Training in progress, epoch 4

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d511f435566797efb5a6f46a10460655cf842f6870a4262395796ad1109cdf2
+oid sha256:5f5ef1eaefa33dd102a169d2e78eb3618abb88e4a7fd7f685b91c6840b1ba66f
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecde2bd9a8ed3ea61b029f351ceecafdc7ec01c4607abab72e3e475eae18dcaa
+oid sha256:bb47901b6dffef04571dd40699fea0865ec7d450cc7e6d04fd69f42f36e3d98a
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9e723fc3b6bbbdd4740aa19173e213376904ce8e389c4df5340e3eea64436b3
+oid sha256:3092f7d0dda2fcf2638277ffd7f7d0de2cfd3eaf8be48381f9f001b324cba8d2
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3c1f9edbbec55782e1ecf51da18c26d31306e2599b42b85821358a512f70983
+oid sha256:805a7b355109f63a2cb595a51a2e8d168e538e1e018088eeb69322ea30ab66d3
 size 1089994880

trainer_log.jsonl

@@ -311,3 +311,81 @@
 {"current_steps": 311, "total_steps": 390, "loss": 0.3501, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "10:52:39", "remaining_time": "2:45:47"}
 {"current_steps": 312, "total_steps": 390, "loss": 0.3451, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "10:54:46", "remaining_time": "2:43:41"}
 {"current_steps": 313, "total_steps": 390, "loss": 0.3358, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "10:57:48", "remaining_time": "2:41:49"}
+{"current_steps": 314, "total_steps": 390, "loss": 0.3019, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "10:59:53", "remaining_time": "2:39:43"}
+{"current_steps": 315, "total_steps": 390, "loss": 0.2879, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "11:01:55", "remaining_time": "2:37:36"}
+{"current_steps": 316, "total_steps": 390, "loss": 0.2918, "lr": 4.228770401229824e-06, "epoch": 4.0448, "percentage": 81.03, "elapsed_time": "11:03:39", "remaining_time": "2:35:24"}
+{"current_steps": 317, "total_steps": 390, "loss": 0.3042, "lr": 4.119321472033779e-06, "epoch": 4.0576, "percentage": 81.28, "elapsed_time": "11:05:46", "remaining_time": "2:33:19"}
+{"current_steps": 318, "total_steps": 390, "loss": 0.3159, "lr": 4.011144731929981e-06, "epoch": 4.0704, "percentage": 81.54, "elapsed_time": "11:07:52", "remaining_time": "2:31:13"}
+{"current_steps": 319, "total_steps": 390, "loss": 0.3121, "lr": 3.904248846874894e-06, "epoch": 4.0832, "percentage": 81.79, "elapsed_time": "11:09:59", "remaining_time": "2:29:07"}
+{"current_steps": 320, "total_steps": 390, "loss": 0.2878, "lr": 3.7986423802166705e-06, "epoch": 4.096, "percentage": 82.05, "elapsed_time": "11:12:04", "remaining_time": "2:27:00"}
+{"current_steps": 321, "total_steps": 390, "loss": 0.2993, "lr": 3.694333792009115e-06, "epoch": 4.1088, "percentage": 82.31, "elapsed_time": "11:14:07", "remaining_time": "2:24:54"}
+{"current_steps": 322, "total_steps": 390, "loss": 0.2846, "lr": 3.5913314383339937e-06, "epoch": 4.1216, "percentage": 82.56, "elapsed_time": "11:15:53", "remaining_time": "2:22:44"}
+{"current_steps": 323, "total_steps": 390, "loss": 0.3322, "lr": 3.4896435706316e-06, "epoch": 4.1344, "percentage": 82.82, "elapsed_time": "11:18:12", "remaining_time": "2:20:40"}
+{"current_steps": 324, "total_steps": 390, "loss": 0.2634, "lr": 3.3892783350397675e-06, "epoch": 4.1472, "percentage": 83.08, "elapsed_time": "11:20:05", "remaining_time": "2:18:32"}
+{"current_steps": 325, "total_steps": 390, "loss": 0.3161, "lr": 3.290243771741275e-06, "epoch": 4.16, "percentage": 83.33, "elapsed_time": "11:22:12", "remaining_time": "2:16:26"}
+{"current_steps": 326, "total_steps": 390, "loss": 0.3188, "lr": 3.1925478143197418e-06, "epoch": 4.1728, "percentage": 83.59, "elapsed_time": "11:24:22", "remaining_time": "2:14:21"}
+{"current_steps": 327, "total_steps": 390, "loss": 0.2987, "lr": 3.0961982891241083e-06, "epoch": 4.1856, "percentage": 83.85, "elapsed_time": "11:26:29", "remaining_time": "2:12:15"}
+{"current_steps": 328, "total_steps": 390, "loss": 0.286, "lr": 3.001202914641628e-06, "epoch": 4.1984, "percentage": 84.1, "elapsed_time": "11:28:38", "remaining_time": "2:10:10"}
+{"current_steps": 329, "total_steps": 390, "loss": 0.2891, "lr": 2.907569300879596e-06, "epoch": 4.2112, "percentage": 84.36, "elapsed_time": "11:30:30", "remaining_time": "2:08:01"}
+{"current_steps": 330, "total_steps": 390, "loss": 0.2889, "lr": 2.815304948755664e-06, "epoch": 4.224, "percentage": 84.62, "elapsed_time": "11:32:47", "remaining_time": "2:05:57"}
+{"current_steps": 331, "total_steps": 390, "loss": 0.2851, "lr": 2.7244172494969978e-06, "epoch": 4.2368, "percentage": 84.87, "elapsed_time": "11:34:43", "remaining_time": "2:03:50"}
+{"current_steps": 332, "total_steps": 390, "loss": 0.305, "lr": 2.6349134840481294e-06, "epoch": 4.2496, "percentage": 85.13, "elapsed_time": "11:36:41", "remaining_time": "2:01:42"}
+{"current_steps": 333, "total_steps": 390, "loss": 0.3191, "lr": 2.546800822487714e-06, "epoch": 4.2624, "percentage": 85.38, "elapsed_time": "11:38:56", "remaining_time": "1:59:38"}
+{"current_steps": 334, "total_steps": 390, "loss": 0.267, "lr": 2.4600863234541338e-06, "epoch": 4.2752, "percentage": 85.64, "elapsed_time": "11:40:45", "remaining_time": "1:57:29"}
+{"current_steps": 335, "total_steps": 390, "loss": 0.3063, "lr": 2.374776933580025e-06, "epoch": 4.288, "percentage": 85.9, "elapsed_time": "11:42:49", "remaining_time": "1:55:23"}
+{"current_steps": 336, "total_steps": 390, "loss": 0.2897, "lr": 2.2908794869358044e-06, "epoch": 4.3008, "percentage": 86.15, "elapsed_time": "11:44:39", "remaining_time": "1:53:14"}
+{"current_steps": 337, "total_steps": 390, "loss": 0.3302, "lr": 2.2084007044821764e-06, "epoch": 4.3136, "percentage": 86.41, "elapsed_time": "11:46:44", "remaining_time": "1:51:08"}
+{"current_steps": 338, "total_steps": 390, "loss": 0.2974, "lr": 2.127347193531757e-06, "epoch": 4.3264, "percentage": 86.67, "elapsed_time": "11:48:57", "remaining_time": "1:49:04"}
+{"current_steps": 339, "total_steps": 390, "loss": 0.2839, "lr": 2.0477254472197237e-06, "epoch": 4.3392, "percentage": 86.92, "elapsed_time": "11:51:14", "remaining_time": "1:47:00"}
+{"current_steps": 340, "total_steps": 390, "loss": 0.2996, "lr": 1.96954184398368e-06, "epoch": 4.352, "percentage": 87.18, "elapsed_time": "11:53:16", "remaining_time": "1:44:53"}
+{"current_steps": 341, "total_steps": 390, "loss": 0.2752, "lr": 1.8928026470526917e-06, "epoch": 4.3648, "percentage": 87.44, "elapsed_time": "11:55:02", "remaining_time": "1:42:44"}
+{"current_steps": 342, "total_steps": 390, "loss": 0.2877, "lr": 1.817514003945524e-06, "epoch": 4.3776, "percentage": 87.69, "elapsed_time": "11:56:58", "remaining_time": "1:40:37"}
+{"current_steps": 343, "total_steps": 390, "loss": 0.2775, "lr": 1.743681945978184e-06, "epoch": 4.3904, "percentage": 87.95, "elapsed_time": "11:58:54", "remaining_time": "1:38:30"}
+{"current_steps": 344, "total_steps": 390, "loss": 0.2923, "lr": 1.6713123877807413e-06, "epoch": 4.4032, "percentage": 88.21, "elapsed_time": "12:00:57", "remaining_time": "1:36:24"}
+{"current_steps": 345, "total_steps": 390, "loss": 0.2776, "lr": 1.6004111268235156e-06, "epoch": 4.416, "percentage": 88.46, "elapsed_time": "12:02:44", "remaining_time": "1:34:16"}
+{"current_steps": 346, "total_steps": 390, "loss": 0.2916, "lr": 1.5309838429526714e-06, "epoch": 4.4288, "percentage": 88.72, "elapsed_time": "12:04:53", "remaining_time": "1:32:10"}
+{"current_steps": 347, "total_steps": 390, "loss": 0.2913, "lr": 1.4630360979351644e-06, "epoch": 4.4416, "percentage": 88.97, "elapsed_time": "12:06:54", "remaining_time": "1:30:04"}
+{"current_steps": 348, "total_steps": 390, "loss": 0.3061, "lr": 1.396573335013236e-06, "epoch": 4.4544, "percentage": 89.23, "elapsed_time": "12:09:13", "remaining_time": "1:28:00"}
+{"current_steps": 349, "total_steps": 390, "loss": 0.2798, "lr": 1.3316008784683265e-06, "epoch": 4.4672, "percentage": 89.49, "elapsed_time": "12:11:23", "remaining_time": "1:25:55"}
+{"current_steps": 350, "total_steps": 390, "loss": 0.299, "lr": 1.2681239331945695e-06, "epoch": 4.48, "percentage": 89.74, "elapsed_time": "12:13:22", "remaining_time": "1:23:48"}
+{"current_steps": 351, "total_steps": 390, "loss": 0.3029, "lr": 1.2061475842818337e-06, "epoch": 4.4928, "percentage": 90.0, "elapsed_time": "12:15:22", "remaining_time": "1:21:42"}
+{"current_steps": 352, "total_steps": 390, "loss": 0.2896, "lr": 1.1456767966083393e-06, "epoch": 4.5056, "percentage": 90.26, "elapsed_time": "12:17:28", "remaining_time": "1:19:36"}
+{"current_steps": 353, "total_steps": 390, "loss": 0.2804, "lr": 1.086716414442952e-06, "epoch": 4.5184, "percentage": 90.51, "elapsed_time": "12:19:38", "remaining_time": "1:17:31"}
+{"current_steps": 354, "total_steps": 390, "loss": 0.3263, "lr": 1.0292711610570904e-06, "epoch": 4.5312, "percentage": 90.77, "elapsed_time": "12:21:47", "remaining_time": "1:15:26"}
+{"current_steps": 355, "total_steps": 390, "loss": 0.2925, "lr": 9.733456383463658e-07, "epoch": 4.5440000000000005, "percentage": 91.03, "elapsed_time": "12:23:45", "remaining_time": "1:13:19"}
+{"current_steps": 356, "total_steps": 390, "loss": 0.2913, "lr": 9.189443264619102e-07, "epoch": 4.5568, "percentage": 91.28, "elapsed_time": "12:25:38", "remaining_time": "1:11:12"}
+{"current_steps": 357, "total_steps": 390, "loss": 0.3092, "lr": 8.660715834514977e-07, "epoch": 4.5696, "percentage": 91.54, "elapsed_time": "12:27:43", "remaining_time": "1:09:07"}
+{"current_steps": 358, "total_steps": 390, "loss": 0.2911, "lr": 8.147316449103959e-07, "epoch": 4.5824, "percentage": 91.79, "elapsed_time": "12:29:35", "remaining_time": "1:07:00"}
+{"current_steps": 359, "total_steps": 390, "loss": 0.3205, "lr": 7.649286236420806e-07, "epoch": 4.5952, "percentage": 92.05, "elapsed_time": "12:31:35", "remaining_time": "1:04:54"}
+{"current_steps": 360, "total_steps": 390, "loss": 0.3082, "lr": 7.166665093287539e-07, "epoch": 4.608, "percentage": 92.31, "elapsed_time": "12:33:42", "remaining_time": "1:02:48"}
+{"current_steps": 361, "total_steps": 390, "loss": 0.3097, "lr": 6.69949168211721e-07, "epoch": 4.6208, "percentage": 92.56, "elapsed_time": "12:35:35", "remaining_time": "1:00:41"}
+{"current_steps": 362, "total_steps": 390, "loss": 0.2703, "lr": 6.247803427816945e-07, "epoch": 4.6336, "percentage": 92.82, "elapsed_time": "12:37:33", "remaining_time": "0:58:35"}
+{"current_steps": 363, "total_steps": 390, "loss": 0.3157, "lr": 5.811636514789598e-07, "epoch": 4.6464, "percentage": 93.08, "elapsed_time": "12:39:42", "remaining_time": "0:56:30"}
+{"current_steps": 364, "total_steps": 390, "loss": 0.3356, "lr": 5.391025884035239e-07, "epoch": 4.6592, "percentage": 93.33, "elapsed_time": "12:42:00", "remaining_time": "0:54:25"}
+{"current_steps": 365, "total_steps": 390, "loss": 0.309, "lr": 4.986005230351954e-07, "epoch": 4.672, "percentage": 93.59, "elapsed_time": "12:44:18", "remaining_time": "0:52:20"}
+{"current_steps": 366, "total_steps": 390, "loss": 0.2899, "lr": 4.5966069996365993e-07, "epoch": 4.6848, "percentage": 93.85, "elapsed_time": "12:46:02", "remaining_time": "0:50:13"}
+{"current_steps": 367, "total_steps": 390, "loss": 0.2814, "lr": 4.22286238628562e-07, "epoch": 4.6975999999999996, "percentage": 94.1, "elapsed_time": "12:48:03", "remaining_time": "0:48:08"}
+{"current_steps": 368, "total_steps": 390, "loss": 0.2847, "lr": 3.8648013306960664e-07, "epoch": 4.7104, "percentage": 94.36, "elapsed_time": "12:50:04", "remaining_time": "0:46:02"}
+{"current_steps": 369, "total_steps": 390, "loss": 0.2982, "lr": 3.522452516867048e-07, "epoch": 4.7232, "percentage": 94.62, "elapsed_time": "12:51:58", "remaining_time": "0:43:56"}
+{"current_steps": 370, "total_steps": 390, "loss": 0.2841, "lr": 3.1958433701019697e-07, "epoch": 4.736, "percentage": 94.87, "elapsed_time": "12:54:10", "remaining_time": "0:41:50"}
+{"current_steps": 371, "total_steps": 390, "loss": 0.2981, "lr": 2.8850000548115155e-07, "epoch": 4.7488, "percentage": 95.13, "elapsed_time": "12:56:17", "remaining_time": "0:39:45"}
+{"current_steps": 372, "total_steps": 390, "loss": 0.3082, "lr": 2.5899474724174313e-07, "epoch": 4.7616, "percentage": 95.38, "elapsed_time": "12:58:31", "remaining_time": "0:37:40"}
+{"current_steps": 373, "total_steps": 390, "loss": 0.3007, "lr": 2.3107092593579905e-07, "epoch": 4.7744, "percentage": 95.64, "elapsed_time": "13:00:35", "remaining_time": "0:35:34"}
+{"current_steps": 374, "total_steps": 390, "loss": 0.269, "lr": 2.0473077851942858e-07, "epoch": 4.7872, "percentage": 95.9, "elapsed_time": "13:02:31", "remaining_time": "0:33:28"}
+{"current_steps": 375, "total_steps": 390, "loss": 0.3078, "lr": 1.799764150818306e-07, "epoch": 4.8, "percentage": 96.15, "elapsed_time": "13:04:49", "remaining_time": "0:31:23"}
+{"current_steps": 376, "total_steps": 390, "loss": 0.2674, "lr": 1.5680981867625566e-07, "epoch": 4.8128, "percentage": 96.41, "elapsed_time": "13:06:42", "remaining_time": "0:29:17"}
+{"current_steps": 377, "total_steps": 390, "loss": 0.2971, "lr": 1.3523284516113955e-07, "epoch": 4.8256, "percentage": 96.67, "elapsed_time": "13:08:53", "remaining_time": "0:27:12"}
+{"current_steps": 378, "total_steps": 390, "loss": 0.3005, "lr": 1.1524722305144231e-07, "epoch": 4.8384, "percentage": 96.92, "elapsed_time": "13:11:10", "remaining_time": "0:25:06"}
+{"current_steps": 379, "total_steps": 390, "loss": 0.3049, "lr": 9.685455338016347e-08, "epoch": 4.8512, "percentage": 97.18, "elapsed_time": "13:13:12", "remaining_time": "0:23:01"}
+{"current_steps": 380, "total_steps": 390, "loss": 0.3064, "lr": 8.005630957010014e-08, "epoch": 4.864, "percentage": 97.44, "elapsed_time": "13:15:14", "remaining_time": "0:20:55"}
+{"current_steps": 381, "total_steps": 390, "loss": 0.3108, "lr": 6.485383731580142e-08, "epoch": 4.8768, "percentage": 97.69, "elapsed_time": "13:17:24", "remaining_time": "0:18:50"}
+{"current_steps": 382, "total_steps": 390, "loss": 0.3014, "lr": 5.1248354475768034e-08, "epoch": 4.8896, "percentage": 97.95, "elapsed_time": "13:19:32", "remaining_time": "0:16:44"}
+{"current_steps": 383, "total_steps": 390, "loss": 0.3115, "lr": 3.924095097489922e-08, "epoch": 4.9024, "percentage": 98.21, "elapsed_time": "13:21:51", "remaining_time": "0:14:39"}
+{"current_steps": 384, "total_steps": 390, "loss": 0.3188, "lr": 2.8832588717164766e-08, "epoch": 4.9152000000000005, "percentage": 98.46, "elapsed_time": "13:23:49", "remaining_time": "0:12:33"}
+{"current_steps": 385, "total_steps": 390, "loss": 0.2944, "lr": 2.0024101508555604e-08, "epoch": 4.928, "percentage": 98.72, "elapsed_time": "13:25:55", "remaining_time": "0:10:27"}
+{"current_steps": 386, "total_steps": 390, "loss": 0.3042, "lr": 1.281619499029274e-08, "epoch": 4.9408, "percentage": 98.97, "elapsed_time": "13:28:02", "remaining_time": "0:08:22"}
+{"current_steps": 387, "total_steps": 390, "loss": 0.2718, "lr": 7.209446582292501e-09, "epoch": 4.9536, "percentage": 99.23, "elapsed_time": "13:29:56", "remaining_time": "0:06:16"}
+{"current_steps": 388, "total_steps": 390, "loss": 0.2858, "lr": 3.2043054369057523e-09, "epoch": 4.9664, "percentage": 99.49, "elapsed_time": "13:31:57", "remaining_time": "0:04:11"}
+{"current_steps": 389, "total_steps": 390, "loss": 0.3056, "lr": 8.010924029533406e-10, "epoch": 4.9792, "percentage": 99.74, "elapsed_time": "13:33:52", "remaining_time": "0:02:05"}
+{"current_steps": 390, "total_steps": 390, "loss": 0.3022, "lr": 0.0, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "13:35:50", "remaining_time": "0:00:00"}
+{"current_steps": 390, "total_steps": 390, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "13:37:52", "remaining_time": "0:00:00"}