Training in progress, epoch 2

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd84cd5b73db618b01cabd80fa50cc53f3a7cf09e8d82da404d3ff8a0993b90b
+oid sha256:0714e26ccdd0984d61053cfd55d16092ae60c0d2d4f0d75731d90fc24aa125a8
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2abd3539632300c126d958d31abe1831fa7ae1a45d3714859161103607282a3d
+oid sha256:b80780c4dcd5f9b6afc2ff1b1386249b95d1d28ffe3ea9636ff0945558e110b9
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a31a511d0d194bf381d4dee5a06e63cf1e2f045c2b1656d5513b19245225bdf4
+oid sha256:9a43f5fffe3c1ef84abf3cfe2a43fa074bf943363292ff6568ad17ce2cadfa8a
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc4050c42dad275f7025924e2aaed640f6e3d99fbcb73f358b24cd2a6c88e3e2
+oid sha256:520e37aa7335f7e257634e2a443bd57b139d269c8d0bbd2bd79516ffdd09f580
 size 1168138808

trainer_log.jsonl

@@ -41,3 +41,89 @@
 {"current_steps": 410, "total_steps": 1278, "loss": 0.3788, "lr": 5e-06, "epoch": 0.9610313507178435, "percentage": 32.08, "elapsed_time": "3:41:48", "remaining_time": "7:49:34"}
 {"current_steps": 420, "total_steps": 1278, "loss": 0.3673, "lr": 5e-06, "epoch": 0.9844711397597422, "percentage": 32.86, "elapsed_time": "3:47:12", "remaining_time": "7:44:09"}
 {"current_steps": 426, "total_steps": 1278, "eval_loss": 0.37145182490348816, "epoch": 0.9985350131848814, "percentage": 33.33, "elapsed_time": "3:55:39", "remaining_time": "7:51:19"}
+{"current_steps": 430, "total_steps": 1278, "loss": 0.3801, "lr": 5e-06, "epoch": 1.0084969235276882, "percentage": 33.65, "elapsed_time": "3:58:50", "remaining_time": "7:51:00"}
+{"current_steps": 440, "total_steps": 1278, "loss": 0.3221, "lr": 5e-06, "epoch": 1.0319367125695869, "percentage": 34.43, "elapsed_time": "4:04:15", "remaining_time": "7:45:11"}
+{"current_steps": 450, "total_steps": 1278, "loss": 0.3257, "lr": 5e-06, "epoch": 1.0553765016114856, "percentage": 35.21, "elapsed_time": "4:09:40", "remaining_time": "7:39:23"}
+{"current_steps": 460, "total_steps": 1278, "loss": 0.3205, "lr": 5e-06, "epoch": 1.078816290653384, "percentage": 35.99, "elapsed_time": "4:15:05", "remaining_time": "7:33:37"}
+{"current_steps": 470, "total_steps": 1278, "loss": 0.3267, "lr": 5e-06, "epoch": 1.1022560796952827, "percentage": 36.78, "elapsed_time": "4:20:30", "remaining_time": "7:27:51"}
+{"current_steps": 480, "total_steps": 1278, "loss": 0.3269, "lr": 5e-06, "epoch": 1.1256958687371814, "percentage": 37.56, "elapsed_time": "4:25:56", "remaining_time": "7:22:06"}
+{"current_steps": 490, "total_steps": 1278, "loss": 0.3299, "lr": 5e-06, "epoch": 1.1491356577790799, "percentage": 38.34, "elapsed_time": "4:31:20", "remaining_time": "7:16:22"}
+{"current_steps": 500, "total_steps": 1278, "loss": 0.3307, "lr": 5e-06, "epoch": 1.1725754468209786, "percentage": 39.12, "elapsed_time": "4:36:43", "remaining_time": "7:10:35"}
+{"current_steps": 510, "total_steps": 1278, "loss": 0.3338, "lr": 5e-06, "epoch": 1.1960152358628773, "percentage": 39.91, "elapsed_time": "4:42:06", "remaining_time": "7:04:49"}
+{"current_steps": 520, "total_steps": 1278, "loss": 0.3253, "lr": 5e-06, "epoch": 1.219455024904776, "percentage": 40.69, "elapsed_time": "4:47:29", "remaining_time": "6:59:04"}
+{"current_steps": 530, "total_steps": 1278, "loss": 0.3296, "lr": 5e-06, "epoch": 1.2428948139466744, "percentage": 41.47, "elapsed_time": "4:52:53", "remaining_time": "6:53:22"}
+{"current_steps": 540, "total_steps": 1278, "loss": 0.3256, "lr": 5e-06, "epoch": 1.2663346029885731, "percentage": 42.25, "elapsed_time": "4:58:17", "remaining_time": "6:47:40"}
+{"current_steps": 550, "total_steps": 1278, "loss": 0.3255, "lr": 5e-06, "epoch": 1.2897743920304716, "percentage": 43.04, "elapsed_time": "5:03:40", "remaining_time": "6:41:56"}
+{"current_steps": 560, "total_steps": 1278, "loss": 0.3225, "lr": 5e-06, "epoch": 1.3132141810723703, "percentage": 43.82, "elapsed_time": "5:09:04", "remaining_time": "6:36:16"}
+{"current_steps": 570, "total_steps": 1278, "loss": 0.3264, "lr": 5e-06, "epoch": 1.336653970114269, "percentage": 44.6, "elapsed_time": "5:14:29", "remaining_time": "6:30:38"}
+{"current_steps": 580, "total_steps": 1278, "loss": 0.3196, "lr": 5e-06, "epoch": 1.3600937591561677, "percentage": 45.38, "elapsed_time": "5:19:53", "remaining_time": "6:24:58"}
+{"current_steps": 590, "total_steps": 1278, "loss": 0.3244, "lr": 5e-06, "epoch": 1.3835335481980662, "percentage": 46.17, "elapsed_time": "5:25:16", "remaining_time": "6:19:17"}
+{"current_steps": 600, "total_steps": 1278, "loss": 0.3224, "lr": 5e-06, "epoch": 1.4069733372399649, "percentage": 46.95, "elapsed_time": "5:30:38", "remaining_time": "6:13:37"}
+{"current_steps": 610, "total_steps": 1278, "loss": 0.3251, "lr": 5e-06, "epoch": 1.4304131262818633, "percentage": 47.73, "elapsed_time": "5:35:59", "remaining_time": "6:07:56"}
+{"current_steps": 620, "total_steps": 1278, "loss": 0.3265, "lr": 5e-06, "epoch": 1.453852915323762, "percentage": 48.51, "elapsed_time": "5:41:23", "remaining_time": "6:02:19"}
+{"current_steps": 630, "total_steps": 1278, "loss": 0.3279, "lr": 5e-06, "epoch": 1.4772927043656607, "percentage": 49.3, "elapsed_time": "5:46:48", "remaining_time": "5:56:43"}
+{"current_steps": 640, "total_steps": 1278, "loss": 0.3227, "lr": 5e-06, "epoch": 1.5007324934075594, "percentage": 50.08, "elapsed_time": "5:52:12", "remaining_time": "5:51:06"}
+{"current_steps": 650, "total_steps": 1278, "loss": 0.3181, "lr": 5e-06, "epoch": 1.524172282449458, "percentage": 50.86, "elapsed_time": "5:57:36", "remaining_time": "5:45:30"}
+{"current_steps": 660, "total_steps": 1278, "loss": 0.3275, "lr": 5e-06, "epoch": 1.5476120714913566, "percentage": 51.64, "elapsed_time": "6:03:01", "remaining_time": "5:39:54"}
+{"current_steps": 670, "total_steps": 1278, "loss": 0.3228, "lr": 5e-06, "epoch": 1.571051860533255, "percentage": 52.43, "elapsed_time": "6:08:24", "remaining_time": "5:34:18"}
+{"current_steps": 680, "total_steps": 1278, "loss": 0.3199, "lr": 5e-06, "epoch": 1.5944916495751538, "percentage": 53.21, "elapsed_time": "6:13:49", "remaining_time": "5:28:44"}
+{"current_steps": 690, "total_steps": 1278, "loss": 0.3317, "lr": 5e-06, "epoch": 1.6179314386170525, "percentage": 53.99, "elapsed_time": "6:19:12", "remaining_time": "5:23:08"}
+{"current_steps": 700, "total_steps": 1278, "loss": 0.3239, "lr": 5e-06, "epoch": 1.6413712276589512, "percentage": 54.77, "elapsed_time": "6:24:35", "remaining_time": "5:17:33"}
+{"current_steps": 710, "total_steps": 1278, "loss": 0.3208, "lr": 5e-06, "epoch": 1.6648110167008499, "percentage": 55.56, "elapsed_time": "6:29:57", "remaining_time": "5:11:57"}
+{"current_steps": 720, "total_steps": 1278, "loss": 0.3184, "lr": 5e-06, "epoch": 1.6882508057427483, "percentage": 56.34, "elapsed_time": "6:35:19", "remaining_time": "5:06:22"}
+{"current_steps": 730, "total_steps": 1278, "loss": 0.3252, "lr": 5e-06, "epoch": 1.7116905947846468, "percentage": 57.12, "elapsed_time": "6:40:41", "remaining_time": "5:00:47"}
+{"current_steps": 740, "total_steps": 1278, "loss": 0.3201, "lr": 5e-06, "epoch": 1.7351303838265455, "percentage": 57.9, "elapsed_time": "6:46:02", "remaining_time": "4:55:11"}
+{"current_steps": 750, "total_steps": 1278, "loss": 0.3258, "lr": 5e-06, "epoch": 1.7585701728684442, "percentage": 58.69, "elapsed_time": "6:51:25", "remaining_time": "4:49:38"}
+{"current_steps": 760, "total_steps": 1278, "loss": 0.3231, "lr": 5e-06, "epoch": 1.7820099619103429, "percentage": 59.47, "elapsed_time": "6:56:49", "remaining_time": "4:44:05"}
+{"current_steps": 770, "total_steps": 1278, "loss": 0.3246, "lr": 5e-06, "epoch": 1.8054497509522416, "percentage": 60.25, "elapsed_time": "7:02:13", "remaining_time": "4:38:33"}
+{"current_steps": 780, "total_steps": 1278, "loss": 0.3219, "lr": 5e-06, "epoch": 1.82888953999414, "percentage": 61.03, "elapsed_time": "7:07:36", "remaining_time": "4:33:00"}
+{"current_steps": 790, "total_steps": 1278, "loss": 0.3217, "lr": 5e-06, "epoch": 1.8523293290360385, "percentage": 61.82, "elapsed_time": "7:13:00", "remaining_time": "4:27:28"}
+{"current_steps": 800, "total_steps": 1278, "loss": 0.3259, "lr": 5e-06, "epoch": 1.8757691180779372, "percentage": 62.6, "elapsed_time": "7:18:21", "remaining_time": "4:21:55"}
+{"current_steps": 810, "total_steps": 1278, "loss": 0.3197, "lr": 5e-06, "epoch": 1.899208907119836, "percentage": 63.38, "elapsed_time": "7:23:43", "remaining_time": "4:16:22"}
+{"current_steps": 820, "total_steps": 1278, "loss": 0.3226, "lr": 5e-06, "epoch": 1.9226486961617346, "percentage": 64.16, "elapsed_time": "7:29:04", "remaining_time": "4:10:49"}
+{"current_steps": 830, "total_steps": 1278, "loss": 0.3221, "lr": 5e-06, "epoch": 1.9460884852036333, "percentage": 64.95, "elapsed_time": "7:34:28", "remaining_time": "4:05:18"}
+{"current_steps": 840, "total_steps": 1278, "loss": 0.3282, "lr": 5e-06, "epoch": 1.9695282742455318, "percentage": 65.73, "elapsed_time": "7:39:51", "remaining_time": "3:59:47"}
+{"current_steps": 850, "total_steps": 1278, "loss": 0.319, "lr": 5e-06, "epoch": 1.9929680632874303, "percentage": 66.51, "elapsed_time": "7:45:16", "remaining_time": "3:54:16"}
+{"current_steps": 852, "total_steps": 1278, "eval_loss": 0.36132651567459106, "epoch": 1.99765602109581, "percentage": 66.67, "elapsed_time": "7:51:39", "remaining_time": "3:55:49"}
+{"current_steps": 860, "total_steps": 1278, "loss": 0.3065, "lr": 5e-06, "epoch": 2.0169938470553763, "percentage": 67.29, "elapsed_time": "7:56:57", "remaining_time": "3:51:49"}
+{"current_steps": 870, "total_steps": 1278, "loss": 0.2738, "lr": 5e-06, "epoch": 2.040433636097275, "percentage": 68.08, "elapsed_time": "8:02:20", "remaining_time": "3:46:11"}
+{"current_steps": 880, "total_steps": 1278, "loss": 0.2731, "lr": 5e-06, "epoch": 2.0638734251391737, "percentage": 68.86, "elapsed_time": "8:07:43", "remaining_time": "3:40:35"}
+{"current_steps": 890, "total_steps": 1278, "loss": 0.2744, "lr": 5e-06, "epoch": 2.0873132141810724, "percentage": 69.64, "elapsed_time": "8:13:05", "remaining_time": "3:34:58"}
+{"current_steps": 900, "total_steps": 1278, "loss": 0.2751, "lr": 5e-06, "epoch": 2.110753003222971, "percentage": 70.42, "elapsed_time": "8:18:29", "remaining_time": "3:29:22"}
+{"current_steps": 910, "total_steps": 1278, "loss": 0.2765, "lr": 5e-06, "epoch": 2.13419279226487, "percentage": 71.21, "elapsed_time": "8:23:51", "remaining_time": "3:23:45"}
+{"current_steps": 920, "total_steps": 1278, "loss": 0.2737, "lr": 5e-06, "epoch": 2.157632581306768, "percentage": 71.99, "elapsed_time": "8:29:12", "remaining_time": "3:18:09"}
+{"current_steps": 930, "total_steps": 1278, "loss": 0.2741, "lr": 5e-06, "epoch": 2.1810723703486667, "percentage": 72.77, "elapsed_time": "8:34:34", "remaining_time": "3:12:32"}
+{"current_steps": 940, "total_steps": 1278, "loss": 0.2756, "lr": 5e-06, "epoch": 2.2045121593905654, "percentage": 73.55, "elapsed_time": "8:39:57", "remaining_time": "3:06:57"}
+{"current_steps": 950, "total_steps": 1278, "loss": 0.2737, "lr": 5e-06, "epoch": 2.227951948432464, "percentage": 74.33, "elapsed_time": "8:45:18", "remaining_time": "3:01:22"}
+{"current_steps": 960, "total_steps": 1278, "loss": 0.2796, "lr": 5e-06, "epoch": 2.251391737474363, "percentage": 75.12, "elapsed_time": "8:50:42", "remaining_time": "2:55:47"}
+{"current_steps": 970, "total_steps": 1278, "loss": 0.273, "lr": 5e-06, "epoch": 2.2748315265162615, "percentage": 75.9, "elapsed_time": "8:56:03", "remaining_time": "2:50:12"}
+{"current_steps": 980, "total_steps": 1278, "loss": 0.273, "lr": 5e-06, "epoch": 2.2982713155581598, "percentage": 76.68, "elapsed_time": "9:01:26", "remaining_time": "2:44:38"}
+{"current_steps": 990, "total_steps": 1278, "loss": 0.2755, "lr": 5e-06, "epoch": 2.3217111046000585, "percentage": 77.46, "elapsed_time": "9:06:49", "remaining_time": "2:39:04"}
+{"current_steps": 1000, "total_steps": 1278, "loss": 0.281, "lr": 5e-06, "epoch": 2.345150893641957, "percentage": 78.25, "elapsed_time": "9:12:11", "remaining_time": "2:33:30"}
+{"current_steps": 1010, "total_steps": 1278, "loss": 0.275, "lr": 5e-06, "epoch": 2.368590682683856, "percentage": 79.03, "elapsed_time": "9:17:35", "remaining_time": "2:27:57"}
+{"current_steps": 1020, "total_steps": 1278, "loss": 0.2778, "lr": 5e-06, "epoch": 2.3920304717257546, "percentage": 79.81, "elapsed_time": "9:22:58", "remaining_time": "2:22:23"}
+{"current_steps": 1030, "total_steps": 1278, "loss": 0.2843, "lr": 5e-06, "epoch": 2.4154702607676533, "percentage": 80.59, "elapsed_time": "9:28:21", "remaining_time": "2:16:50"}
+{"current_steps": 1040, "total_steps": 1278, "loss": 0.278, "lr": 5e-06, "epoch": 2.438910049809552, "percentage": 81.38, "elapsed_time": "9:33:43", "remaining_time": "2:11:17"}
+{"current_steps": 1050, "total_steps": 1278, "loss": 0.2758, "lr": 5e-06, "epoch": 2.46234983885145, "percentage": 82.16, "elapsed_time": "9:39:07", "remaining_time": "2:05:45"}
+{"current_steps": 1060, "total_steps": 1278, "loss": 0.2749, "lr": 5e-06, "epoch": 2.485789627893349, "percentage": 82.94, "elapsed_time": "9:44:29", "remaining_time": "2:00:12"}
+{"current_steps": 1070, "total_steps": 1278, "loss": 0.2829, "lr": 5e-06, "epoch": 2.5092294169352476, "percentage": 83.72, "elapsed_time": "9:49:51", "remaining_time": "1:54:39"}
+{"current_steps": 1080, "total_steps": 1278, "loss": 0.2792, "lr": 5e-06, "epoch": 2.5326692059771463, "percentage": 84.51, "elapsed_time": "9:55:15", "remaining_time": "1:49:07"}
+{"current_steps": 1090, "total_steps": 1278, "loss": 0.2768, "lr": 5e-06, "epoch": 2.556108995019045, "percentage": 85.29, "elapsed_time": "10:00:39", "remaining_time": "1:43:36"}
+{"current_steps": 1100, "total_steps": 1278, "loss": 0.2837, "lr": 5e-06, "epoch": 2.5795487840609432, "percentage": 86.07, "elapsed_time": "10:06:03", "remaining_time": "1:38:04"}
+{"current_steps": 1110, "total_steps": 1278, "loss": 0.2732, "lr": 5e-06, "epoch": 2.602988573102842, "percentage": 86.85, "elapsed_time": "10:11:27", "remaining_time": "1:32:32"}
+{"current_steps": 1120, "total_steps": 1278, "loss": 0.2838, "lr": 5e-06, "epoch": 2.6264283621447406, "percentage": 87.64, "elapsed_time": "10:16:50", "remaining_time": "1:27:01"}
+{"current_steps": 1130, "total_steps": 1278, "loss": 0.2799, "lr": 5e-06, "epoch": 2.6498681511866393, "percentage": 88.42, "elapsed_time": "10:22:14", "remaining_time": "1:21:29"}
+{"current_steps": 1140, "total_steps": 1278, "loss": 0.2831, "lr": 5e-06, "epoch": 2.673307940228538, "percentage": 89.2, "elapsed_time": "10:27:38", "remaining_time": "1:15:58"}
+{"current_steps": 1150, "total_steps": 1278, "loss": 0.2795, "lr": 5e-06, "epoch": 2.6967477292704367, "percentage": 89.98, "elapsed_time": "10:33:01", "remaining_time": "1:10:27"}
+{"current_steps": 1160, "total_steps": 1278, "loss": 0.282, "lr": 5e-06, "epoch": 2.7201875183123354, "percentage": 90.77, "elapsed_time": "10:38:24", "remaining_time": "1:04:56"}
+{"current_steps": 1170, "total_steps": 1278, "loss": 0.2798, "lr": 5e-06, "epoch": 2.7436273073542337, "percentage": 91.55, "elapsed_time": "10:43:48", "remaining_time": "0:59:25"}
+{"current_steps": 1180, "total_steps": 1278, "loss": 0.2785, "lr": 5e-06, "epoch": 2.7670670963961324, "percentage": 92.33, "elapsed_time": "10:49:12", "remaining_time": "0:53:55"}
+{"current_steps": 1190, "total_steps": 1278, "loss": 0.2871, "lr": 5e-06, "epoch": 2.790506885438031, "percentage": 93.11, "elapsed_time": "10:54:34", "remaining_time": "0:48:24"}
+{"current_steps": 1200, "total_steps": 1278, "loss": 0.277, "lr": 5e-06, "epoch": 2.8139466744799297, "percentage": 93.9, "elapsed_time": "10:59:54", "remaining_time": "0:42:53"}
+{"current_steps": 1210, "total_steps": 1278, "loss": 0.284, "lr": 5e-06, "epoch": 2.8373864635218284, "percentage": 94.68, "elapsed_time": "11:05:16", "remaining_time": "0:37:23"}
+{"current_steps": 1220, "total_steps": 1278, "loss": 0.279, "lr": 5e-06, "epoch": 2.8608262525637267, "percentage": 95.46, "elapsed_time": "11:10:40", "remaining_time": "0:31:53"}
+{"current_steps": 1230, "total_steps": 1278, "loss": 0.2805, "lr": 5e-06, "epoch": 2.8842660416056254, "percentage": 96.24, "elapsed_time": "11:16:03", "remaining_time": "0:26:22"}
+{"current_steps": 1240, "total_steps": 1278, "loss": 0.2819, "lr": 5e-06, "epoch": 2.907705830647524, "percentage": 97.03, "elapsed_time": "11:21:27", "remaining_time": "0:20:53"}
+{"current_steps": 1250, "total_steps": 1278, "loss": 0.276, "lr": 5e-06, "epoch": 2.9311456196894228, "percentage": 97.81, "elapsed_time": "11:26:50", "remaining_time": "0:15:23"}
+{"current_steps": 1260, "total_steps": 1278, "loss": 0.2795, "lr": 5e-06, "epoch": 2.9545854087313215, "percentage": 98.59, "elapsed_time": "11:32:13", "remaining_time": "0:09:53"}
+{"current_steps": 1270, "total_steps": 1278, "loss": 0.2817, "lr": 5e-06, "epoch": 2.97802519777322, "percentage": 99.37, "elapsed_time": "11:37:36", "remaining_time": "0:04:23"}