparrot_training - Step 3711: {'lr': 0.000493812148194339, 'samples': 1900544, 'steps': 3711, 'batch_loss/train': 0.9062775727361441}
+12/22/2021 02:35:41 - INFO - codeparrot_training - Step 3712: {'lr': 0.000493808662303466, 'samples': 1901056, 'steps': 3712, 'batch_loss/train': 0.9554779622703791}
+12/22/2021 02:35:52 - INFO - codeparrot_training - Step 3713: {'lr': 0.0004938051754433016, 'samples': 1901568, 'steps': 3713, 'batch_loss/train': 0.8990859221667051}
+12/22/2021 02:36:05 - INFO - codeparrot_training - Step 3714: {'lr': 0.00049380168761386, 'samples': 1902080, 'steps': 3714, 'batch_loss/train': 0.7776436768472195}
+12/22/2021 02:36:15 - INFO - codeparrot_training - Step 3715: {'lr': 0.000493798198815155, 'samples': 1902592, 'steps': 3715, 'batch_loss/train': 0.8665605848655105}
+12/22/2021 02:36:26 - INFO - codeparrot_training - Step 3716: {'lr': 0.0004937947090472004, 'samples': 1903104, 'steps': 3716, 'batch_loss/train': 0.7853714087978005}
+12/22/2021 02:36:38 - INFO - codeparrot_training - Step 3717: {'lr': 0.0004937912183100101, 'samples': 1903616, 'steps': 3717, 'batch_loss/train': 0.7539542373269796}
+12/22/2021 02:36:49 - INFO - codeparrot_training - Step 3718: {'lr': 0.0004937877266035978, 'samples': 1904128, 'steps': 3718, 'batch_loss/train': 0.8744692080654204}
+12/22/2021 02:36:59 - INFO - codeparrot_training - Step 3719: {'lr': 0.0004937842339279777, 'samples': 1904640, 'steps': 3719, 'batch_loss/train': 0.8569204686209559}
+12/22/2021 02:37:11 - INFO - codeparrot_training - Step 3720: {'lr': 0.0004937807402831635, 'samples': 1905152, 'steps': 3720, 'batch_loss/train': 0.7682564994320273}
+12/22/2021 02:37:22 - INFO - codeparrot_training - Step 3721: {'lr': 0.0004937772456691692, 'samples': 1905664, 'steps': 3721, 'batch_loss/train': 1.0924650533124804}
+12/22/2021 02:37:33 - INFO - codeparrot_training - Step 3722: {'lr': 0.0004937737500860085, 'samples': 1906176, 'steps': 3722, 'batch_loss/train': 0.9254699042066932}
+12/22/2021 02:37:43 - INFO - codeparrot_training - Step 3723: {'lr': 0.0004937702535336955, 'samples': 1906688, 'steps': 3723, 'batch_loss/train': 0.9108530124649405}
+12/22/2021 02:37:57 - INFO - codeparrot_training - Step 3724: {'lr': 0.000493766756012244, 'samples': 1907200, 'steps': 3724, 'batch_loss/train': 0.9177951514720917}
+12/22/2021 02:38:07 - INFO - codeparrot_training - Step 3725: {'lr': 0.0004937632575216679, 'samples': 1907712, 'steps': 3725, 'batch_loss/train': 1.58736028149724}
+12/22/2021 02:38:18 - INFO - codeparrot_training - Step 3726: {'lr': 0.0004937597580619811, 'samples': 1908224, 'steps': 3726, 'batch_loss/train': 0.6940076700411737}
+12/22/2021 02:38:30 - INFO - codeparrot_training - Step 3727: {'lr': 0.0004937562576331976, 'samples': 1908736, 'steps': 3727, 'batch_loss/train': 0.93151596467942}
+12/22/2021 02:38:41 - INFO - codeparrot_training - Step 3728: {'lr': 0.0004937527562353313, 'samples': 1909248, 'steps': 3728, 'batch_loss/train': 0.8667444619350135}
+12/22/2021 02:38:51 - INFO - codeparrot_training - Step 3729: {'lr': 0.0004937492538683958, 'samples': 1909760, 'steps': 3729, 'batch_loss/train': 0.8251191028393805}
+12/22/2021 02:39:02 - INFO - codeparrot_training - Step 3730: {'lr': 0.0004937457505324056, 'samples': 1910272, 'steps': 3730, 'batch_loss/train': 2.5965562192723155}
+12/22/2021 02:39:14 - INFO - codeparrot_training - Step 3731: {'lr': 0.0004937422462273742, 'samples': 1910784, 'steps': 3731, 'batch_loss/train': 0.8418670655228198}
+12/22/2021 02:39:25 - INFO - codeparrot_training - Step 3732: {'lr': 0.0004937387409533157, 'samples': 1911296, 'steps': 3732, 'batch_loss/train': 0.8680355180986226}
+12/22/2021 02:39:35 - INFO - codeparrot_training - Step 3733: {'lr': 0.0004937352347102441, 'samples': 1911808, 'steps': 3733, 'batch_loss/train': 0.7991327196359634}
+12/22/2021 02:39:48 - INFO - codeparrot_training - Step 3734: {'lr': 0.0004937317274981731, 'samples': 1912320, 'steps': 3734, 'batch_loss/train': 0.9300766452215612}
+12/22/2021 02:39:58 - INFO - codeparrot_training - Step 3735: {'lr': 0.0004937282193171169, 'samples': 1912832, 'steps': 3735, 'batch_loss/train': 0.875653357245028}
+12/22/2021 02:40:09 - INFO - codeparrot_training - Step 3736: {'lr': 0.0004937247101670892, 'samples': 1913344, 'steps': 3736, 'batch_loss/train': 1.0622287299484015}
+12/22/2021 02:40:21 - INFO - codeparrot_training - Step 3737: {'lr': 0.0004937212000481041, 'samples': 1913856, 'steps': 3737, 'batch_loss/train': 0.8742702966555953}
+12/22/2021 02:40:32 - INFO - codeparrot_training - Step 3738: {'lr': 0.0004937176889601755, 'samples': 1914368, 'steps': 3738, 'batch_loss/train': 0.86161985155195}
+12/22/2021 02:40:42 - INFO - codeparrot_training - Step 3739: {'lr': 0.0004937141769033175, 'samples': 1914880, 'steps': 3739, 'batch_loss/train': 0.9091787878423929}
+12/22/2021 02:40:55 - INFO - codeparrot_training - Step 3740: {'lr': 0.0004937106638775439, 'samples': 1915392, 'steps': 3740, 'batch_loss/train': 0.8842210378497839}
+12/22/2021 02:41:06 - INFO - codeparrot_training - Step 3741: {'lr': 0.0004937071498828688, 'samples': 1915904, 'steps': 3741, 'batch_loss/train': 0.8322340531740338}
+12/22/2021 02:41:16 - INFO - codeparrot_training - Step 3742: {'lr': 0.000493703634919306, 'samples': 1916416, 'steps': 3742, 'batch_loss/train': 0.8923069657757878}
+12/22/2021 02:41:27 - INFO - codeparrot_training - Step 3743: {'lr': 0.0004937001189868696, 'samples': 1916928, 'steps': 3743, 'batch_loss/train': 0.9037461522966623}
+12/22/2021 02:41:39 - INFO - codeparrot_training - Step 3744: {'lr': 0.0004936966020855735, 'samples': 1917440, 'steps': 3744, 'batch_loss/train': 0.8962100022472441}
+12/22/2021 02:41:49 - INFO - codeparrot_training - Step 3745: {'lr': 0.0004936930842154318, 'samples': 1917952, 'steps': 3745, 'batch_loss/train': 0.8037969917058945}
+12/22/2021 02:42:00 - INFO - codeparrot_training - Step 3746: {'lr': 0.0004936895653764584, 'samples': 1918464, 'steps': 3746, 'batch_loss/train': 0.8700243709608912}
+12/22/2021 02:42:12 - INFO - codeparrot_training - Step 3747: {'lr': 0.0004936860455686672, 'samples': 1918976, 'steps': 3747, 'batch_loss/train': 0.8389458516612649}
+12/22/2021 02:42:23 - INFO - codeparrot_training - Step 3748: {'lr': 0.0004936825247920724, 'samples': 1919488, 'steps': 3748, 'batch_loss/train': 0.8706636801362038}
+12/22/2021 02:42:34 - INFO - codeparrot_training - Step 3749: {'lr': 0.0004936790030466879, 'samples': 1920000, 'steps': 3749, 'batch_loss/train': 1.7911450904794037}
+12/22/2021 02:42:46 - INFO - codeparrot_training - Step 3750: {'lr': 0.0004936754803325276, 'samples': 1920512, 'steps': 3750, 'batch_loss/train': 0.8968791607767344}
+12/22/2021 02:42:56 - INFO - codeparrot_training - Step 3751: {'lr': 0.0004936719566496058, 'samples': 1921024, 'steps': 3751, 'batch_loss/train': 0.9759563449770212}
+12/22/2021 02:43:07 - INFO - codeparrot_training - Step 3752: {'lr': 0.0004936684319979361, 'samples': 1921536, 'steps': 3752, 'batch_loss/train': 0.8528996258974075}
+12/22/2021 02:43:18 - INFO - codeparrot_training - Step 3753: {'lr': 0.0004936649063775327, 'samples': 1922048, 'steps': 3753, 'batch_loss/train': 0.8533864188939333}
+12/22/2021 02:43:30 - INFO - codeparrot_training - Step 3754: {'lr': 0.0004936613797884098, 'samples': 1922560, 'steps': 3754, 'batch_loss/train': 0.9278583582490683}
+12/22/2021 02:43:41 - INFO - codeparrot_training - Step 3755: {'lr': 0.0004936578522305811, 'samples': 1923072, 'steps': 3755, 'batch_loss/train': 0.9637786388630047}
+12/22/2021 02:43:52 - INFO - codeparrot_training - Step 3756: {'lr': 0.0004936543237040609, 'samples': 1923584, 'steps': 3756, 'batch_loss/train': 0.9153960263356566}
+12/22/2021 02:44:04 - INFO - codeparrot_training - Step 3757: {'lr': 0.0004936507942088631, 'samples': 1924096, 'steps': 3757, 'batch_loss/train': 0.7233433681540191}
+12/22/2021 02:44:15 - INFO - codeparrot_training - Step 3758: {'lr': 0.0004936472637450017, 'samples': 1924608, 'steps': 3758, 'batch_loss/train': 0.8644535755738616}
+12/22/2021 02:44:25 - INFO - codeparrot_training - Step 3759: {'lr': 0.0004936437323124908, 'samples': 1925120, 'steps': 3759, 'batch_loss/train': 0.8718647081404924}
+12/22/2021 02:44:38 - INFO - codeparrot_training - Step 3760: {'lr': 0.0004936401999113444, 'samples': 1925632, 'steps': 3760, 'batch_loss/train': 0.8403368499130011}
+12/22/2021 02:44:48 - INFO - codeparrot_training - Step 3761: {'lr': 0.0004936366665415766, 'samples': 1926144, 'steps': 3761, 'batch_loss/train': 1.8116241469979286}
+12/22/2021 02:44:59 - INFO - codeparrot_training - Step 3762: {'lr': 0.0004936331322032012, 'samples': 1926656, 'steps': 3762, 'batch_loss/train': 0.9391850866377354}
+12/22/2021 02:45:10 - INFO - codeparrot_training - Step 3763: {'lr': 0.0004936295968962327, 'samples': 1927168, 'steps': 3763, 'batch_loss/train': 1.042867235839367}
+12/22/2021 02:45:22 - INFO - codeparrot_training - Step 3764: {'lr': 0.0004936260606206848, 'samples': 1927680, 'steps': 3764, 'batch_loss/train': 0.9154640473425388}
+12/22/2021 02:45:33 - INFO - codeparrot_training - Step 3765: {'lr': 0.0004936225233765718, 'samples': 1928192, 'steps': 3765, 'batch_loss/train': 0.948992533609271}
+12/22/2021 02:45:44 - INFO - codeparrot_training - Step 3766: {'lr': 0.0004936189851639076, 'samples': 1928704, 'steps': 3766, 'batch_loss/train': 0.9629520233720541}
+12/22/2021 02:45:56 - INFO - codeparrot_training - Step 3767: {'lr': 0.0004936154459827062, 'samples': 1929216, 'steps': 3767, 'batch_loss/train': 0.9275340298190713}
+12/22/2021 02:46:06 - INFO - codeparrot_training - Step 3768: {'lr': 0.0004936119058329818, 'samples': 1929728, 'steps': 3768, 'batch_loss/train': 0.8784381435252726}
+12/22/2021 02:46:17 - INFO - codeparrot_training - Step 3769: {'lr': 0.0004936083647147485, 'samples': 1930240, 'steps': 3769, 'batch_loss/train': 1.014723513275385}
+12/22/2021 02:46:30 - INFO - codeparrot_training - Step 3770: {'lr': 0.0004936048226280203, 'samples': 1930752, 'steps': 3770, 'batch_loss/train': 0.8563129166141152}
+12/22/2021 02:46:40 - INFO - codeparrot_training - Step 3771: {'lr': 0.0004936012795728113, 'samples': 1931264, 'steps': 3771, 'batch_loss/train': 0.8295387299731374}
+12/22/2021 02:46:51 - INFO - codeparrot_training - Step 3772: {'lr': 0.0004935977355491355, 'samples': 1931776, 'steps': 3772, 'batch_loss/train': 0.8888448006473482}
+12/22/2021 02:47:02 - INFO - codeparrot_training - Step 3773: {'lr': 0.0004935941905570073, 'samples': 1932288, 'steps': 3773, 'batch_loss/train': 0.8409133991226554}
+12/22/2021 02:47:14 - INFO - codeparrot_training - Step 3774: {'lr': 0.0004935906445964405, 'samples': 1932800, 'steps': 3774, 'batch_loss/train': 0.84512999933213}
+12/22/2021 02:47:24 - INFO - codeparrot_training - Step 3775: {'lr': 0.0004935870976674492, 'samples': 1933312, 'steps': 3775, 'batch_loss/train': 0.8995063658803701}
+12/22/2021 02:47:35 - INFO - codeparrot_training - Step 3776: {'lr': 0.0004935835497700476, 'samples': 1933824, 'steps': 3776, 'batch_loss/train': 0.923853381536901}
+12/22/2021 02:47:47 - INFO - codeparrot_training - Step 3777: {'lr': 0.0004935800009042497, 'samples': 1934336, 'steps': 3777, 'batch_loss/train': 0.9007323170080781}
+12/22/2021 02:47:58 - INFO - codeparrot_training - Step 3778: {'lr': 0.0004935764510700698, 'samples': 1934848, 'steps': 3778, 'batch_loss/train': 0.8202476426959038}
+12/22/2021 02:48:09 - INFO - codeparrot_training - Step 3779: {'lr': 0.0004935729002675218, 'samples': 1935360, 'steps': 3779, 'batch_loss/train': 1.1605665972456336}
+12/22/2021 02:48:22 - INFO - codeparrot_training - Step 3780: {'lr': 0.00049356934849662, 'samples': 1935872, 'steps': 3780, 'batch_loss/train': 0.7942460384219885}
+12/22/2021 02:48:33 - INFO - codeparrot_training - Step 3781: {'lr': 0.0004935657957573785, 'samples': 1936384, 'steps': 3781, 'batch_loss/train': 1.1023618336766958}
+12/22/2021 02:48:43 - INFO - codeparrot_training - Step 3782: {'lr': 0.0004935622420498113, 'samples': 1936896, 'steps': 3782, 'batch_loss/train': 1.6150321764871478}
+12/22/2021 02:48:54 - INFO - codeparrot_training - Step 3783: {'lr': 0.0004935586873739326, 'samples': 1937408, 'steps': 3783, 'batch_loss/train': 1.1446838593110442}
+12/22/2021 02:49:06 - INFO - codeparrot_training - Step 3784: {'lr': 0.0004935551317297566, 'samples': 1937920, 'steps': 3784, 'batch_loss/train': 0.9644232727587223}
+12/22/2021 02:49:17 - INFO - codeparrot_training - Step 3785: {'lr': 0.0004935515751172972, 'samples': 1938432, 'steps': 3785, 'batch_loss/train': 0.8307030852884054}
+12/22/2021 02:49:27 - INFO - codeparrot_training - Step 3786: {'lr': 0.0004935480175365688, 'samples': 1938944, 'steps': 3786, 'batch_loss/train': 0.93092046584934}
+12/22/2021 02:49:38 - INFO - codeparrot_training - Step 3787: {'lr': 0.0004935444589875853, 'samples': 1939456, 'steps': 3787, 'batch_loss/train': 0.9085046174004674}
+12/22/2021 02:49:50 - INFO - codeparrot_training - Step 3788: {'lr': 0.0004935408994703611, 'samples': 1939968, 'steps': 3788, 'batch_loss/train': 0.9460109192878008}
+12/22/2021 02:50:00 - INFO - codeparrot_training - Step 3789: {'lr': 0.0004935373389849103, 'samples': 1940480, 'steps': 3789, 'batch_loss/train': 0.793442026595585}
+12/22/2021 02:50:11 - INFO - codeparrot_training - Step 3790: {'lr': 0.0004935337775312468, 'samples': 1940992, 'steps': 3790, 'batch_loss/train': 0.8823752286843956}
+12/22/2021 02:50:23 - INFO - codeparrot_training - Step 3791: {'lr': 0.0004935302151093852, 'samples': 1941504, 'steps': 3791, 'batch_loss/train': 0.8942114543169737}
+12/22/2021 02:50:34 - INFO - codeparrot_training - Step 3792: {'lr': 0.0004935266517193393, 'samples': 1942016, 'steps': 3792, 'batch_loss/train': 0.9843899719417095}
+12/22/2021 02:50:44 - INFO - codeparrot_training - Step 3793: {'lr': 0.0004935230873611234, 'samples': 1942528, 'steps': 3793, 'batch_loss/train': 0.8916125278919935}
+12/22/2021 02:50:57 - INFO - codeparrot_training - Step 3794: {'lr': 0.0004935195220347517, 'samples': 1943040, 'steps': 3794, 'batch_loss/train': 0.9275600267574191}
+12/22/2021 02:51:08 - INFO - codeparrot_training - Step 3795: {'lr': 0.0004935159557402382, 'samples': 1943552, 'steps': 3795, 'batch_loss/train': 0.9085673121735454}
+12/22/2021 02:51:18 - INFO - codeparrot_training - Step 3796: {'lr': 0.0004935123884775973, 'samples': 1944064, 'steps': 3796, 'batch_loss/train': 0.7847347231581807}
+12/22/2021 02:51:30 - INFO - codeparrot_training - Step 3797: {'lr': 0.000493508820246843, 'samples': 1944576, 'steps': 3797, 'batch_loss/train': 0.8392064590007067}
+12/22/2021 02:51:41 - INFO - codeparrot_training - Step 3798: {'lr': 0.0004935052510479897, 'samples': 1945088, 'steps': 3798, 'batch_loss/train': 0.9343324014917016}
+12/22/2021 02:51:52 - INFO - codeparrot_training - Step 3799: {'lr': 0.0004935016808810514, 'samples': 1945600, 'steps': 3799, 'batch_loss/train': 0.8433773340657353}
+12/22/2021 02:52:02 - INFO - codeparrot_training - Step 3800: {'lr': 0.0004934981097460424, 'samples': 1946112, 'steps': 3800, 'batch_loss/train': 0.8842285927385092}
+12/22/2021 02:52:15 - INFO - codeparrot_training - Step 3801: {'lr': 0.0004934945376429768, 'samples': 1946624, 'steps': 3801, 'batch_loss/train': 0.8370447773486376}
+12/22/2021 02:52:26 - INFO - codeparrot_training - Step 3802: {'lr': 0.000493490964571869, 'samples': 1947136, 'steps': 3802, 'batch_loss/train': 0.8043763479217887}
+12/22/2021 02:52:36 - INFO - codeparrot_training - Step 3803: {'lr': 0.0004934873905327329, 'samples': 1947648, 'steps': 3803, 'batch_loss/train': 0.8584928940981627}
+12/22/2021 02:52:48 - INFO - codeparrot_training - Step 3804: {'lr': 0.000493483815525583, 'samples': 1948160, 'steps': 3804, 'batch_loss/train': 0.858178704045713}
+12/22/2021 02:52:59 - INFO - codeparrot_training - Step 3805: {'lr': 0.0004934802395504332, 'samples': 1948672, 'steps': 3805, 'batch_loss/train': 0.8357215044088662}
+12/22/2021 02:53:10 - INFO - codeparrot_training - Step 3806: {'lr': 0.0004934766626072981, 'samples': 1949184, 'steps': 3806, 'batch_loss/train': 0.8188387360423803}
+12/22/2021 02:53:22 - INFO - codeparrot_training - Step 3807: {'lr': 0.0004934730846961916, 'samples': 1949696, 'steps': 3807, 'batch_loss/train': 0.9045049669221044}
+12/22/2021 02:53:32 - INFO - codeparrot_training - Step 3808: {'lr': 0.0004934695058171282, 'samples': 1950208, 'steps': 3808, 'batch_loss/train': 0.9567530667409301}
+12/22/2021 02:53:43 - INFO - codeparrot_training - Step 3809: {'lr': 0.0004934659259701218, 'samples': 1950720, 'steps': 3809, 'batch_loss/train': 0.9193551195785403}
+12/22/2021 02:53:54 - INFO - codeparrot_training - Step 3810: {'lr': 0.0004934623451551868, 'samples': 1951232, 'steps': 3810, 'batch_loss/train': 0.8828546367585659}
+12/22/2021 02:54:06 - INFO - codeparrot_training - Step 3811: {'lr': 0.0004934587633723376, 'samples': 1951744, 'steps': 3811, 'batch_loss/train': 0.8745678209234029}
+12/22/2021 02:54:17 - INFO - codeparrot_training - Step 3812: {'lr': 0.0004934551806215881, 'samples': 1952256, 'steps': 3812, 'batch_loss/train': 0.8780061267316341}
+12/22/2021 02:54:28 - INFO - codeparrot_training - Step 3813: {'lr': 0.0004934515969029528, 'samples': 1952768, 'steps': 3813, 'batch_loss/train': 0.8838810017332435}
+12/22/2021 02:54:40 - INFO - codeparrot_training - Step 3814: {'lr': 0.000493448012216446, 'samples': 1953280, 'steps': 3814, 'batch_loss/train': 0.9207546710968018}
+12/22/2021 02:54:50 - INFO - codeparrot_training - Step 3815: {'lr': 0.0004934444265620817, 'samples': 1953792, 'steps': 3815, 'batch_loss/train': 0.9235510937869549}
+12/22/2021 02:55:01 - INFO - codeparrot_training - Step 3816: {'lr': 0.0004934408399398743, 'samples': 1954304, 'steps': 3816, 'batch_loss/train': 0.835369573906064}
+12/22/2021 02:55:14 - INFO - codeparrot_training - Step 3817: {'lr': 0.0004934372523498381, 'samples': 1954816, 'steps': 3817, 'batch_loss/train': 0.8079075608402491}
+12/22/2021 02:55:24 - INFO - codeparrot_training - Step 3818: {'lr': 0.0004934336637919871, 'samples': 1955328, 'steps': 3818, 'batch_loss/train': 0.9456892469897866}
+12/22/2021 02:55:35 - INFO - codeparrot_training - Step 3819: {'lr': 0.000493430074266336, 'samples': 1955840, 'steps': 3819, 'batch_loss/train': 0.87785336188972}
+12/22/2021 02:55:45 - INFO - codeparrot_training - Step 3820: {'lr': 0.0004934264837728987, 'samples': 1956352, 'steps': 3820, 'batch_loss/train': 0.8012208454310894}
+12/22/2021 02:55:58 - INFO - codeparrot_training - Step 3821: {'lr': 0.0004934228923116897, 'samples': 1956864, 'steps': 3821, 'batch_loss/train': 0.739445025101304}
+12/22/2021 02:56:08 - INFO - codeparrot_training - Step 3822: {'lr': 0.0004934192998827232, 'samples': 1957376, 'steps': 3822, 'batch_loss/train': 0.8686580862849951}
+12/22/2021 02:56:19 - INFO - codeparrot_training - Step 3823: {'lr': 0.0004934157064860134, 'samples': 1957888, 'steps': 3823, 'batch_loss/train': 0.9037773348391056}
+12/22/2021 02:56:31 - INFO - codeparrot_training - Step 3824: {'lr': 0.0004934121121215748, 'samples': 1958400, 'steps': 3824, 'batch_loss/train': 0.8799220873042941}
+12/22/2021 02:56:42 - INFO - codeparrot_training - Step 3825: {'lr': 0.0004934085167894213, 'samples': 1958912, 'steps': 3825, 'batch_loss/train': 0.8213279251940548}
+12/22/2021 02:56:52 - INFO - codeparrot_training - Step 3826: {'lr': 0.0004934049204895676, 'samples': 1959424, 'steps': 3826, 'batch_loss/train': 1.6960221035405993}
+12/22/2021 02:57:04 - INFO - codeparrot_training - Step 3827: {'lr': 0.0004934013232220279, 'samples': 1959936, 'steps': 3827, 'batch_loss/train': 0.7514405031688511}
+12/22/2021 02:57:15 - INFO - codeparrot_training - Step 3828: {'lr': 0.0004933977249868164, 'samples': 1960448, 'steps': 3828, 'batch_loss/train': 0.89906468661502}
+12/22/2021 02:57:26 - INFO - codeparrot_training - Step 3829: {'lr': 0.0004933941257839475, 'samples': 1960960, 'steps': 3829, 'batch_loss/train': 0.92047721426934}
+12/22/2021 02:57:36 - INFO - codeparrot_training - Step 3830: {'lr': 0.0004933905256134354, 'samples': 1961472, 'steps': 3830, 'batch_loss/train': 0.8562086718156934}
+12/22/2021 02:57:49 - INFO - codeparrot_training - Step 3831: {'lr': 0.0004933869244752943, 'samples': 1961984, 'steps': 3831, 'batch_loss/train': 0.7722583990544081}
+12/22/2021 02:58:00 - INFO - codeparrot_training - Step 3832: {'lr': 0.000493383322369539, 'samples': 1962496, 'steps': 3832, 'batch_loss/train': 0.8859816547483206}
+12/22/2021 02:58:10 - INFO - codeparrot_training - Step 3833: {'lr': 0.0004933797192961833, 'samples': 1963008, 'steps': 3833, 'batch_loss/train': 0.7720382558181882}
+12/22/2021 02:58:22 - INFO - codeparrot_training - Step 3834: {'lr': 0.0004933761152552418, 'samples': 1963520, 'steps': 3834, 'batch_loss/train': 0.9004795998334885}
+12/22/2021 02:58:33 - INFO - codeparrot_training - Step 3835: {'lr': 0.0004933725102467287, 'samples': 1964032, 'steps': 3835, 'batch_loss/train': 0.9689303785562515}
+12/22/2021 02:58:43 - INFO - codeparrot_training - Step 3836: {'lr': 0.0004933689042706585, 'samples': 1964544, 'steps': 3836, 'batch_loss/train': 0.9114434849470854}
+12/22/2021 02:58:55 - INFO - codeparrot_training - Step 3837: {'lr': 0.0004933652973270453, 'samples': 1965056, 'steps': 3837, 'batch_loss/train': 0.8811247888952494}
+12/22/2021 02:59:06 - INFO - codeparrot_training - Step 3838: {'lr': 0.0004933616894159037, 'samples': 1965568, 'steps': 3838, 'batch_loss/train': 1.076737537048757}
+12/22/2021 02:59:17 - INFO - codeparrot_training - Step 3839: {'lr': 0.0004933580805372478, 'samples': 1966080, 'steps': 3839, 'batch_loss/train': 0.8767387922853231}
+12/22/2021 02:59:29 - INFO - codeparrot_training - Step 3840: {'lr': 0.0004933544706910922, 'samples': 1966592, 'steps': 3840, 'batch_loss/train': 0.7454911158420146}
+12/22/2021 02:59:40 - INFO - codeparrot_training - Step 3841: {'lr': 0.000493350859877451, 'samples': 1967104, 'steps': 3841, 'batch_loss/train': 0.7605250785127282}
+12/22/2021 02:59:51 - INFO - codeparrot_training - Step 3842: {'lr': 0.0004933472480963387, 'samples': 1967616, 'steps': 3842, 'batch_loss/train': 0.8632157635875046}
+12/22/2021 03:00:01 - INFO - codeparrot_training - Step 3843: {'lr': 0.0004933436353477697, 'samples': 1968128, 'steps': 3843, 'batch_loss/train': 0.9379818886518478}
+12/22/2021 03:00:13 - INFO - codeparrot_training - Step 3844: {'lr': 0.0004933400216317581, 'samples': 1968640, 'steps': 3844, 'batch_loss/train': 0.8442303249612451}
+12/22/2021 03:00:24 - INFO - codeparrot_training - Step 3845: {'lr': 0.0004933364069483185, 'samples': 1969152, 'steps': 3845, 'batch_loss/train': 0.7561356239020824}
+12/22/2021 03:00:34 - INFO - codeparrot_training - Step 3846: {'lr': 0.0004933327912974653, 'samples': 1969664, 'steps': 3846, 'batch_loss/train': 0.8705980135127902}
+12/22/2021 03:00:47 - INFO - codeparrot_training - Step 3847: {'lr': 0.0004933291746792129, 'samples': 1970176, 'steps': 3847, 'batch_loss/train': 0.8357559628784657}
+12/22/2021 03:00:58 - INFO - codeparrot_training - Step 3848: {'lr': 0.0004933255570935755, 'samples': 1970688, 'steps': 3848, 'batch_loss/train': 0.7942328061908484}
+12/22/2021 03:01:09 - INFO - codeparrot_training - Step 3849: {'lr': 0.0004933219385405674, 'samples': 1971200, 'steps': 3849, 'batch_loss/train': 1.105294725857675}
+12/22/2021 03:01:21 - INFO - codeparrot_training - Step 3850: {'lr': 0.0004933183190202033, 'samples': 1971712, 'steps': 3850, 'batch_loss/train': 0.7367704003117979}
+12/22/2021 03:01:31 - INFO - codeparrot_training - Step 3851: {'lr': 0.0004933146985324975, 'samples': 1972224, 'steps': 3851, 'batch_loss/train': 0.8952564429491758}
+12/22/2021 03:01:42 - INFO - codeparrot_training - Step 3852: {'lr': 0.0004933110770774642, 'samples': 1972736, 'steps': 3852, 'batch_loss/train': 0.8151126080192626}
+12/22/2021 03:01:52 - INFO - codeparrot_training - Step 3853: {'lr': 0.0004933074546551179, 'samples': 1973248, 'steps': 3853, 'batch_loss/train': 0.8732803547754884}
+12/22/2021 03:02:05 - INFO - codeparrot_training - Step 3854: {'lr': 0.0004933038312654732, 'samples': 1973760, 'steps': 3854, 'batch_loss/train': 1.0026607951149344}
+12/22/2021 03:02:15 - INFO - codeparrot_training - Step 3855: {'lr': 0.0004933002069085441, 'samples': 1974272, 'steps': 3855, 'batch_loss/train': 0.7407977811526507}
+12/22/2021 03:02:26 - INFO - codeparrot_training - Step 3856: {'lr': 0.0004932965815843454, 'samples': 1974784, 'steps': 3856, 'batch_loss/train': 0.7021969703491777}
+12/22/2021 03:02:39 - INFO - codeparrot_training - Step 3857: {'lr': 0.0004932929552928914, 'samples': 1975296, 'steps': 3857, 'batch_loss/train': 0.8418228719383478}
+12/22/2021 03:02:49 - INFO - codeparrot_training - Step 3858: {'lr': 0.0004932893280341964, 'samples': 1975808, 'steps': 3858, 'batch_loss/train': 0.8094428973272443}
+12/22/2021 03:03:00 - INFO - codeparrot_training - Step 3859: {'lr': 0.0004932856998082749, 'samples': 1976320, 'steps': 3859, 'batch_loss/train': 0.8810163140296936}
+12/22/2021 03:03:12 - INFO - codeparrot_training - Step 3860: {'lr': 0.0004932820706151414, 'samples': 1976832, 'steps': 3860, 'batch_loss/train': 0.8627619971521199}
+12/22/2021 03:03:23 - INFO - codeparrot_training - Step 3861: {'lr': 0.0004932784404548101, 'samples': 1977344, 'steps': 3861, 'batch_loss/train': 0.9168316442519426}
+12/22/2021 03:03:33 - INFO - codeparrot_training - Step 3862: {'lr': 0.0004932748093272956, 'samples': 1977856, 'steps': 3862, 'batch_loss/train': 0.7957651475444436}
+12/22/2021 03:03:44 - INFO - codeparrot_training - Step 3863: {'lr': 0.0004932711772326125, 'samples': 1978368, 'steps': 3863, 'batch_loss/train': 0.8357260311022401}
+12/22/2021 03:03:56 - INFO - codeparrot_training - Step 3864: {'lr': 0.0004932675441707749, 'samples': 1978880, 'steps': 3864, 'batch_loss/train': 0.8389697624370456}
+12/22/2021 03:04:07 - INFO - codeparrot_training - Step 3865: {'lr': 0.0004932639101417974, 'samples': 1979392, 'steps': 3865, 'batch_loss/train': 0.8550601061433554}
+12/22/2021 03:04:17 - INFO - codeparrot_training - Step 3866: {'lr': 0.0004932602751456945, 'samples': 1979904, 'steps': 3866, 'batch_loss/train': 0.7959549902006984}
+12/22/2021 03:04:29 - INFO - codeparrot_training - Step 3867: {'lr': 0.0004932566391824806, 'samples': 1980416, 'steps': 3867, 'batch_loss/train': 0.7526218174025416}
+12/22/2021 03:04:40 - INFO - codeparrot_training - Step 3868: {'lr': 0.00049325300225217, 'samples': 1980928, 'steps': 3868, 'batch_loss/train': 0.8627567188814282}
+12/22/2021 03:04:51 - INFO - codeparrot_training - Step 3869: {'lr': 0.0004932493643547774, 'samples': 1981440, 'steps': 3869, 'batch_loss/train': 0.8175106435082853}
+12/22/2021 03:05:03 - INFO - codeparrot_training - Step 3870: {'lr': 0.0004932457254903172, 'samples': 1981952, 'steps': 3870, 'batch_loss/train': 0.8299692878499627}
+12/22/2021 03:05:14 - INFO - codeparrot_training - Step 3871: {'lr': 0.0004932420856588039, 'samples': 1982464, 'steps': 3871, 'batch_loss/train': 0.9673319458961487}
+12/22/2021 03:05:24 - INFO - codeparrot_training - Step 3872: {'lr': 0.0004932384448602518, 'samples': 1982976, 'steps': 3872, 'batch_loss/train': 0.8853581510484219}
+12/22/2021 03:05:36 - INFO - codeparrot_training - Step 3873: {'lr': 0.0004932348030946756, 'samples': 1983488, 'steps': 3873, 'batch_loss/train': 0.8844238193705678}
+12/22/2021 03:05:47 - INFO - codeparrot_training - Step 3874: {'lr': 0.0004932311603620896, 'samples': 1984000, 'steps': 3874, 'batch_loss/train': 0.9274575170129538}
+12/22/2021 03:05:58 - INFO - codeparrot_training - Step 3875: {'lr': 0.0004932275166625084, 'samples': 1984512, 'steps': 3875, 'batch_loss/train': 0.9914575247094035}
+12/22/2021 03:06:08 - INFO - codeparrot_training - Step 3876: {'lr': 0.0004932238719959464, 'samples': 1985024, 'steps': 3876, 'batch_loss/train': 0.8374196030199528}
+12/22/2021 03:06:20 - INFO - codeparrot_training - Step 3877: {'lr': 0.000493220226362418, 'samples': 1985536, 'steps': 3877, 'batch_loss/train': 0.810539124533534}
+12/22/2021 03:06:31 - INFO - codeparrot_training - Step 3878: {'lr': 0.000493216579761938, 'samples': 1986048, 'steps': 3878, 'batch_loss/train': 0.8527323370799422}
+12/22/2021 03:06:42 - INFO - codeparrot_training - Step 3879: {'lr': 0.0004932129321945206, 'samples': 1986560, 'steps': 3879, 'batch_loss/train': 0.8350735884159803}
+12/22/2021 03:06:54 - INFO - codeparrot_training - Step 3880: {'lr': 0.0004932092836601805, 'samples': 1987072, 'steps': 3880, 'batch_loss/train': 0.9590949066914618}
+12/22/2021 03:07:05 - INFO - codeparrot_training - Step 3881: {'lr': 0.000493205634158932, 'samples': 1987584, 'steps': 3881, 'batch_loss/train': 0.9650401920080185}
+12/22/2021 03:07:16 - INFO - codeparrot_training - Step 3882: {'lr': 0.0004932019836907898, 'samples': 1988096, 'steps': 3882, 'batch_loss/train': 0.8384674405679107}
+12/22/2021 03:07:28 - INFO - codeparrot_training - Step 3883: {'lr': 0.0004931983322557684, 'samples': 1988608, 'steps': 3883, 'batch_loss/train': 0.9073997475206852}
+12/22/2021 03:07:38 - INFO - codeparrot_training - Step 3884: {'lr': 0.0004931946798538823, 'samples': 1989120, 'steps': 3884, 'batch_loss/train': 1.008957359008491}
+12/22/2021 03:07:49 - INFO - codeparrot_training - Step 3885: {'lr': 0.0004931910264851458, 'samples': 1989632, 'steps': 3885, 'batch_loss/train': 0.8374830596148968}
+12/22/2021 03:08:00 - INFO - codeparrot_training - Step 3886: {'lr': 0.0004931873721495737, 'samples': 1990144, 'steps': 3886, 'batch_loss/train': 0.9547140579670668}
+12/22/2021 03:08:12 - INFO - codeparrot_training - Step 3887: {'lr': 0.0004931837168471805, 'samples': 1990656, 'steps': 3887, 'batch_loss/train': 0.8437651824206114}
+12/22/2021 03:08:23 - INFO - codeparrot_training - Step 3888: {'lr': 0.0004931800605779805, 'samples': 1991168, 'steps': 3888, 'batch_loss/train': 0.8827533386647701}
+12/22/2021 03:08:34 - INFO - codeparrot_training - Step 3889: {'lr': 0.0004931764033419885, 'samples': 1991680, 'steps': 3889, 'batch_loss/train': 0.8302919287234545}
+12/22/2021 03:08:46 - INFO - codeparrot_training - Step 3890: {'lr': 0.0004931727451392189, 'samples': 1992192, 'steps': 3890, 'batch_loss/train': 1.562019070610404}
+12/22/2021 03:08:56 - INFO - codeparrot_training - Step 3891: {'lr': 0.0004931690859696863, 'samples': 1992704, 'steps': 3891, 'batch_loss/train': 0.6735600819811225}
+12/22/2021 03:09:07 - INFO - codeparrot_training - Step 3892: {'lr': 0.0004931654258334053, 'samples': 1993216, 'steps': 3892, 'batch_loss/train': 0.8193907630629838}
+12/22/2021 03:09:19 - INFO - codeparrot_training - Step 3893: {'lr': 0.0004931617647303903, 'samples': 1993728, 'steps': 3893, 'batch_loss/train': 0.9119421700015664}
+12/22/2021 03:09:30 - INFO - codeparrot_training - Step 3894: {'lr': 0.000493158102660656, 'samples': 1994240, 'steps': 3894, 'batch_loss/train': 0.8828867739066482}
+12/22/2021 03:09:40 - INFO - codeparrot_training - Step 3895: {'lr': 0.0004931544396242168, 'samples': 1994752, 'steps': 3895, 'batch_loss/train': 0.9571973392739892}
+12/22/2021 03:09:53 - INFO - codeparrot_training - Step 3896: {'lr': 0.0004931507756210875, 'samples': 1995264, 'steps': 3896, 'batch_loss/train': 0.7557554412633181}
+12/22/2021 03:10:04 - INFO - codeparrot_training - Step 3897: {'lr': 0.0004931471106512824, 'samples': 1995776, 'steps': 3897, 'batch_loss/train': 0.966940370388329}
+12/22/2021 03:10:14 - INFO - codeparrot_training - Step 3898: {'lr': 0.0004931434447148162, 'samples': 1996288, 'steps': 3898, 'batch_loss/train': 0.7110615766141564}
+12/22/2021 03:10:25 - INFO - codeparrot_training - Step 3899: {'lr': 0.0004931397778117036, 'samples': 1996800, 'steps': 3899, 'batch_loss/train': 0.9368090350180864}
+12/22/2021 03:10:38 - INFO - codeparrot_training - Step 3900: {'lr': 0.0004931361099419589, 'samples': 1997312, 'steps': 3900, 'batch_loss/train': 0.9381023864261806}
+12/22/2021 03:10:48 - INFO - codeparrot_training - Step 3901: {'lr': 0.0004931324411055969, 'samples': 1997824, 'steps': 3901, 'batch_loss/train': 0.8043716205283999}
+12/22/2021 03:10:59 - INFO - codeparrot_training - Step 3902: {'lr': 0.0004931287713026321, 'samples': 1998336, 'steps': 3902, 'batch_loss/train': 0.9005447374656796}
+12/22/2021 03:11:11 - INFO - codeparrot_training - Step 3903: {'lr': 0.0004931251005330791, 'samples': 1998848, 'steps': 3903, 'batch_loss/train': 0.8559758923947811}
+12/22/2021 03:11:22 - INFO - codeparrot_training - Step 3904: {'lr': 0.0004931214287969525, 'samples': 1999360, 'steps': 3904, 'batch_loss/train': 0.8582718628458679}
+12/22/2021 03:11:32 - INFO - codeparrot_training - Step 3905: {'lr': 0.000493117756094267, 'samples': 1999872, 'steps': 3905, 'batch_loss/train': 0.7367847251007333}
+12/22/2021 03:11:44 - INFO - codeparrot_training - Step 3906: {'lr': 0.0004931140824250371, 'samples': 2000384, 'steps': 3906, 'batch_loss/train': 0.9151057740673423}
+12/22/2021 03:11:55 - INFO - codeparrot_training - Step 3907: {'lr': 0.0004931104077892772, 'samples': 2000896, 'steps': 3907, 'batch_loss/train': 0.918741153087467}
+12/22/2021 03:12:05 - INFO - codeparrot_training - Step 3908: {'lr': 0.0004931067321870023, 'samples': 2001408, 'steps': 3908, 'batch_loss/train': 0.8395575573667884}
+12/22/2021 03:12:16 - INFO - codeparrot_training - Step 3909: {'lr': 0.0004931030556182268, 'samples': 2001920, 'steps': 3909, 'batch_loss/train': 0.8448283183388412}
+12/22/2021 03:12:29 - INFO - codeparrot_training - Step 3910: {'lr': 0.0004930993780829652, 'samples': 2002432, 'steps': 3910, 'batch_loss/train': 0.8309317911043763}
+12/22/2021 03:12:39 - INFO - codeparrot_training - Step 3911: {'lr': 0.0004930956995812324, 'samples': 2002944, 'steps': 3911, 'batch_loss/train': 0.9689611354842782}
+12/22/2021 03:12:50 - INFO - codeparrot_training - Step 3912: {'lr': 0.0004930920201130428, 'samples': 2003456, 'steps': 3912, 'batch_loss/train': 0.80058483639732}
+12/22/2021 03:13:02 - INFO - codeparrot_training - Step 3913: {'lr': 0.0004930883396784113, 'samples': 2003968, 'steps': 3913, 'batch_loss/train': 0.973320534452796}
+12/22/2021 03:13:13 - INFO - codeparrot_training - Step 3914: {'lr': 0.0004930846582773522, 'samples': 2004480, 'steps': 3914, 'batch_loss/train': 0.7821514308452606}
+12/22/2021 03:13:23 - INFO - codeparrot_training - Step 3915: {'lr': 0.0004930809759098803, 'samples': 2004992, 'steps': 3915, 'batch_loss/train': 0.8534503588452935}
+12/22/2021 03:13:36 - INFO - codeparrot_training - Step 3916: {'lr': 0.0004930772925760102, 'samples': 2005504, 'steps': 3916, 'batch_loss/train': 0.8088550022803247}
+12/22/2021 03:13:47 - INFO - codeparrot_training - Step 3917: {'lr': 0.0004930736082757566, 'samples': 2006016, 'steps': 3917, 'batch_loss/train': 0.9357772294897586}
+12/22/2021 03:13:57 - INFO - codeparrot_training - Step 3918: {'lr': 0.0004930699230091341, 'samples': 2006528, 'steps': 3918, 'batch_loss/train': 0.8147646440193057}
+12/22/2021 03:14:09 - INFO - codeparrot_training - Step 3919: {'lr': 0.0004930662367761574, 'samples': 2007040, 'steps': 3919, 'batch_loss/train': 0.8136955020017922}
+12/22/2021 03:14:20 - INFO - codeparrot_training - Step 3920: {'lr': 0.000493062549576841, 'samples': 2007552, 'steps': 3920, 'batch_loss/train': 0.8642320623621345}
+12/22/2021 03:14:30 - INFO - codeparrot_training - Step 3921: {'lr': 0.0004930588614111999, 'samples': 2008064, 'steps': 3921, 'batch_loss/train': 0.9008946660906076}
+12/22/2021 03:14:41 - INFO - codeparrot_training - Step 3922: {'lr': 0.0004930551722792483, 'samples': 2008576, 'steps': 3922, 'batch_loss/train': 0.8513338938355446}
+12/22/2021 03:14:53 - INFO - codeparrot_training - Step 3923: {'lr': 0.0004930514821810013, 'samples': 2009088, 'steps': 3923, 'batch_loss/train': 0.763062552548945}
+12/22/2021 03:15:04 - INFO - codeparrot_training - Step 3924: {'lr': 0.0004930477911164733, 'samples': 2009600, 'steps': 3924, 'batch_loss/train': 0.822375706396997}
+12/22/2021 03:15:14 - INFO - codeparrot_training - Step 3925: {'lr': 0.000493044099085679, 'samples': 2010112, 'steps': 3925, 'batch_loss/train': 0.7947790520265698}
+12/22/2021 03:15:27 - INFO - codeparrot_training - Step 3926: {'lr': 0.0004930404060886332, 'samples': 2010624, 'steps': 3926, 'batch_loss/train': 0.850260779261589}
+12/22/2021 03:15:38 - INFO - codeparrot_training - Step 3927: {'lr': 0.0004930367121253505, 'samples': 2011136, 'steps': 3927, 'batch_loss/train': 0.882644783705473}
+12/22/2021 03:15:48 - INFO - codeparrot_training - Step 3928: {'lr': 0.0004930330171958457, 'samples': 2011648, 'steps': 3928, 'batch_loss/train': 0.8367344061844051}
+12/22/2021 03:16:00 - INFO - codeparrot_training - Step 3929: {'lr': 0.0004930293213001333, 'samples': 2012160, 'steps': 3929, 'batch_loss/train': 0.7689497340470552}
+12/22/2021 03:16:11 - INFO - codeparrot_training - Step 3930: {'lr': 0.000493025624438228, 'samples': 2012672, 'steps': 3930, 'batch_loss/train': 0.8501249547116458}
+12/22/2021 03:16:22 - INFO - codeparrot_training - Step 3931: {'lr': 0.0004930219266101447, 'samples': 2013184, 'steps': 3931, 'batch_loss/train': 0.8033738858066499}
+12/22/2021 03:16:32 - INFO - codeparrot_training - Step 3932: {'lr': 0.000493018227815898, 'samples': 2013696, 'steps': 3932, 'batch_loss/train': 0.9191227182745934}
+12/22/2021 03:16:44 - INFO - codeparrot_training - Step 3933: {'lr': 0.0004930145280555025, 'samples': 2014208, 'steps': 3933, 'batch_loss/train': 0.8806504644453526}
+12/22/2021 03:16:55 - INFO - codeparrot_training - Step 3934: {'lr': 0.000493010827328973, 'samples': 2014720, 'steps': 3934, 'batch_loss/train': 0.6737387403845787}
+12/22/2021 03:17:05 - INFO - codeparrot_training - Step 3935: {'lr': 0.0004930071256363242, 'samples': 2015232, 'steps': 3935, 'batch_loss/train': 0.8183085494674742}
+12/22/2021 03:17:19 - INFO - codeparrot_training - Step 3936: {'lr': 0.0004930034229775709, 'samples': 2015744, 'steps': 3936, 'batch_loss/train': 0.8656334890983999}
+12/22/2021 03:17:30 - INFO - codeparrot_training - Step 3937: {'lr': 0.0004929997193527277, 'samples': 2016256, 'steps': 3937, 'batch_loss/train': 0.8002016507089138}
+12/22/2021 03:17:40 - INFO - codeparrot_training - Step 3938: {'lr': 0.0004929960147618093, 'samples': 2016768, 'steps': 3938, 'batch_loss/train': 0.9789000083692372}
+12/22/2021 03:17:52 - INFO - codeparrot_training - Step 3939: {'lr': 0.0004929923092048306, 'samples': 2017280, 'steps': 3939, 'batch_loss/train': 1.2592190178111196}
+12/22/2021 03:18:03 - INFO - codeparrot_training - Step 3940: {'lr': 0.0004929886026818062, 'samples': 2017792, 'steps': 3940, 'batch_loss/train': 0.8581275949254632}
+12/22/2021 03:18:14 - INFO - codeparrot_training - Step 3941: {'lr': 0.0004929848951927509, 'samples': 2018304, 'steps': 3941, 'batch_loss/train': 0.9207782819867134}
+12/22/2021 03:18:26 - INFO - codeparrot_training - Step 3942: {'lr': 0.0004929811867376793, 'samples': 2018816, 'steps': 3942, 'batch_loss/train': 0.7627676008269191}
+12/22/2021 03:18:37 - INFO - codeparrot_training - Step 3943: {'lr': 0.0004929774773166064, 'samples': 2019328, 'steps': 3943, 'batch_loss/train': 0.7873056810349226}
+12/22/2021 03:18:48 - INFO - codeparrot_training - Step 3944: {'lr': 0.0004929737669295466, 'samples': 2019840, 'steps': 3944, 'batch_loss/train': 0.7888134242966771}
+12/22/2021 03:18:58 - INFO - codeparrot_training - Step 3945: {'lr': 0.000492970055576515, 'samples': 2020352, 'steps': 3945, 'batch_loss/train': 0.7963713677600026}
+12/22/2021 03:19:10 - INFO - codeparrot_training - Step 3946: {'lr': 0.0004929663432575262, 'samples': 2020864, 'steps': 3946, 'batch_loss/train': 0.9198372159153223}
+12/22/2021 03:19:21 - INFO - codeparrot_training - Step 3947: {'lr': 0.0004929626299725949, 'samples': 2021376, 'steps': 3947, 'batch_loss/train': 0.9403694430366158}
+12/22/2021 03:19:32 - INFO - codeparrot_training - Step 3948: {'lr': 0.0004929589157217359, 'samples': 2021888, 'steps': 3948, 'batch_loss/train': 0.9057676559314132}
+12/22/2021 03:19:44 - INFO - codeparrot_training - Step 3949: {'lr': 0.000492955200504964, 'samples': 2022400, 'steps': 3949, 'batch_loss/train': 0.7494741673581302}
+12/22/2021 03:19:55 - INFO - codeparrot_training - Step 3950: {'lr': 0.000492951484322294, 'samples': 2022912, 'steps': 3950, 'batch_loss/train': 0.863868709653616}
+12/22/2021 03:20:05 - INFO - codeparrot_training - Step 3951: {'lr': 0.0004929477671737406, 'samples': 2023424, 'steps': 3951, 'batch_loss/train': 0.9050410622730851}
+12/22/2021 03:20:18 - INFO - codeparrot_training - Step 3952: {'lr': 0.0004929440490593187, 'samples': 2023936, 'steps': 3952, 'batch_loss/train': 0.7452170795295388}
+12/22/2021 03:20:28 - INFO - codeparrot_training - Step 3953: {'lr': 0.0004929403299790429, 'samples': 2024448, 'steps': 3953, 'batch_loss/train': 0.8952322481200099}
+12/22/2021 03:20:39 - INFO - codeparrot_training - Step 3954: {'lr': 0.0004929366099329281, 'samples': 2024960, 'steps': 3954, 'batch_loss/train': 0.9086220040917397}
+12/22/2021 03:20:50 - INFO - codeparrot_training - Step 3955: {'lr': 0.0004929328889209891, 'samples': 2025472, 'steps': 3955, 'batch_loss/train': 0.8106886129826307}
+12/22/2021 03:21:02 - INFO - codeparrot_training - Step 3956: {'lr': 0.0004929291669432406, 'samples': 2025984, 'steps': 3956, 'batch_loss/train': 0.8356507141143084}
+12/22/2021 03:21:13 - INFO - codeparrot_training - Step 3957: {'lr': 0.0004929254439996974, 'samples': 2026496, 'steps': 3957, 'batch_loss/train': 0.5621949810301885}
+12/22/2021 03:21:24 - INFO - codeparrot_training - Step 3958: {'lr': 0.0004929217200903745, 'samples': 2027008, 'steps': 3958, 'batch_loss/train': 0.96055016387254}
+12/22/2021 03:21:37 - INFO - codeparrot_training - Step 3959: {'lr': 0.0004929179952152865, 'samples': 2027520, 'steps': 3959, 'batch_loss/train': 0.8803301360458136}
+12/22/2021 03:21:47 - INFO - codeparrot_training - Step 3960: {'lr': 0.0004929142693744483, 'samples': 2028032, 'steps': 3960, 'batch_loss/train': 0.8416177555918694}
+12/22/2021 03:21:58 - INFO - codeparrot_training - Step 3961: {'lr': 0.0004929105425678747, 'samples': 2028544, 'steps': 3961, 'batch_loss/train': 0.816517666913569}
+12/22/2021 03:22:10 - INFO - codeparrot_training - Step 3962: {'lr': 0.0004929068147955804, 'samples': 2029056, 'steps': 3962, 'batch_loss/train': 0.6996951932087541}
+12/22/2021 03:22:20 - INFO - codeparrot_training - Step 3963: {'lr': 0.0004929030860575805, 'samples': 2029568, 'steps': 3963, 'batch_loss/train': 0.8543358547613025}
+12/22/2021 03:22:31 - INFO - codeparrot_training - Step 3964: {'lr': 0.0004928993563538895, 'samples': 2030080, 'steps': 3964, 'batch_loss/train': 0.976449036039412}
+12/22/2021 03:22:42 - INFO - codeparrot_training - Step 3965: {'lr': 0.0004928956256845223, 'samples': 2030592, 'steps': 3965, 'batch_loss/train': 0.7406814554706216}
+12/22/2021 03:22:54 - INFO - codeparrot_training - Step 3966: {'lr': 0.000492891894049494, 'samples': 2031104, 'steps': 3966, 'batch_loss/train': 0.7277922327630222}
+12/22/2021 03:23:04 - INFO - codeparrot_training - Step 3967: {'lr': 0.0004928881614488192, 'samples': 2031616, 'steps': 3967, 'batch_loss/train': 0.8887613015249372}
+12/22/2021 03:23:15 - INFO - codeparrot_training - Step 3968: {'lr': 0.0004928844278825128, 'samples': 2032128, 'steps': 3968, 'batch_loss/train': 0.8376848599873483}
+12/22/2021 03:23:27 - INFO - codeparrot_training - Step 3969: {'lr': 0.0004928806933505895, 'samples': 2032640, 'steps': 3969, 'batch_loss/train': 0.8786351103335619}
+12/22/2021 03:23:38 - INFO - codeparrot_training - Step 3970: {'lr': 0.0004928769578530644, 'samples': 2033152, 'steps': 3970, 'batch_loss/train': 0.7829575063660741}
+12/22/2021 03:23:48 - INFO - codeparrot_training - Step 3971: {'lr': 0.0004928732213899521, 'samples': 2033664, 'steps': 3971, 'batch_loss/train': 0.7181234874296933}
+12/22/2021 03:24:01 - INFO - codeparrot_training - Step 3972: {'lr': 0.0004928694839612676, 'samples': 2034176, 'steps': 3972, 'batch_loss/train': 0.8288478744216263}
+12/22/2021 03:24:12 - INFO - codeparrot_training - Step 3973: {'lr': 0.0004928657455670258, 'samples': 2034688, 'steps': 3973, 'batch_loss/train': 0.8714688718318939}
+12/22/2021 03:24:22 - INFO - codeparrot_training - Step 3974: {'lr': 0.0004928620062072415, 'samples': 2035200, 'steps': 3974, 'batch_loss/train': 0.8959438819438219}
+12/22/2021 03:24:33 - INFO - codeparrot_training - Step 3975: {'lr': 0.0004928582658819295, 'samples': 2035712, 'steps': 3975, 'batch_loss/train': 0.8504805788397789}
+12/22/2021 03:24:45 - INFO - codeparrot_training - Step 3976: {'lr': 0.0004928545245911047, 'samples': 2036224, 'steps': 3976, 'batch_loss/train': 0.8421950861811638}
+12/22/2021 03:24:55 - INFO - codeparrot_training - Step 3977: {'lr': 0.0004928507823347822, 'samples': 2036736, 'steps': 3977, 'batch_loss/train': 0.8208606177940965}
+12/22/2021 03:25:06 - INFO - codeparrot_training - Step 3978: {'lr': 0.0004928470391129766, 'samples': 2037248, 'steps': 3978, 'batch_loss/train': 0.8018357967957854}
+12/22/2021 03:25:18 - INFO - codeparrot_training - Step 3979: {'lr': 0.0004928432949257028, 'samples': 2037760, 'steps': 3979, 'batch_loss/train': 0.8892128756269813}
+12/22/2021 03:25:29 - INFO - codeparrot_training - Step 3980: {'lr': 0.0004928395497729757, 'samples': 2038272, 'steps': 3980, 'batch_loss/train': 0.8581522945314646}
+12/22/2021 03:25:39 - INFO - codeparrot_training - Step 3981: {'lr': 0.0004928358036548104, 'samples': 2038784, 'steps': 3981, 'batch_loss/train': 0.8016374306753278}
+12/22/2021 03:25:53 - INFO - codeparrot_training - Step 3982: {'lr': 0.0004928320565712216, 'samples': 2039296, 'steps': 3982, 'batch_loss/train': 0.9006948256865144}
+12/22/2021 03:26:03 - INFO - codeparrot_training - Step 3983: {'lr': 0.0004928283085222241, 'samples': 2039808, 'steps': 3983, 'batch_loss/train': 0.7625440126284957}
+12/22/2021 03:26:14 - INFO - codeparrot_training - Step 3984: {'lr': 0.0004928245595078331, 'samples': 2040320, 'steps': 3984, 'batch_loss/train': 0.8810455435886979}
+12/22/2021 03:26:26 - INFO - codeparrot_training - Step 3985: {'lr': 0.0004928208095280633, 'samples': 2040832, 'steps': 3985, 'batch_loss/train': 0.6100566554814577}
+12/22/2021 03:26:37 - INFO - codeparrot_training - Step 3986: {'lr': 0.0004928170585829296, 'samples': 2041344, 'steps': 3986, 'batch_loss/train': 0.7510919773485512}
+12/22/2021 03:26:47 - INFO - codeparrot_training - Step 3987: {'lr': 0.000492813306672447, 'samples': 2041856, 'steps': 3987, 'batch_loss/train': 0.7714018076658249}
+12/22/2021 03:26:58 - INFO - codeparrot_training - Step 3988: {'lr': 0.0004928095537966304, 'samples': 2042368, 'steps': 3988, 'batch_loss/train': 0.7487285176757723}
+12/22/2021 03:27:10 - INFO - codeparrot_training - Step 3989: {'lr': 0.0004928057999554946, 'samples': 2042880, 'steps': 3989, 'batch_loss/train': 0.8488930584862828}
+12/22/2021 03:27:20 - INFO - codeparrot_training - Step 3990: {'lr': 0.0004928020451490547, 'samples': 2043392, 'steps': 3990, 'batch_loss/train': 0.9103718847036362}
+12/22/2021 03:27:31 - INFO - codeparrot_training - Step 3991: {'lr': 0.0004927982893773255, 'samples': 2043904, 'steps': 3991, 'batch_loss/train': 0.7831796370446682}
+12/22/2021 03:27:44 - INFO - codeparrot_training - Step 3992: {'lr': 0.000492794532640322, 'samples': 2044416, 'steps': 3992, 'batch_loss/train': 0.8909170497208834}
+12/22/2021 03:27:54 - INFO - codeparrot_training - Step 3993: {'lr': 0.0004927907749380591, 'samples': 2044928, 'steps': 3993, 'batch_loss/train': 0.8144533315207809}
+12/22/2021 03:28:05 - INFO - codeparrot_training - Step 3994: {'lr': 0.0004927870162705518, 'samples': 2045440, 'steps': 3994, 'batch_loss/train': 0.794631714001298}
+12/22/2021 03:28:17 - INFO - codeparrot_training - Step 3995: {'lr': 0.000492783256637815, 'samples': 2045952, 'steps': 3995, 'batch_loss/train': 0.908253900706768}
+12/22/2021 03:28:28 - INFO - codeparrot_training - Step 3996: {'lr': 0.0004927794960398635, 'samples': 2046464, 'steps': 3996, 'batch_loss/train': 0.7966419719159603}
+12/22/2021 03:28:38 - INFO - codeparrot_training - Step 3997: {'lr': 0.0004927757344767125, 'samples': 2046976, 'steps': 3997, 'batch_loss/train': 0.8370355293154716}
+12/22/2021 03:28:49 - INFO - codeparrot_training - Step 3998: {'lr': 0.0004927719719483768, 'samples': 2047488, 'steps': 3998, 'batch_loss/train': 0.7639365149661899}
+12/22/2021 03:29:02 - INFO - codeparrot_training - Step 3999: {'lr': 0.0004927682084548715, 'samples': 2048000, 'steps': 3999, 'batch_loss/train': 0.7497921297326684}
+12/22/2021 03:29:12 - INFO - codeparrot_training - Step 4000: {'lr': 0.0004927644439962115, 'samples': 2048512, 'steps': 4000, 'batch_loss/train': 1.939749263226986}
+12/22/2021 03:29:23 - INFO - codeparrot_training - Step 4001: {'lr': 0.0004927606785724116, 'samples': 2049024, 'steps': 4001, 'batch_loss/train': 0.9224952477961779}
+12/22/2021 03:29:35 - INFO - codeparrot_training - Step 4002: {'lr': 0.000492756912183487, 'samples': 2049536, 'steps': 4002, 'batch_loss/train': 0.8272404531016946}
+12/22/2021 03:29:46 - INFO - codeparrot_training - Step 4003: {'lr': 0.0004927531448294524, 'samples': 2050048, 'steps': 4003, 'batch_loss/train': 0.7317931945435703}
+12/22/2021 03:29:56 - INFO - codeparrot_training - Step 4004: {'lr': 0.0004927493765103231, 'samples': 2050560, 'steps': 4004, 'batch_loss/train': 0.8750862628221512}
+12/22/2021 03:30:08 - INFO - codeparrot_training - Step 4005: {'lr': 0.000492745607226114, 'samples': 2051072, 'steps': 4005, 'batch_loss/train': 0.8990721963346004}
+12/22/2021 03:30:19 - INFO - codeparrot_training - Step 4006: {'lr': 0.0004927418369768399, 'samples': 2051584, 'steps': 4006, 'batch_loss/train': 0.9704464334063232}
+12/22/2021 03:30:30 - INFO - codeparrot_training - Step 4007: {'lr': 0.000492738065762516, 'samples': 2052096, 'steps': 4007, 'batch_loss/train': 0.8910357942804694}
+12/22/2021 03:30:40 - INFO - codeparrot_training - Step 4008: {'lr': 0.0004927342935831572, 'samples': 2052608, 'steps': 4008, 'batch_loss/train': 0.8607935458421707}
+12/22/2021 03:30:53 - INFO - codeparrot_training - Step 4009: {'lr': 0.0004927305204387785, 'samples': 2053120, 'steps': 4009, 'batch_loss/train': 0.8567226156592369}
+12/22/2021 03:31:03 - INFO - codeparrot_training - Step 4010: {'lr': 0.0004927267463293948, 'samples': 2053632, 'steps': 4010, 'batch_loss/train': 0.7735480377450585}
+12/22/2021 03:31:14 - INFO - codeparrot_training - Step 4011: {'lr': 0.0004927229712550213, 'samples': 2054144, 'steps': 4011, 'batch_loss/train': 0.8865181477740407}
+12/22/2021 03:31:26 - INFO - codeparrot_training - Step 4012: {'lr': 0.0004927191952156729, 'samples': 2054656, 'steps': 4012, 'batch_loss/train': 0.8445950420573354}
+12/22/2021 03:31:37 - INFO - codeparrot_training - Step 4013: {'lr': 0.0004927154182113646, 'samples': 2055168, 'steps': 4013, 'batch_loss/train': 0.9298778753727674}
+12/22/2021 03:31:47 - INFO - codeparrot_training - Step 4014: {'lr': 0.0004927116402421116, 'samples': 2055680, 'steps': 4014, 'batch_loss/train': 0.8360939025878906}
+12/22/2021 03:31:59 - INFO - codeparrot_training - Step 4015: {'lr': 0.0004927078613079285, 'samples': 2056192, 'steps': 4015, 'batch_loss/train': 0.8786779902875423}
+12/22/2021 03:32:10 - INFO - codeparrot_training - Step 4016: {'lr': 0.0004927040814088307, 'samples': 2056704, 'steps': 4016, 'batch_loss/train': 0.7898402875289321}
+12/22/2021 03:32:21 - INFO - codeparrot_training - Step 4017: {'lr': 0.0004927003005448332, 'samples': 2057216, 'steps': 4017, 'batch_loss/train': 0.8690209090709686}
+12/22/2021 03:32:33 - INFO - codeparrot_training - Step 4018: {'lr': 0.0004926965187159509, 'samples': 2057728, 'steps': 4018, 'batch_loss/train': 0.8544766263803467}
+12/22/2021 03:32:43 - INFO - codeparrot_training - Step 4019: {'lr': 0.0004926927359221988, 'samples': 2058240, 'steps': 4019, 'batch_loss/train': 0.8264490514993668}
+12/22/2021 03:32:54 - INFO - codeparrot_training - Step 4020: {'lr': 0.0004926889521635921, 'samples': 2058752, 'steps': 4020, 'batch_loss/train': 0.877487201243639}
+12/22/2021 03:33:05 - INFO - codeparrot_training - Step 4021: {'lr': 0.0004926851674401457, 'samples': 2059264, 'steps': 4021, 'batch_loss/train': 0.9886155249550939}
+12/22/2021 03:33:17 - INFO - codeparrot_training - Step 4022: {'lr': 0.0004926813817518748, 'samples': 2059776, 'steps': 4022, 'batch_loss/train': 0.96681207139045}
+12/22/2021 03:33:28 - INFO - codeparrot_training - Step 4023: {'lr': 0.0004926775950987943, 'samples': 2060288, 'steps': 4023, 'batch_loss/train': 0.8597860326990485}
+12/22/2021 03:33:39 - INFO - codeparrot_training - Step 4024: {'lr': 0.0004926738074809193, 'samples': 2060800, 'steps': 4024, 'batch_loss/train': 0.8022804544307292}
+12/22/2021 03:33:51 - INFO - codeparrot_training - Step 4025: {'lr': 0.0004926700188982649, 'samples': 2061312, 'steps': 4025, 'batch_loss/train': 1.12282660510391}
+12/22/2021 03:34:01 - INFO - codeparrot_training - Step 4026: {'lr': 0.000492666229350846, 'samples': 2061824, 'steps': 4026, 'batch_loss/train': 0.8577085128054023}
+12/22/2021 03:34:12 - INFO - codeparrot_training - Step 4027: {'lr': 0.000492662438838678, 'samples': 2062336, 'steps': 4027, 'batch_loss/train': 0.813668274320662}
+12/22/2021 03:34:25 - INFO - codeparrot_training - Step 4028: {'lr': 0.0004926586473617757, 'samples': 2062848, 'steps': 4028, 'batch_loss/train': 0.8566002333536744}
+12/22/2021 03:34:35 - INFO - codeparrot_training - Step 4029: {'lr': 0.0004926548549201542, 'samples': 2063360, 'steps': 4029, 'batch_loss/train': 0.9147388422861695}
+12/22/2021 03:34:46 - INFO - codeparrot_training - Step 4030: {'lr': 0.0004926510615138286, 'samples': 2063872, 'steps': 4030, 'batch_loss/train': 0.9181901644915342}
+12/22/2021 03:34:56 - INFO - codeparrot_training - Step 4031: {'lr': 0.0004926472671428142, 'samples': 2064384, 'steps': 4031, 'batch_loss/train': 0.7982976287603378}
+12/22/2021 03:35:09 - INFO - codeparrot_training - Step 4032: {'lr': 0.0004926434718071257, 'samples': 2064896, 'steps': 4032, 'batch_loss/train': 0.9180630436167121}
+12/22/2021 03:35:19 - INFO - codeparrot_training - Step 4033: {'lr': 0.0004926396755067785, 'samples': 2065408, 'steps': 4033, 'batch_loss/train': 0.8358725449070334}
+12/22/2021 03:35:30 - INFO - codeparrot_training - Step 4034: {'lr': 0.0004926358782417874, 'samples': 2065920, 'steps': 4034, 'batch_loss/train': 0.8483314928598702}
+12/22/2021 03:35:42 - INFO - codeparrot_training - Step 4035: {'lr': 0.0004926320800121678, 'samples': 2066432, 'steps': 4035, 'batch_loss/train': 0.7135164469946176}
+12/22/2021 03:35:52 - INFO - codeparrot_training - Step 4036: {'lr': 0.0004926282808179345, 'samples': 2066944, 'steps': 4036, 'batch_loss/train': 0.7975619584321976}
+12/22/2021 03:36:03 - INFO - codeparrot_training - Step 4037: {'lr': 0.0004926244806591029, 'samples': 2067456, 'steps': 4037, 'batch_loss/train': 0.920528088696301}
+12/22/2021 03:36:16 - INFO - codeparrot_training - Step 4038: {'lr': 0.000492620679535688, 'samples': 2067968, 'steps': 4038, 'batch_loss/train': 0.8891797438263893}
+12/22/2021 03:36:27 - INFO - codeparrot_training - Step 4039: {'lr': 0.0004926168774477047, 'samples': 2068480, 'steps': 4039, 'batch_loss/train': 0.8778839907608926}
+12/22/2021 03:36:37 - INFO - codeparrot_training - Step 4040: {'lr': 0.0004926130743951686, 'samples': 2068992, 'steps': 4040, 'batch_loss/train': 0.7715625325217843}
+12/22/2021 03:36:48 - INFO - codeparrot_training - Step 4041: {'lr': 0.0004926092703780943, 'samples': 2069504, 'steps': 4041, 'batch_loss/train': 0.8303506067022681}
+12/22/2021 03:37:00 - INFO - codeparrot_training - Step 4042: {'lr': 0.0004926054653964972, 'samples': 2070016, 'steps': 4042, 'batch_loss/train': 0.9952564276754856}
+12/22/2021 03:37:11 - INFO - codeparrot_training - Step 4043: {'lr': 0.0004926016594503925, 'samples': 2070528, 'steps': 4043, 'batch_loss/train': 0.8283628281205893}
+12/22/2021 03:37:21 - INFO - codeparrot_training - Step 4044: {'lr': 0.000492597852539795, 'samples': 2071040, 'steps': 4044, 'batch_loss/train': 0.8273870786651969}
+12/22/2021 03:37:34 - INFO - codeparrot_training - Step 4045: {'lr': 0.0004925940446647201, 'samples': 2071552, 'steps': 4045, 'batch_loss/train': 0.8455392615869641}
+12/22/2021 03:37:45 - INFO - codeparrot_training - Step 4046: {'lr': 0.000492590235825183, 'samples': 2072064, 'steps': 4046, 'batch_loss/train': 1.0025887973606586}
+12/22/2021 03:37:55 - INFO - codeparrot_training - Step 4047: {'lr': 0.0004925864260211986, 'samples': 2072576, 'steps': 4047, 'batch_loss/train': 0.9002260910347104}
+12/22/2021 03:38:07 - INFO - codeparrot_training - Step 4048: {'lr': 0.0004925826152527822, 'samples': 2073088, 'steps': 4048, 'batch_loss/train': 0.8416243176907301}
+12/22/2021 03:38:18 - INFO - codeparrot_training - Step 4049: {'lr': 0.0004925788035199488, 'samples': 2073600, 'steps': 4049, 'batch_loss/train': 0.93688546679914}
+12/22/2021 03:38:28 - INFO - codeparrot_training - Step 4050: {'lr': 0.0004925749908227139, 'samples': 2074112, 'steps': 4050, 'batch_loss/train': 0.8470156388357282}
+12/22/2021 03:38:40 - INFO - codeparrot_training - Step 4051: {'lr': 0.0004925711771610924, 'samples': 2074624, 'steps': 4051, 'batch_loss/train': 0.8448299306910485}
+12/22/2021 03:38:51 - INFO - codeparrot_training - Step 4052: {'lr': 0.0004925673625350993, 'samples': 2075136, 'steps': 4052, 'batch_loss/train': 0.842994038015604}
+12/22/2021 03:39:02 - INFO - codeparrot_training - Step 4053: {'lr': 0.0004925635469447501, 'samples': 2075648, 'steps': 4053, 'batch_loss/train': 0.8194690030068159}
+12/22/2021 03:39:12 - INFO - codeparrot_training - Step 4054: {'lr': 0.0004925597303900598, 'samples': 2076160, 'steps': 4054, 'batch_loss/train': 0.917898066341877}
+12/22/2021 03:39:24 - INFO - codeparrot_training - Step 4055: {'lr': 0.0004925559128710436, 'samples': 2076672, 'steps': 4055, 'batch_loss/train': 0.8899425034178421}
+12/22/2021 03:39:35 - INFO - codeparrot_training - Step 4056: {'lr': 0.0004925520943877167, 'samples': 2077184, 'steps': 4056, 'batch_loss/train': 0.8386385953053832}
+12/22/2021 03:39:46 - INFO - codeparrot_training - Step 4057: {'lr': 0.0004925482749400942, 'samples': 2077696, 'steps': 4057, 'batch_loss/train': 0.8371183546259999}
+12/22/2021 03:39:59 - INFO - codeparrot_training - Step 4058: {'lr': 0.0004925444545281914, 'samples': 2078208, 'steps': 4058, 'batch_loss/train': 0.8975976807996631}
+12/22/2021 03:40:09 - INFO - codeparrot_training - Step 4059: {'lr': 0.0004925406331520234, 'samples': 2078720, 'steps': 4059, 'batch_loss/train': 0.9045816473662853}
+12/22/2021 03:40:20 - INFO - codeparrot_training - Step 4060: {'lr': 0.0004925368108116054, 'samples': 2079232, 'steps': 4060, 'batch_loss/train': 0.8102682735770941}
+12/22/2021 03:40:32 - INFO - codeparrot_training - Step 4061: {'lr': 0.0004925329875069526, 'samples': 2079744, 'steps': 4061, 'batch_loss/train': 0.8013631673529744}
+12/22/2021 03:40:43 - INFO - codeparrot_training - Step 4062: {'lr': 0.0004925291632380803, 'samples': 2080256, 'steps': 4062, 'batch_loss/train': 0.8012921512126923}
+12/22/2021 03:40:53 - INFO - codeparrot_training - Step 4063: {'lr': 0.0004925253380050035, 'samples': 2080768, 'steps': 4063, 'batch_loss/train': 0.8662208784371614}
+12/22/2021 03:41:04 - INFO - codeparrot_training - Step 4064: {'lr': 0.0004925215118077377, 'samples': 2081280, 'steps': 4064, 'batch_loss/train': 0.887549351900816}
+12/22/2021 03:41:16 - INFO - codeparrot_training - Step 4065: {'lr': 0.0004925176846462978, 'samples': 2081792, 'steps': 4065, 'batch_loss/train': 0.8047728394158185}
+12/22/2021 03:41:26 - INFO - codeparrot_training - Step 4066: {'lr': 0.0004925138565206992, 'samples': 2082304, 'steps': 4066, 'batch_loss/train': 0.9118258021771908}
+12/22/2021 03:41:37 - INFO - codeparrot_training - Step 4067: {'lr': 0.0004925100274309571, 'samples': 2082816, 'steps': 4067, 'batch_loss/train': 0.7800125600770116}
+12/22/2021 03:41:49 - INFO - codeparrot_training - Step 4068: {'lr': 0.0004925061973770867, 'samples': 2083328, 'steps': 4068, 'batch_loss/train': 0.842938145622611}
+12/22/2021 03:42:00 - INFO - codeparrot_training - Step 4069: {'lr': 0.0004925023663591031, 'samples': 2083840, 'steps': 4069, 'batch_loss/train': 0.8663719743490219}
+12/22/2021 03:42:11 - INFO - codeparrot_training - Step 4070: {'lr': 0.0004924985343770219, 'samples': 2084352, 'steps': 4070, 'batch_loss/train': 0.8080026539973915}
+12/22/2021 03:42:23 - INFO - codeparrot_training - Step 4071: {'lr': 0.0004924947014308578, 'samples': 2084864, 'steps': 4071, 'batch_loss/train': 0.8576187444850802}
+12/22/2021 03:42:33 - INFO - codeparrot_training - Step 4072: {'lr': 0.0004924908675206266, 'samples': 2085376, 'steps': 4072, 'batch_loss/train': 0.8730600103735924}
+12/22/2021 03:42:44 - INFO - codeparrot_training - Step 4073: {'lr': 0.0004924870326463431, 'samples': 2085888, 'steps': 4073, 'batch_loss/train': 0.7766828294843435}
+12/22/2021 03:42:57 - INFO - codeparrot_training - Step 4074: {'lr': 0.0004924831968080228, 'samples': 2086400, 'steps': 4074, 'batch_loss/train': 0.8401000639423728}
+12/22/2021 03:43:07 - INFO - codeparrot_training - Step 4075: {'lr': 0.0004924793600056809, 'samples': 2086912, 'steps': 4075, 'batch_loss/train': 0.8160884510725737}
+12/22/2021 03:43:18 - INFO - codeparrot_training - Step 4076: {'lr': 0.0004924755222393325, 'samples': 2087424, 'steps': 4076, 'batch_loss/train': 0.9883578100707382}
+12/22/2021 03:43:29 - INFO - codeparrot_training - Step 4077: {'lr': 0.0004924716835089931, 'samples': 2087936, 'steps': 4077, 'batch_loss/train': 0.9357633530162275}
+12/22/2021 03:43:41 - INFO - codeparrot_training - Step 4078: {'lr': 0.0004924678438146776, 'samples': 2088448, 'steps': 4078, 'batch_loss/train': 0.8292823480442166}
+12/22/2021 03:43:51 - INFO - codeparrot_training - Step 4079: {'lr': 0.0004924640031564019, 'samples': 2088960, 'steps': 4079, 'batch_loss/train': 0.8427103636786342}
+12/22/2021 03:44:02 - INFO - codeparrot_training - Step 4080: {'lr': 0.0004924601615341806, 'samples': 2089472, 'steps': 4080, 'batch_loss/train': 0.8121208697557449}
+12/22/2021 03:44:14 - INFO - codeparrot_training - Step 4081: {'lr': 0.0004924563189480293, 'samples': 2089984, 'steps': 4081, 'batch_loss/train': 0.8540441486984491}
+12/22/2021 03:44:25 - INFO - codeparrot_training - Step 4082: {'lr': 0.0004924524753979632, 'samples': 2090496, 'steps': 4082, 'batch_loss/train': 0.8646829561330378}
+12/22/2021 03:44:36 - INFO - codeparrot_training - Step 4083: {'lr': 0.0004924486308839976, 'samples': 2091008, 'steps': 4083, 'batch_loss/train': 0.8439098326489329}
+12/22/2021 03:44:46 - INFO - codeparrot_training - Step 4084: {'lr': 0.0004924447854061479, 'samples': 2091520, 'steps': 4084, 'batch_loss/train': 0.8474629046395421}
+12/22/2021 03:44:59 - INFO - codeparrot_training - Step 4085: {'lr': 0.0004924409389644292, 'samples': 2092032, 'steps': 4085, 'batch_loss/train': 0.840415452606976}
+12/22/2021 03:45:09 - INFO - codeparrot_training - Step 4086: {'lr': 0.0004924370915588568, 'samples': 2092544, 'steps': 4086, 'batch_loss/train': 0.7762196827679873}
+12/22/2021 03:45:20 - INFO - codeparrot_training - Step 4087: {'lr': 0.0004924332431894461, 'samples': 2093056, 'steps': 4087, 'batch_loss/train': 0.8470400171354413}
+12/22/2021 03:45:32 - INFO - codeparrot_training - Step 4088: {'lr': 0.0004924293938562125, 'samples': 2093568, 'steps': 4088, 'batch_loss/train': 0.8784585501998663}
+12/22/2021 03:45:43 - INFO - codeparrot_training - Step 4089: {'lr': 0.000492425543559171, 'samples': 2094080, 'steps': 4089, 'batch_loss/train': 0.9186237771064043}
+12/22/2021 03:45:53 - INFO - codeparrot_training - Step 4090: {'lr': 0.0004924216922983372, 'samples': 2094592, 'steps': 4090, 'batch_loss/train': 0.8462586454115808}
+12/22/2021 03:46:05 - INFO - codeparrot_training - Step 4091: {'lr': 0.0004924178400737263, 'samples': 2095104, 'steps': 4091, 'batch_loss/train': 0.7473504939116538}
+12/22/2021 03:46:16 - INFO - codeparrot_training - Step 4092: {'lr': 0.0004924139868853534, 'samples': 2095616, 'steps': 4092, 'batch_loss/train': 0.8914831876754761}
+12/22/2021 03:46:27 - INFO - codeparrot_training - Step 4093: {'lr': 0.0004924101327332342, 'samples': 2096128, 'steps': 4093, 'batch_loss/train': 0.918848617002368}
+12/22/2021 03:46:38 - INFO - codeparrot_training - Step 4094: {'lr': 0.0004924062776173838, 'samples': 2096640, 'steps': 4094, 'batch_loss/train': 0.913783541880548}
+12/22/2021 03:46:49 - INFO - codeparrot_training - Step 4095: {'lr': 0.0004924024215378175, 'samples': 2097152, 'steps': 4095, 'batch_loss/train': 0.7991795456036925}
+12/22/2021 03:47:00 - INFO - codeparrot_training - Step 4096: {'lr': 0.0004923985644945508, 'samples': 2097664, 'steps': 4096, 'batch_loss/train': 0.7815361036919057}
+12/22/2021 03:47:10 - INFO - codeparrot_training - Step 4097: {'lr': 0.000492394706487599, 'samples': 2098176, 'steps': 4097, 'batch_loss/train': 0.801373035646975}
+12/22/2021 03:47:23 - INFO - codeparrot_training - Step 4098: {'lr': 0.0004923908475169772, 'samples': 2098688, 'steps': 4098, 'batch_loss/train': 0.9192048946861178}
+12/22/2021 03:47:34 - INFO - codeparrot_training - Step 4099: {'lr': 0.000492386987582701, 'samples': 2099200, 'steps': 4099, 'batch_loss/train': 0.8191734198480844}
+12/22/2021 03:47:45 - INFO - codeparrot_training - Step 4100: {'lr': 0.0004923831266847856, 'samples': 2099712, 'steps': 4100, 'batch_loss/train': 0.8017001561820507}
+12/22/2021 03:47:57 - INFO - codeparrot_training - Step 4101: {'lr': 0.0004923792648232465, 'samples': 2100224, 'steps': 4101, 'batch_loss/train': 0.877462980337441}
+12/22/2021 03:48:08 - INFO - codeparrot_training - Step 4102: {'lr': 0.0004923754019980988, 'samples': 2100736, 'steps': 4102, 'batch_loss/train': 0.7437187423929572}
+12/22/2021 03:48:18 - INFO - codeparrot_training - Step 4103: {'lr': 0.0004923715382093582, 'samples': 2101248, 'steps': 4103, 'batch_loss/train': 0.519745439873077}
+12/22/2021 03:48:31 - INFO - codeparrot_training - Step 4104: {'lr': 0.0004923676734570398, 'samples': 2101760, 'steps': 4104, 'batch_loss/train': 0.9059451539069414}
+12/22/2021 03:48:41 - INFO - codeparrot_training - Step 4105: {'lr': 0.0004923638077411591, 'samples': 2102272, 'steps': 4105, 'batch_loss/train': 0.770162015222013}
+12/22/2021 03:48:52 - INFO - codeparrot_training - Step 4106: {'lr': 0.0004923599410617313, 'samples': 2102784, 'steps': 4106, 'batch_loss/train': 0.7957731019705534}
+12/22/2021 03:49:03 - INFO - codeparrot_training - Step 4107: {'lr': 0.0004923560734187719, 'samples': 2103296, 'steps': 4107, 'batch_loss/train': 1.098386156372726}
+12/22/2021 03:49:15 - INFO - codeparrot_training - Step 4108: {'lr': 0.0004923522048122964, 'samples': 2103808, 'steps': 4108, 'batch_loss/train': 0.8004101002588868}
+12/22/2021 03:49:25 - INFO - codeparrot_training - Step 4109: {'lr': 0.00049234833524232, 'samples': 2104320, 'steps': 4109, 'batch_loss/train': 0.927650012075901}
+12/22/2021 03:49:36 - INFO - codeparrot_training - Step 4110: {'lr': 0.0004923444647088581, 'samples': 2104832, 'steps': 4110, 'batch_loss/train': 0.8178929818095639}
+12/22/2021 03:49:48 - INFO - codeparrot_training - Step 4111: {'lr': 0.000492340593211926, 'samples': 2105344, 'steps': 4111, 'batch_loss/train': 0.9088439680635929}
+12/22/2021 03:49:59 - INFO - codeparrot_training - Step 4112: {'lr': 0.0004923367207515393, 'samples': 2105856, 'steps': 4112, 'batch_loss/train': 0.7563310931436718}
+12/22/2021 03:50:09 - INFO - codeparrot_training - Step 4113: {'lr': 0.0004923328473277134, 'samples': 2106368, 'steps': 4113, 'batch_loss/train': 0.8010037818457931}
+12/22/2021 03:50:22 - INFO - codeparrot_training - Step 4114: {'lr': 0.0004923289729404634, 'samples': 2106880, 'steps': 4114, 'batch_loss/train': 0.8588320389389992}
+12/22/2021 03:50:33 - INFO - codeparrot_training - Step 4115: {'lr': 0.000492325097589805, 'samples': 2107392, 'steps': 4115, 'batch_loss/train': 0.8981123650446534}
+12/22/2021 03:50:43 - INFO - codeparrot_training - Step 4116: {'lr': 0.0004923212212757537, 'samples': 2107904, 'steps': 4116, 'batch_loss/train': 0.7968896902166307}
+12/22/2021 03:50:55 - INFO - codeparrot_training - Step 4117: {'lr': 0.0004923173439983244, 'samples': 2108416, 'steps': 4117, 'batch_loss/train': 0.8182796519249678}
+12/22/2021 03:51:06 - INFO - codeparrot_training - Step 4118: {'lr': 0.000492313465757533, 'samples': 2108928, 'steps': 4118, 'batch_loss/train': 0.8806311342632398}
+12/22/2021 03:51:17 - INFO - codeparrot_training - Step 4119: {'lr': 0.0004923095865533947, 'samples': 2109440, 'steps': 4119, 'batch_loss/train': 0.840994376456365}
+12/22/2021 03:51:27 - INFO - codeparrot_training - Step 4120: {'lr': 0.0004923057063859251, 'samples': 2109952, 'steps': 4120, 'batch_loss/train': 0.8425967460498214}
+12/22/2021 03:51:39 - INFO - codeparrot_training - Step 4121: {'lr': 0.0004923018252551393, 'samples': 2110464, 'steps': 4121, 'batch_loss/train': 0.920306664891541}
+12/22/2021 03:51:50 - INFO - codeparrot_training - Step 4122: {'lr': 0.0004922979431610531, 'samples': 2110976, 'steps': 4122, 'batch_loss/train': 0.8342994092963636}
+12/22/2021 03:52:01 - INFO - codeparrot_training - Step 4123: {'lr': 0.0004922940601036817, 'samples': 2111488, 'steps': 4123, 'batch_loss/train': 0.8120628613978624}
+12/22/2021 03:52:13 - INFO - codeparrot_training - Step 4124: {'lr': 0.0004922901760830406, 'samples': 2112000, 'steps': 4124, 'batch_loss/train': 0.874008446931839}
+12/22/2021 03:52:24 - INFO - codeparrot_training - Step 4125: {'lr': 0.0004922862910991452, 'samples': 2112512, 'steps': 4125, 'batch_loss/train': 0.8032994526438415}
+12/22/2021 03:52:34 - INFO - codeparrot_training - Step 4126: {'lr': 0.0004922824051520111, 'samples': 2113024, 'steps': 4126, 'batch_loss/train': 0.8865904361009598}
+12/22/2021 03:52:46 - INFO - codeparrot_training - Step 4127: {'lr': 0.0004922785182416535, 'samples': 2113536, 'steps': 4127, 'batch_loss/train': 0.7786675738170743}
+12/22/2021 03:52:57 - INFO - codeparrot_training - Step 4128: {'lr': 0.0004922746303680881, 'samples': 2114048, 'steps': 4128, 'batch_loss/train': 0.9352441132068634}
+12/22/2021 03:53:08 - INFO - codeparrot_training - Step 4129: {'lr': 0.0004922707415313303, 'samples': 2114560, 'steps': 4129, 'batch_loss/train': 0.8524200143292546}
+12/22/2021 03:53:18 - INFO - codeparrot_training - Step 4130: {'lr': 0.0004922668517313955, 'samples': 2115072, 'steps': 4130, 'batch_loss/train': 0.8909002440050244}
+12/22/2021 03:53:31 - INFO - codeparrot_training - Step 4131: {'lr': 0.0004922629609682991, 'samples': 2115584, 'steps': 4131, 'batch_loss/train': 0.8615256734192371}
+12/22/2021 03:53:41 - INFO - codeparrot_training - Step 4132: {'lr': 0.0004922590692420566, 'samples': 2116096, 'steps': 4132, 'batch_loss/train': 0.7947524776682258}
+12/22/2021 03:53:52 - INFO - codeparrot_training - Step 4133: {'lr': 0.0004922551765526836, 'samples': 2116608, 'steps': 4133, 'batch_loss/train': 0.8576065422967076}
+12/22/2021 03:54:05 - INFO - codeparrot_training - Step 4134: {'lr': 0.0004922512829001955, 'samples': 2117120, 'steps': 4134, 'batch_loss/train': 0.6755987210199237}
+12/22/2021 03:54:15 - INFO - codeparrot_training - Step 4135: {'lr': 0.0004922473882846077, 'samples': 2117632, 'steps': 4135, 'batch_loss/train': 0.9504460757598281}
+12/22/2021 03:54:26 - INFO - codeparrot_training - Step 4136: {'lr': 0.0004922434927059358, 'samples': 2118144, 'steps': 4136, 'batch_loss/train': 0.9165382497012615}
+12/22/2021 03:54:38 - INFO - codeparrot_training - Step 4137: {'lr': 0.0004922395961641953, 'samples': 2118656, 'steps': 4137, 'batch_loss/train': 0.9348579905927181}
+12/22/2021 03:54:49 - INFO - codeparrot_training - Step 4138: {'lr': 0.0004922356986594014, 'samples': 2119168, 'steps': 4138, 'batch_loss/train': 0.8500338159501553}
+12/22/2021 03:54:59 - INFO - codeparrot_training - Step 4139: {'lr': 0.00049223180019157, 'samples': 2119680, 'steps': 4139, 'batch_loss/train': 0.826232872903347}
+12/22/2021 03:55:10 - INFO - codeparrot_training - Step 4140: {'lr': 0.0004922279007607165, 'samples': 2120192, 'steps': 4140, 'batch_loss/train': 0.7446947055868804}
+12/22/2021 03:55:22 - INFO - codeparrot_training - Step 4141: {'lr': 0.0004922240003668562, 'samples': 2120704, 'steps': 4141, 'batch_loss/train': 0.5670101901050657}
+12/22/2021 03:55:33 - INFO - codeparrot_training - Step 4142: {'lr': 0.0004922200990100048, 'samples': 2121216, 'steps': 4142, 'batch_loss/train': 0.9021270740777254}
+12/22/2021 03:55:43 - INFO - codeparrot_training - Step 4143: {'lr': 0.0004922161966901777, 'samples': 2121728, 'steps': 4143, 'batch_loss/train': 0.9323629504069686}
+12/22/2021 03:55:56 - INFO - codeparrot_training - Step 4144: {'lr': 0.0004922122934073904, 'samples': 2122240, 'steps': 4144, 'batch_loss/train': 0.8500166293233633}
+12/22/2021 03:56:07 - INFO - codeparrot_training - Step 4145: {'lr': 0.0004922083891616586, 'samples': 2122752, 'steps': 4145, 'batch_loss/train': 0.8094088472425938}
+12/22/2021 03:56:17 - INFO - codeparrot_training - Step 4146: {'lr': 0.0004922044839529977, 'samples': 2123264, 'steps': 4146, 'batch_loss/train': 0.787008099257946}
+12/22/2021 03:56:29 - INFO - codeparrot_training - Step 4147: {'lr': 0.0004922005777814231, 'samples': 2123776, 'steps': 4147, 'batch_loss/train': 0.8856616225093603}
+12/22/2021 03:56:40 - INFO - codeparrot_training - Step 4148: {'lr': 0.0004921966706469505, 'samples': 2124288, 'steps': 4148, 'batch_loss/train': 0.8817527913488448}
+12/22/2021 03:56:51 - INFO - codeparrot_training - Step 4149: {'lr': 0.0004921927625495954, 'samples': 2124800, 'steps': 4149, 'batch_loss/train': 0.8503183955326676}
+12/22/2021 03:57:03 - INFO - codeparrot_training - Step 4150: {'lr': 0.0004921888534893733, 'samples': 2125312, 'steps': 4150, 'batch_loss/train': 0.8844315791502595}
+12/22/2021 03:57:13 - INFO - codeparrot_training - Step 4151: {'lr': 0.0004921849434662999, 'samples': 2125824, 'steps': 4151, 'batch_loss/train': 0.8079833211377263}
+12/22/2021 03:57:24 - INFO - codeparrot_training - Step 4152: {'lr': 0.0004921810324803905, 'samples': 2126336, 'steps': 4152, 'batch_loss/train': 0.5724159111268818}
+12/22/2021 03:57:35 - INFO - codeparrot_training - Step 4153: {'lr': 0.0004921771205316607, 'samples': 2126848, 'steps': 4153, 'batch_loss/train': 0.6515989694744349}
+12/22/2021 03:57:47 - INFO - codeparrot_training - Step 4154: {'lr': 0.0004921732076201263, 'samples': 2127360, 'steps': 4154, 'batch_loss/train': 0.9112244881689548}
+12/22/2021 03:57:58 - INFO - codeparrot_training - Step 4155: {'lr': 0.0004921692937458025, 'samples': 2127872, 'steps': 4155, 'batch_loss/train': 0.8497237404808402}
+12/22/2021 03:58:08 - INFO - codeparrot_training - Step 4156: {'lr': 0.0004921653789087051, 'samples': 2128384, 'steps': 4156, 'batch_loss/train': 0.9024626226164401}
+12/22/2021 03:58:21 - INFO - codeparrot_training - Step 4157: {'lr': 0.0004921614631088495, 'samples': 2128896, 'steps': 4157, 'batch_loss/train': 0.8117280481383204}
+12/22/2021 03:58:31 - INFO - codeparrot_training - Step 4158: {'lr': 0.0004921575463462516, 'samples': 2129408, 'steps': 4158, 'batch_loss/train': 0.7531013395637274}
+12/22/2021 03:58:42 - INFO - codeparrot_training - Step 4159: {'lr': 0.0004921536286209265, 'samples': 2129920, 'steps': 4159, 'batch_loss/train': 0.8092886880040169}
+12/22/2021 03:58:53 - INFO - codeparrot_training - Step 4160: {'lr': 0.00049214970993289, 'samples': 2130432, 'steps': 4160, 'batch_loss/train': 0.8370175296440721}
+12/22/2021 03:59:05 - INFO - codeparrot_training - Step 4161: {'lr': 0.0004921457902821578, 'samples': 2130944, 'steps': 4161, 'batch_loss/train': 0.8419553088024259}
+12/22/2021 03:59:16 - INFO - codeparrot_training - Step 4162: {'lr': 0.0004921418696687453, 'samples': 2131456, 'steps': 4162, 'batch_loss/train': 0.930520792491734}
+12/22/2021 03:59:27 - INFO - codeparrot_training - Step 4163: {'lr': 0.0004921379480926682, 'samples': 2131968, 'steps': 4163, 'batch_loss/train': 0.8297982150688767}
+12/22/2021 03:59:39 - INFO - codeparrot_training - Step 4164: {'lr': 0.0004921340255539421, 'samples': 2132480, 'steps': 4164, 'batch_loss/train': 0.7703292658552527}
+12/22/2021 03:59:49 - INFO - codeparrot_training - Step 4165: {'lr': 0.0004921301020525823, 'samples': 2132992, 'steps': 4165, 'batch_loss/train': 0.841952009126544}
+12/22/2021 04:00:00 - INFO - codeparrot_training - Step 4166: {'lr': 0.0004921261775886049, 'samples': 2133504, 'steps': 4166, 'batch_loss/train': 0.7798296669498086}
+12/22/2021 04:00:12 - INFO - codeparrot_training - Step 4167: {'lr': 0.0004921222521620251, 'samples': 2134016, 'steps': 4167, 'batch_loss/train': 1.006100881844759}
+12/22/2021 04:00:23 - INFO - codeparrot_training - Step 4168: {'lr': 0.0004921183257728587, 'samples': 2134528, 'steps': 4168, 'batch_loss/train': 0.8528145980089903}
+12/22/2021 04:00:33 - INFO - codeparrot_training - Step 4169: {'lr': 0.0004921143984211213, 'samples': 2135040, 'steps': 4169, 'batch_loss/train': 0.8339375359937549}
+12/22/2021 04:00:46 - INFO - codeparrot_training - Step 4170: {'lr': 0.0004921104701068284, 'samples': 2135552, 'steps': 4170, 'batch_loss/train': 0.7577645003329962}
+12/22/2021 04:00:57 - INFO - codeparrot_training - Step 4171: {'lr': 0.0004921065408299958, 'samples': 2136064, 'steps': 4171, 'batch_loss/train': 1.2949805464595556}
+12/22/2021 04:01:07 - INFO - codeparrot_training - Step 4172: {'lr': 0.0004921026105906388, 'samples': 2136576, 'steps': 4172, 'batch_loss/train': 0.9009168511256576}
+12/22/2021 04:01:18 - INFO - codeparrot_training - Step 4173: {'lr': 0.0004920986793887734, 'samples': 2137088, 'steps': 4173, 'batch_loss/train': 0.8433825736865401}
+12/22/2021 04:01:30 - INFO - codeparrot_training - Step 4174: {'lr': 0.000492094747224415, 'samples': 2137600, 'steps': 4174, 'batch_loss/train': 0.9215331058949232}
+12/22/2021 04:01:41 - INFO - codeparrot_training - Step 4175: {'lr': 0.0004920908140975793, 'samples': 2138112, 'steps': 4175, 'batch_loss/train': 0.8705638372339308}
+12/22/2021 04:01:52 - INFO - codeparrot_training - Step 4176: {'lr': 0.0004920868800082819, 'samples': 2138624, 'steps': 4176, 'batch_loss/train': 0.9390399809926748}
+12/22/2021 04:02:04 - INFO - codeparrot_training - Step 4177: {'lr': 0.0004920829449565386, 'samples': 2139136, 'steps': 4177, 'batch_loss/train': 0.8569097490981221}
+12/22/2021 04:02:15 - INFO - codeparrot_training - Step 4178: {'lr': 0.0004920790089423648, 'samples': 2139648, 'steps': 4178, 'batch_loss/train': 0.9303377270698547}
+12/22/2021 04:02:25 - INFO - codeparrot_training - Step 4179: {'lr': 0.0004920750719657762, 'samples': 2140160, 'steps': 4179, 'batch_loss/train': 0.8319423738867044}
+12/22/2021 04:02:37 - INFO - codeparrot_training - Step 4180: {'lr': 0.0004920711340267888, 'samples': 2140672, 'steps': 4180, 'batch_loss/train': 0.8132032584398985}
+12/22/2021 04:02:48 - INFO - codeparrot_training - Step 4181: {'lr': 0.0004920671951254178, 'samples': 2141184, 'steps': 4181, 'batch_loss/train': 0.9055496519431472}
+12/22/2021 04:02:58 - INFO - codeparrot_training - Step 4182: {'lr': 0.0004920632552616789, 'samples': 2141696, 'steps': 4182, 'batch_loss/train': 0.9279581867158413}
+12/22/2021 04:03:09 - INFO - codeparrot_training - Step 4183: {'lr': 0.0004920593144355881, 'samples': 2142208, 'steps': 4183, 'batch_loss/train': 0.8589329849928617}
+12/22/2021 04:03:22 - INFO - codeparrot_training - Step 4184: {'lr': 0.0004920553726471608, 'samples': 2142720, 'steps': 4184, 'batch_loss/train': 0.8395436815917492}
+12/22/2021 04:03:32 - INFO - codeparrot_training - Step 4185: {'lr': 0.0004920514298964127, 'samples': 2143232, 'steps': 4185, 'batch_loss/train': 0.7087234170176089}
+12/22/2021 04:03:43 - INFO - codeparrot_training - Step 4186: {'lr': 0.0004920474861833595, 'samples': 2143744, 'steps': 4186, 'batch_loss/train': 0.9538164502009749}
+12/22/2021 04:03:55 - INFO - codeparrot_training - Step 4187: {'lr': 0.000492043541508017, 'samples': 2144256, 'steps': 4187, 'batch_loss/train': 0.9009403511881828}
+12/22/2021 04:04:06 - INFO - codeparrot_training - Step 4188: {'lr': 0.0004920395958704007, 'samples': 2144768, 'steps': 4188, 'batch_loss/train': 0.9118561772629619}
+12/22/2021 04:04:16 - INFO - codeparrot_training - Step 4189: {'lr': 0.0004920356492705263, 'samples': 2145280, 'steps': 4189, 'batch_loss/train': 0.8730563372373581}
+12/22/2021 04:04:29 - INFO - codeparrot_training - Step 4190: {'lr': 0.0004920317017084096, 'samples': 2145792, 'steps': 4190, 'batch_loss/train': 0.9488238608464599}
+12/22/2021 04:04:40 - INFO - codeparrot_training - Step 4191: {'lr': 0.0004920277531840662, 'samples': 2146304, 'steps': 4191, 'batch_loss/train': 0.9781081806868315}
+12/22/2021 04:04:50 - INFO - codeparrot_training - Step 4192: {'lr': 0.0004920238036975119, 'samples': 2146816, 'steps': 4192, 'batch_loss/train': 0.8862302796915174}
+12/22/2021 04:05:01 - INFO - codeparrot_training - Step 4193: {'lr': 0.0004920198532487623, 'samples': 2147328, 'steps': 4193, 'batch_loss/train': 0.9819248989224434}
+12/22/2021 04:05:13 - INFO - codeparrot_training - Step 4194: {'lr': 0.0004920159018378332, 'samples': 2147840, 'steps': 4194, 'batch_loss/train': 1.1086815905291587}
+12/22/2021 04:05:24 - INFO - codeparrot_training - Step 4195: {'lr': 0.0004920119494647402, 'samples': 2148352, 'steps': 4195, 'batch_loss/train': 0.922237922437489}
+12/22/2021 04:05:35 - INFO - codeparrot_training - Step 4196: {'lr': 0.0004920079961294991, 'samples': 2148864, 'steps': 4196, 'batch_loss/train': 0.8239907678216696}
+12/22/2021 04:05:47 - INFO - codeparrot_training - Step 4197: {'lr': 0.0004920040418321256, 'samples': 2149376, 'steps': 4197, 'batch_loss/train': 0.8792415484786034}
+12/22/2021 04:05:58 - INFO - codeparrot_training - Step 4198: {'lr': 0.0004920000865726354, 'samples': 2149888, 'steps': 4198, 'batch_loss/train': 0.8275346867740154}
+12/22/2021 04:06:08 - INFO - codeparrot_training - Step 4199: {'lr': 0.0004919961303510442, 'samples': 2150400, 'steps': 4199, 'batch_loss/train': 0.7876558126881719}
+12/22/2021 04:06:20 - INFO - codeparrot_training - Step 4200: {'lr': 0.0004919921731673677, 'samples': 2150912, 'steps': 4200, 'batch_loss/train': 0.8251504953950644}
+12/22/2021 04:06:31 - INFO - codeparrot_training - Step 4201: {'lr': 0.0004919882150216219, 'samples': 2151424, 'steps': 4201, 'batch_loss/train': 0.8830639310181141}
+12/22/2021 04:06:41 - INFO - codeparrot_training - Step 4202: {'lr': 0.0004919842559138221, 'samples': 2151936, 'steps': 4202, 'batch_loss/train': 0.8418839145451784}
+12/22/2021 04:06:52 - INFO - codeparrot_training - Step 4203: {'lr': 0.0004919802958439844, 'samples': 2152448, 'steps': 4203, 'batch_loss/train': 0.8450416726991534}
+12/22/2021 04:07:05 - INFO - codeparrot_training - Step 4204: {'lr': 0.0004919763348121244, 'samples': 2152960, 'steps': 4204, 'batch_loss/train': 0.7476040422916412}
+12/22/2021 04:07:15 - INFO - codeparrot_training - Step 4205: {'lr': 0.0004919723728182578, 'samples': 2153472, 'steps': 4205, 'batch_loss/train': 0.9225826757028699}
+12/22/2021 04:07:26 - INFO - codeparrot_training - Step 4206: {'lr': 0.0004919684098624005, 'samples': 2153984, 'steps': 4206, 'batch_loss/train': 0.8907818743027747}
+12/22/2021 04:07:38 - INFO - codeparrot_training - Step 4207: {'lr': 0.0004919644459445682, 'samples': 2154496, 'steps': 4207, 'batch_loss/train': 0.8607776360586286}
+12/22/2021 04:07:49 - INFO - codeparrot_training - Step 4208: {'lr': 0.0004919604810647764, 'samples': 2155008, 'steps': 4208, 'batch_loss/train': 0.8636884298175573}
+12/22/2021 04:07:59 - INFO - codeparrot_training - Step 4209: {'lr': 0.0004919565152230412, 'samples': 2155520, 'steps': 4209, 'batch_loss/train': 0.8663858054205775}
+12/22/2021 04:08:11 - INFO - codeparrot_training - Step 4210: {'lr': 0.0004919525484193783, 'samples': 2156032, 'steps': 4210, 'batch_loss/train': 0.83458595816046}
+12/22/2021 04:08:22 - INFO - codeparrot_training - Step 4211: {'lr': 0.0004919485806538034, 'samples': 2156544, 'steps': 4211, 'batch_loss/train': 0.875915807671845}
+12/22/2021 04:08:33 - INFO - codeparrot_training - Step 4212: {'lr': 0.0004919446119263323, 'samples': 2157056, 'steps': 4212, 'batch_loss/train': 0.631615602876991}
+12/22/2021 04:08:45 - INFO - codeparrot_training - Step 4213: {'lr': 0.0004919406422369809, 'samples': 2157568, 'steps': 4213, 'batch_loss/train': 0.8464700803160667}
+12/22/2021 04:08:56 - INFO - codeparrot_training - Step 4214: {'lr': 0.0004919366715857648, 'samples': 2158080, 'steps': 4214, 'batch_loss/train': 0.7966765407472849}
+12/22/2021 04:09:06 - INFO - codeparrot_training - Step 4215: {'lr': 0.0004919326999726996, 'samples': 2158592, 'steps': 4215, 'batch_loss/train': 0.8686229945160449}
+12/22/2021 04:09:17 - INFO - codeparrot_training - Step 4216: {'lr': 0.0004919287273978016, 'samples': 2159104, 'steps': 4216, 'batch_loss/train': 0.8444241369143128}
+12/22/2021 04:09:29 - INFO - codeparrot_training - Step 4217: {'lr': 0.0004919247538610862, 'samples': 2159616, 'steps': 4217, 'batch_loss/train': 0.7683601351454854}
+12/22/2021 04:09:40 - INFO - codeparrot_training - Step 4218: {'lr': 0.0004919207793625695, 'samples': 2160128, 'steps': 4218, 'batch_loss/train': 0.8407889101654291}
+12/22/2021 04:09:50 - INFO - codeparrot_training - Step 4219: {'lr': 0.0004919168039022669, 'samples': 2160640, 'steps': 4219, 'batch_loss/train': 0.8537206966429949}
+12/22/2021 04:10:03 - INFO - codeparrot_training - Step 4220: {'lr': 0.0004919128274801946, 'samples': 2161152, 'steps': 4220, 'batch_loss/train': 0.9095764169469476}
+12/22/2021 04:10:14 - INFO - codeparrot_training - Step 4221: {'lr': 0.0004919088500963682, 'samples': 2161664, 'steps': 4221, 'batch_loss/train': 0.8450834965333343}
+12/22/2021 04:10:24 - INFO - codeparrot_training - Step 4222: {'lr': 0.0004919048717508034, 'samples': 2162176, 'steps': 4222, 'batch_loss/train': 0.5983525580959395}
+12/22/2021 04:10:37 - INFO - codeparrot_training - Step 4223: {'lr': 0.0004919008924435164, 'samples': 2162688, 'steps': 4223, 'batch_loss/train': 0.7912319777533412}
+12/22/2021 04:10:47 - INFO - codeparrot_training - Step 4224: {'lr': 0.0004918969121745227, 'samples': 2163200, 'steps': 4224, 'batch_loss/train': 0.732310350984335}
+12/22/2021 04:10:58 - INFO - codeparrot_training - Step 4225: {'lr': 0.0004918929309438381, 'samples': 2163712, 'steps': 4225, 'batch_loss/train': 0.8868085164576769}
+12/22/2021 04:11:09 - INFO - codeparrot_training - Step 4226: {'lr': 0.0004918889487514788, 'samples': 2164224, 'steps': 4226, 'batch_loss/train': 0.8994815619662404}
+12/22/2021 04:11:21 - INFO - codeparrot_training - Step 4227: {'lr': 0.0004918849655974601, 'samples': 2164736, 'steps': 4227, 'batch_loss/train': 0.7697261534631252}
+12/22/2021 04:11:31 - INFO - codeparrot_training - Step 4228: {'lr': 0.0004918809814817983, 'samples': 2165248, 'steps': 4228, 'batch_loss/train': 0.7518858457915485}
+12/22/2021 04:11:42 - INFO - codeparrot_training - Step 4229: {'lr': 0.000491876996404509, 'samples': 2165760, 'steps': 4229, 'batch_loss/train': 0.858812041580677}
+12/22/2021 04:11:55 - INFO - codeparrot_training - Step 4230: {'lr': 0.0004918730103656081, 'samples': 2166272, 'steps': 4230, 'batch_loss/train': 0.8146057026460767}
+12/22/2021 04:12:05 - INFO - codeparrot_training - Step 4231: {'lr': 0.0004918690233651113, 'samples': 2166784, 'steps': 4231, 'batch_loss/train': 0.8729232931509614}
+12/22/2021 04:12:16 - INFO - codeparrot_training - Step 4232: {'lr': 0.0004918650354030347, 'samples': 2167296, 'steps': 4232, 'batch_loss/train': 0.6907808653777465}
+12/22/2021 04:12:28 - INFO - codeparrot_training - Step 4233: {'lr': 0.000491861046479394, 'samples': 2167808, 'steps': 4233, 'batch_loss/train': 0.9290086850523949}
+12/22/2021 04:12:39 - INFO - codeparrot_training - Step 4234: {'lr': 0.0004918570565942052, 'samples': 2168320, 'steps': 4234, 'batch_loss/train': 0.9269060548394918}
+12/22/2021 04:12:49 - INFO - codeparrot_training - Step 4235: {'lr': 0.0004918530657474841, 'samples': 2168832, 'steps': 4235, 'batch_loss/train': 0.8176009701564908}
+12/22/2021 04:13:01 - INFO - codeparrot_training - Step 4236: {'lr': 0.0004918490739392464, 'samples': 2169344, 'steps': 4236, 'batch_loss/train': 0.8197090420871973}
+12/22/2021 04:13:12 - INFO - codeparrot_training - Step 4237: {'lr': 0.000491845081169508, 'samples': 2169856, 'steps': 4237, 'batch_loss/train': 0.6932108988985419}
+12/22/2021 04:13:23 - INFO - codeparrot_training - Step 4238: {'lr': 0.0004918410874382852, 'samples': 2170368, 'steps': 4238, 'batch_loss/train': 0.8045588014647365}
+12/22/2021 04:13:33 - INFO - codeparrot_training - Step 4239: {'lr': 0.0004918370927455933, 'samples': 2170880, 'steps': 4239, 'batch_loss/train': 0.8588037146255374}
+12/22/2021 04:13:45 - INFO - codeparrot_training - Step 4240: {'lr': 0.0004918330970914485, 'samples': 2171392, 'steps': 4240, 'batch_loss/train': 0.9035855205729604}
+12/22/2021 04:13:56 - INFO - codeparrot_training - Step 4241: {'lr': 0.0004918291004758666, 'samples': 2171904, 'steps': 4241, 'batch_loss/train': 0.8279299810528755}
+12/22/2021 04:14:07 - INFO - codeparrot_training - Step 4242: {'lr': 0.0004918251028988635, 'samples': 2172416, 'steps': 4242, 'batch_loss/train': 0.8381521226838231}
+12/22/2021 04:14:19 - INFO - codeparrot_training - Step 4243: {'lr': 0.0004918211043604551, 'samples': 2172928, 'steps': 4243, 'batch_loss/train': 0.8244550214149058}
+12/22/2021 04:14:30 - INFO - codeparrot_training - Step 4244: {'lr': 0.0004918171048606573, 'samples': 2173440, 'steps': 4244, 'batch_loss/train': 0.8142349328845739}
+12/22/2021 04:14:41 - INFO - codeparrot_training - Step 4245: {'lr': 0.0004918131043994861, 'samples': 2173952, 'steps': 4245, 'batch_loss/train': 0.8831957075744867}
+12/22/2021 04:14:53 - INFO - codeparrot_training - Step 4246: {'lr': 0.0004918091029769572, 'samples': 2174464, 'steps': 4246, 'batch_loss/train': 0.7677228793036193}
+12/22/2021 04:15:03 - INFO - codeparrot_training - Step 4247: {'lr': 0.0004918051005930866, 'samples': 2174976, 'steps': 4247, 'batch_loss/train': 0.9148524203337729}
+12/22/2021 04:15:14 - INFO - codeparrot_training - Step 4248: {'lr': 0.0004918010972478903, 'samples': 2175488, 'steps': 4248, 'batch_loss/train': 0.7921742289327085}
+12/22/2021 04:15:25 - INFO - codeparrot_training - Step 4249: {'lr': 0.0004917970929413841, 'samples': 2176000, 'steps': 4249, 'batch_loss/train': 0.9120081048458815}
+12/22/2021 04:15:37 - INFO - codeparrot_training - Step 4250: {'lr': 0.0004917930876735839, 'samples': 2176512, 'steps': 4250, 'batch_loss/train': 0.8244171927217394}
+12/22/2021 04:15:47 - INFO - codeparrot_training - Step 4251: {'lr': 0.0004917890814445057, 'samples': 2177024, 'steps': 4251, 'batch_loss/train': 0.7848007027059793}
+12/22/2021 04:15:58 - INFO - codeparrot_training - Step 4252: {'lr': 0.0004917850742541655, 'samples': 2177536, 'steps': 4252, 'batch_loss/train': 0.9193526171147823}
+12/22/2021 04:16:11 - INFO - codeparrot_training - Step 4253: {'lr': 0.0004917810661025791, 'samples': 2178048, 'steps': 4253, 'batch_loss/train': 0.8568741017952561}
+12/22/2021 04:16:21 - INFO - codeparrot_training - Step 4254: {'lr': 0.0004917770569897624, 'samples': 2178560, 'steps': 4254, 'batch_loss/train': 0.8943828670307994}
+12/22/2021 04:16:32 - INFO - codeparrot_training - Step 4255: {'lr': 0.0004917730469157315, 'samples': 2179072, 'steps': 4255, 'batch_loss/train': 0.810413773637265}
+12/22/2021 04:16:44 - INFO - codeparrot_training - Step 4256: {'lr': 0.0004917690358805022, 'samples': 2179584, 'steps': 4256, 'batch_loss/train': 0.9113845699466765}
+12/22/2021 04:16:55 - INFO - codeparrot_training - Step 4257: {'lr': 0.0004917650238840906, 'samples': 2180096, 'steps': 4257, 'batch_loss/train': 0.8623527302406728}
+12/22/2021 04:17:06 - INFO - codeparrot_training - Step 4258: {'lr': 0.0004917610109265125, 'samples': 2180608, 'steps': 4258, 'batch_loss/train': 0.8641026802361012}
+12/22/2021 04:17:16 - INFO - codeparrot_training - Step 4259: {'lr': 0.0004917569970077838, 'samples': 2181120, 'steps': 4259, 'batch_loss/train': 0.8389777424745262}
+12/22/2021 04:17:29 - INFO - codeparrot_training - Step 4260: {'lr': 0.0004917529821279207, 'samples': 2181632, 'steps': 4260, 'batch_loss/train': 0.8519561602734029}
+12/22/2021 04:17:39 - INFO - codeparrot_training - Step 4261: {'lr': 0.0004917489662869389, 'samples': 2182144, 'steps': 4261, 'batch_loss/train': 0.9113058946095407}
+12/22/2021 04:17:50 - INFO - codeparrot_training - Step 4262: {'lr': 0.0004917449494848546, 'samples': 2182656, 'steps': 4262, 'batch_loss/train': 0.7968486715108156}
+12/22/2021 04:18:02 - INFO - codeparrot_training - Step 4263: {'lr': 0.0004917409317216836, 'samples': 2183168, 'steps': 4263, 'batch_loss/train': 0.8811958925798535}
+12/22/2021 04:18:13 - INFO - codeparrot_training - Step 4264: {'lr': 0.000491736912997442, 'samples': 2183680, 'steps': 4264, 'batch_loss/train': 0.8660278837196529}
+12/22/2021 04:18:23 - INFO - codeparrot_training - Step 4265: {'lr': 0.0004917328933121457, 'samples': 2184192, 'steps': 4265, 'batch_loss/train': 0.8070195340551436}
+12/22/2021 04:18:36 - INFO - codeparrot_training - Step 4266: {'lr': 0.0004917288726658106, 'samples': 2184704, 'steps': 4266, 'batch_loss/train': 0.7929613990709186}
+12/22/2021 04:18:46 - INFO - codeparrot_training - Step 4267: {'lr': 0.0004917248510584528, 'samples': 2185216, 'steps': 4267, 'batch_loss/train': 0.904638612177223}
+12/22/2021 04:18:57 - INFO - codeparrot_training - Step 4268: {'lr': 0.0004917208284900883, 'samples': 2185728, 'steps': 4268, 'batch_loss/train': 0.9198421272449195}
+12/22/2021 04:19:07 - INFO - codeparrot_training - Step 4269: {'lr': 0.0004917168049607331, 'samples': 2186240, 'steps': 4269, 'batch_loss/train': 0.82564309053123}
+12/22/2021 04:19:20 - INFO - codeparrot_training - Step 4270: {'lr': 0.0004917127804704031, 'samples': 2186752, 'steps': 4270, 'batch_loss/train': 0.9663230860605836}
+12/22/2021 04:19:31 - INFO - codeparrot_training - Step 4271: {'lr': 0.0004917087550191143, 'samples': 2187264, 'steps': 4271, 'batch_loss/train': 0.9898975621908903}
+12/22/2021 04:19:41 - INFO - codeparrot_training - Step 4272: {'lr': 0.0004917047286068829, 'samples': 2187776, 'steps': 4272, 'batch_loss/train': 0.8915459495037794}
+12/22/2021 04:19:54 - INFO - codeparrot_training - Step 4273: {'lr': 0.0004917007012337246, 'samples': 2188288, 'steps': 4273, 'batch_loss/train': 0.8515634760260582}
+12/22/2021 04:20:04 - INFO - codeparrot_training - Step 4274: {'lr': 0.0004916966728996557, 'samples': 2188800, 'steps': 4274, 'batch_loss/train': 0.8997660977765918}
+12/22/2021 04:20:15 - INFO - codeparrot_training - Step 4275: {'lr': 0.0004916926436046921, 'samples': 2189312, 'steps': 4275, 'batch_loss/train': 0.911219228990376}
+12/22/2021 04:20:27 - INFO - codeparrot_training - Step 4276: {'lr': 0.0004916886133488496, 'samples': 2189824, 'steps': 4276, 'batch_loss/train': 0.9021259834989905}
+12/22/2021 04:20:38 - INFO - codeparrot_training - Step 4277: {'lr': 0.0004916845821321446, 'samples': 2190336, 'steps': 4277, 'batch_loss/train': 0.9018486775457859}
+12/22/2021 04:20:48 - INFO - codeparrot_training - Step 4278: {'lr': 0.000491680549954593, 'samples': 2190848, 'steps': 4278, 'batch_loss/train': 0.8041638755239546}
+12/22/2021 04:20:59 - INFO - codeparrot_training - Step 4279: {'lr': 0.0004916765168162107, 'samples': 2191360, 'steps': 4279, 'batch_loss/train': 0.8360296441242099}
+12/22/2021 04:21:11 - INFO - codeparrot_training - Step 4280: {'lr': 0.0004916724827170138, 'samples': 2191872, 'steps': 4280, 'batch_loss/train': 0.8398772007785738}
+12/22/2021 04:21:21 - INFO - codeparrot_training - Step 4281: {'lr': 0.0004916684476570185, 'samples': 2192384, 'steps': 4281, 'batch_loss/train': 0.7536044353619218}
+12/22/2021 04:21:32 - INFO - codeparrot_training - Step 4282: {'lr': 0.0004916644116362406, 'samples': 2192896, 'steps': 4282, 'batch_loss/train': 0.8800013419240713}
+12/22/2021 04:21:45 - INFO - codeparrot_training - Step 4283: {'lr': 0.0004916603746546963, 'samples': 2193408, 'steps': 4283, 'batch_loss/train': 0.943959946744144}
+12/22/2021 04:21:56 - INFO - codeparrot_training - Step 4284: {'lr': 0.0004916563367124015, 'samples': 2193920, 'steps': 4284, 'batch_loss/train': 1.0458155032247305}
+12/22/2021 04:22:06 - INFO - codeparrot_training - Step 4285: {'lr': 0.0004916522978093724, 'samples': 2194432, 'steps': 4285, 'batch_loss/train': 0.8263000678271055}
+12/22/2021 04:22:18 - INFO - codeparrot_training - Step 4286: {'lr': 0.0004916482579456251, 'samples': 2194944, 'steps': 4286, 'batch_loss/train': 0.6502634531352669}
+12/22/2021 04:22:29 - INFO - codeparrot_training - Step 4287: {'lr': 0.0004916442171211754, 'samples': 2195456, 'steps': 4287, 'batch_loss/train': 0.7300446379231289}
+12/22/2021 04:22:39 - INFO - codeparrot_training - Step 4288: {'lr': 0.0004916401753360396, 'samples': 2195968, 'steps': 4288, 'batch_loss/train': 0.7999651785939932}
+12/22/2021 04:22:52 - INFO - codeparrot_training - Step 4289: {'lr': 0.0004916361325902338, 'samples': 2196480, 'steps': 4289, 'batch_loss/train': 0.8447217689827085}
+12/22/2021 04:23:03 - INFO - codeparrot_training - Step 4290: {'lr': 0.0004916320888837739, 'samples': 2196992, 'steps': 4290, 'batch_loss/train': 1.4963058098219335}
+12/22/2021 04:23:14 - INFO - codeparrot_training - Step 4291: {'lr': 0.0004916280442166759, 'samples': 2197504, 'steps': 4291, 'batch_loss/train': 0.8934101993218064}
+12/22/2021 04:23:24 - INFO - codeparrot_training - Step 4292: {'lr': 0.0004916239985889563, 'samples': 2198016, 'steps': 4292, 'batch_loss/train': 0.8289038199000061}
+12/22/2021 04:23:37 - INFO - codeparrot_training - Step 4293: {'lr': 0.0004916199520006308, 'samples': 2198528, 'steps': 4293, 'batch_loss/train': 0.6786834923550487}
+12/22/2021 04:23:47 - INFO - codeparrot_training - Step 4294: {'lr': 0.0004916159044517156, 'samples': 2199040, 'steps': 4294, 'batch_loss/train': 0.7881987635046244}
+12/22/2021 04:23:58 - INFO - codeparrot_training - Step 4295: {'lr': 0.0004916118559422267, 'samples': 2199552, 'steps': 4295, 'batch_loss/train': 0.841077177785337}
+12/22/2021 04:24:10 - INFO - codeparrot_training - Step 4296: {'lr': 0.0004916078064721804, 'samples': 2200064, 'steps': 4296, 'batch_loss/train': 0.8503197869285941}
+12/22/2021 04:24:20 - INFO - codeparrot_training - Step 4297: {'lr': 0.0004916037560415927, 'samples': 2200576, 'steps': 4297, 'batch_loss/train': 0.8673441684804857}
+12/22/2021 04:24:31 - INFO - codeparrot_training - Step 4298: {'lr': 0.0004915997046504797, 'samples': 2201088, 'steps': 4298, 'batch_loss/train': 0.7526493291370571}
+12/22/2021 04:24:44 - INFO - codeparrot_training - Step 4299: {'lr': 0.0004915956522988575, 'samples': 2201600, 'steps': 4299, 'batch_loss/train': 0.8334763366729021}
+12/22/2021 04:24:54 - INFO - codeparrot_training - Step 4300: {'lr': 0.0004915915989867421, 'samples': 2202112, 'steps': 4300, 'batch_loss/train': 0.836633768863976}
+12/22/2021 04:25:05 - INFO - codeparrot_training - Step 4301: {'lr': 0.0004915875447141498, 'samples': 2202624, 'steps': 4301, 'batch_loss/train': 0.8552018594928086}
+12/22/2021 04:25:16 - INFO - codeparrot_training - Step 4302: {'lr': 0.0004915834894810967, 'samples': 2203136, 'steps': 4302, 'batch_loss/train': 0.819814101792872}
+12/22/2021 04:25:28 - INFO - codeparrot_training - Step 4303: {'lr': 0.0004915794332875987, 'samples': 2203648, 'steps': 4303, 'batch_loss/train': 0.6780428306665272}
+12/22/2021 04:25:38 - INFO - codeparrot_training - Step 4304: {'lr': 0.0004915753761336722, 'samples': 2204160, 'steps': 4304, 'batch_loss/train': 0.7966506266966462}
+12/22/2021 04:25:49 - INFO - codeparrot_training - Step 4305: {'lr': 0.0004915713180193332, 'samples': 2204672, 'steps': 4305, 'batch_loss/train': 0.9035773146897554}
+12/22/2021 04:26:01 - INFO - codeparrot_training - Step 4306: {'lr': 0.0004915672589445979, 'samples': 2205184, 'steps': 4306, 'batch_loss/train': 0.7459883964620531}
+12/22/2021 04:26:12 - INFO - codeparrot_training - Step 4307: {'lr': 0.0004915631989094824, 'samples': 2205696, 'steps': 4307, 'batch_loss/train': 0.928390633314848}
+12/22/2021 04:26:23 - INFO - codeparrot_training - Step 4308: {'lr': 0.0004915591379140027, 'samples': 2206208, 'steps': 4308, 'batch_loss/train': 0.8931056968867779}
+12/22/2021 04:26:35 - INFO - codeparrot_training - Step 4309: {'lr': 0.0004915550759581753, 'samples': 2206720, 'steps': 4309, 'batch_loss/train': 0.8859048169106245}
+12/22/2021 04:26:45 - INFO - codeparrot_training - Step 4310: {'lr': 0.0004915510130420158, 'samples': 2207232, 'steps': 4310, 'batch_loss/train': 0.8397634271532297}
+12/22/2021 04:26:56 - INFO - codeparrot_training - Step 4311: {'lr': 0.000491546949165541, 'samples': 2207744, 'steps': 4311, 'batch_loss/train': 0.7807764271274209}
+12/22/2021 04:27:07 - INFO - codeparrot_training - Step 4312: {'lr': 0.0004915428843287666, 'samples': 2208256, 'steps': 4312, 'batch_loss/train': 0.8280781302601099}
+12/22/2021 04:27:19 - INFO - codeparrot_training - Step 4313: {'lr': 0.0004915388185317089, 'samples': 2208768, 'steps': 4313, 'batch_loss/train': 0.8607384227216244}
+12/22/2021 04:27:30 - INFO - codeparrot_training - Step 4314: {'lr': 0.000491534751774384, 'samples': 2209280, 'steps': 4314, 'batch_loss/train': 0.8272448405623436}
+12/22/2021 04:27:40 - INFO - codeparrot_training - Step 4315: {'lr': 0.0004915306840568083, 'samples': 2209792, 'steps': 4315, 'batch_loss/train': 0.871538856998086}
+12/22/2021 04:27:52 - INFO - codeparrot_training - Step 4316: {'lr': 0.0004915266153789976, 'samples': 2210304, 'steps': 4316, 'batch_loss/train': 0.8684214428067207}
+12/22/2021 04:28:03 - INFO - codeparrot_training - Step 4317: {'lr': 0.0004915225457409684, 'samples': 2210816, 'steps': 4317, 'batch_loss/train': 0.8546538418158889}
+12/22/2021 04:28:13 - INFO - codeparrot_training - Step 4318: {'lr': 0.0004915184751427367, 'samples': 2211328, 'steps': 4318, 'batch_loss/train': 0.7153084180317819}
+12/22/2021 04:28:26 - INFO - codeparrot_training - Step 4319: {'lr': 0.0004915144035843187, 'samples': 2211840, 'steps': 4319, 'batch_loss/train': 1.0290447762236}
+12/22/2021 04:28:37 - INFO - codeparrot_training - Step 4320: {'lr': 0.0004915103310657307, 'samples': 2212352, 'steps': 4320, 'batch_loss/train': 0.9303810987621546}
+12/22/2021 04:28:47 - INFO - codeparrot_training - Step 4321: {'lr': 0.0004915062575869888, 'samples': 2212864, 'steps': 4321, 'batch_loss/train': 0.8502654423937201}
+12/22/2021 04:28:59 - INFO - codeparrot_training - Step 4322: {'lr': 0.0004915021831481092, 'samples': 2213376, 'steps': 4322, 'batch_loss/train': 0.9260749395471066}
+12/22/2021 04:29:10 - INFO - codeparrot_training - Step 4323: {'lr': 0.0004914981077491081, 'samples': 2213888, 'steps': 4323, 'batch_loss/train': 0.8449598010629416}
+12/22/2021 04:29:20 - INFO - codeparrot_training - Step 4324: {'lr': 0.0004914940313900017, 'samples': 2214400, 'steps': 4324, 'batch_loss/train': 0.905383724719286}
+12/22/2021 04:29:31 - INFO - codeparrot_training - Step 4325: {'lr': 0.0004914899540708062, 'samples': 2214912, 'steps': 4325, 'batch_loss/train': 0.7623560610227287}
+12/22/2021 04:29:43 - INFO - codeparrot_training - Step 4326: {'lr': 0.0004914858757915379, 'samples': 2215424, 'steps': 4326, 'batch_loss/train': 0.8833630029112101}
+12/22/2021 04:29:54 - INFO - codeparrot_training - Step 4327: {'lr': 0.000491481796552213, 'samples': 2215936, 'steps': 4327, 'batch_loss/train': 0.7579985377378762}
+12/22/2021 04:30:04 - INFO - codeparrot_training - Step 4328: {'lr': 0.0004914777163528474, 'samples': 2216448, 'steps': 4328, 'batch_loss/train': 0.8453649329021573}
+12/22/2021 04:30:17 - INFO - codeparrot_training - Step 4329: {'lr': 0.0004914736351934578, 'samples': 2216960, 'steps': 4329, 'batch_loss/train': 0.8972917823120952}
+12/22/2021 04:30:28 - INFO - codeparrot_training - Step 4330: {'lr': 0.0004914695530740601, 'samples': 2217472, 'steps': 4330, 'batch_loss/train': 0.8705263687297702}
+12/22/2021 04:30:38 - INFO - codeparrot_training - Step 4331: {'lr': 0.0004914654699946706, 'samples': 2217984, 'steps': 4331, 'batch_loss/train': 0.8144289206247777}
+12/22/2021 04:30:51 - INFO - codeparrot_training - Step 4332: {'lr': 0.0004914613859553057, 'samples': 2218496, 'steps': 4332, 'batch_loss/train': 0.8889299537986517}
+12/22/2021 04:31:01 - INFO - codeparrot_training - Step 4333: {'lr': 0.0004914573009559814, 'samples': 2219008, 'steps': 4333, 'batch_loss/train': 0.834584609605372}
+12/22/2021 04:31:12 - INFO - codeparrot_training - Step 4334: {'lr': 0.0004914532149967141, 'samples': 2219520, 'steps': 4334, 'batch_loss/train': 0.9567328579723835}
+12/22/2021 04:31:22 - INFO - codeparrot_training - Step 4335: {'lr': 0.00049144912807752, 'samples': 2220032, 'steps': 4335, 'batch_loss/train': 0.8596513941884041}
+12/22/2021 04:31:35 - INFO - codeparrot_training - Step 4336: {'lr': 0.0004914450401984152, 'samples': 2220544, 'steps': 4336, 'batch_loss/train': 0.8836327902972698}
+12/22/2021 04:31:46 - INFO - codeparrot_training - Step 4337: {'lr': 0.0004914409513594163, 'samples': 2221056, 'steps': 4337, 'batch_loss/train': 0.8168367631733418}
+12/22/2021 04:31:56 - INFO - codeparrot_training - Step 4338: {'lr': 0.0004914368615605391, 'samples': 2221568, 'steps': 4338, 'batch_loss/train': 0.8262974533718079}
+12/22/2021 04:32:08 - INFO - codeparrot_training - Step 4339: {'lr': 0.0004914327708018003, 'samples': 2222080, 'steps': 4339, 'batch_loss/train': 0.8271156130358577}
+12/22/2021 04:32:19 - INFO - codeparrot_training - Step 4340: {'lr': 0.0004914286790832159, 'samples': 2222592, 'steps': 4340, 'batch_loss/train': 0.7762467744760215}
+12/22/2021 04:32:30 - INFO - codeparrot_training - Step 4341: {'lr': 0.0004914245864048022, 'samples': 2223104, 'steps': 4341, 'batch_loss/train': 0.7999018141999841}
+12/22/2021 04:32:42 - INFO - codeparrot_training - Step 4342: {'lr': 0.0004914204927665755, 'samples': 2223616, 'steps': 4342, 'batch_loss/train': 0.8941382877528667}
+12/22/2021 04:32:52 - INFO - codeparrot_training - Step 4343: {'lr': 0.0004914163981685521, 'samples': 2224128, 'steps': 4343, 'batch_loss/train': 0.8529383409768343}
+12/22/2021 04:33:03 - INFO - codeparrot_training - Step 4344: {'lr': 0.0004914123026107483, 'samples': 2224640, 'steps': 4344, 'batch_loss/train': 0.8716491600498557}
+12/22/2021 04:33:13 - INFO - codeparrot_training - Step 4345: {'lr': 0.0004914082060931803, 'samples': 2225152, 'steps': 4345, 'batch_loss/train': 0.8688375055789948}
+12/22/2021 04:33:27 - INFO - codeparrot_training - Step 4346: {'lr': 0.0004914041086158643, 'samples': 2225664, 'steps': 4346, 'batch_loss/train': 0.7994059952907264}
+12/22/2021 04:33:37 - INFO - codeparrot_training - Step 4347: {'lr': 0.0004914000101788169, 'samples': 2226176, 'steps': 4347, 'batch_loss/train': 0.8570217899978161}
+12/22/2021 04:33:48 - INFO - codeparrot_training - Step 4348: {'lr': 0.0004913959107820541, 'samples': 2226688, 'steps': 4348, 'batch_loss/train': 0.759948680177331}
+12/22/2021 04:34:00 - INFO - codeparrot_training - Step 4349: {'lr': 0.0004913918104255924, 'samples': 2227200, 'steps': 4349, 'batch_loss/train': 0.6070269639603794}
+12/22/2021 04:34:11 - INFO - codeparrot_training - Step 4350: {'lr': 0.000491387709109448, 'samples': 2227712, 'steps': 4350, 'batch_loss/train': 0.7912876233458519}
+12/22/2021 04:34:21 - INFO - codeparrot_training - Step 4351: {'lr': 0.0004913836068336371, 'samples': 2228224, 'steps': 4351, 'batch_loss/train': 0.7168423091061413}
+12/22/2021 04:34:33 - INFO - codeparrot_training - Step 4352: {'lr': 0.0004913795035981762, 'samples': 2228736, 'steps': 4352, 'batch_loss/train': 0.8378981999121606}
+12/22/2021 04:34:44 - INFO - codeparrot_training - Step 4353: {'lr': 0.0004913753994030815, 'samples': 2229248, 'steps': 4353, 'batch_loss/train': 0.8789275642484426}
+12/22/2021 04:34:54 - INFO - codeparrot_training - Step 4354: {'lr': 0.0004913712942483695, 'samples': 2229760, 'steps': 4354, 'batch_loss/train': 0.9983461257070303}
+12/22/2021 04:35:05 - INFO - codeparrot_training - Step 4355: {'lr': 0.0004913671881340562, 'samples': 2230272, 'steps': 4355, 'batch_loss/train': 0.8305387832224369}
+12/22/2021 04:35:17 - INFO - codeparrot_training - Step 4356: {'lr': 0.0004913630810601581, 'samples': 2230784, 'steps': 4356, 'batch_loss/train': 0.8214098606258631}
+12/22/2021 04:35:28 - INFO - codeparrot_training - Step 4357: {'lr': 0.0004913589730266917, 'samples': 2231296, 'steps': 4357, 'batch_loss/train': 0.8066215198487043}
+12/22/2021 04:35:38 - INFO - codeparrot_training - Step 4358: {'lr': 0.0004913548640336729, 'samples': 2231808, 'steps': 4358, 'batch_loss/train': 0.8230480141937733}
+12/22/2021 04:35:51 - INFO - codeparrot_training - Step 4359: {'lr': 0.0004913507540811185, 'samples': 2232320, 'steps': 4359, 'batch_loss/train': 0.7813420053571463}
+12/22/2021 04:36:02 - INFO - codeparrot_training - Step 4360: {'lr': 0.0004913466431690445, 'samples': 2232832, 'steps': 4360, 'batch_loss/train': 0.8544958839192986}
+12/22/2021 04:36:12 - INFO - codeparrot_training - Step 4361: {'lr': 0.0004913425312974675, 'samples': 2233344, 'steps': 4361, 'batch_loss/train': 0.8760593868792057}
+12/22/2021 04:36:24 - INFO - codeparrot_training - Step 4362: {'lr': 0.0004913384184664036, 'samples': 2233856, 'steps': 4362, 'batch_loss/train': 0.8553951736539602}
+12/22/2021 04:36:35 - INFO - codeparrot_training - Step 4363: {'lr': 0.0004913343046758693, 'samples': 2234368, 'steps': 4363, 'batch_loss/train': 0.8247763961553574}
+12/22/2021 04:36:46 - INFO - codeparrot_training - Step 4364: {'lr': 0.000491330189925881, 'samples': 2234880, 'steps': 4364, 'batch_loss/train': 0.824323145672679}
+12/22/2021 04:36:58 - INFO - codeparrot_training - Step 4365: {'lr': 0.000491326074216455, 'samples': 2235392, 'steps': 4365, 'batch_loss/train': 0.7620609644800425}
+12/22/2021 04:37:09 - INFO - codeparrot_training - Step 4366: {'lr': 0.0004913219575476076, 'samples': 2235904, 'steps': 4366, 'batch_loss/train': 0.8685972932726145}
+12/22/2021 04:37:19 - INFO - codeparrot_training - Step 4367: {'lr': 0.0004913178399193551, 'samples': 2236416, 'steps': 4367, 'batch_loss/train': 0.8301494945771992}
+12/22/2021 04:37:30 - INFO - codeparrot_training - Step 4368: {'lr': 0.0004913137213317141, 'samples': 2236928, 'steps': 4368, 'batch_loss/train': 0.8394230350386351}
+12/22/2021 04:37:42 - INFO - codeparrot_training - Step 4369: {'lr': 0.0004913096017847008, 'samples': 2237440, 'steps': 4369, 'batch_loss/train': 0.7621159784030169}
+12/22/2021 04:37:53 - INFO - codeparrot_training - Step 4370: {'lr': 0.0004913054812783318, 'samples': 2237952, 'steps': 4370, 'batch_loss/train': 0.8487726273015141}
+12/22/2021 04:38:03 - INFO - codeparrot_training - Step 4371: {'lr': 0.0004913013598126231, 'samples': 2238464, 'steps': 4371, 'batch_loss/train': 0.800506578758359}
+12/22/2021 04:38:15 - INFO - codeparrot_training - Step 4372: {'lr': 0.0004912972373875915, 'samples': 2238976, 'steps': 4372, 'batch_loss/train': 0.865969062782824}
+12/22/2021 04:38:26 - INFO - codeparrot_training - Step 4373: {'lr': 0.0004912931140032532, 'samples': 2239488, 'steps': 4373, 'batch_loss/train': 0.9593783812597394}
+12/22/2021 04:38:37 - INFO - codeparrot_training - Step 4374: {'lr': 0.0004912889896596244, 'samples': 2240000, 'steps': 4374, 'batch_loss/train': 0.8752002874389291}
+12/22/2021 04:38:50 - INFO - codeparrot_training - Step 4375: {'lr': 0.0004912848643567219, 'samples': 2240512, 'steps': 4375, 'batch_loss/train': 0.9686876833438873}
+12/22/2021 04:39:01 - INFO - codeparrot_training - Step 4376: {'lr': 0.0004912807380945617, 'samples': 2241024, 'steps': 4376, 'batch_loss/train': 0.8089068531990051}
+12/22/2021 04:39:11 - INFO - codeparrot_training - Step 4377: {'lr': 0.0004912766108731605, 'samples': 2241536, 'steps': 4377, 'batch_loss/train': 0.8065771916881204}
+12/22/2021 04:39:22 - INFO - codeparrot_training - Step 4378: {'lr': 0.0004912724826925346, 'samples': 2242048, 'steps': 4378, 'batch_loss/train': 0.7044837472494692}
+12/22/2021 04:39:34 - INFO - codeparrot_training - Step 4379: {'lr': 0.0004912683535527002, 'samples': 2242560, 'steps': 4379, 'batch_loss/train': 0.8578854100778699}
+12/22/2021 04:39:45 - INFO - codeparrot_training - Step 4380: {'lr': 0.0004912642234536741, 'samples': 2243072, 'steps': 4380, 'batch_loss/train': 0.814509361051023}
+12/22/2021 04:39:55 - INFO - codeparrot_training - Step 4381: {'lr': 0.0004912600923954727, 'samples': 2243584, 'steps': 4381, 'batch_loss/train': 0.8083323931787163}
+12/22/2021 04:40:07 - INFO - codeparrot_training - Step 4382: {'lr': 0.000491255960378112, 'samples': 2244096, 'steps': 4382, 'batch_loss/train': 0.8257894795387983}
+12/22/2021 04:40:18 - INFO - codeparrot_training - Step 4383: {'lr': 0.0004912518274016089, 'samples': 2244608, 'steps': 4383, 'batch_loss/train': 0.8662349423393607}
+12/22/2021 04:40:28 - INFO - codeparrot_training - Step 4384: {'lr': 0.0004912476934659795, 'samples': 2245120, 'steps': 4384, 'batch_loss/train': 0.8560129594989121}
+12/22/2021 04:40:42 - INFO - codeparrot_training - Step 4385: {'lr': 0.0004912435585712404, 'samples': 2245632, 'steps': 4385, 'batch_loss/train': 0.8162845754995942}
+12/22/2021 04:40:53 - INFO - codeparrot_training - Step 4386: {'lr': 0.0004912394227174079, 'samples': 2246144, 'steps': 4386, 'batch_loss/train': 0.7768817562609911}
+12/22/2021 04:41:04 - INFO - codeparrot_training - Step 4387: {'lr': 0.0004912352859044988, 'samples': 2246656, 'steps': 4387, 'batch_loss/train': 0.8936093067750335}
+12/22/2021 04:41:14 - INFO - codeparrot_training - Step 4388: {'lr': 0.0004912311481325291, 'samples': 2247168, 'steps': 4388, 'batch_loss/train': 1.1603546403348446}
+12/22/2021 04:41:26 - INFO - codeparrot_training - Step 4389: {'lr': 0.0004912270094015155, 'samples': 2247680, 'steps': 4389, 'batch_loss/train': 1.0338610066100955}
+12/22/2021 04:41:37 - INFO - codeparrot_training - Step 4390: {'lr': 0.0004912228697114743, 'samples': 2248192, 'steps': 4390, 'batch_loss/train': 0.8225042428821325}
+12/22/2021 04:41:48 - INFO - codeparrot_training - Step 4391: {'lr': 0.0004912187290624221, 'samples': 2248704, 'steps': 4391, 'batch_loss/train': 0.8637838016729802}
+12/22/2021 04:42:00 - INFO - codeparrot_training - Step 4392: {'lr': 0.0004912145874543753, 'samples': 2249216, 'steps': 4392, 'batch_loss/train': 0.9040963547304273}
+12/22/2021 04:42:10 - INFO - codeparrot_training - Step 4393: {'lr': 0.0004912104448873504, 'samples': 2249728, 'steps': 4393, 'batch_loss/train': 0.7512270987499505}
+12/22/2021 04:42:21 - INFO - codeparrot_training - Step 4394: {'lr': 0.0004912063013613639, 'samples': 2250240, 'steps': 4394, 'batch_loss/train': 0.6600972732994705}
+12/22/2021 04:42:35 - INFO - codeparrot_training - Step 4395: {'lr': 0.0004912021568764322, 'samples': 2250752, 'steps': 4395, 'batch_loss/train': 0.8731367462314665}
+12/22/2021 04:42:46 - INFO - codeparrot_training - Step 4396: {'lr': 0.0004911980114325718, 'samples': 2251264, 'steps': 4396, 'batch_loss/train': 0.7806921643204987}
+12/22/2021 04:42:56 - INFO - codeparrot_training - Step 4397: {'lr': 0.0004911938650297991, 'samples': 2251776, 'steps': 4397, 'batch_loss/train': 0.9399443846195936}
+12/22/2021 04:43:07 - INFO - codeparrot_training - Step 4398: {'lr': 0.0004911897176681307, 'samples': 2252288, 'steps': 4398, 'batch_loss/train': 0.8369409227743745}
+12/22/2021 04:43:19 - INFO - codeparrot_training - Step 4399: {'lr': 0.0004911855693475832, 'samples': 2252800, 'steps': 4399, 'batch_loss/train': 0.8093470465391874}
+12/22/2021 04:43:29 - INFO - codeparrot_training - Step 4400: {'lr': 0.0004911814200681728, 'samples': 2253312, 'steps': 4400, 'batch_loss/train': 0.8003094922751188}
+12/22/2021 04:43:40 - INFO - codeparrot_training - Step 4401: {'lr': 0.0004911772698299161, 'samples': 2253824, 'steps': 4401, 'batch_loss/train': 0.7825276516377926}
+12/22/2021 04:43:54 - INFO - codeparrot_training - Step 4402: {'lr': 0.0004911731186328297, 'samples': 2254336, 'steps': 4402, 'batch_loss/train': 0.8577448213472962}
+12/22/2021 04:44:04 - INFO - codeparrot_training - Step 4403: {'lr': 0.00049116896647693, 'samples': 2254848, 'steps': 4403, 'batch_loss/train': 0.8877853509038687}
+12/22/2021 04:44:15 - INFO - codeparrot_training - Step 4404: {'lr': 0.0004911648133622337, 'samples': 2255360, 'steps': 4404, 'batch_loss/train': 0.8982436810620129}
+12/22/2021 04:44:27 - INFO - codeparrot_training - Step 4405: {'lr': 0.000491160659288757, 'samples': 2255872, 'steps': 4405, 'batch_loss/train': 0.7663659891113639}
+12/22/2021 04:44:38 - INFO - codeparrot_training - Step 4406: {'lr': 0.0004911565042565166, 'samples': 2256384, 'steps': 4406, 'batch_loss/train': 0.8552565285935998}
+12/22/2021 04:44:49 - INFO - codeparrot_training - Step 4407: {'lr': 0.0004911523482655291, 'samples': 2256896, 'steps': 4407, 'batch_loss/train': 0.8909098757430911}
+12/22/2021 04:45:01 - INFO - codeparrot_training - Step 4408: {'lr': 0.0004911481913158108, 'samples': 2257408, 'steps': 4408, 'batch_loss/train': 0.8994851433672011}
+12/22/2021 04:45:11 - INFO - codeparrot_training - Step 4409: {'lr': 0.0004911440334073784, 'samples': 2257920, 'steps': 4409, 'batch_loss/train': 0.9619122911244631}
+12/22/2021 04:45:22 - INFO - codeparrot_training - Step 4410: {'lr': 0.0004911398745402484, 'samples': 2258432, 'steps': 4410, 'batch_loss/train': 0.8882929319515824}
+12/22/2021 04:45:33 - INFO - codeparrot_training - Step 4411: {'lr': 0.0004911357147144373, 'samples': 2258944, 'steps': 4411, 'batch_loss/train': 0.8700050804764032}
+12/22/2021 04:45:46 - INFO - codeparrot_training - Step 4412: {'lr': 0.0004911315539299616, 'samples': 2259456, 'steps': 4412, 'batch_loss/train': 0.8474257923662663}
+12/22/2021 04:45:57 - INFO - codeparrot_training - Step 4413: {'lr': 0.0004911273921868379, 'samples': 2259968, 'steps': 4413, 'batch_loss/train': 1.0131636802107096}
+12/22/2021 04:46:08 - INFO - codeparrot_training - Step 4414: {'lr': 0.0004911232294850828, 'samples': 2260480, 'steps': 4414, 'batch_loss/train': 0.8477210476994514}
+12/22/2021 04:46:20 - INFO - codeparrot_training - Step 4415: {'lr': 0.0004911190658247127, 'samples': 2260992, 'steps': 4415, 'batch_loss/train': 0.842244123108685}
+12/22/2021 04:46:30 - INFO - codeparrot_training - Step 4416: {'lr': 0.0004911149012057443, 'samples': 2261504, 'steps': 4416, 'batch_loss/train': 0.8421527352184057}
+12/22/2021 04:46:41 - INFO - codeparrot_training - Step 4417: {'lr': 0.0004911107356281941, 'samples': 2262016, 'steps': 4417, 'batch_loss/train': 0.8741696048527956}
+12/22/2021 04:46:53 - INFO - codeparrot_training - Step 4418: {'lr': 0.0004911065690920785, 'samples': 2262528, 'steps': 4418, 'batch_loss/train': 0.8470067149028182}
+12/22/2021 04:47:04 - INFO - codeparrot_training - Step 4419: {'lr': 0.0004911024015974144, 'samples': 2263040, 'steps': 4419, 'batch_loss/train': 0.7909521497786045}
+12/22/2021 04:47:15 - INFO - codeparrot_training - Step 4420: {'lr': 0.0004910982331442182, 'samples': 2263552, 'steps': 4420, 'batch_loss/train': 0.8368228925392032}
+12/22/2021 04:47:25 - INFO - codeparrot_training - Step 4421: {'lr': 0.0004910940637325063, 'samples': 2264064, 'steps': 4421, 'batch_loss/train': 1.0501950066536665}
+12/22/2021 04:47:39 - INFO - codeparrot_training - Step 4422: {'lr': 0.0004910898933622956, 'samples': 2264576, 'steps': 4422, 'batch_loss/train': 0.6129891681484878}
+12/22/2021 04:47:50 - INFO - codeparrot_training - Step 4423: {'lr': 0.0004910857220336024, 'samples': 2265088, 'steps': 4423, 'batch_loss/train': 0.8376237573102117}
+12/22/2021 04:48:00 - INFO - codeparrot_training - Step 4424: {'lr': 0.0004910815497464434, 'samples': 2265600, 'steps': 4424, 'batch_loss/train': 0.8774800039827824}
+12/22/2021 04:48:12 - INFO - codeparrot_training - Step 4425: {'lr': 0.0004910773765008353, 'samples': 2266112, 'steps': 4425, 'batch_loss/train': 0.9039821373298764}
+12/22/2021 04:48:23 - INFO - codeparrot_training - Step 4426: {'lr': 0.0004910732022967945, 'samples': 2266624, 'steps': 4426, 'batch_loss/train': 0.7905682311393321}
+12/22/2021 04:48:34 - INFO - codeparrot_training - Step 4427: {'lr': 0.0004910690271343376, 'samples': 2267136, 'steps': 4427, 'batch_loss/train': 0.8590633049607277}
+12/22/2021 04:48:44 - INFO - codeparrot_training - Step 4428: {'lr': 0.0004910648510134814, 'samples': 2267648, 'steps': 4428, 'batch_loss/train': 0.7075971263693646}
+12/22/2021 04:48:56 - INFO - codeparrot_training - Step 4429: {'lr': 0.0004910606739342424, 'samples': 2268160, 'steps': 4429, 'batch_loss/train': 0.9245136110112071}
+12/22/2021 04:49:07 - INFO - codeparrot_training - Step 4430: {'lr': 0.000491056495896637, 'samples': 2268672, 'steps': 4430, 'batch_loss/train': 0.8254746170714498}
+12/22/2021 04:49:18 - INFO - codeparrot_training - Step 4431: {'lr': 0.0004910523169006822, 'samples': 2269184, 'steps': 4431, 'batch_loss/train': 0.8274789536371827}
+12/22/2021 04:49:32 - INFO - codeparrot_training - Step 4432: {'lr': 0.0004910481369463942, 'samples': 2269696, 'steps': 4432, 'batch_loss/train': 0.8326917092781514}
+12/22/2021 04:49:42 - INFO - codeparrot_training - Step 4433: {'lr': 0.00049104395603379, 'samples': 2270208, 'steps': 4433, 'batch_loss/train': 0.9098015194758773}
+12/22/2021 04:49:53 - INFO - codeparrot_training - Step 4434: {'lr': 0.000491039774162886, 'samples': 2270720, 'steps': 4434, 'batch_loss/train': 0.8259419649839401}
+12/22/2021 04:50:05 - INFO - codeparrot_training - Step 4435: {'lr': 0.0004910355913336988, 'samples': 2271232, 'steps': 4435, 'batch_loss/train': 0.8773518428206444}
+12/22/2021 04:50:16 - INFO - codeparrot_training - Step 4436: {'lr': 0.0004910314075462452, 'samples': 2271744, 'steps': 4436, 'batch_loss/train': 0.735341764986515}
+12/22/2021 04:50:26 - INFO - codeparrot_training - Step 4437: {'lr': 0.0004910272228005417, 'samples': 2272256, 'steps': 4437, 'batch_loss/train': 0.800392840988934}
+12/22/2021 04:50:38 - INFO - codeparrot_training - Step 4438: {'lr': 0.0004910230370966049, 'samples': 2272768, 'steps': 4438, 'batch_loss/train': 0.9243511683307588}
+12/22/2021 04:50:49 - INFO - codeparrot_training - Step 4439: {'lr': 0.0004910188504344516, 'samples': 2273280, 'steps': 4439, 'batch_loss/train': 0.7621354758739471}
+12/22/2021 04:51:00 - INFO - codeparrot_training - Step 4440: {'lr': 0.0004910146628140983, 'samples': 2273792, 'steps': 4440, 'batch_loss/train': 0.7615276854485273}
+12/22/2021 04:51:10 - INFO - codeparrot_training - Step 4441: {'lr': 0.0004910104742355617, 'samples': 2274304, 'steps': 4441, 'batch_loss/train': 0.8453859235160053}
+12/22/2021 04:51:24 - INFO - codeparrot_training - Step 4442: {'lr': 0.0004910062846988584, 'samples': 2274816, 'steps': 4442, 'batch_loss/train': 0.7246930431574583}
+12/22/2021 04:51:35 - INFO - codeparrot_training - Step 4443: {'lr': 0.0004910020942040053, 'samples': 2275328, 'steps': 4443, 'batch_loss/train': 0.8424735520966351}
+12/22/2021 04:51:45 - INFO - codeparrot_training - Step 4444: {'lr': 0.0004909979027510188, 'samples': 2275840, 'steps': 4444, 'batch_loss/train': 0.7691285111941397}
+12/22/2021 04:51:57 - INFO - codeparrot_training - Step 4445: {'lr': 0.0004909937103399156, 'samples': 2276352, 'steps': 4445, 'batch_loss/train': 0.9281305223703384}
+12/22/2021 04:52:08 - INFO - codeparrot_training - Step 4446: {'lr': 0.0004909895169707124, 'samples': 2276864, 'steps': 4446, 'batch_loss/train': 0.9803616432473063}
+12/22/2021 04:52:19 - INFO - codeparrot_training - Step 4447: {'lr': 0.0004909853226434259, 'samples': 2277376, 'steps': 4447, 'batch_loss/train': 0.8627274129539728}
+12/22/2021 04:52:31 - INFO - codeparrot_training - Step 4448: {'lr': 0.0004909811273580727, 'samples': 2277888, 'steps': 4448, 'batch_loss/train': 0.738302931189537}
+12/22/2021 04:52:41 - INFO - codeparrot_training - Step 4449: {'lr': 0.0004909769311146696, 'samples': 2278400, 'steps': 4449, 'batch_loss/train': 0.9979618107900023}
+12/22/2021 04:52:52 - INFO - codeparrot_training - Step 4450: {'lr': 0.0004909727339132331, 'samples': 2278912, 'steps': 4450, 'batch_loss/train': 0.8984070168808103}
+12/22/2021 04:53:03 - INFO - codeparrot_training - Step 4451: {'lr': 0.00049096853575378, 'samples': 2279424, 'steps': 4451, 'batch_loss/train': 0.9306482020765543}
+12/22/2021 04:53:16 - INFO - codeparrot_training - Step 4452: {'lr': 0.0004909643366363271, 'samples': 2279936, 'steps': 4452, 'batch_loss/train': 0.8965840209275484}
+12/22/2021 04:53:27 - INFO - codeparrot_training - Step 4453: {'lr': 0.000490960136560891, 'samples': 2280448, 'steps': 4453, 'batch_loss/train': 0.8636475945822895}
+12/22/2021 04:53:38 - INFO - codeparrot_training - Step 4454: {'lr': 0.0004909559355274883, 'samples': 2280960, 'steps': 4454, 'batch_loss/train': 0.8603773410432041}
+12/22/2021 04:53:50 - INFO - codeparrot_training - Step 4455: {'lr': 0.0004909517335361358, 'samples': 2281472, 'steps': 4455, 'batch_loss/train': 0.8115797969512641}
+12/22/2021 04:54:00 - INFO - codeparrot_training - Step 4456: {'lr': 0.0004909475305868501, 'samples': 2281984, 'steps': 4456, 'batch_loss/train': 0.9128471277654171}
+12/22/2021 04:54:11 - INFO - codeparrot_training - Step 4457: {'lr': 0.0004909433266796482, 'samples': 2282496, 'steps': 4457, 'batch_loss/train': 0.7981330892071128}
+12/22/2021 04:54:23 - INFO - codeparrot_training - Step 4458: {'lr': 0.0004909391218145464, 'samples': 2283008, 'steps': 4458, 'batch_loss/train': 0.920263109728694}
+12/22/2021 04:54:34 - INFO - codeparrot_training - Step 4459: {'lr': 0.0004909349159915617, 'samples': 2283520, 'steps': 4459, 'batch_loss/train': 0.9429194652475417}
+12/22/2021 04:54:44 - INFO - codeparrot_training - Step 4460: {'lr': 0.0004909307092107108, 'samples': 2284032, 'steps': 4460, 'batch_loss/train': 0.8637862885370851}
+12/22/2021 04:54:58 - INFO - codeparrot_training - Step 4461: {'lr': 0.0004909265014720103, 'samples': 2284544, 'steps': 4461, 'batch_loss/train': 0.7900959574617445}
+12/22/2021 04:55:09 - INFO - codeparrot_training - Step 4462: {'lr': 0.000490922292775477, 'samples': 2285056, 'steps': 4462, 'batch_loss/train': 0.9256550362333655}
+12/22/2021 04:55:19 - INFO - codeparrot_training - Step 4463: {'lr': 0.0004909180831211277, 'samples': 2285568, 'steps': 4463, 'batch_loss/train': 0.710028724744916}
+12/22/2021 04:55:30 - INFO - codeparrot_training - Step 4464: {'lr': 0.0004909138725089791, 'samples': 2286080, 'steps': 4464, 'batch_loss/train': 0.9054735414683819}
+12/22/2021 04:55:42 - INFO - codeparrot_training - Step 4465: {'lr': 0.0004909096609390478, 'samples': 2286592, 'steps': 4465, 'batch_loss/train': 0.8041528251487762}
+12/22/2021 04:55:53 - INFO - codeparrot_training - Step 4466: {'lr': 0.0004909054484113507, 'samples': 2287104, 'steps': 4466, 'batch_loss/train': 0.8063451442867517}
+12/22/2021 04:56:04 - INFO - codeparrot_training - Step 4467: {'lr': 0.0004909012349259045, 'samples': 2287616, 'steps': 4467, 'batch_loss/train': 0.7996640615165234}
+12/22/2021 04:56:16 - INFO - codeparrot_training - Step 4468: {'lr': 0.000490897020482726, 'samples': 2288128, 'steps': 4468, 'batch_loss/train': 0.8639720734208822}
+12/22/2021 04:56:26 - INFO - codeparrot_training - Step 4469: {'lr': 0.0004908928050818319, 'samples': 2288640, 'steps': 4469, 'batch_loss/train': 0.9351622872054577}
+12/22/2021 04:56:37 - INFO - codeparrot_training - Step 4470: {'lr': 0.0004908885887232389, 'samples': 2289152, 'steps': 4470, 'batch_loss/train': 0.8561831591650844}
+12/22/2021 04:56:51 - INFO - codeparrot_training - Step 4471: {'lr': 0.0004908843714069638, 'samples': 2289664, 'steps': 4471, 'batch_loss/train': 0.8860693546012044}
+12/22/2021 04:57:02 - INFO - codeparrot_training - Step 4472: {'lr': 0.0004908801531330235, 'samples': 2290176, 'steps': 4472, 'batch_loss/train': 0.8034948045387864}
+12/22/2021 04:57:13 - INFO - codeparrot_training - Step 4473: {'lr': 0.0004908759339014346, 'samples': 2290688, 'steps': 4473, 'batch_loss/train': 0.8965884735807776}
+12/22/2021 04:57:23 - INFO - codeparrot_training - Step 4474: {'lr': 0.0004908717137122139, 'samples': 2291200, 'steps': 4474, 'batch_loss/train': 0.9972191522829235}
+12/22/2021 04:57:35 - INFO - codeparrot_training - Step 4475: {'lr': 0.0004908674925653783, 'samples': 2291712, 'steps': 4475, 'batch_loss/train': 1.1217596540227532}
+12/22/2021 04:57:46 - INFO - codeparrot_training - Step 4476: {'lr': 0.0004908632704609445, 'samples': 2292224, 'steps': 4476, 'batch_loss/train': 0.8806676249951124}
+12/22/2021 04:57:57 - INFO - codeparrot_training - Step 4477: {'lr': 0.0004908590473989291, 'samples': 2292736, 'steps': 4477, 'batch_loss/train': 0.8897327240556479}
+12/22/2021 04:58:11 - INFO - codeparrot_training - Step 4478: {'lr': 0.0004908548233793493, 'samples': 2293248, 'steps': 4478, 'batch_loss/train': 0.8133748946711421}
+12/22/2021 04:58:21 - INFO - codeparrot_training - Step 4479: {'lr': 0.0004908505984022216, 'samples': 2293760, 'steps': 4479, 'batch_loss/train': 0.9163514608517289}
+12/22/2021 04:58:32 - INFO - codeparrot_training - Step 4480: {'lr': 0.0004908463724675628, 'samples': 2294272, 'steps': 4480, 'batch_loss/train': 0.8814560770988464}
+12/22/2021 04:58:44 - INFO - codeparrot_training - Step 4481: {'lr': 0.0004908421455753899, 'samples': 2294784, 'steps': 4481, 'batch_loss/train': 0.8898887718096375}
+12/22/2021 04:58:55 - INFO - codeparrot_training - Step 4482: {'lr': 0.0004908379177257194, 'samples': 2295296, 'steps': 4482, 'batch_loss/train': 0.8804589658975601}
+12/22/2021 04:59:05 - INFO - codeparrot_training - Step 4483: {'lr': 0.0004908336889185684, 'samples': 2295808, 'steps': 4483, 'batch_loss/train': 0.8639893550425768}
+12/22/2021 04:59:16 - INFO - codeparrot_training - Step 4484: {'lr': 0.0004908294591539535, 'samples': 2296320, 'steps': 4484, 'batch_loss/train': 0.7909381031058729}
+12/22/2021 04:59:28 - INFO - codeparrot_training - Step 4485: {'lr': 0.0004908252284318916, 'samples': 2296832, 'steps': 4485, 'batch_loss/train': 0.8721143761649728}
+12/22/2021 04:59:38 - INFO - codeparrot_training - Step 4486: {'lr': 0.0004908209967523996, 'samples': 2297344, 'steps': 4486, 'batch_loss/train': 0.8771800005342811}
+12/22/2021 04:59:49 - INFO - codeparrot_training - Step 4487: {'lr': 0.0004908167641154942, 'samples': 2297856, 'steps': 4487, 'batch_loss/train': 0.7540180124342442}
+12/22/2021 05:00:01 - INFO - codeparrot_training - Step 4488: {'lr': 0.0004908125305211923, 'samples': 2298368, 'steps': 4488, 'batch_loss/train': 0.7781521873548627}
+12/22/2021 05:00:12 - INFO - codeparrot_training - Step 4489: {'lr': 0.0004908082959695107, 'samples': 2298880, 'steps': 4489, 'batch_loss/train': 0.8174245655536652}
+12/22/2021 05:00:23 - INFO - codeparrot_training - Step 4490: {'lr': 0.0004908040604604662, 'samples': 2299392, 'steps': 4490, 'batch_loss/train': 0.8766718963161111}
+12/22/2021 05:00:37 - INFO - codeparrot_training - Step 4491: {'lr': 0.0004907998239940758, 'samples': 2299904, 'steps': 4491, 'batch_loss/train': 0.8892779489979148}
+12/22/2021 05:00:47 - INFO - codeparrot_training - Step 4492: {'lr': 0.000490795586570356, 'samples': 2300416, 'steps': 4492, 'batch_loss/train': 0.8672011904418468}
+12/22/2021 05:00:58 - INFO - codeparrot_training - Step 4493: {'lr': 0.000490791348189324, 'samples': 2300928, 'steps': 4493, 'batch_loss/train': 0.8793912557885051}
+12/22/2021 05:01:09 - INFO - codeparrot_training - Step 4494: {'lr': 0.0004907871088509966, 'samples': 2301440, 'steps': 4494, 'batch_loss/train': 0.5006250035949051}
+12/22/2021 05:01:21 - INFO - codeparrot_training - Step 4495: {'lr': 0.0004907828685553904, 'samples': 2301952, 'steps': 4495, 'batch_loss/train': 0.8914337689056993}
+12/22/2021 05:01:31 - INFO - codeparrot_training - Step 4496: {'lr': 0.0004907786273025226, 'samples': 2302464, 'steps': 4496, 'batch_loss/train': 0.7561483760364354}
+12/22/2021 05:01:42 - INFO - codeparrot_training - Step 4497: {'lr': 0.0004907743850924098, 'samples': 2302976, 'steps': 4497, 'batch_loss/train': 0.8203543098643422}
+12/22/2021 05:01:54 - INFO - codeparrot_training - Step 4498: {'lr': 0.000490770141925069, 'samples': 2303488, 'steps': 4498, 'batch_loss/train': 0.8177482038736343}
+12/22/2021 05:02:05 - INFO - codeparrot_training - Step 4499: {'lr': 0.000490765897800517, 'samples': 2304000, 'steps': 4499, 'batch_loss/train': 0.972559662302956}
+12/22/2021 05:02:16 - INFO - codeparrot_training - Step 4500: {'lr': 0.0004907616527187707, 'samples': 2304512, 'steps': 4500, 'batch_loss/train': 0.9467790741473436}
+12/22/2021 05:02:29 - INFO - codeparrot_training - Step 4501: {'lr': 0.000490757406679847, 'samples': 2305024, 'steps': 4501, 'batch_loss/train': 0.8586147530004382}
+12/22/2021 05:02:40 - INFO - codeparrot_training - Step 4502: {'lr': 0.0004907531596837628, 'samples': 2305536, 'steps': 4502, 'batch_loss/train': 0.9199285414069891}
+12/22/2021 05:02:51 - INFO - codeparrot_training - Step 4503: {'lr': 0.0004907489117305349, 'samples': 2306048, 'steps': 4503, 'batch_loss/train': 0.9137954544275999}
+12/22/2021 05:03:01 - INFO - codeparrot_training - Step 4504: {'lr': 0.0004907446628201801, 'samples': 2306560, 'steps': 4504, 'batch_loss/train': 0.9680771278217435}
+12/22/2021 05:03:13 - INFO - codeparrot_training - Step 4505: {'lr': 0.0004907404129527156, 'samples': 2307072, 'steps': 4505, 'batch_loss/train': 0.919852661434561}
+12/22/2021 05:03:24 - INFO - codeparrot_training - Step 4506: {'lr': 0.000490736162128158, 'samples': 2307584, 'steps': 4506, 'batch_loss/train': 0.9246813748031855}
+12/22/2021 05:03:34 - INFO - codeparrot_training - Step 4507: {'lr': 0.0004907319103465244, 'samples': 2308096, 'steps': 4507, 'batch_loss/train': 0.9155094735324383}
+12/22/2021 05:03:48 - INFO - codeparrot_training - Step 4508: {'lr': 0.0004907276576078315, 'samples': 2308608, 'steps': 4508, 'batch_loss/train': 0.9555933214724064}
+12/22/2021 05:03:59 - INFO - codeparrot_training - Step 4509: {'lr': 0.0004907234039120965, 'samples': 2309120, 'steps': 4509, 'batch_loss/train': 0.9638576582074165}
+12/22/2021 05:04:10 - INFO - codeparrot_training - Step 4510: {'lr': 0.000490719149259336, 'samples': 2309632, 'steps': 4510, 'batch_loss/train': 0.8549946490675211}
+12/22/2021 05:04:21 - INFO - codeparrot_training - Step 4511: {'lr': 0.0004907148936495672, 'samples': 2310144, 'steps': 4511, 'batch_loss/train': 0.8434853479266167}
+12/22/2021 05:04:32 - INFO - codeparrot_training - Step 4512: {'lr': 0.0004907106370828068, 'samples': 2310656, 'steps': 4512, 'batch_loss/train': 0.8765092082321644}
+12/22/2021 05:04:43 - INFO - codeparrot_training - Step 4513: {'lr': 0.0004907063795590717, 'samples': 2311168, 'steps': 4513, 'batch_loss/train': 0.9490054761990905}
+12/22/2021 05:04:53 - INFO - codeparrot_training - Step 4514: {'lr': 0.0004907021210783791, 'samples': 2311680, 'steps': 4514, 'batch_loss/train': 0.6650582491420209}
+12/22/2021 05:05:05 - INFO - codeparrot_training - Step 4515: {'lr': 0.0004906978616407456, 'samples': 2312192, 'steps': 4515, 'batch_loss/train': 0.9259910238906741}
+12/22/2021 05:05:16 - INFO - codeparrot_training - Step 4516: {'lr': 0.0004906936012461883, 'samples': 2312704, 'steps': 4516, 'batch_loss/train': 0.8779153395444155}
+12/22/2021 05:05:27 - INFO - codeparrot_training - Step 4517: {'lr': 0.0004906893398947242, 'samples': 2313216, 'steps': 4517, 'batch_loss/train': 0.8220060290768743}
+12/22/2021 05:05:39 - INFO - codeparrot_training - Step 4518: {'lr': 0.0004906850775863701, 'samples': 2313728, 'steps': 4518, 'batch_loss/train': 0.895450628362596}
+12/22/2021 05:05:50 - INFO - codeparrot_training - Step 4519: {'lr': 0.0004906808143211431, 'samples': 2314240, 'steps': 4519, 'batch_loss/train': 0.8014659222681075}
+12/22/2021 05:06:01 - INFO - codeparrot_training - Step 4520: {'lr': 0.00049067655009906, 'samples': 2314752, 'steps': 4520, 'batch_loss/train': 0.7161218263208866}
+12/22/2021 05:06:13 - INFO - codeparrot_training - Step 4521: {'lr': 0.0004906722849201378, 'samples': 2315264, 'steps': 4521, 'batch_loss/train': 0.7995186583139002}
+12/22/2021 05:06:24 - INFO - codeparrot_training - Step 4522: {'lr': 0.0004906680187843935, 'samples': 2315776, 'steps': 4522, 'batch_loss/train': 0.8536771470680833}
+12/22/2021 05:06:34 - INFO - codeparrot_training - Step 4523: {'lr': 0.000490663751691844, 'samples': 2316288, 'steps': 4523, 'batch_loss/train': 0.8579108947888017}
+12/22/2021 05:06:46 - INFO - codeparrot_training - Step 4524: {'lr': 0.0004906594836425062, 'samples': 2316800, 'steps': 4524, 'batch_loss/train': 0.8683698941022158}
+12/22/2021 05:06:57 - INFO - codeparrot_training - Step 4525: {'lr': 0.0004906552146363973, 'samples': 2317312, 'steps': 4525, 'batch_loss/train': 0.6334838517941535}
+12/22/2021 05:07:08 - INFO - codeparrot_training - Step 4526: {'lr': 0.0004906509446735341, 'samples': 2317824, 'steps': 4526, 'batch_loss/train': 0.9095436092466116}
+12/22/2021 05:07:18 - INFO - codeparrot_training - Step 4527: {'lr': 0.0004906466737539337, 'samples': 2318336, 'steps': 4527, 'batch_loss/train': 0.8403153244871646}
+12/22/2021 05:07:30 - INFO - codeparrot_training - Step 4528: {'lr': 0.0004906424018776129, 'samples': 2318848, 'steps': 4528, 'batch_loss/train': 0.7996029583737254}
+12/22/2021 05:07:41 - INFO - codeparrot_training - Step 4529: {'lr': 0.0004906381290445888, 'samples': 2319360, 'steps': 4529, 'batch_loss/train': 0.9649016633629799}
+12/22/2021 05:07:52 - INFO - codeparrot_training - Step 4530: {'lr': 0.0004906338552548783, 'samples': 2319872, 'steps': 4530, 'batch_loss/train': 0.735960575286299}
+12/22/2021 05:08:04 - INFO - codeparrot_training - Step 4531: {'lr': 0.0004906295805084985, 'samples': 2320384, 'steps': 4531, 'batch_loss/train': 0.8512612003833055}
+12/22/2021 05:08:15 - INFO - codeparrot_training - Step 4532: {'lr': 0.0004906253048054663, 'samples': 2320896, 'steps': 4532, 'batch_loss/train': 0.7424246231094003}
+12/22/2021 05:08:26 - INFO - codeparrot_training - Step 4533: {'lr': 0.0004906210281457987, 'samples': 2321408, 'steps': 4533, 'batch_loss/train': 0.862918977625668}
+12/22/2021 05:08:36 - INFO - codeparrot_training - Step 4534: {'lr': 0.0004906167505295129, 'samples': 2321920, 'steps': 4534, 'batch_loss/train': 1.1041178461164236}
+12/22/2021 05:08:48 - INFO - codeparrot_training - Step 4535: {'lr': 0.0004906124719566258, 'samples': 2322432, 'steps': 4535, 'batch_loss/train': 0.955032299272716}
+12/22/2021 05:08:59 - INFO - codeparrot_training - Step 4536: {'lr': 0.0004906081924271542, 'samples': 2322944, 'steps': 4536, 'batch_loss/train': 0.8470449068117887}
+12/22/2021 05:09:09 - INFO - codeparrot_training - Step 4537: {'lr': 0.0004906039119411152, 'samples': 2323456, 'steps': 4537, 'batch_loss/train': 0.9465688238851726}
+12/22/2021 05:09:22 - INFO - codeparrot_training - Step 4538: {'lr': 0.0004905996304985261, 'samples': 2323968, 'steps': 4538, 'batch_loss/train': 0.9312055530026555}
+12/22/2021 05:09:32 - INFO - codeparrot_training - Step 4539: {'lr': 0.0004905953480994036, 'samples': 2324480, 'steps': 4539, 'batch_loss/train': 0.8200385058298707}
+12/22/2021 05:09:43 - INFO - codeparrot_training - Step 4540: {'lr': 0.0004905910647437649, 'samples': 2324992, 'steps': 4540, 'batch_loss/train': 0.6266604211414233}
+12/22/2021 05:09:56 - INFO - codeparrot_training - Step 4541: {'lr': 0.0004905867804316269, 'samples': 2325504, 'steps': 4541, 'batch_loss/train': 0.9382193014025688}
+12/22/2021 05:10:07 - INFO - codeparrot_training - Step 4542: {'lr': 0.0004905824951630068, 'samples': 2326016, 'steps': 4542, 'batch_loss/train': 0.8781315619125962}
+12/22/2021 05:10:17 - INFO - codeparrot_training - Step 4543: {'lr': 0.0004905782089379215, 'samples': 2326528, 'steps': 4543, 'batch_loss/train': 0.939152397448197}
+12/22/2021 05:10:28 - INFO - codeparrot_training - Step 4544: {'lr': 0.000490573921756388, 'samples': 2327040, 'steps': 4544, 'batch_loss/train': 1.0296334475278854}
+12/22/2021 05:10:40 - INFO - codeparrot_training - Step 4545: {'lr': 0.0004905696336184235, 'samples': 2327552, 'steps': 4545, 'batch_loss/train': 0.8271511709317565}
+12/22/2021 05:10:51 - INFO - codeparrot_training - Step 4546: {'lr': 0.000490565344524045, 'samples': 2328064, 'steps': 4546, 'batch_loss/train': 0.8622129997238517}
+12/22/2021 05:11:01 - INFO - codeparrot_training - Step 4547: {'lr': 0.0004905610544732695, 'samples': 2328576, 'steps': 4547, 'batch_loss/train': 0.9305679742246866}
+12/22/2021 05:11:14 - INFO - codeparrot_training - Step 4548: {'lr': 0.000490556763466114, 'samples': 2329088, 'steps': 4548, 'batch_loss/train': 0.85017781984061}
+12/22/2021 05:11:25 - INFO - codeparrot_training - Step 4549: {'lr': 0.0004905524715025958, 'samples': 2329600, 'steps': 4549, 'batch_loss/train': 0.8331185262650251}
+12/22/2021 05:11:35 - INFO - codeparrot_training - Step 4550: {'lr': 0.0004905481785827317, 'samples': 2330112, 'steps': 4550, 'batch_loss/train': 0.8713033171370625}
+12/22/2021 05:11:47 - INFO - codeparrot_training - Step 4551: {'lr': 0.0004905438847065388, 'samples': 2330624, 'steps': 4551, 'batch_loss/train': 0.8570882566273212}
+12/22/2021 05:11:58 - INFO - codeparrot_training - Step 4552: {'lr': 0.0004905395898740344, 'samples': 2331136, 'steps': 4552, 'batch_loss/train': 0.8495499640703201}
+12/22/2021 05:12:08 - INFO - codeparrot_training - Step 4553: {'lr': 0.0004905352940852353, 'samples': 2331648, 'steps': 4553, 'batch_loss/train': 0.8811652674339712}
+12/22/2021 05:12:19 - INFO - codeparrot_training - Step 4554: {'lr': 0.0004905309973401587, 'samples': 2332160, 'steps': 4554, 'batch_loss/train': 0.7779306762386113}
+12/22/2021 05:12:31 - INFO - codeparrot_training - Step 4555: {'lr': 0.0004905266996388217, 'samples': 2332672, 'steps': 4555, 'batch_loss/train': 0.8681117771193385}
+12/22/2021 05:12:42 - INFO - codeparrot_training - Step 4556: {'lr': 0.0004905224009812413, 'samples': 2333184, 'steps': 4556, 'batch_loss/train': 0.8347870726138353}
+12/22/2021 05:12:52 - INFO - codeparrot_training - Step 4557: {'lr': 0.0004905181013674347, 'samples': 2333696, 'steps': 4557, 'batch_loss/train': 0.8342241114005446}
+12/22/2021 05:13:05 - INFO - codeparrot_training - Step 4558: {'lr': 0.0004905138007974191, 'samples': 2334208, 'steps': 4558, 'batch_loss/train': 0.8152538002468646}
+12/22/2021 05:13:16 - INFO - codeparrot_training - Step 4559: {'lr': 0.0004905094992712113, 'samples': 2334720, 'steps': 4559, 'batch_loss/train': 0.8247867645695806}
+12/22/2021 05:13:26 - INFO - codeparrot_training - Step 4560: {'lr': 0.0004905051967888285, 'samples': 2335232, 'steps': 4560, 'batch_loss/train': 0.9078517146408558}
+12/22/2021 05:13:38 - INFO - codeparrot_training - Step 4561: {'lr': 0.0004905008933502879, 'samples': 2335744, 'steps': 4561, 'batch_loss/train': 0.7458389364182949}
+12/22/2021 05:13:49 - INFO - codeparrot_training - Step 4562: {'lr': 0.0004904965889556066, 'samples': 2336256, 'steps': 4562, 'batch_loss/train': 0.9573906604200602}
+12/22/2021 05:14:00 - INFO - codeparrot_training - Step 4563: {'lr': 0.0004904922836048016, 'samples': 2336768, 'steps': 4563, 'batch_loss/train': 0.8746203677728772}
+12/22/2021 05:14:12 - INFO - codeparrot_training - Step 4564: {'lr': 0.00049048797729789, 'samples': 2337280, 'steps': 4564, 'batch_loss/train': 0.7793659372255206}
+12/22/2021 05:14:23 - INFO - codeparrot_training - Step 4565: {'lr': 0.0004904836700348891, 'samples': 2337792, 'steps': 4565, 'batch_loss/train': 0.890867137350142}
+12/22/2021 05:14:33 - INFO - codeparrot_training - Step 4566: {'lr': 0.000490479361815816, 'samples': 2338304, 'steps': 4566, 'batch_loss/train': 0.8718393961898983}
+12/22/2021 05:14:44 - INFO - codeparrot_training - Step 4567: {'lr': 0.0004904750526406877, 'samples': 2338816, 'steps': 4567, 'batch_loss/train': 0.9218784379772842}
+12/22/2021 05:14:56 - INFO - codeparrot_training - Step 4568: {'lr': 0.0004904707425095214, 'samples': 2339328, 'steps': 4568, 'batch_loss/train': 0.8522556377574801}
+12/22/2021 05:15:06 - INFO - codeparrot_training - Step 4569: {'lr': 0.0004904664314223342, 'samples': 2339840, 'steps': 4569, 'batch_loss/train': 0.8754020165652037}
+12/22/2021 05:15:17 - INFO - codeparrot_training - Step 4570: {'lr': 0.0004904621193791433, 'samples': 2340352, 'steps': 4570, 'batch_loss/train': 0.8524485467933118}
+12/22/2021 05:15:30 - INFO - codeparrot_training - Step 4571: {'lr': 0.0004904578063799659, 'samples': 2340864, 'steps': 4571, 'batch_loss/train': 0.8596793340984732}
+12/22/2021 05:15:40 - INFO - codeparrot_training - Step 4572: {'lr': 0.0004904534924248189, 'samples': 2341376, 'steps': 4572, 'batch_loss/train': 0.8204932883381844}
+12/22/2021 05:15:51 - INFO - codeparrot_training - Step 4573: {'lr': 0.0004904491775137197, 'samples': 2341888, 'steps': 4573, 'batch_loss/train': 0.7975587798282504}
+12/22/2021 05:16:03 - INFO - codeparrot_training - Step 4574: {'lr': 0.0004904448616466852, 'samples': 2342400, 'steps': 4574, 'batch_loss/train': 0.8540769312530756}
+12/22/2021 05:16:14 - INFO - codeparrot_training - Step 4575: {'lr': 0.0004904405448237329, 'samples': 2342912, 'steps': 4575, 'batch_loss/train': 0.7354127075523138}
+12/22/2021 05:16:24 - INFO - codeparrot_training - Step 4576: {'lr': 0.0004904362270448798, 'samples': 2343424, 'steps': 4576, 'batch_loss/train': 0.8587034177035093}
+12/22/2021 05:16:35 - INFO - codeparrot_training - Step 4577: {'lr': 0.0004904319083101429, 'samples': 2343936, 'steps': 4577, 'batch_loss/train': 0.8105435948818922}
+12/22/2021 05:16:48 - INFO - codeparrot_training - Step 4578: {'lr': 0.0004904275886195396, 'samples': 2344448, 'steps': 4578, 'batch_loss/train': 0.8528214311227202}
+12/22/2021 05:16:58 - INFO - codeparrot_training - Step 4579: {'lr': 0.0004904232679730869, 'samples': 2344960, 'steps': 4579, 'batch_loss/train': 0.8448275746777654}
+12/22/2021 05:17:09 - INFO - codeparrot_training - Step 4580: {'lr': 0.0004904189463708022, 'samples': 2345472, 'steps': 4580, 'batch_loss/train': 0.7996860770508647}
+12/22/2021 05:17:21 - INFO - codeparrot_training - Step 4581: {'lr': 0.0004904146238127024, 'samples': 2345984, 'steps': 4581, 'batch_loss/train': 0.7189640321303159}
+12/22/2021 05:17:32 - INFO - codeparrot_training - Step 4582: {'lr': 0.000490410300298805, 'samples': 2346496, 'steps': 4582, 'batch_loss/train': 0.9284991305321455}
+12/22/2021 05:17:42 - INFO - codeparrot_training - Step 4583: {'lr': 0.0004904059758291269, 'samples': 2347008, 'steps': 4583, 'batch_loss/train': 0.824628762784414}
+12/22/2021 05:17:54 - INFO - codeparrot_training - Step 4584: {'lr': 0.0004904016504036855, 'samples': 2347520, 'steps': 4584, 'batch_loss/train': 0.8455335032194853}
+12/22/2021 05:18:05 - INFO - codeparrot_training - Step 4585: {'lr': 0.0004903973240224978, 'samples': 2348032, 'steps': 4585, 'batch_loss/train': 0.7312934116926044}
+12/22/2021 05:18:16 - INFO - codeparrot_training - Step 4586: {'lr': 0.0004903929966855812, 'samples': 2348544, 'steps': 4586, 'batch_loss/train': 0.9430673681199551}
+12/22/2021 05:18:26 - INFO - codeparrot_training - Step 4587: {'lr': 0.0004903886683929528, 'samples': 2349056, 'steps': 4587, 'batch_loss/train': 0.8869965933263302}
+12/22/2021 05:18:39 - INFO - codeparrot_training - Step 4588: {'lr': 0.0004903843391446298, 'samples': 2349568, 'steps': 4588, 'batch_loss/train': 0.9145477656275034}
+12/22/2021 05:18:50 - INFO - codeparrot_training - Step 4589: {'lr': 0.0004903800089406294, 'samples': 2350080, 'steps': 4589, 'batch_loss/train': 0.8991410974413157}
+12/22/2021 05:19:00 - INFO - codeparrot_training - Step 4590: {'lr': 0.000490375677780969, 'samples': 2350592, 'steps': 4590, 'batch_loss/train': 0.9018108081072569}
+12/22/2021 05:19:12 - INFO - codeparrot_training - Step 4591: {'lr': 0.0004903713456656654, 'samples': 2351104, 'steps': 4591, 'batch_loss/train': 0.8571840059012175}
+12/22/2021 05:19:23 - INFO - codeparrot_training - Step 4592: {'lr': 0.0004903670125947364, 'samples': 2351616, 'steps': 4592, 'batch_loss/train': 0.9608303466811776}
+12/22/2021 05:19:34 - INFO - codeparrot_training - Step 4593: {'lr': 0.0004903626785681987, 'samples': 2352128, 'steps': 4593, 'batch_loss/train': 0.7886392744258046}
+12/22/2021 05:19:47 - INFO - codeparrot_training - Step 4594: {'lr': 0.0004903583435860697, 'samples': 2352640, 'steps': 4594, 'batch_loss/train': 0.8474338166415691}
+12/22/2021 05:19:57 - INFO - codeparrot_training - Step 4595: {'lr': 0.0004903540076483669, 'samples': 2353152, 'steps': 4595, 'batch_loss/train': 0.883853274397552}
+12/22/2021 05:20:08 - INFO - codeparrot_training - Step 4596: {'lr': 0.0004903496707551072, 'samples': 2353664, 'steps': 4596, 'batch_loss/train': 0.9092966383323073}
+12/22/2021 05:20:18 - INFO - codeparrot_training - Step 4597: {'lr': 0.000490345332906308, 'samples': 2354176, 'steps': 4597, 'batch_loss/train': 0.8070572186261415}
+12/22/2021 05:20:31 - INFO - codeparrot_training - Step 4598: {'lr': 0.0004903409941019864, 'samples': 2354688, 'steps': 4598, 'batch_loss/train': 0.9133243560791016}
+12/22/2021 05:20:41 - INFO - codeparrot_training - Step 4599: {'lr': 0.00049033665434216, 'samples': 2355200, 'steps': 4599, 'batch_loss/train': 0.8495410340838134}
+12/22/2021 05:20:52 - INFO - codeparrot_training - Step 4600: {'lr': 0.0004903323136268455, 'samples': 2355712, 'steps': 4600, 'batch_loss/train': 1.0855380753055215}
+12/22/2021 05:21:04 - INFO - codeparrot_training - Step 4601: {'lr': 0.0004903279719560607, 'samples': 2356224, 'steps': 4601, 'batch_loss/train': 0.8661505524069071}
+12/22/2021 05:21:15 - INFO - codeparrot_training - Step 4602: {'lr': 0.0004903236293298225, 'samples': 2356736, 'steps': 4602, 'batch_loss/train': 0.6889974935911596}
+12/22/2021 05:21:25 - INFO - codeparrot_training - Step 4603: {'lr': 0.0004903192857481484, 'samples': 2357248, 'steps': 4603, 'batch_loss/train': 0.8174928883090615}
+12/22/2021 05:21:37 - INFO - codeparrot_training - Step 4604: {'lr': 0.0004903149412110554, 'samples': 2357760, 'steps': 4604, 'batch_loss/train': 0.7811952559277415}
+12/22/2021 05:21:48 - INFO - codeparrot_training - Step 4605: {'lr': 0.0004903105957185611, 'samples': 2358272, 'steps': 4605, 'batch_loss/train': 0.8003590672742575}
+12/22/2021 05:21:59 - INFO - codeparrot_training - Step 4606: {'lr': 0.0004903062492706825, 'samples': 2358784, 'steps': 4606, 'batch_loss/train': 0.9205117197707295}
+12/22/2021 05:22:11 - INFO - codeparrot_training - Step 4607: {'lr': 0.000490301901867437, 'samples': 2359296, 'steps': 4607, 'batch_loss/train': 0.9959717895835638}
+12/22/2021 05:22:22 - INFO - codeparrot_training - Step 4608: {'lr': 0.000490297553508842, 'samples': 2359808, 'steps': 4608, 'batch_loss/train': 0.873446230776608}
+12/22/2021 05:22:33 - INFO - codeparrot_training - Step 4609: {'lr': 0.0004902932041949145, 'samples': 2360320, 'steps': 4609, 'batch_loss/train': 1.0240419576875865}
+12/22/2021 05:22:43 - INFO - codeparrot_training - Step 4610: {'lr': 0.000490288853925672, 'samples': 2360832, 'steps': 4610, 'batch_loss/train': 0.9231995670124888}
+12/22/2021 05:22:55 - INFO - codeparrot_training - Step 4611: {'lr': 0.0004902845027011318, 'samples': 2361344, 'steps': 4611, 'batch_loss/train': 0.8554347716271877}
+12/22/2021 05:23:06 - INFO - codeparrot_training - Step 4612: {'lr': 0.0004902801505213111, 'samples': 2361856, 'steps': 4612, 'batch_loss/train': 0.869145855307579}
+12/22/2021 05:23:17 - INFO - codeparrot_training - Step 4613: {'lr': 0.0004902757973862272, 'samples': 2362368, 'steps': 4613, 'batch_loss/train': 0.9361643120646477}
+12/22/2021 05:23:29 - INFO - codeparrot_training - Step 4614: {'lr': 0.0004902714432958975, 'samples': 2362880, 'steps': 4614, 'batch_loss/train': 0.8538794470950961}
+12/22/2021 05:23:39 - INFO - codeparrot_training - Step 4615: {'lr': 0.0004902670882503393, 'samples': 2363392, 'steps': 4615, 'batch_loss/train': 0.9098050566390157}
+12/22/2021 05:23:50 - INFO - codeparrot_training - Step 4616: {'lr': 0.0004902627322495699, 'samples': 2363904, 'steps': 4616, 'batch_loss/train': 0.899462531786412}
+12/22/2021 05:24:03 - INFO - codeparrot_training - Step 4617: {'lr': 0.0004902583752936066, 'samples': 2364416, 'steps': 4617, 'batch_loss/train': 0.8209617389366031}
+12/22/2021 05:24:13 - INFO - codeparrot_training - Step 4618: {'lr': 0.0004902540173824665, 'samples': 2364928, 'steps': 4618, 'batch_loss/train': 0.8263073544949293}
+12/22/2021 05:24:24 - INFO - codeparrot_training - Step 4619: {'lr': 0.0004902496585161673, 'samples': 2365440, 'steps': 4619, 'batch_loss/train': 1.0453309882432222}
+12/22/2021 05:24:35 - INFO - codeparrot_training - Step 4620: {'lr': 0.0004902452986947262, 'samples': 2365952, 'steps': 4620, 'batch_loss/train': 2.1080478746443987}
+12/22/2021 05:24:47 - INFO - codeparrot_training - Step 4621: {'lr': 0.0004902409379181605, 'samples': 2366464, 'steps': 4621, 'batch_loss/train': 0.9085658937692642}
+12/22/2021 05:24:57 - INFO - codeparrot_training - Step 4622: {'lr': 0.0004902365761864875, 'samples': 2366976, 'steps': 4622, 'batch_loss/train': 0.8818166870623827}
+12/22/2021 05:25:08 - INFO - codeparrot_training - Step 4623: {'lr': 0.0004902322134997247, 'samples': 2367488, 'steps': 4623, 'batch_loss/train': 0.794861315516755}
+12/22/2021 05:25:21 - INFO - codeparrot_training - Step 4624: {'lr': 0.0004902278498578891, 'samples': 2368000, 'steps': 4624, 'batch_loss/train': 0.6933790950570256}
+12/22/2021 05:25:32 - INFO - codeparrot_training - Step 4625: {'lr': 0.0004902234852609985, 'samples': 2368512, 'steps': 4625, 'batch_loss/train': 1.360093167051673}
+12/22/2021 05:25:43 - INFO - codeparrot_training - Step 4626: {'lr': 0.00049021911970907, 'samples': 2369024, 'steps': 4626, 'batch_loss/train': 1.0006458293646574}
+12/22/2021 05:25:53 - INFO - codeparrot_training - Step 4627: {'lr': 0.0004902147532021208, 'samples': 2369536, 'steps': 4627, 'batch_loss/train': 0.6165992827154696}
+12/22/2021 05:26:05 - INFO - codeparrot_training - Step 4628: {'lr': 0.0004902103857401686, 'samples': 2370048, 'steps': 4628, 'batch_loss/train': 0.9190306598320603}
+12/22/2021 05:26:16 - INFO - codeparrot_training - Step 4629: {'lr': 0.0004902060173232306, 'samples': 2370560, 'steps': 4629, 'batch_loss/train': 0.8391031995415688}
+12/22/2021 05:26:27 - INFO - codeparrot_training - Step 4630: {'lr': 0.0004902016479513241, 'samples': 2371072, 'steps': 4630, 'batch_loss/train': 0.8331723753362894}
+12/22/2021 05:26:39 - INFO - codeparrot_training - Step 4631: {'lr': 0.0004901972776244667, 'samples': 2371584, 'steps': 4631, 'batch_loss/train': 0.9789747772738338}
+12/22/2021 05:26:49 - INFO - codeparrot_training - Step 4632: {'lr': 0.0004901929063426755, 'samples': 2372096, 'steps': 4632, 'batch_loss/train': 0.8740890370681882}
+12/22/2021 05:27:00 - INFO - codeparrot_training - Step 4633: {'lr': 0.000490188534105968, 'samples': 2372608, 'steps': 4633, 'batch_loss/train': 0.9647713704034686}
+12/22/2021 05:27:10 - INFO - codeparrot_training - Step 4634: {'lr': 0.0004901841609143615, 'samples': 2373120, 'steps': 4634, 'batch_loss/train': 0.9329115336295217}
+12/22/2021 05:27:23 - INFO - codeparrot_training - Step 4635: {'lr': 0.0004901797867678736, 'samples': 2373632, 'steps': 4635, 'batch_loss/train': 0.7030652347020805}
+12/22/2021 05:27:34 - INFO - codeparrot_training - Step 4636: {'lr': 0.0004901754116665214, 'samples': 2374144, 'steps': 4636, 'batch_loss/train': 0.9464276684448123}
+12/22/2021 05:27:45 - INFO - codeparrot_training - Step 4637: {'lr': 0.0004901710356103227, 'samples': 2374656, 'steps': 4637, 'batch_loss/train': 0.7658823998644948}
+12/22/2021 05:27:57 - INFO - codeparrot_training - Step 4638: {'lr': 0.0004901666585992945, 'samples': 2375168, 'steps': 4638, 'batch_loss/train': 0.8512355457060039}
+12/22/2021 05:28:07 - INFO - codeparrot_training - Step 4639: {'lr': 0.0004901622806334543, 'samples': 2375680, 'steps': 4639, 'batch_loss/train': 0.9532221604604274}
+12/22/2021 05:28:18 - INFO - codeparrot_training - Step 4640: {'lr': 0.0004901579017128196, 'samples': 2376192, 'steps': 4640, 'batch_loss/train': 0.8292650077491999}
+12/22/2021 05:28:30 - INFO - codeparrot_training - Step 4641: {'lr': 0.0004901535218374078, 'samples': 2376704, 'steps': 4641, 'batch_loss/train': 0.8650107309222221}
+12/22/2021 05:28:41 - INFO - codeparrot_training - Step 4642: {'lr': 0.0004901491410072363, 'samples': 2377216, 'steps': 4642, 'batch_loss/train': 0.8228635438717902}
+12/22/2021 05:28:51 - INFO - codeparrot_training - Step 4643: {'lr': 0.0004901447592223224, 'samples': 2377728, 'steps': 4643, 'batch_loss/train': 0.7810203351546079}
+12/22/2021 05:29:04 - INFO - codeparrot_training - Step 4644: {'lr': 0.0004901403764826836, 'samples': 2378240, 'steps': 4644, 'batch_loss/train': 0.7865223467815667}
+12/22/2021 05:29:15 - INFO - codeparrot_training - Step 4645: {'lr': 0.0004901359927883374, 'samples': 2378752, 'steps': 4645, 'batch_loss/train': 0.8611668609082699}
+12/22/2021 05:29:25 - INFO - codeparrot_training - Step 4646: {'lr': 0.0004901316081393012, 'samples': 2379264, 'steps': 4646, 'batch_loss/train': 0.9094913341104984}
+12/22/2021 05:29:36 - INFO - codeparrot_training - Step 4647: {'lr': 0.0004901272225355923, 'samples': 2379776, 'steps': 4647, 'batch_loss/train': 0.839872170239687}
+12/22/2021 05:29:48 - INFO - codeparrot_training - Step 4648: {'lr': 0.0004901228359772283, 'samples': 2380288, 'steps': 4648, 'batch_loss/train': 0.8667188506806269}
+12/22/2021 05:29:59 - INFO - codeparrot_training - Step 4649: {'lr': 0.0004901184484642266, 'samples': 2380800, 'steps': 4649, 'batch_loss/train': 0.9003892475739121}
+12/22/2021 05:30:09 - INFO - codeparrot_training - Step 4650: {'lr': 0.0004901140599966045, 'samples': 2381312, 'steps': 4650, 'batch_loss/train': 0.9060362004674971}
+12/22/2021 05:30:21 - INFO - codeparrot_training - Step 4651: {'lr': 0.0004901096705743796, 'samples': 2381824, 'steps': 4651, 'batch_loss/train': 0.8143169092945755}
+12/22/2021 05:30:32 - INFO - codeparrot_training - Step 4652: {'lr': 0.0004901052801975694, 'samples': 2382336, 'steps': 4652, 'batch_loss/train': 0.8696380525361747}
+12/22/2021 05:30:43 - INFO - codeparrot_training - Step 4653: {'lr': 0.0004901008888661912, 'samples': 2382848, 'steps': 4653, 'batch_loss/train': 0.8638692544773221}
+12/22/2021 05:30:53 - INFO - codeparrot_training - Step 4654: {'lr': 0.0004900964965802626, 'samples': 2383360, 'steps': 4654, 'batch_loss/train': 0.8818233939819038}
+12/22/2021 05:31:06 - INFO - codeparrot_training - Step 4655: {'lr': 0.0004900921033398008, 'samples': 2383872, 'steps': 4655, 'batch_loss/train': 0.8776472159661353}
+12/22/2021 05:31:17 - INFO - codeparrot_training - Step 4656: {'lr': 0.0004900877091448235, 'samples': 2384384, 'steps': 4656, 'batch_loss/train': 0.7758060521446168}
+12/22/2021 05:31:27 - INFO - codeparrot_training - Step 4657: {'lr': 0.0004900833139953484, 'samples': 2384896, 'steps': 4657, 'batch_loss/train': 0.9206443731673062}
+12/22/2021 05:31:40 - INFO - codeparrot_training - Step 4658: {'lr': 0.0004900789178913924, 'samples': 2385408, 'steps': 4658, 'batch_loss/train': 0.7933828285895288}
+12/22/2021 05:31:50 - INFO - codeparrot_training - Step 4659: {'lr': 0.0004900745208329733, 'samples': 2385920, 'steps': 4659, 'batch_loss/train': 0.8929068697616458}
+12/22/2021 05:32:01 - INFO - codeparrot_training - Step 4660: {'lr': 0.0004900701228201087, 'samples': 2386432, 'steps': 4660, 'batch_loss/train': 0.9193641571328044}
+12/22/2021 05:32:13 - INFO - codeparrot_training - Step 4661: {'lr': 0.0004900657238528158, 'samples': 2386944, 'steps': 4661, 'batch_loss/train': 1.526666210964322}
+12/22/2021 05:32:24 - INFO - codeparrot_training - Step 4662: {'lr': 0.0004900613239311123, 'samples': 2387456, 'steps': 4662, 'batch_loss/train': 0.8656842103227973}
+12/22/2021 05:32:34 - INFO - codeparrot_training - Step 4663: {'lr': 0.0004900569230550156, 'samples': 2387968, 'steps': 4663, 'batch_loss/train': 0.8517012582160532}
+12/22/2021 05:32:45 - INFO - codeparrot_training - Step 4664: {'lr': 0.0004900525212245433, 'samples': 2388480, 'steps': 4664, 'batch_loss/train': 1.277628567069769}
+12/22/2021 05:32:58 - INFO - codeparrot_training - Step 4665: {'lr': 0.0004900481184397127, 'samples': 2388992, 'steps': 4665, 'batch_loss/train': 0.9328899951651692}
+12/22/2021 05:33:09 - INFO - codeparrot_training - Step 4666: {'lr': 0.0004900437147005414, 'samples': 2389504, 'steps': 4666, 'batch_loss/train': 0.8792198719456792}
+12/22/2021 05:33:19 - INFO - codeparrot_training - Step 4667: {'lr': 0.0004900393100070469, 'samples': 2390016, 'steps': 4667, 'batch_loss/train': 0.9007315933704376}
+12/22/2021 05:33:31 - INFO - codeparrot_training - Step 4668: {'lr': 0.0004900349043592469, 'samples': 2390528, 'steps': 4668, 'batch_loss/train': 0.8137525953352451}
+12/22/2021 05:33:42 - INFO - codeparrot_training - Step 4669: {'lr': 0.0004900304977571586, 'samples': 2391040, 'steps': 4669, 'batch_loss/train': 0.8157358483877033}
+12/22/2021 05:33:52 - INFO - codeparrot_training - Step 4670: {'lr': 0.0004900260902007998, 'samples': 2391552, 'steps': 4670, 'batch_loss/train': 0.8861128818243742}
+12/22/2021 05:34:04 - INFO - codeparrot_training - Step 4671: {'lr': 0.0004900216816901878, 'samples': 2392064, 'steps': 4671, 'batch_loss/train': 0.8891404131427407}
+12/22/2021 05:34:15 - INFO - codeparrot_training - Step 4672: {'lr': 0.0004900172722253403, 'samples': 2392576, 'steps': 4672, 'batch_loss/train': 0.8815219579264522}
+12/22/2021 05:34:26 - INFO - codeparrot_training - Step 4673: {'lr': 0.0004900128618062747, 'samples': 2393088, 'steps': 4673, 'batch_loss/train': 0.9583655903115869}
+12/22/2021 05:34:36 - INFO - codeparrot_training - Step 4674: {'lr': 0.0004900084504330086, 'samples': 2393600, 'steps': 4674, 'batch_loss/train': 0.8290217723697424}
+12/22/2021 05:34:49 - INFO - codeparrot_training - Step 4675: {'lr': 0.0004900040381055594, 'samples': 2394112, 'steps': 4675, 'batch_loss/train': 0.7887717741541564}
+12/22/2021 05:34:59 - INFO - codeparrot_training - Step 4676: {'lr': 0.000489999624823945, 'samples': 2394624, 'steps': 4676, 'batch_loss/train': 0.8688865583389997}
+12/22/2021 05:35:10 - INFO - codeparrot_training - Step 4677: {'lr': 0.0004899952105881826, 'samples': 2395136, 'steps': 4677, 'batch_loss/train': 0.9816875448450446}
+12/22/2021 05:35:22 - INFO - codeparrot_training - Step 4678: {'lr': 0.0004899907953982899, 'samples': 2395648, 'steps': 4678, 'batch_loss/train': 1.2295084111392498}
+12/22/2021 05:35:33 - INFO - codeparrot_training - Step 4679: {'lr': 0.0004899863792542843, 'samples': 2396160, 'steps': 4679, 'batch_loss/train': 0.9045986756682396}
+12/22/2021 05:35:43 - INFO - codeparrot_training - Step 4680: {'lr': 0.0004899819621561836, 'samples': 2396672, 'steps': 4680, 'batch_loss/train': 0.9453831277787685}
+12/22/2021 05:35:56 - INFO - codeparrot_training - Step 4681: {'lr': 0.0004899775441040052, 'samples': 2397184, 'steps': 4681, 'batch_loss/train': 0.8209117446094751}
+12/22/2021 05:36:07 - INFO - codeparrot_training - Step 4682: {'lr': 0.0004899731250977667, 'samples': 2397696, 'steps': 4682, 'batch_loss/train': 0.7099014499690384}
+12/22/2021 05:36:17 - INFO - codeparrot_training - Step 4683: {'lr': 0.0004899687051374856, 'samples': 2398208, 'steps': 4683, 'batch_loss/train': 0.8359908619895577}
+12/22/2021 05:36:28 - INFO - codeparrot_training - Step 4684: {'lr': 0.0004899642842231797, 'samples': 2398720, 'steps': 4684, 'batch_loss/train': 0.8578286489937454}
+12/22/2021 05:36:40 - INFO - codeparrot_training - Step 4685: {'lr': 0.0004899598623548662, 'samples': 2399232, 'steps': 4685, 'batch_loss/train': 0.9778510965406895}
+12/22/2021 05:36:51 - INFO - codeparrot_training - Step 4686: {'lr': 0.000489955439532563, 'samples': 2399744, 'steps': 4686, 'batch_loss/train': 1.667997750453651}
+12/22/2021 05:37:01 - INFO - codeparrot_training - Step 4687: {'lr': 0.0004899510157562875, 'samples': 2400256, 'steps': 4687, 'batch_loss/train': 0.8966680308803916}
+12/22/2021 05:37:13 - INFO - codeparrot_training - Step 4688: {'lr': 0.0004899465910260575, 'samples': 2400768, 'steps': 4688, 'batch_loss/train': 0.907324779778719}
+12/22/2021 05:37:24 - INFO - codeparrot_training - Step 4689: {'lr': 0.0004899421653418904, 'samples': 2401280, 'steps': 4689, 'batch_loss/train': 0.8261666349135339}
+12/22/2021 05:37:35 - INFO - codeparrot_training - Step 4690: {'lr': 0.0004899377387038037, 'samples': 2401792, 'steps': 4690, 'batch_loss/train': 0.9321572971530259}
+12/22/2021 05:37:47 - INFO - codeparrot_training - Step 4691: {'lr': 0.0004899333111118154, 'samples': 2402304, 'steps': 4691, 'batch_loss/train': 0.8877207012847066}
+12/22/2021 05:37:57 - INFO - codeparrot_training - Step 4692: {'lr': 0.0004899288825659427, 'samples': 2402816, 'steps': 4692, 'batch_loss/train': 0.849187099840492}
+12/22/2021 05:38:08 - INFO - codeparrot_training - Step 4693: {'lr': 0.0004899244530662033, 'samples': 2403328, 'steps': 4693, 'batch_loss/train': 0.8010710030794144}
+12/22/2021 05:38:21 - INFO - codeparrot_training - Step 4694: {'lr': 0.000489920022612615, 'samples': 2403840, 'steps': 4694, 'batch_loss/train': 0.9494202854111791}
+12/22/2021 05:38:32 - INFO - codeparrot_training - Step 4695: {'lr': 0.0004899155912051952, 'samples': 2404352, 'steps': 4695, 'batch_loss/train': 0.9274922190234065}
+12/22/2021 05:38:42 - INFO - codeparrot_training - Step 4696: {'lr': 0.0004899111588439617, 'samples': 2404864, 'steps': 4696, 'batch_loss/train': 0.938635416328907}
+12/22/2021 05:38:53 - INFO - codeparrot_training - Step 4697: {'lr': 0.000489906725528932, 'samples': 2405376, 'steps': 4697, 'batch_loss/train': 0.8738009287044406}
+12/22/2021 05:39:05 - INFO - codeparrot_training - Step 4698: {'lr': 0.0004899022912601236, 'samples': 2405888, 'steps': 4698, 'batch_loss/train': 0.870822736993432}
+12/22/2021 05:39:15 - INFO - codeparrot_training - Step 4699: {'lr': 0.0004898978560375544, 'samples': 2406400, 'steps': 4699, 'batch_loss/train': 0.9104921109974384}
+12/22/2021 05:39:26 - INFO - codeparrot_training - Step 4700: {'lr': 0.0004898934198612419, 'samples': 2406912, 'steps': 4700, 'batch_loss/train': 0.8699377765879035}
+12/22/2021 05:39:39 - INFO - codeparrot_training - Step 4701: {'lr': 0.0004898889827312037, 'samples': 2407424, 'steps': 4701, 'batch_loss/train': 0.9113212209194899}
+12/22/2021 05:39:49 - INFO - codeparrot_training - Step 4702: {'lr': 0.0004898845446474575, 'samples': 2407936, 'steps': 4702, 'batch_loss/train': 0.849408102221787}
+12/22/2021 05:40:00 - INFO - codeparrot_training - Step 4703: {'lr': 0.000489880105610021, 'samples': 2408448, 'steps': 4703, 'batch_loss/train': 0.8941238056868315}
+12/22/2021 05:40:12 - INFO - codeparrot_training - Step 4704: {'lr': 0.0004898756656189116, 'samples': 2408960, 'steps': 4704, 'batch_loss/train': 1.0079377628862858}
+12/22/2021 05:40:23 - INFO - codeparrot_training - Step 4705: {'lr': 0.0004898712246741472, 'samples': 2409472, 'steps': 4705, 'batch_loss/train': 0.880921171978116}
+12/22/2021 05:40:33 - INFO - codeparrot_training - Step 4706: {'lr': 0.0004898667827757455, 'samples': 2409984, 'steps': 4706, 'batch_loss/train': 0.8649303708225489}
+12/22/2021 05:40:44 - INFO - codeparrot_training - Step 4707: {'lr': 0.0004898623399237239, 'samples': 2410496, 'steps': 4707, 'batch_loss/train': 0.8292835699394345}
+12/22/2021 05:40:57 - INFO - codeparrot_training - Step 4708: {'lr': 0.0004898578961181003, 'samples': 2411008, 'steps': 4708, 'batch_loss/train': 0.8948356937617064}
+12/22/2021 05:41:07 - INFO - codeparrot_training - Step 4709: {'lr': 0.0004898534513588922, 'samples': 2411520, 'steps': 4709, 'batch_loss/train': 0.9203171655535698}
+12/22/2021 05:41:18 - INFO - codeparrot_training - Step 4710: {'lr': 0.0004898490056461174, 'samples': 2412032, 'steps': 4710, 'batch_loss/train': 1.0332338837906718}
+12/22/2021 05:41:30 - INFO - codeparrot_training - Step 4711: {'lr': 0.0004898445589797935, 'samples': 2412544, 'steps': 4711, 'batch_loss/train': 1.1074281483888626}
+12/22/2021 05:41:41 - INFO - codeparrot_training - Step 4712: {'lr': 0.0004898401113599382, 'samples': 2413056, 'steps': 4712, 'batch_loss/train': 0.9200476091355085}
+12/22/2021 05:41:52 - INFO - codeparrot_training - Step 4713: {'lr': 0.0004898356627865691, 'samples': 2413568, 'steps': 4713, 'batch_loss/train': 0.8686068197712302}
+12/22/2021 05:42:03 - INFO - codeparrot_training - Step 4714: {'lr': 0.000489831213259704, 'samples': 2414080, 'steps': 4714, 'batch_loss/train': 0.9382328558713198}
+12/22/2021 05:42:15 - INFO - codeparrot_training - Step 4715: {'lr': 0.0004898267627793606, 'samples': 2414592, 'steps': 4715, 'batch_loss/train': 0.8927031913772225}
+12/22/2021 05:42:25 - INFO - codeparrot_training - Step 4716: {'lr': 0.0004898223113455565, 'samples': 2415104, 'steps': 4716, 'batch_loss/train': 0.8882098281756043}
+12/22/2021 05:42:36 - INFO - codeparrot_training - Step 4717: {'lr': 0.0004898178589583096, 'samples': 2415616, 'steps': 4717, 'batch_loss/train': 0.8870672178454697}
+12/22/2021 05:42:48 - INFO - codeparrot_training - Step 4718: {'lr': 0.0004898134056176372, 'samples': 2416128, 'steps': 4718, 'batch_loss/train': 0.8273202423006296}
+12/22/2021 05:42:59 - INFO - codeparrot_training - Step 4719: {'lr': 0.0004898089513235574, 'samples': 2416640, 'steps': 4719, 'batch_loss/train': 0.8490454284474254}
+12/22/2021 05:43:09 - INFO - codeparrot_training - Step 4720: {'lr': 0.0004898044960760877, 'samples': 2417152, 'steps': 4720, 'batch_loss/train': 0.8419190244749188}
+12/22/2021 05:43:22 - INFO - codeparrot_training - Step 4721: {'lr': 0.0004898000398752459, 'samples': 2417664, 'steps': 4721, 'batch_loss/train': 0.7603944423608482}
+12/22/2021 05:43:33 - INFO - codeparrot_training - Step 4722: {'lr': 0.0004897955827210497, 'samples': 2418176, 'steps': 4722, 'batch_loss/train': 0.9887412246316671}
+12/22/2021 05:43:43 - INFO - codeparrot_training - Step 4723: {'lr': 0.0004897911246135167, 'samples': 2418688, 'steps': 4723, 'batch_loss/train': 1.029698956757784}
+12/22/2021 05:43:55 - INFO - codeparrot_training - Step 4724: {'lr': 0.0004897866655526649, 'samples': 2419200, 'steps': 4724, 'batch_loss/train': 0.8818455683067441}
+12/22/2021 05:44:06 - INFO - codeparrot_training - Step 4725: {'lr': 0.0004897822055385117, 'samples': 2419712, 'steps': 4725, 'batch_loss/train': 0.8259754227474332}
+12/22/2021 05:44:17 - INFO - codeparrot_training - Step 4726: {'lr': 0.0004897777445710751, 'samples': 2420224, 'steps': 4726, 'batch_loss/train': 0.7811438087373972}
+12/22/2021 05:44:27 - INFO - codeparrot_training - Step 4727: {'lr': 0.0004897732826503727, 'samples': 2420736, 'steps': 4727, 'batch_loss/train': 0.8952704854309559}
+12/22/2021 05:44:40 - INFO - codeparrot_training - Step 4728: {'lr': 0.0004897688197764222, 'samples': 2421248, 'steps': 4728, 'batch_loss/train': 0.8343784064054489}
+12/22/2021 05:44:50 - INFO - codeparrot_training - Step 4729: {'lr': 0.0004897643559492415, 'samples': 2421760, 'steps': 4729, 'batch_loss/train': 0.7600196897983551}
+12/22/2021 05:45:01 - INFO - codeparrot_training - Step 4730: {'lr': 0.0004897598911688482, 'samples': 2422272, 'steps': 4730, 'batch_loss/train': 0.8858982659876347}
+12/22/2021 05:45:13 - INFO - codeparrot_training - Step 4731: {'lr': 0.0004897554254352601, 'samples': 2422784, 'steps': 4731, 'batch_loss/train': 0.8740650126710534}
+12/22/2021 05:45:23 - INFO - codeparrot_training - Step 4732: {'lr': 0.0004897509587484949, 'samples': 2423296, 'steps': 4732, 'batch_loss/train': 1.6503102369606495}
+12/22/2021 05:45:34 - INFO - codeparrot_training - Step 4733: {'lr': 0.0004897464911085706, 'samples': 2423808, 'steps': 4733, 'batch_loss/train': 0.8254860602319241}
+12/22/2021 05:45:47 - INFO - codeparrot_training - Step 4734: {'lr': 0.0004897420225155046, 'samples': 2424320, 'steps': 4734, 'batch_loss/train': 0.8738939571194351}
+12/22/2021 05:45:58 - INFO - codeparrot_training - Step 4735: {'lr': 0.0004897375529693148, 'samples': 2424832, 'steps': 4735, 'batch_loss/train': 0.7476444293279201}
+12/22/2021 05:46:08 - INFO - codeparrot_training - Step 4736: {'lr': 0.0004897330824700192, 'samples': 2425344, 'steps': 4736, 'batch_loss/train': 0.8056006943807006}
+12/22/2021 05:46:19 - INFO - codeparrot_training - Step 4737: {'lr': 0.0004897286110176353, 'samples': 2425856, 'steps': 4737, 'batch_loss/train': 0.8416024437174201}
+12/22/2021 05:46:31 - INFO - codeparrot_training - Step 4738: {'lr': 0.000489724138612181, 'samples': 2426368, 'steps': 4738, 'batch_loss/train': 0.864123678766191}
+12/22/2021 05:46:42 - INFO - codeparrot_training - Step 4739: {'lr': 0.000489719665253674, 'samples': 2426880, 'steps': 4739, 'batch_loss/train': 1.0573223326355219}
+12/22/2021 05:46:52 - INFO - codeparrot_training - Step 4740: {'lr': 0.0004897151909421321, 'samples': 2427392, 'steps': 4740, 'batch_loss/train': 0.7552709971787408}
+12/22/2021 05:47:05 - INFO - codeparrot_training - Step 4741: {'lr': 0.0004897107156775731, 'samples': 2427904, 'steps': 4741, 'batch_loss/train': 0.8612934835255146}
+12/22/2021 05:47:16 - INFO - codeparrot_training - Step 4742: {'lr': 0.0004897062394600148, 'samples': 2428416, 'steps': 4742, 'batch_loss/train': 0.9006940638646483}
+12/22/2021 05:47:26 - INFO - codeparrot_training - Step 4743: {'lr': 0.0004897017622894751, 'samples': 2428928, 'steps': 4743, 'batch_loss/train': 0.8731550453230739}
+12/22/2021 05:47:38 - INFO - codeparrot_training - Step 4744: {'lr': 0.0004896972841659716, 'samples': 2429440, 'steps': 4744, 'batch_loss/train': 0.877603180706501}
+12/22/2021 05:47:49 - INFO - codeparrot_training - Step 4745: {'lr': 0.0004896928050895222, 'samples': 2429952, 'steps': 4745, 'batch_loss/train': 0.888151309452951}
+12/22/2021 05:48:00 - INFO - codeparrot_training - Step 4746: {'lr': 0.0004896883250601449, 'samples': 2430464, 'steps': 4746, 'batch_loss/train': 0.797690718434751}
+12/22/2021 05:48:10 - INFO - codeparrot_training - Step 4747: {'lr': 0.0004896838440778571, 'samples': 2430976, 'steps': 4747, 'batch_loss/train': 0.836217406205833}
+12/22/2021 05:48:22 - INFO - codeparrot_training - Step 4748: {'lr': 0.000489679362142677, 'samples': 2431488, 'steps': 4748, 'batch_loss/train': 0.852365336380899}
+12/22/2021 05:48:33 - INFO - codeparrot_training - Step 4749: {'lr': 0.0004896748792546221, 'samples': 2432000, 'steps': 4749, 'batch_loss/train': 0.882318802177906}
+12/22/2021 05:48:44 - INFO - codeparrot_training - Step 4750: {'lr': 0.0004896703954137103, 'samples': 2432512, 'steps': 4750, 'batch_loss/train': 0.8632469540461898}
+12/22/2021 05:48:56 - INFO - codeparrot_training - Step 4751: {'lr': 0.0004896659106199598, 'samples': 2433024, 'steps': 4751, 'batch_loss/train': 0.8827535177115351}
+12/22/2021 05:49:07 - INFO - codeparrot_training - Step 4752: {'lr': 0.000489661424873388, 'samples': 2433536, 'steps': 4752, 'batch_loss/train': 0.823852134635672}
+12/22/2021 05:49:17 - INFO - codeparrot_training - Step 4753: {'lr': 0.0004896569381740127, 'samples': 2434048, 'steps': 4753, 'batch_loss/train': 0.836799361044541}
+12/22/2021 05:49:29 - INFO - codeparrot_training - Step 4754: {'lr': 0.0004896524505218522, 'samples': 2434560, 'steps': 4754, 'batch_loss/train': 0.8468020083382726}
+12/22/2021 05:49:40 - INFO - codeparrot_training - Step 4755: {'lr': 0.0004896479619169239, 'samples': 2435072, 'steps': 4755, 'batch_loss/train': 0.916930666193366}
+12/22/2021 05:49:51 - INFO - codeparrot_training - Step 4756: {'lr': 0.0004896434723592458, 'samples': 2435584, 'steps': 4756, 'batch_loss/train': 0.84939696919173}
+12/22/2021 05:50:03 - INFO - codeparrot_training - Step 4757: {'lr': 0.0004896389818488357, 'samples': 2436096, 'steps': 4757, 'batch_loss/train': 0.8416456556878984}
+12/22/2021 05:50:14 - INFO - codeparrot_training - Step 4758: {'lr': 0.0004896344903857115, 'samples': 2436608, 'steps': 4758, 'batch_loss/train': 0.8899242291226983}
+12/22/2021 05:50:24 - INFO - codeparrot_training - Step 4759: {'lr': 0.0004896299979698911, 'samples': 2437120, 'steps': 4759, 'batch_loss/train': 1.2607581317424774}
+12/22/2021 05:50:35 - INFO - codeparrot_training - Step 4760: {'lr': 0.0004896255046013923, 'samples': 2437632, 'steps': 4760, 'batch_loss/train': 0.8955657221376896}
+12/22/2021 05:50:47 - INFO - codeparrot_training - Step 4761: {'lr': 0.000489621010280233, 'samples': 2438144, 'steps': 4761, 'batch_loss/train': 0.8781210165470839}
+12/22/2021 05:50:58 - INFO - codeparrot_training - Step 4762: {'lr': 0.000489616515006431, 'samples': 2438656, 'steps': 4762, 'batch_loss/train': 0.856322611682117}
+12/22/2021 05:51:08 - INFO - codeparrot_training - Step 4763: {'lr': 0.0004896120187800042, 'samples': 2439168, 'steps': 4763, 'batch_loss/train': 0.8876886460930109}
+12/22/2021 05:51:20 - INFO - codeparrot_training - Step 4764: {'lr': 0.0004896075216009704, 'samples': 2439680, 'steps': 4764, 'batch_loss/train': 0.7832733672112226}
+12/22/2021 05:51:31 - INFO - codeparrot_training - Step 4765: {'lr': 0.0004896030234693477, 'samples': 2440192, 'steps': 4765, 'batch_loss/train': 0.8554117809981108}
+12/22/2021 05:51:42 - INFO - codeparrot_training - Step 4766: {'lr': 0.0004895985243851538, 'samples': 2440704, 'steps': 4766, 'batch_loss/train': 0.8214857801795006}
+12/22/2021 05:51:54 - INFO - codeparrot_training - Step 4767: {'lr': 0.0004895940243484067, 'samples': 2441216, 'steps': 4767, 'batch_loss/train': 0.6619344763457775}
+12/22/2021 05:52:04 - INFO - codeparrot_training - Step 4768: {'lr': 0.0004895895233591242, 'samples': 2441728, 'steps': 4768, 'batch_loss/train': 0.851491560228169}
+12/22/2021 05:52:15 - INFO - codeparrot_training - Step 4769: {'lr': 0.0004895850214173241, 'samples': 2442240, 'steps': 4769, 'batch_loss/train': 0.9806192582473159}
+12/22/2021 05:52:25 - INFO - codeparrot_training - Step 4770: {'lr': 0.0004895805185230245, 'samples': 2442752, 'steps': 4770, 'batch_loss/train': 0.9466247437521815}
+12/22/2021 05:52:38 - INFO - codeparrot_training - Step 4771: {'lr': 0.0004895760146762433, 'samples': 2443264, 'steps': 4771, 'batch_loss/train': 0.9641015958040953}
+12/22/2021 05:52:49 - INFO - codeparrot_training - Step 4772: {'lr': 0.0004895715098769983, 'samples': 2443776, 'steps': 4772, 'batch_loss/train': 0.8265406205318868}
+12/22/2021 05:53:00 - INFO - codeparrot_training - Step 4773: {'lr': 0.0004895670041253074, 'samples': 2444288, 'steps': 4773, 'batch_loss/train': 0.8828124809078872}
+12/22/2021 05:53:12 - INFO - codeparrot_training - Step 4774: {'lr': 0.0004895624974211886, 'samples': 2444800, 'steps': 4774, 'batch_loss/train': 0.7308535580523312}
+12/22/2021 05:53:23 - INFO - codeparrot_training - Step 4775: {'lr': 0.0004895579897646596, 'samples': 2445312, 'steps': 4775, 'batch_loss/train': 0.8371193977072835}
+12/22/2021 05:53:33 - INFO - codeparrot_training - Step 4776: {'lr': 0.0004895534811557386, 'samples': 2445824, 'steps': 4776, 'batch_loss/train': 0.9098690608516335}
+12/22/2021 05:53:44 - INFO - codeparrot_training - Step 4777: {'lr': 0.0004895489715944435, 'samples': 2446336, 'steps': 4777, 'batch_loss/train': 0.8766644150018692}
+12/22/2021 05:53:57 - INFO - codeparrot_training - Step 4778: {'lr': 0.000489544461080792, 'samples': 2446848, 'steps': 4778, 'batch_loss/train': 0.8682454703375697}
+12/22/2021 05:54:07 - INFO - codeparrot_training - Step 4779: {'lr': 0.0004895399496148021, 'samples': 2447360, 'steps': 4779, 'batch_loss/train': 0.9028678452596068}
+12/22/2021 05:54:18 - INFO - codeparrot_training - Step 4780: {'lr': 0.000489535437196492, 'samples': 2447872, 'steps': 4780, 'batch_loss/train': 1.4302107356488705}
+12/22/2021 05:54:31 - INFO - codeparrot_training - Step 4781: {'lr': 0.0004895309238258794, 'samples': 2448384, 'steps': 4781, 'batch_loss/train': 0.9242234386038035}
+12/22/2021 05:54:41 - INFO - codeparrot_training - Step 4782: {'lr': 0.0004895264095029823, 'samples': 2448896, 'steps': 4782, 'batch_loss/train': 1.0215579215437174}
+12/22/2021 05:54:52 - INFO - codeparrot_training - Step 4783: {'lr': 0.0004895218942278186, 'samples': 2449408, 'steps': 4783, 'batch_loss/train': 0.8611331060528755}
+12/22/2021 05:55:03 - INFO - codeparrot_training - Step 4784: {'lr': 0.0004895173780004063, 'samples': 2449920, 'steps': 4784, 'batch_loss/train': 0.8653955650515854}
+12/22/2021 05:55:15 - INFO - codeparrot_training - Step 4785: {'lr': 0.0004895128608207633, 'samples': 2450432, 'steps': 4785, 'batch_loss/train': 0.9540949985384941}
+12/22/2021 05:55:26 - INFO - codeparrot_training - Step 4786: {'lr': 0.0004895083426889077, 'samples': 2450944, 'steps': 4786, 'batch_loss/train': 1.0111564695835114}
+12/22/2021 05:55:36 - INFO - codeparrot_training - Step 4787: {'lr': 0.0004895038236048572, 'samples': 2451456, 'steps': 4787, 'batch_loss/train': 0.890831345692277}
+12/22/2021 05:55:49 - INFO - codeparrot_training - Step 4788: {'lr': 0.00048949930356863, 'samples': 2451968, 'steps': 4788, 'batch_loss/train': 0.8243619576096535}
+12/22/2021 05:56:00 - INFO - codeparrot_training - Step 4789: {'lr': 0.000489494782580244, 'samples': 2452480, 'steps': 4789, 'batch_loss/train': 0.872888557612896}
+12/22/2021 05:56:10 - INFO - codeparrot_training - Step 4790: {'lr': 0.0004894902606397173, 'samples': 2452992, 'steps': 4790, 'batch_loss/train': 0.8059537326917052}
+12/22/2021 05:56:22 - INFO - codeparrot_training - Step 4791: {'lr': 0.0004894857377470677, 'samples': 2453504, 'steps': 4791, 'batch_loss/train': 0.804004130885005}
+12/22/2021 05:56:33 - INFO - codeparrot_training - Step 4792: {'lr': 0.0004894812139023131, 'samples': 2454016, 'steps': 4792, 'batch_loss/train': 0.8758954703807831}
+12/22/2021 05:56:43 - INFO - codeparrot_training - Step 4793: {'lr': 0.0004894766891054718, 'samples': 2454528, 'steps': 4793, 'batch_loss/train': 0.9155638227239251}
+12/22/2021 05:56:55 - INFO - codeparrot_training - Step 4794: {'lr': 0.0004894721633565614, 'samples': 2455040, 'steps': 4794, 'batch_loss/train': 0.870713890530169}
+12/22/2021 05:57:06 - INFO - codeparrot_training - Step 4795: {'lr': 0.0004894676366556002, 'samples': 2455552, 'steps': 4795, 'batch_loss/train': 0.828155203955248}
+12/22/2021 05:57:17 - INFO - codeparrot_training - Step 4796: {'lr': 0.0004894631090026062, 'samples': 2456064, 'steps': 4796, 'batch_loss/train': 0.9764314910862595}
+12/22/2021 05:57:27 - INFO - codeparrot_training - Step 4797: {'lr': 0.0004894585803975972, 'samples': 2456576, 'steps': 4797, 'batch_loss/train': 0.9002700485289097}
+12/22/2021 05:57:40 - INFO - codeparrot_training - Step 4798: {'lr': 0.0004894540508405912, 'samples': 2457088, 'steps': 4798, 'batch_loss/train': 0.8783863089047372}
+12/22/2021 05:57:51 - INFO - codeparrot_training - Step 4799: {'lr': 0.0004894495203316065, 'samples': 2457600, 'steps': 4799, 'batch_loss/train': 1.1464869873598218}
+12/22/2021 05:58:02 - INFO - codeparrot_training - Step 4800: {'lr': 0.0004894449888706608, 'samples': 2458112, 'steps': 4800, 'batch_loss/train': 0.9252524385228753}
+12/22/2021 05:58:14 - INFO - codeparrot_training - Step 4801: {'lr': 0.0004894404564577722, 'samples': 2458624, 'steps': 4801, 'batch_loss/train': 0.9626491079106927}
+12/22/2021 05:58:25 - INFO - codeparrot_training - Step 4802: {'lr': 0.0004894359230929589, 'samples': 2459136, 'steps': 4802, 'batch_loss/train': 0.9331808965653181}
+12/22/2021 05:58:35 - INFO - codeparrot_training - Step 4803: {'lr': 0.0004894313887762388, 'samples': 2459648, 'steps': 4803, 'batch_loss/train': 1.0017683347687125}
+12/22/2021 05:58:46 - INFO - codeparrot_training - Step 4804: {'lr': 0.0004894268535076298, 'samples': 2460160, 'steps': 4804, 'batch_loss/train': 0.8879474103450775}
+12/22/2021 05:58:58 - INFO - codeparrot_training - Step 4805: {'lr': 0.00048942231728715, 'samples': 2460672, 'steps': 4805, 'batch_loss/train': 0.9078800035640597}
+12/22/2021 05:59:08 - INFO - codeparrot_training - Step 4806: {'lr': 0.0004894177801148175, 'samples': 2461184, 'steps': 4806, 'batch_loss/train': 1.4339326620101929}
+12/22/2021 05:59:19 - INFO - codeparrot_training - Step 4807: {'lr': 0.0004894132419906502, 'samples': 2461696, 'steps': 4807, 'batch_loss/train': 0.922285582870245}
+12/22/2021 05:59:31 - INFO - codeparrot_training - Step 4808: {'lr': 0.0004894087029146665, 'samples': 2462208, 'steps': 4808, 'batch_loss/train': 0.7596188454190269}
+12/22/2021 05:59:42 - INFO - codeparrot_training - Step 4809: {'lr': 0.000489404162886884, 'samples': 2462720, 'steps': 4809, 'batch_loss/train': 0.8629690539091825}
+12/22/2021 05:59:52 - INFO - codeparrot_training - Step 4810: {'lr': 0.0004893996219073211, 'samples': 2463232, 'steps': 4810, 'batch_loss/train': 0.8326163615565747}
+12/22/2021 06:00:06 - INFO - codeparrot_training - Step 4811: {'lr': 0.0004893950799759956, 'samples': 2463744, 'steps': 4811, 'batch_loss/train': 0.8858857275918126}
+12/22/2021 06:00:17 - INFO - codeparrot_training - Step 4812: {'lr': 0.0004893905370929256, 'samples': 2464256, 'steps': 4812, 'batch_loss/train': 0.8645848063752055}
+12/22/2021 06:00:28 - INFO - codeparrot_training - Step 4813: {'lr': 0.0004893859932581292, 'samples': 2464768, 'steps': 4813, 'batch_loss/train': 0.8285825131461024}
+12/22/2021 06:00:40 - INFO - codeparrot_training - Step 4814: {'lr': 0.0004893814484716246, 'samples': 2465280, 'steps': 4814, 'batch_loss/train': 0.8250753311440349}
+12/22/2021 06:00:50 - INFO - codeparrot_training - Step 4815: {'lr': 0.0004893769027334297, 'samples': 2465792, 'steps': 4815, 'batch_loss/train': 0.8010852250736207}
+12/22/2021 06:01:01 - INFO - codeparrot_training - Step 4816: {'lr': 0.0004893723560435625, 'samples': 2466304, 'steps': 4816, 'batch_loss/train': 0.8299886742606759}
+12/22/2021 06:01:12 - INFO - codeparrot_training - Step 4817: {'lr': 0.0004893678084020414, 'samples': 2466816, 'steps': 4817, 'batch_loss/train': 0.8326175892725587}
+12/22/2021 06:01:26 - INFO - codeparrot_training - Step 4818: {'lr': 0.0004893632598088842, 'samples': 2467328, 'steps': 4818, 'batch_loss/train': 0.7935682255774736}
+12/22/2021 06:01:36 - INFO - codeparrot_training - Step 4819: {'lr': 0.0004893587102641091, 'samples': 2467840, 'steps': 4819, 'batch_loss/train': 0.8955145124346018}
+12/22/2021 06:01:47 - INFO - codeparrot_training - Step 4820: {'lr': 0.000489354159767734, 'samples': 2468352, 'steps': 4820, 'batch_loss/train': 0.8664062730967999}
+12/22/2021 06:01:59 - INFO - codeparrot_training - Step 4821: {'lr': 0.0004893496083197773, 'samples': 2468864, 'steps': 4821, 'batch_loss/train': 0.8961376706138253}
+12/22/2021 06:02:09 - INFO - codeparrot_training - Step 4822: {'lr': 0.0004893450559202568, 'samples': 2469376, 'steps': 4822, 'batch_loss/train': 0.9192093135789037}
+12/22/2021 06:02:20 - INFO - codeparrot_training - Step 4823: {'lr': 0.0004893405025691908, 'samples': 2469888, 'steps': 4823, 'batch_loss/train': 0.8529096208512783}
+12/22/2021 06:02:34 - INFO - codeparrot_training - Step 4824: {'lr': 0.0004893359482665973, 'samples': 2470400, 'steps': 4824, 'batch_loss/train': 0.8378188833594322}
+12/22/2021 06:02:45 - INFO - codeparrot_training - Step 4825: {'lr': 0.0004893313930124945, 'samples': 2470912, 'steps': 4825, 'batch_loss/train': 0.8634252110496163}
+12/22/2021 06:02:55 - INFO - codeparrot_training - Step 4826: {'lr': 0.0004893268368069004, 'samples': 2471424, 'steps': 4826, 'batch_loss/train': 0.8089898083126172}
+12/22/2021 06:03:07 - INFO - codeparrot_training - Step 4827: {'lr': 0.0004893222796498332, 'samples': 2471936, 'steps': 4827, 'batch_loss/train': 0.839616765268147}
+12/22/2021 06:03:18 - INFO - codeparrot_training - Step 4828: {'lr': 0.0004893177215413109, 'samples': 2472448, 'steps': 4828, 'batch_loss/train': 0.8707883968017995}
+12/22/2021 06:03:29 - INFO - codeparrot_training - Step 4829: {'lr': 0.0004893131624813518, 'samples': 2472960, 'steps': 4829, 'batch_loss/train': 0.8318832016084343}
+12/22/2021 06:03:39 - INFO - codeparrot_training - Step 4830: {'lr': 0.0004893086024699739, 'samples': 2473472, 'steps': 4830, 'batch_loss/train': 0.8539703758433461}
+12/22/2021 06:03:51 - INFO - codeparrot_training - Step 4831: {'lr': 0.0004893040415071953, 'samples': 2473984, 'steps': 4831, 'batch_loss/train': 0.7329705939628184}
+12/22/2021 06:04:02 - INFO - codeparrot_training - Step 4832: {'lr': 0.0004892994795930342, 'samples': 2474496, 'steps': 4832, 'batch_loss/train': 0.8651347095146775}
+12/22/2021 06:04:13 - INFO - codeparrot_training - Step 4833: {'lr': 0.0004892949167275088, 'samples': 2475008, 'steps': 4833, 'batch_loss/train': 0.8311507338657975}
+12/22/2021 06:04:26 - INFO - codeparrot_training - Step 4834: {'lr': 0.0004892903529106372, 'samples': 2475520, 'steps': 4834, 'batch_loss/train': 0.792690203525126}
+12/22/2021 06:04:37 - INFO - codeparrot_training - Step 4835: {'lr': 0.0004892857881424374, 'samples': 2476032, 'steps': 4835, 'batch_loss/train': 0.8359676720574498}
+12/22/2021 06:04:48 - INFO - codeparrot_training - Step 4836: {'lr': 0.0004892812224229277, 'samples': 2476544, 'steps': 4836, 'batch_loss/train': 0.9099986478686333}
+12/22/2021 06:05:00 - INFO - codeparrot_training - Step 4837: {'lr': 0.0004892766557521262, 'samples': 2477056, 'steps': 4837, 'batch_loss/train': 1.0203783866018057}
+12/22/2021 06:05:10 - INFO - codeparrot_training - Step 4838: {'lr': 0.000489272088130051, 'samples': 2477568, 'steps': 4838, 'batch_loss/train': 0.8512644972652197}
+12/22/2021 06:05:21 - INFO - codeparrot_training - Step 4839: {'lr': 0.0004892675195567204, 'samples': 2478080, 'steps': 4839, 'batch_loss/train': 0.8396337293088436}
+12/22/2021 06:05:32 - INFO - codeparrot_training - Step 4840: {'lr': 0.0004892629500321525, 'samples': 2478592, 'steps': 4840, 'batch_loss/train': 0.7681135924067348}
+12/22/2021 06:05:44 - INFO - codeparrot_training - Step 4841: {'lr': 0.0004892583795563654, 'samples': 2479104, 'steps': 4841, 'batch_loss/train': 0.765113758854568}
+12/22/2021 06:05:54 - INFO - codeparrot_training - Step 4842: {'lr': 0.0004892538081293774, 'samples': 2479616, 'steps': 4842, 'batch_loss/train': 0.6849686030764133}
+12/22/2021 06:06:05 - INFO - codeparrot_training - Step 4843: {'lr': 0.0004892492357512065, 'samples': 2480128, 'steps': 4843, 'batch_loss/train': 0.8720608539879322}
+12/22/2021 06:06:17 - INFO - codeparrot_training - Step 4844: {'lr': 0.000489244662421871, 'samples': 2480640, 'steps': 4844, 'batch_loss/train': 0.8614648319780827}
+12/22/2021 06:06:28 - INFO - codeparrot_training - Step 4845: {'lr': 0.0004892400881413891, 'samples': 2481152, 'steps': 4845, 'batch_loss/train': 0.8915302027016878}
+12/22/2021 06:06:39 - INFO - codeparrot_training - Step 4846: {'lr': 0.000489235512909779, 'samples': 2481664, 'steps': 4846, 'batch_loss/train': 0.7794659232022241}
+12/22/2021 06:06:52 - INFO - codeparrot_training - Step 4847: {'lr': 0.0004892309367270587, 'samples': 2482176, 'steps': 4847, 'batch_loss/train': 0.7623191657476127}
+12/22/2021 06:07:03 - INFO - codeparrot_training - Step 4848: {'lr': 0.0004892263595932466, 'samples': 2482688, 'steps': 4848, 'batch_loss/train': 0.8345967289060354}
+12/22/2021 06:07:14 - INFO - codeparrot_training - Step 4849: {'lr': 0.0004892217815083608, 'samples': 2483200, 'steps': 4849, 'batch_loss/train': 0.8729309644550085}
+12/22/2021 06:07:24 - INFO - codeparrot_training - Step 4850: {'lr': 0.0004892172024724195, 'samples': 2483712, 'steps': 4850, 'batch_loss/train': 0.8546615736559033}
+12/22/2021 06:07:37 - INFO - codeparrot_training - Step 4851: {'lr': 0.000489212622485441, 'samples': 2484224, 'steps': 4851, 'batch_loss/train': 0.5937001995043829}
+12/22/2021 06:07:47 - INFO - codeparrot_training - Step 4852: {'lr': 0.0004892080415474433, 'samples': 2484736, 'steps': 4852, 'batch_loss/train': 0.8600810393691063}
+12/22/2021 06:07:58 - INFO - codeparrot_training - Step 4853: {'lr': 0.0004892034596584449, 'samples': 2485248, 'steps': 4853, 'batch_loss/train': 0.8777376469224691}
+12/22/2021 06:08:10 - INFO - codeparrot_training - Step 4854: {'lr': 0.0004891988768184638, 'samples': 2485760, 'steps': 4854, 'batch_loss/train': 1.0641091577708721}
+12/22/2021 06:08:21 - INFO - codeparrot_training - Step 4855: {'lr': 0.0004891942930275182, 'samples': 2486272, 'steps': 4855, 'batch_loss/train': 0.8806906817480922}
+12/22/2021 06:08:31 - INFO - codeparrot_training - Step 4856: {'lr': 0.0004891897082856266, 'samples': 2486784, 'steps': 4856, 'batch_loss/train': 1.3511718660593033}
+12/22/2021 06:08:45 - INFO - codeparrot_training - Step 4857: {'lr': 0.0004891851225928069, 'samples': 2487296, 'steps': 4857, 'batch_loss/train': 0.8081442788243294}
+12/22/2021 06:08:56 - INFO - codeparrot_training - Step 4858: {'lr': 0.0004891805359490775, 'samples': 2487808, 'steps': 4858, 'batch_loss/train': 0.8510625176131725}
+12/22/2021 06:09:06 - INFO - codeparrot_training - Step 4859: {'lr': 0.0004891759483544566, 'samples': 2488320, 'steps': 4859, 'batch_loss/train': 0.8231836222112179}
+12/22/2021 06:09:18 - INFO - codeparrot_training - Step 4860: {'lr': 0.0004891713598089624, 'samples': 2488832, 'steps': 4860, 'batch_loss/train': 0.7920321598649025}
+12/22/2021 06:09:29 - INFO - codeparrot_training - Step 4861: {'lr': 0.0004891667703126133, 'samples': 2489344, 'steps': 4861, 'batch_loss/train': 0.8507118560373783}
+12/22/2021 06:09:40 - INFO - codeparrot_training - Step 4862: {'lr': 0.0004891621798654273, 'samples': 2489856, 'steps': 4862, 'batch_loss/train': 0.8092920454218984}
+12/22/2021 06:09:50 - INFO - codeparrot_training - Step 4863: {'lr': 0.0004891575884674227, 'samples': 2490368, 'steps': 4863, 'batch_loss/train': 0.8336324701085687}
+12/22/2021 06:10:05 - INFO - codeparrot_training - Step 4864: {'lr': 0.000489152996118618, 'samples': 2490880, 'steps': 4864, 'batch_loss/train': 0.8532057483680546}
+12/22/2021 06:10:15 - INFO - codeparrot_training - Step 4865: {'lr': 0.0004891484028190313, 'samples': 2491392, 'steps': 4865, 'batch_loss/train': 0.8638418577611446}
+12/22/2021 06:10:26 - INFO - codeparrot_training - Step 4866: {'lr': 0.0004891438085686807, 'samples': 2491904, 'steps': 4866, 'batch_loss/train': 0.8087279424071312}
+12/22/2021 06:10:38 - INFO - codeparrot_training - Step 4867: {'lr': 0.0004891392133675848, 'samples': 2492416, 'steps': 4867, 'batch_loss/train': 0.9047911781817675}
+12/22/2021 06:10:49 - INFO - codeparrot_training - Step 4868: {'lr': 0.0004891346172157615, 'samples': 2492928, 'steps': 4868, 'batch_loss/train': 0.8179152216762304}
+12/22/2021 06:10:59 - INFO - codeparrot_training - Step 4869: {'lr': 0.0004891300201132294, 'samples': 2493440, 'steps': 4869, 'batch_loss/train': 0.7388020101934671}
+12/22/2021 06:11:11 - INFO - codeparrot_training - Step 4870: {'lr': 0.0004891254220600065, 'samples': 2493952, 'steps': 4870, 'batch_loss/train': 0.8287974065169692}
+12/22/2021 06:11:22 - INFO - codeparrot_training - Step 4871: {'lr': 0.0004891208230561112, 'samples': 2494464, 'steps': 4871, 'batch_loss/train': 1.0391075005754828}
+12/22/2021 06:11:32 - INFO - codeparrot_training - Step 4872: {'lr': 0.000489116223101562, 'samples': 2494976, 'steps': 4872, 'batch_loss/train': 0.8974265828728676}
+12/22/2021 06:11:46 - INFO - codeparrot_training - Step 4873: {'lr': 0.0004891116221963769, 'samples': 2495488, 'steps': 4873, 'batch_loss/train': 0.8618247546255589}
+12/22/2021 06:11:57 - INFO - codeparrot_training - Step 4874: {'lr': 0.0004891070203405742, 'samples': 2496000, 'steps': 4874, 'batch_loss/train': 0.9354149866849184}
+12/22/2021 06:12:07 - INFO - codeparrot_training - Step 4875: {'lr': 0.0004891024175341723, 'samples': 2496512, 'steps': 4875, 'batch_loss/train': 0.8726594569161534}
+12/22/2021 06:12:18 - INFO - codeparrot_training - Step 4876: {'lr': 0.0004890978137771894, 'samples': 2497024, 'steps': 4876, 'batch_loss/train': 0.9168099798262119}
+12/22/2021 06:12:30 - INFO - codeparrot_training - Step 4877: {'lr': 0.0004890932090696441, 'samples': 2497536, 'steps': 4877, 'batch_loss/train': 0.6704823895124719}
+12/22/2021 06:12:41 - INFO - codeparrot_training - Step 4878: {'lr': 0.0004890886034115543, 'samples': 2498048, 'steps': 4878, 'batch_loss/train': 0.9247748255729675}
+12/22/2021 06:12:51 - INFO - codeparrot_training - Step 4879: {'lr': 0.0004890839968029384, 'samples': 2498560, 'steps': 4879, 'batch_loss/train': 0.917789913713932}
+12/22/2021 06:13:05 - INFO - codeparrot_training - Step 4880: {'lr': 0.000489079389243815, 'samples': 2499072, 'steps': 4880, 'batch_loss/train': 0.9062646627426147}
+12/22/2021 06:13:16 - INFO - codeparrot_training - Step 4881: {'lr': 0.000489074780734202, 'samples': 2499584, 'steps': 4881, 'batch_loss/train': 0.8129159649834037}
+12/22/2021 06:13:26 - INFO - codeparrot_training - Step 4882: {'lr': 0.0004890701712741182, 'samples': 2500096, 'steps': 4882, 'batch_loss/train': 0.7994407210499048}
+12/22/2021 06:13:38 - INFO - codeparrot_training - Step 4883: {'lr': 0.0004890655608635816, 'samples': 2500608, 'steps': 4883, 'batch_loss/train': 0.8542783046141267}
+12/22/2021 06:13:49 - INFO - codeparrot_training - Step 4884: {'lr': 0.0004890609495026105, 'samples': 2501120, 'steps': 4884, 'batch_loss/train': 0.940254146233201}
+12/22/2021 06:14:00 - INFO - codeparrot_training - Step 4885: {'lr': 0.0004890563371912234, 'samples': 2501632, 'steps': 4885, 'batch_loss/train': 0.8525793347507715}
+12/22/2021 06:14:12 - INFO - codeparrot_training - Step 4886: {'lr': 0.0004890517239294385, 'samples': 2502144, 'steps': 4886, 'batch_loss/train': 0.8124392926692963}
+12/22/2021 06:14:22 - INFO - codeparrot_training - Step 4887: {'lr': 0.0004890471097172743, 'samples': 2502656, 'steps': 4887, 'batch_loss/train': 0.8305366178974509}
+12/22/2021 06:14:33 - INFO - codeparrot_training - Step 4888: {'lr': 0.000489042494554749, 'samples': 2503168, 'steps': 4888, 'batch_loss/train': 0.9007789017632604}
+12/22/2021 06:14:43 - INFO - codeparrot_training - Step 4889: {'lr': 0.000489037878441881, 'samples': 2503680, 'steps': 4889, 'batch_loss/train': 0.7769419602118433}
+12/22/2021 06:14:55 - INFO - codeparrot_training - Step 4890: {'lr': 0.0004890332613786886, 'samples': 2504192, 'steps': 4890, 'batch_loss/train': 0.8656888613477349}
+12/22/2021 06:15:06 - INFO - codeparrot_training - Step 4891: {'lr': 0.0004890286433651904, 'samples': 2504704, 'steps': 4891, 'batch_loss/train': 0.8363634869456291}
+12/22/2021 06:15:17 - INFO - codeparrot_training - Step 4892: {'lr': 0.0004890240244014044, 'samples': 2505216, 'steps': 4892, 'batch_loss/train': 0.7856450523249805}
+12/22/2021 06:15:30 - INFO - codeparrot_training - Step 4893: {'lr': 0.0004890194044873491, 'samples': 2505728, 'steps': 4893, 'batch_loss/train': 0.7224272296298295}
+12/22/2021 06:15:41 - INFO - codeparrot_training - Step 4894: {'lr': 0.000489014783623043, 'samples': 2506240, 'steps': 4894, 'batch_loss/train': 0.8056339360773563}
+12/22/2021 06:15:52 - INFO - codeparrot_training - Step 4895: {'lr': 0.0004890101618085043, 'samples': 2506752, 'steps': 4895, 'batch_loss/train': 0.8929878631606698}
+12/22/2021 06:16:04 - INFO - codeparrot_training - Step 4896: {'lr': 0.0004890055390437515, 'samples': 2507264, 'steps': 4896, 'batch_loss/train': 0.8101188603322953}
+12/22/2021 06:16:14 - INFO - codeparrot_training - Step 4897: {'lr': 0.000489000915328803, 'samples': 2507776, 'steps': 4897, 'batch_loss/train': 0.7918894882313907}
+12/22/2021 06:16:25 - INFO - codeparrot_training - Step 4898: {'lr': 0.0004889962906636769, 'samples': 2508288, 'steps': 4898, 'batch_loss/train': 0.8021686980500817}
+12/22/2021 06:16:35 - INFO - codeparrot_training - Step 4899: {'lr': 0.0004889916650483919, 'samples': 2508800, 'steps': 4899, 'batch_loss/train': 0.8358808420598507}
+12/22/2021 06:16:48 - INFO - codeparrot_training - Step 4900: {'lr': 0.0004889870384829664, 'samples': 2509312, 'steps': 4900, 'batch_loss/train': 0.8794752787798643}
+12/22/2021 06:16:58 - INFO - codeparrot_training - Step 4901: {'lr': 0.0004889824109674185, 'samples': 2509824, 'steps': 4901, 'batch_loss/train': 0.8325082408264279}
+12/22/2021 06:17:09 - INFO - codeparrot_training - Step 4902: {'lr': 0.0004889777825017668, 'samples': 2510336, 'steps': 4902, 'batch_loss/train': 0.9181616585701704}
+12/22/2021 06:17:23 - INFO - codeparrot_training - Step 4903: {'lr': 0.0004889731530860297, 'samples': 2510848, 'steps': 4903, 'batch_loss/train': 0.8401491753757}
+12/22/2021 06:17:33 - INFO - codeparrot_training - Step 4904: {'lr': 0.0004889685227202255, 'samples': 2511360, 'steps': 4904, 'batch_loss/train': 0.783416991122067}
+12/22/2021 06:17:44 - INFO - codeparrot_training - Step 4905: {'lr': 0.0004889638914043728, 'samples': 2511872, 'steps': 4905, 'batch_loss/train': 0.8908946961164474}
+12/22/2021 06:17:56 - INFO - codeparrot_training - Step 4906: {'lr': 0.0004889592591384898, 'samples': 2512384, 'steps': 4906, 'batch_loss/train': 0.986887626349926}
+12/22/2021 06:18:07 - INFO - codeparrot_training - Step 4907: {'lr': 0.0004889546259225951, 'samples': 2512896, 'steps': 4907, 'batch_loss/train': 0.883234680572059}
+12/22/2021 06:18:18 - INFO - codeparrot_training - Step 4908: {'lr': 0.000488949991756707, 'samples': 2513408, 'steps': 4908, 'batch_loss/train': 1.7456344235688448}
+12/22/2021 06:18:28 - INFO - codeparrot_training - Step 4909: {'lr': 0.000488945356640844, 'samples': 2513920, 'steps': 4909, 'batch_loss/train': 0.8983127484098077}
+12/22/2021 06:18:42 - INFO - codeparrot_training - Step 4910: {'lr': 0.0004889407205750243, 'samples': 2514432, 'steps': 4910, 'batch_loss/train': 0.8459378206171095}
+12/22/2021 06:18:53 - INFO - codeparrot_training - Step 4911: {'lr': 0.0004889360835592667, 'samples': 2514944, 'steps': 4911, 'batch_loss/train': 0.7960054343566298}
+12/22/2021 06:19:03 - INFO - codeparrot_training - Step 4912: {'lr': 0.0004889314455935894, 'samples': 2515456, 'steps': 4912, 'batch_loss/train': 0.7130440566688776}
+12/22/2021 06:19:15 - INFO - codeparrot_training - Step 4913: {'lr': 0.0004889268066780109, 'samples': 2515968, 'steps': 4913, 'batch_loss/train': 0.7974855378270149}
+12/22/2021 06:19:26 - INFO - codeparrot_training - Step 4914: {'lr': 0.0004889221668125496, 'samples': 2516480, 'steps': 4914, 'batch_loss/train': 0.9555186918005347}
+12/22/2021 06:19:37 - INFO - codeparrot_training - Step 4915: {'lr': 0.000488917525997224, 'samples': 2516992, 'steps': 4915, 'batch_loss/train': 0.8706473726779222}
+12/22/2021 06:19:49 - INFO - codeparrot_training - Step 4916: {'lr': 0.0004889128842320526, 'samples': 2517504, 'steps': 4916, 'batch_loss/train': 0.8868661848828197}
+12/22/2021 06:19:59 - INFO - codeparrot_training - Step 4917: {'lr': 0.0004889082415170537, 'samples': 2518016, 'steps': 4917, 'batch_loss/train': 0.836289532482624}
+12/22/2021 06:20:10 - INFO - codeparrot_training - Step 4918: {'lr': 0.0004889035978522458, 'samples': 2518528, 'steps': 4918, 'batch_loss/train': 0.8319826498627663}
+12/22/2021 06:20:21 - INFO - codeparrot_training - Step 4919: {'lr': 0.0004888989532376474, 'samples': 2519040, 'steps': 4919, 'batch_loss/train': 0.8569427160546184}
+12/22/2021 06:20:34 - INFO - codeparrot_training - Step 4920: {'lr': 0.0004888943076732771, 'samples': 2519552, 'steps': 4920, 'batch_loss/train': 0.7693746904260479}
+12/22/2021 06:20:45 - INFO - codeparrot_training - Step 4921: {'lr': 0.0004888896611591531, 'samples': 2520064, 'steps': 4921, 'batch_loss/train': 0.7883839998394251}
+12/22/2021 06:20:56 - INFO - codeparrot_training - Step 4922: {'lr': 0.0004888850136952941, 'samples': 2520576, 'steps': 4922, 'batch_loss/train': 0.8241212562425062}
+12/22/2021 06:21:08 - INFO - codeparrot_training - Step 4923: {'lr': 0.0004888803652817184, 'samples': 2521088, 'steps': 4923, 'batch_loss/train': 0.7836155788972974}
+12/22/2021 06:21:19 - INFO - codeparrot_training - Step 4924: {'lr': 0.0004888757159184447, 'samples': 2521600, 'steps': 4924, 'batch_loss/train': 0.8874483983963728}
+12/22/2021 06:21:29 - INFO - codeparrot_training - Step 4925: {'lr': 0.0004888710656054912, 'samples': 2522112, 'steps': 4925, 'batch_loss/train': 0.5586250246269628}
+12/22/2021 06:21:41 - INFO - codeparrot_training - Step 4926: {'lr': 0.0004888664143428767, 'samples': 2522624, 'steps': 4926, 'batch_loss/train': 0.9078589169075713}
+12/22/2021 06:21:52 - INFO - codeparrot_training - Step 4927: {'lr': 0.0004888617621306194, 'samples': 2523136, 'steps': 4927, 'batch_loss/train': 0.8767602816224098}
+12/22/2021 06:22:02 - INFO - codeparrot_training - Step 4928: {'lr': 0.0004888571089687379, 'samples': 2523648, 'steps': 4928, 'batch_loss/train': 1.0531121343374252}
+12/22/2021 06:22:14 - INFO - codeparrot_training - Step 4929: {'lr': 0.0004888524548572508, 'samples': 2524160, 'steps': 4929, 'batch_loss/train': 0.8383704135194421}
+12/22/2021 06:22:25 - INFO - codeparrot_training - Step 4930: {'lr': 0.0004888477997961765, 'samples': 2524672, 'steps': 4930, 'batch_loss/train': 0.8181331967934966}
+12/22/2021 06:22:36 - INFO - codeparrot_training - Step 4931: {'lr': 0.0004888431437855335, 'samples': 2525184, 'steps': 4931, 'batch_loss/train': 0.829911857843399}
+12/22/2021 06:22:46 - INFO - codeparrot_training - Step 4932: {'lr': 0.0004888384868253404, 'samples': 2525696, 'steps': 4932, 'batch_loss/train': 0.7890358632430434}
+12/22/2021 06:23:00 - INFO - codeparrot_training - Step 4933: {'lr': 0.0004888338289156157, 'samples': 2526208, 'steps': 4933, 'batch_loss/train': 0.9955997270881198}
+12/22/2021 06:23:11 - INFO - codeparrot_training - Step 4934: {'lr': 0.0004888291700563778, 'samples': 2526720, 'steps': 4934, 'batch_loss/train': 1.0420809127390385}
+12/22/2021 06:23:22 - INFO - codeparrot_training - Step 4935: {'lr': 0.0004888245102476453, 'samples': 2527232, 'steps': 4935, 'batch_loss/train': 0.909764098469168}
+12/22/2021 06:23:34 - INFO - codeparrot_training - Step 4936: {'lr': 0.0004888198494894367, 'samples': 2527744, 'steps': 4936, 'batch_loss/train': 0.8257213095203042}
+12/22/2021 06:23:44 - INFO - codeparrot_training - Step 4937: {'lr': 0.0004888151877817706, 'samples': 2528256, 'steps': 4937, 'batch_loss/train': 0.9138863971456885}
+12/22/2021 06:23:55 - INFO - codeparrot_training - Step 4938: {'lr': 0.0004888105251246655, 'samples': 2528768, 'steps': 4938, 'batch_loss/train': 0.7877942927880213}
+12/22/2021 06:24:09 - INFO - codeparrot_training - Step 4939: {'lr': 0.0004888058615181398, 'samples': 2529280, 'steps': 4939, 'batch_loss/train': 0.7478074862156063}
+12/22/2021 06:24:19 - INFO - codeparrot_training - Step 4940: {'lr': 0.0004888011969622124, 'samples': 2529792, 'steps': 4940, 'batch_loss/train': 0.8402346549555659}
+12/22/2021 06:24:30 - INFO - codeparrot_training - Step 4941: {'lr': 0.0004887965314569014, 'samples': 2530304, 'steps': 4941, 'batch_loss/train': 0.9378176229074597}
+12/22/2021 06:24:41 - INFO - codeparrot_training - Step 4942: {'lr': 0.0004887918650022257, 'samples': 2530816, 'steps': 4942, 'batch_loss/train': 0.7866222767625004}
+12/22/2021 06:24:53 - INFO - codeparrot_training - Step 4943: {'lr': 0.0004887871975982036, 'samples': 2531328, 'steps': 4943, 'batch_loss/train': 0.8699145391583443}
+12/22/2021 06:25:03 - INFO - codeparrot_training - Step 4944: {'lr': 0.0004887825292448538, 'samples': 2531840, 'steps': 4944, 'batch_loss/train': 0.8386723245494068}
+12/22/2021 06:25:14 - INFO - codeparrot_training - Step 4945: {'lr': 0.0004887778599421948, 'samples': 2532352, 'steps': 4945, 'batch_loss/train': 0.7481547992210835}
+12/22/2021 06:25:26 - INFO - codeparrot_training - Step 4946: {'lr': 0.0004887731896902452, 'samples': 2532864, 'steps': 4946, 'batch_loss/train': 0.8914304384961724}
+12/22/2021 06:25:37 - INFO - codeparrot_training - Step 4947: {'lr': 0.0004887685184890236, 'samples': 2533376, 'steps': 4947, 'batch_loss/train': 0.8275982507038862}
+12/22/2021 06:25:47 - INFO - codeparrot_training - Step 4948: {'lr': 0.0004887638463385485, 'samples': 2533888, 'steps': 4948, 'batch_loss/train': 0.8020043754950166}
+12/22/2021 06:26:00 - INFO - codeparrot_training - Step 4949: {'lr': 0.0004887591732388386, 'samples': 2534400, 'steps': 4949, 'batch_loss/train': 0.7773739714175463}
+12/22/2021 06:26:11 - INFO - codeparrot_training - Step 4950: {'lr': 0.0004887544991899123, 'samples': 2534912, 'steps': 4950, 'batch_loss/train': 0.9138218834996223}
+12/22/2021 06:26:21 - INFO - codeparrot_training - Step 4951: {'lr': 0.0004887498241917882, 'samples': 2535424, 'steps': 4951, 'batch_loss/train': 0.8527651708573103}
+12/22/2021 06:26:34 - INFO - codeparrot_training - Step 4952: {'lr': 0.0004887451482444849, 'samples': 2535936, 'steps': 4952, 'batch_loss/train': 0.8449178719893098}
+12/22/2021 06:26:44 - INFO - codeparrot_training - Step 4953: {'lr': 0.0004887404713480211, 'samples': 2536448, 'steps': 4953, 'batch_loss/train': 0.8603670578449965}
+12/22/2021 06:26:55 - INFO - codeparrot_training - Step 4954: {'lr': 0.0004887357935024154, 'samples': 2536960, 'steps': 4954, 'batch_loss/train': 0.9232867108657956}
+12/22/2021 06:27:06 - INFO - codeparrot_training - Step 4955: {'lr': 0.0004887311147076862, 'samples': 2537472, 'steps': 4955, 'batch_loss/train': 0.9573373245075345}
+12/22/2021 06:27:18 - INFO - codeparrot_training - Step 4956: {'lr': 0.0004887264349638524, 'samples': 2537984, 'steps': 4956, 'batch_loss/train': 0.8092666286975145}
+12/22/2021 06:27:28 - INFO - codeparrot_training - Step 4957: {'lr': 0.0004887217542709324, 'samples': 2538496, 'steps': 4957, 'batch_loss/train': 0.8307648794725537}
+12/22/2021 06:27:39 - INFO - codeparrot_training - Step 4958: {'lr': 0.0004887170726289447, 'samples': 2539008, 'steps': 4958, 'batch_loss/train': 0.8899243976920843}
+12/22/2021 06:27:52 - INFO - codeparrot_training - Step 4959: {'lr': 0.0004887123900379082, 'samples': 2539520, 'steps': 4959, 'batch_loss/train': 0.882855542935431}
+12/22/2021 06:28:02 - INFO - codeparrot_training - Step 4960: {'lr': 0.0004887077064978412, 'samples': 2540032, 'steps': 4960, 'batch_loss/train': 0.701606247574091}
+12/22/2021 06:28:13 - INFO - codeparrot_training - Step 4961: {'lr': 0.0004887030220087627, 'samples': 2540544, 'steps': 4961, 'batch_loss/train': 2.0212436942383647}
+12/22/2021 06:28:25 - INFO - codeparrot_training - Step 4962: {'lr': 0.0004886983365706911, 'samples': 2541056, 'steps': 4962, 'batch_loss/train': 0.8411136418581009}
+12/22/2021 06:28:36 - INFO - codeparrot_training - Step 4963: {'lr': 0.0004886936501836449, 'samples': 2541568, 'steps': 4963, 'batch_loss/train': 0.8441598974168301}
+12/22/2021 06:28:46 - INFO - codeparrot_training - Step 4964: {'lr': 0.000488688962847643, 'samples': 2542080, 'steps': 4964, 'batch_loss/train': 0.8455916093662381}
+12/22/2021 06:28:57 - INFO - codeparrot_training - Step 4965: {'lr': 0.0004886842745627038, 'samples': 2542592, 'steps': 4965, 'batch_loss/train': 0.8889451390132308}
+12/22/2021 06:29:09 - INFO - codeparrot_training - Step 4966: {'lr': 0.000488679585328846, 'samples': 2543104, 'steps': 4966, 'batch_loss/train': 0.7929069604724646}
+12/22/2021 06:29:20 - INFO - codeparrot_training - Step 4967: {'lr': 0.0004886748951460885, 'samples': 2543616, 'steps': 4967, 'batch_loss/train': 1.001233596354723}
+12/22/2021 06:29:31 - INFO - codeparrot_training - Step 4968: {'lr': 0.0004886702040144496, 'samples': 2544128, 'steps': 4968, 'batch_loss/train': 0.8585275579243898}
+12/22/2021 06:29:43 - INFO - codeparrot_training - Step 4969: {'lr': 0.0004886655119339481, 'samples': 2544640, 'steps': 4969, 'batch_loss/train': 1.034215236082673}
+12/22/2021 06:29:54 - INFO - codeparrot_training - Step 4970: {'lr': 0.0004886608189046027, 'samples': 2545152, 'steps': 4970, 'batch_loss/train': 0.8377849506214261}
+12/22/2021 06:30:04 - INFO - codeparrot_training - Step 4971: {'lr': 0.0004886561249264319, 'samples': 2545664, 'steps': 4971, 'batch_loss/train': 0.8523126216605306}
+12/22/2021 06:30:17 - INFO - codeparrot_training - Step 4972: {'lr': 0.0004886514299994545, 'samples': 2546176, 'steps': 4972, 'batch_loss/train': 0.9025827292352915}
+12/22/2021 06:30:27 - INFO - codeparrot_training - Step 4973: {'lr': 0.0004886467341236892, 'samples': 2546688, 'steps': 4973, 'batch_loss/train': 0.8945728838443756}
+12/22/2021 06:30:38 - INFO - codeparrot_training - Step 4974: {'lr': 0.0004886420372991545, 'samples': 2547200, 'steps': 4974, 'batch_loss/train': 0.89814661629498}
+12/22/2021 06:30:48 - INFO - codeparrot_training - Step 4975: {'lr': 0.0004886373395258692, 'samples': 2547712, 'steps': 4975, 'batch_loss/train': 0.6792180235497653}
+12/22/2021 06:31:01 - INFO - codeparrot_training - Step 4976: {'lr': 0.000488632640803852, 'samples': 2548224, 'steps': 4976, 'batch_loss/train': 0.8670194745063782}
+12/22/2021 06:31:12 - INFO - codeparrot_training - Step 4977: {'lr': 0.0004886279411331215, 'samples': 2548736, 'steps': 4977, 'batch_loss/train': 0.8967490899376571}
+12/22/2021 06:31:22 - INFO - codeparrot_training - Step 4978: {'lr': 0.0004886232405136963, 'samples': 2549248, 'steps': 4978, 'batch_loss/train': 0.5250988856423646}
+12/22/2021 06:31:35 - INFO - codeparrot_training - Step 4979: {'lr': 0.0004886185389455953, 'samples': 2549760, 'steps': 4979, 'batch_loss/train': 0.9665238726884127}
+12/22/2021 06:31:46 - INFO - codeparrot_training - Step 4980: {'lr': 0.000488613836428837, 'samples': 2550272, 'steps': 4980, 'batch_loss/train': 0.9862922234460711}
+12/22/2021 06:31:56 - INFO - codeparrot_training - Step 4981: {'lr': 0.0004886091329634403, 'samples': 2550784, 'steps': 4981, 'batch_loss/train': 1.2031910424120724}
+12/22/2021 06:32:08 - INFO - codeparrot_training - Step 4982: {'lr': 0.0004886044285494237, 'samples': 2551296, 'steps': 4982, 'batch_loss/train': 0.7784961732104421}
+12/22/2021 06:32:19 - INFO - codeparrot_training - Step 4983: {'lr': 0.0004885997231868061, 'samples': 2551808, 'steps': 4983, 'batch_loss/train': 0.6730921814450994}
+12/22/2021 06:32:30 - INFO - codeparrot_training - Step 4984: {'lr': 0.0004885950168756059, 'samples': 2552320, 'steps': 4984, 'batch_loss/train': 0.8643502220511436}
+12/22/2021 06:32:42 - INFO - codeparrot_training - Step 4985: {'lr': 0.0004885903096158422, 'samples': 2552832, 'steps': 4985, 'batch_loss/train': 0.8439259333536029}
+12/22/2021 06:32:53 - INFO - codeparrot_training - Step 4986: {'lr': 0.0004885856014075334, 'samples': 2553344, 'steps': 4986, 'batch_loss/train': 0.7322236965410411}
+12/22/2021 06:33:04 - INFO - codeparrot_training - Step 4987: {'lr': 0.0004885808922506983, 'samples': 2553856, 'steps': 4987, 'batch_loss/train': 0.8568874904885888}
+12/22/2021 06:33:14 - INFO - codeparrot_training - Step 4988: {'lr': 0.0004885761821453557, 'samples': 2554368, 'steps': 4988, 'batch_loss/train': 0.8341573365032673}
+12/22/2021 06:33:27 - INFO - codeparrot_training - Step 4989: {'lr': 0.0004885714710915243, 'samples': 2554880, 'steps': 4989, 'batch_loss/train': 0.6961626239353791}
+12/22/2021 06:33:37 - INFO - codeparrot_training - Step 4990: {'lr': 0.0004885667590892229, 'samples': 2555392, 'steps': 4990, 'batch_loss/train': 0.8997619859874249}
+12/22/2021 06:33:48 - INFO - codeparrot_training - Step 4991: {'lr': 0.00048856204613847, 'samples': 2555904, 'steps': 4991, 'batch_loss/train': 0.778249517083168}
+12/22/2021 06:34:00 - INFO - codeparrot_training - Step 4992: {'lr': 0.0004885573322392845, 'samples': 2556416, 'steps': 4992, 'batch_loss/train': 0.7451556499581784}
+12/22/2021 06:34:10 - INFO - codeparrot_training - Step 4993: {'lr': 0.0004885526173916853, 'samples': 2556928, 'steps': 4993, 'batch_loss/train': 0.7986269295215607}
+12/22/2021 06:34:21 - INFO - codeparrot_training - Step 4994: {'lr': 0.0004885479015956908, 'samples': 2557440, 'steps': 4994, 'batch_loss/train': 0.895805636420846}
+12/22/2021 06:34:34 - INFO - codeparrot_training - Step 4995: {'lr': 0.0004885431848513198, 'samples': 2557952, 'steps': 4995, 'batch_loss/train': 0.8972878735512495}
+12/22/2021 06:34:44 - INFO - codeparrot_training - Step 4996: {'lr': 0.0004885384671585914, 'samples': 2558464, 'steps': 4996, 'batch_loss/train': 0.634955593268387}
+12/22/2021 06:34:55 - INFO - codeparrot_training - Step 4997: {'lr': 0.000488533748517524, 'samples': 2558976, 'steps': 4997, 'batch_loss/train': 0.6228164002532139}
+12/22/2021 06:35:06 - INFO - codeparrot_training - Step 4998: {'lr': 0.0004885290289281366, 'samples': 2559488, 'steps': 4998, 'batch_loss/train': 0.6954452490899712}
+12/22/2021 06:35:18 - INFO - codeparrot_training - Step 4999: {'lr': 0.0004885243083904477, 'samples': 2560000, 'steps': 4999, 'batch_loss/train': 0.7173171901376918}
+12/22/2021 06:35:18 - INFO - codeparrot_training - Evaluating and saving model checkpoint
+12/22/2021 07:03:01 - INFO - codeparrot_training - Batch size: torch.Size([0, 2048])
+12/22/2021 07:03:01 - INFO - codeparrot_training - Step 5000: {'loss/eval': 0.8700061440467834, 'perplexity': 2.386925458908081}