Training in progress, step 288

model-00001-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:284813b793c38081d4c9a1c92b0f6f9400be7e4336029a7e9b53aaf766876236
+oid sha256:272a6da1072fc2c2afe34157aef0e032b60262a1000a09702473648798a4e29f
 size 4986211280

model-00002-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ac3f841225a72d3473735a825f2699a2c984e8123756cdf108703a29e650a08
+oid sha256:e17a4ff0b1a7c6e0dd4396cc223ca7c5da7cbd0d518cf101f9998e0eb4ae8d98
 size 4954847344

model-00003-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1606cbeae382859892871a35f9a5599a4c5cb93e0d46bdf2a322e113a3146434
+oid sha256:d680fb4ac8c8eb27470b85968909d2f8e8c2b2778bb3b45ba2adad1119f35fbe
 size 4954847392

model-00004-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdc93a8f228b65408c98c95670e7085cdd0759fc95c102e0fdd5f1a9e08b5d9f
+oid sha256:b8d66bfd3fe1a609452b1f497c3d5cc6aae87bcf8845486c57f498259fbff167
 size 4954847392

model-00005-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf593544a6b9bcae1227176f7c98e1c7fad15e3372b10d8ae3138c8894074721
+oid sha256:50e4e229f934dcaf8ccf4edea0b09b72239d038025bbed0018cc72b09f833f86
 size 4954847392

model-00006-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9a0eb72fa1d9b006d5b2fd21c4f57d40fe29550d041500e63047e39cc4dc94b
+oid sha256:0cef124f728d55feaee61883e17e2df19ab0523392a362a761167035c8bbede4
 size 4734533160

trainer_log.jsonl

@@ -201,3 +201,89 @@
 {"current_steps": 201, "total_steps": 288, "loss": 0.2739, "lr": 2.5880434661951826e-06, "epoch": 2.093183779119931, "percentage": 69.79, "elapsed_time": "6:47:20", "remaining_time": "2:56:18"}
 {"current_steps": 202, "total_steps": 288, "loss": 0.2767, "lr": 2.5350967883797095e-06, "epoch": 2.103537532355479, "percentage": 70.14, "elapsed_time": "6:49:28", "remaining_time": "2:54:19"}
 {"current_steps": 203, "total_steps": 288, "loss": 0.2797, "lr": 2.4825127664774008e-06, "epoch": 2.1138912855910266, "percentage": 70.49, "elapsed_time": "6:51:22", "remaining_time": "2:52:15"}
+{"current_steps": 204, "total_steps": 288, "loss": 0.2815, "lr": 2.4302991370624106e-06, "epoch": 2.1242450388265746, "percentage": 70.83, "elapsed_time": "6:53:20", "remaining_time": "2:50:12"}
+{"current_steps": 205, "total_steps": 288, "loss": 0.3051, "lr": 2.3784635822138424e-06, "epoch": 2.1345987920621226, "percentage": 71.18, "elapsed_time": "6:55:29", "remaining_time": "2:48:13"}
+{"current_steps": 206, "total_steps": 288, "loss": 0.2598, "lr": 2.3270137283855022e-06, "epoch": 2.1449525452976705, "percentage": 71.53, "elapsed_time": "6:57:28", "remaining_time": "2:46:10"}
+{"current_steps": 207, "total_steps": 288, "loss": 0.271, "lr": 2.2759571452838325e-06, "epoch": 2.155306298533218, "percentage": 71.88, "elapsed_time": "6:59:27", "remaining_time": "2:44:08"}
+{"current_steps": 208, "total_steps": 288, "loss": 0.2848, "lr": 2.2253013447541993e-06, "epoch": 2.165660051768766, "percentage": 72.22, "elapsed_time": "7:01:32", "remaining_time": "2:42:07"}
+{"current_steps": 209, "total_steps": 288, "loss": 0.2781, "lr": 2.17505377967569e-06, "epoch": 2.176013805004314, "percentage": 72.57, "elapsed_time": "7:03:29", "remaining_time": "2:40:04"}
+{"current_steps": 210, "total_steps": 288, "loss": 0.2716, "lr": 2.125221842864585e-06, "epoch": 2.186367558239862, "percentage": 72.92, "elapsed_time": "7:05:43", "remaining_time": "2:38:07"}
+{"current_steps": 211, "total_steps": 288, "loss": 0.2491, "lr": 2.075812865986677e-06, "epoch": 2.19672131147541, "percentage": 73.26, "elapsed_time": "7:07:42", "remaining_time": "2:36:05"}
+{"current_steps": 212, "total_steps": 288, "loss": 0.2755, "lr": 2.0268341184785674e-06, "epoch": 2.2070750647109576, "percentage": 73.61, "elapsed_time": "7:09:41", "remaining_time": "2:34:02"}
+{"current_steps": 213, "total_steps": 288, "loss": 0.3165, "lr": 1.978292806478134e-06, "epoch": 2.2174288179465056, "percentage": 73.96, "elapsed_time": "7:11:40", "remaining_time": "2:31:59"}
+{"current_steps": 214, "total_steps": 288, "loss": 0.2417, "lr": 1.930196071764312e-06, "epoch": 2.2277825711820536, "percentage": 74.31, "elapsed_time": "7:13:38", "remaining_time": "2:29:57"}
+{"current_steps": 215, "total_steps": 288, "loss": 0.2748, "lr": 1.8825509907063328e-06, "epoch": 2.2381363244176016, "percentage": 74.65, "elapsed_time": "7:15:40", "remaining_time": "2:27:55"}
+{"current_steps": 216, "total_steps": 288, "loss": 0.2696, "lr": 1.8353645732225977e-06, "epoch": 2.248490077653149, "percentage": 75.0, "elapsed_time": "7:17:39", "remaining_time": "2:25:53"}
+{"current_steps": 217, "total_steps": 288, "loss": 0.2821, "lr": 1.7886437617493206e-06, "epoch": 2.258843830888697, "percentage": 75.35, "elapsed_time": "7:19:39", "remaining_time": "2:23:50"}
+{"current_steps": 218, "total_steps": 288, "loss": 0.2609, "lr": 1.7423954302191047e-06, "epoch": 2.269197584124245, "percentage": 75.69, "elapsed_time": "7:21:38", "remaining_time": "2:21:48"}
+{"current_steps": 219, "total_steps": 288, "loss": 0.2792, "lr": 1.6966263830495939e-06, "epoch": 2.279551337359793, "percentage": 76.04, "elapsed_time": "7:23:38", "remaining_time": "2:19:46"}
+{"current_steps": 220, "total_steps": 288, "loss": 0.2662, "lr": 1.6513433541423529e-06, "epoch": 2.2899050905953406, "percentage": 76.39, "elapsed_time": "7:25:37", "remaining_time": "2:17:44"}
+{"current_steps": 221, "total_steps": 288, "loss": 0.2748, "lr": 1.6065530058921253e-06, "epoch": 2.3002588438308886, "percentage": 76.74, "elapsed_time": "7:28:02", "remaining_time": "2:15:49"}
+{"current_steps": 222, "total_steps": 288, "loss": 0.2729, "lr": 1.562261928206608e-06, "epoch": 2.3106125970664366, "percentage": 77.08, "elapsed_time": "7:30:00", "remaining_time": "2:13:47"}
+{"current_steps": 223, "total_steps": 288, "loss": 0.2551, "lr": 1.5184766375368914e-06, "epoch": 2.3209663503019846, "percentage": 77.43, "elapsed_time": "7:32:07", "remaining_time": "2:11:47"}
+{"current_steps": 224, "total_steps": 288, "loss": 0.2984, "lr": 1.4752035759187106e-06, "epoch": 2.331320103537532, "percentage": 77.78, "elapsed_time": "7:34:07", "remaining_time": "2:09:45"}
+{"current_steps": 225, "total_steps": 288, "loss": 0.2909, "lr": 1.4324491100246386e-06, "epoch": 2.34167385677308, "percentage": 78.12, "elapsed_time": "7:36:08", "remaining_time": "2:07:43"}
+{"current_steps": 226, "total_steps": 288, "loss": 0.2805, "lr": 1.390219530227378e-06, "epoch": 2.352027610008628, "percentage": 78.47, "elapsed_time": "7:38:07", "remaining_time": "2:05:40"}
+{"current_steps": 227, "total_steps": 288, "loss": 0.2878, "lr": 1.348521049674264e-06, "epoch": 2.362381363244176, "percentage": 78.82, "elapsed_time": "7:40:12", "remaining_time": "2:03:40"}
+{"current_steps": 228, "total_steps": 288, "loss": 0.2621, "lr": 1.3073598033731427e-06, "epoch": 2.372735116479724, "percentage": 79.17, "elapsed_time": "7:42:18", "remaining_time": "2:01:39"}
+{"current_steps": 229, "total_steps": 288, "loss": 0.2816, "lr": 1.2667418472897386e-06, "epoch": 2.3830888697152717, "percentage": 79.51, "elapsed_time": "7:44:22", "remaining_time": "1:59:38"}
+{"current_steps": 230, "total_steps": 288, "loss": 0.2571, "lr": 1.2266731574566536e-06, "epoch": 2.3934426229508197, "percentage": 79.86, "elapsed_time": "7:46:17", "remaining_time": "1:57:35"}
+{"current_steps": 231, "total_steps": 288, "loss": 0.2601, "lr": 1.1871596290941278e-06, "epoch": 2.4037963761863677, "percentage": 80.21, "elapsed_time": "7:48:24", "remaining_time": "1:55:34"}
+{"current_steps": 232, "total_steps": 288, "loss": 0.2579, "lr": 1.1482070757426855e-06, "epoch": 2.414150129421915, "percentage": 80.56, "elapsed_time": "7:50:22", "remaining_time": "1:53:32"}
+{"current_steps": 233, "total_steps": 288, "loss": 0.2751, "lr": 1.1098212284078037e-06, "epoch": 2.424503882657463, "percentage": 80.9, "elapsed_time": "7:52:20", "remaining_time": "1:51:29"}
+{"current_steps": 234, "total_steps": 288, "loss": 0.2879, "lr": 1.07200773471672e-06, "epoch": 2.434857635893011, "percentage": 81.25, "elapsed_time": "7:54:25", "remaining_time": "1:49:28"}
+{"current_steps": 235, "total_steps": 288, "loss": 0.2753, "lr": 1.0347721580875125e-06, "epoch": 2.445211389128559, "percentage": 81.6, "elapsed_time": "7:56:26", "remaining_time": "1:47:27"}
+{"current_steps": 236, "total_steps": 288, "loss": 0.2737, "lr": 9.981199769105605e-07, "epoch": 2.455565142364107, "percentage": 81.94, "elapsed_time": "7:58:28", "remaining_time": "1:45:25"}
+{"current_steps": 237, "total_steps": 288, "loss": 0.2794, "lr": 9.62056583742527e-07, "epoch": 2.4659188955996547, "percentage": 82.29, "elapsed_time": "8:00:31", "remaining_time": "1:43:24"}
+{"current_steps": 238, "total_steps": 288, "loss": 0.2887, "lr": 9.26587284512957e-07, "epoch": 2.4762726488352027, "percentage": 82.64, "elapsed_time": "8:02:29", "remaining_time": "1:41:21"}
+{"current_steps": 239, "total_steps": 288, "loss": 0.2695, "lr": 8.917172977436356e-07, "epoch": 2.4866264020707507, "percentage": 82.99, "elapsed_time": "8:04:31", "remaining_time": "1:39:20"}
+{"current_steps": 240, "total_steps": 288, "loss": 0.2767, "lr": 8.574517537807897e-07, "epoch": 2.4969801553062987, "percentage": 83.33, "elapsed_time": "8:06:28", "remaining_time": "1:37:17"}
+{"current_steps": 241, "total_steps": 288, "loss": 0.2919, "lr": 8.237956940402758e-07, "epoch": 2.5073339085418462, "percentage": 83.68, "elapsed_time": "8:08:28", "remaining_time": "1:35:15"}
+{"current_steps": 242, "total_steps": 288, "loss": 0.2378, "lr": 7.907540702658456e-07, "epoch": 2.5176876617773942, "percentage": 84.03, "elapsed_time": "8:10:34", "remaining_time": "1:33:15"}
+{"current_steps": 243, "total_steps": 288, "loss": 0.2443, "lr": 7.583317438006094e-07, "epoch": 2.528041415012942, "percentage": 84.38, "elapsed_time": "8:12:34", "remaining_time": "1:31:13"}
+{"current_steps": 244, "total_steps": 288, "loss": 0.2702, "lr": 7.265334848717931e-07, "epoch": 2.53839516824849, "percentage": 84.72, "elapsed_time": "8:14:48", "remaining_time": "1:29:13"}
+{"current_steps": 245, "total_steps": 288, "loss": 0.2805, "lr": 6.953639718889077e-07, "epoch": 2.548748921484038, "percentage": 85.07, "elapsed_time": "8:16:47", "remaining_time": "1:27:11"}
+{"current_steps": 246, "total_steps": 288, "loss": 0.2729, "lr": 6.648277907554235e-07, "epoch": 2.5591026747195857, "percentage": 85.42, "elapsed_time": "8:18:54", "remaining_time": "1:25:10"}
+{"current_steps": 247, "total_steps": 288, "loss": 0.2904, "lr": 6.349294341940593e-07, "epoch": 2.5694564279551337, "percentage": 85.76, "elapsed_time": "8:20:50", "remaining_time": "1:23:08"}
+{"current_steps": 248, "total_steps": 288, "loss": 0.2742, "lr": 6.056733010857713e-07, "epoch": 2.5798101811906817, "percentage": 86.11, "elapsed_time": "8:22:52", "remaining_time": "1:21:06"}
+{"current_steps": 249, "total_steps": 288, "loss": 0.2753, "lr": 5.770636958225617e-07, "epoch": 2.5901639344262293, "percentage": 86.46, "elapsed_time": "8:24:49", "remaining_time": "1:19:04"}
+{"current_steps": 250, "total_steps": 288, "loss": 0.2905, "lr": 5.491048276741784e-07, "epoch": 2.6005176876617773, "percentage": 86.81, "elapsed_time": "8:26:47", "remaining_time": "1:17:01"}
+{"current_steps": 251, "total_steps": 288, "loss": 0.305, "lr": 5.218008101688172e-07, "epoch": 2.6108714408973253, "percentage": 87.15, "elapsed_time": "8:28:47", "remaining_time": "1:15:00"}
+{"current_steps": 252, "total_steps": 288, "loss": 0.2827, "lr": 4.951556604879049e-07, "epoch": 2.6212251941328732, "percentage": 87.5, "elapsed_time": "8:30:43", "remaining_time": "1:12:57"}
+{"current_steps": 253, "total_steps": 288, "loss": 0.2875, "lr": 4.6917329887506133e-07, "epoch": 2.6315789473684212, "percentage": 87.85, "elapsed_time": "8:32:45", "remaining_time": "1:10:56"}
+{"current_steps": 254, "total_steps": 288, "loss": 0.263, "lr": 4.43857548059321e-07, "epoch": 2.641932700603969, "percentage": 88.19, "elapsed_time": "8:34:41", "remaining_time": "1:08:53"}
+{"current_steps": 255, "total_steps": 288, "loss": 0.283, "lr": 4.192121326927073e-07, "epoch": 2.6522864538395168, "percentage": 88.54, "elapsed_time": "8:36:44", "remaining_time": "1:06:52"}
+{"current_steps": 256, "total_steps": 288, "loss": 0.2675, "lr": 3.952406788022267e-07, "epoch": 2.6626402070750648, "percentage": 88.89, "elapsed_time": "8:38:46", "remaining_time": "1:04:50"}
+{"current_steps": 257, "total_steps": 288, "loss": 0.2798, "lr": 3.71946713256382e-07, "epoch": 2.6729939603106128, "percentage": 89.24, "elapsed_time": "8:40:48", "remaining_time": "1:02:49"}
+{"current_steps": 258, "total_steps": 288, "loss": 0.2981, "lr": 3.4933366324627183e-07, "epoch": 2.6833477135461603, "percentage": 89.58, "elapsed_time": "8:42:45", "remaining_time": "1:00:47"}
+{"current_steps": 259, "total_steps": 288, "loss": 0.2517, "lr": 3.274048557813553e-07, "epoch": 2.6937014667817083, "percentage": 89.93, "elapsed_time": "8:44:42", "remaining_time": "0:58:45"}
+{"current_steps": 260, "total_steps": 288, "loss": 0.2628, "lr": 3.061635171999566e-07, "epoch": 2.7040552200172563, "percentage": 90.28, "elapsed_time": "8:46:39", "remaining_time": "0:56:42"}
+{"current_steps": 261, "total_steps": 288, "loss": 0.2717, "lr": 2.85612772694579e-07, "epoch": 2.7144089732528043, "percentage": 90.62, "elapsed_time": "8:48:39", "remaining_time": "0:54:41"}
+{"current_steps": 262, "total_steps": 288, "loss": 0.2682, "lr": 2.6575564585210487e-07, "epoch": 2.7247627264883523, "percentage": 90.97, "elapsed_time": "8:50:39", "remaining_time": "0:52:39"}
+{"current_steps": 263, "total_steps": 288, "loss": 0.2774, "lr": 2.4659505820893827e-07, "epoch": 2.7351164797239, "percentage": 91.32, "elapsed_time": "8:52:42", "remaining_time": "0:50:38"}
+{"current_steps": 264, "total_steps": 288, "loss": 0.2738, "lr": 2.2813382882116986e-07, "epoch": 2.745470232959448, "percentage": 91.67, "elapsed_time": "8:54:50", "remaining_time": "0:48:37"}
+{"current_steps": 265, "total_steps": 288, "loss": 0.2721, "lr": 2.1037467384981024e-07, "epoch": 2.755823986194996, "percentage": 92.01, "elapsed_time": "8:56:48", "remaining_time": "0:46:35"}
+{"current_steps": 266, "total_steps": 288, "loss": 0.2744, "lr": 1.933202061611722e-07, "epoch": 2.7661777394305433, "percentage": 92.36, "elapsed_time": "8:58:48", "remaining_time": "0:44:33"}
+{"current_steps": 267, "total_steps": 288, "loss": 0.2625, "lr": 1.769729349424415e-07, "epoch": 2.7765314926660913, "percentage": 92.71, "elapsed_time": "9:00:51", "remaining_time": "0:42:32"}
+{"current_steps": 268, "total_steps": 288, "loss": 0.2459, "lr": 1.6133526533250566e-07, "epoch": 2.7868852459016393, "percentage": 93.06, "elapsed_time": "9:02:53", "remaining_time": "0:40:30"}
+{"current_steps": 269, "total_steps": 288, "loss": 0.2688, "lr": 1.4640949806809523e-07, "epoch": 2.7972389991371873, "percentage": 93.4, "elapsed_time": "9:05:04", "remaining_time": "0:38:29"}
+{"current_steps": 270, "total_steps": 288, "loss": 0.2562, "lr": 1.3219782914527633e-07, "epoch": 2.8075927523727353, "percentage": 93.75, "elapsed_time": "9:07:07", "remaining_time": "0:36:28"}
+{"current_steps": 271, "total_steps": 288, "loss": 0.2861, "lr": 1.1870234949636072e-07, "epoch": 2.817946505608283, "percentage": 94.1, "elapsed_time": "9:09:11", "remaining_time": "0:34:27"}
+{"current_steps": 272, "total_steps": 288, "loss": 0.2618, "lr": 1.0592504468227127e-07, "epoch": 2.828300258843831, "percentage": 94.44, "elapsed_time": "9:11:10", "remaining_time": "0:32:25"}
+{"current_steps": 273, "total_steps": 288, "loss": 0.2793, "lr": 9.386779460041018e-08, "epoch": 2.838654012079379, "percentage": 94.79, "elapsed_time": "9:13:12", "remaining_time": "0:30:23"}
+{"current_steps": 274, "total_steps": 288, "loss": 0.2808, "lr": 8.253237320807461e-08, "epoch": 2.8490077653149264, "percentage": 95.14, "elapsed_time": "9:15:15", "remaining_time": "0:28:22"}
+{"current_steps": 275, "total_steps": 288, "loss": 0.2673, "lr": 7.192044826145772e-08, "epoch": 2.8593615185504744, "percentage": 95.49, "elapsed_time": "9:17:12", "remaining_time": "0:26:20"}
+{"current_steps": 276, "total_steps": 288, "loss": 0.2675, "lr": 6.203358107027491e-08, "epoch": 2.8697152717860224, "percentage": 95.83, "elapsed_time": "9:19:25", "remaining_time": "0:24:19"}
+{"current_steps": 277, "total_steps": 288, "loss": 0.2798, "lr": 5.2873226268052026e-08, "epoch": 2.8800690250215704, "percentage": 96.18, "elapsed_time": "9:21:23", "remaining_time": "0:22:17"}
+{"current_steps": 278, "total_steps": 288, "loss": 0.2631, "lr": 4.444073159810769e-08, "epoch": 2.8904227782571184, "percentage": 96.53, "elapsed_time": "9:23:20", "remaining_time": "0:20:15"}
+{"current_steps": 279, "total_steps": 288, "loss": 0.2769, "lr": 3.673733771526466e-08, "epoch": 2.9007765314926663, "percentage": 96.88, "elapsed_time": "9:25:18", "remaining_time": "0:18:14"}
+{"current_steps": 280, "total_steps": 288, "loss": 0.2695, "lr": 2.976417800331144e-08, "epoch": 2.911130284728214, "percentage": 97.22, "elapsed_time": "9:27:18", "remaining_time": "0:16:12"}
+{"current_steps": 281, "total_steps": 288, "loss": 0.2908, "lr": 2.352227840825394e-08, "epoch": 2.921484037963762, "percentage": 97.57, "elapsed_time": "9:29:16", "remaining_time": "0:14:10"}
+{"current_steps": 282, "total_steps": 288, "loss": 0.2741, "lr": 1.8012557287367394e-08, "epoch": 2.93183779119931, "percentage": 97.92, "elapsed_time": "9:31:52", "remaining_time": "0:12:10"}
+{"current_steps": 283, "total_steps": 288, "loss": 0.2374, "lr": 1.3235825274081626e-08, "epoch": 2.9421915444348574, "percentage": 98.26, "elapsed_time": "9:33:53", "remaining_time": "0:10:08"}
+{"current_steps": 284, "total_steps": 288, "loss": 0.2781, "lr": 9.192785158713691e-09, "epoch": 2.9525452976704054, "percentage": 98.61, "elapsed_time": "9:35:52", "remaining_time": "0:08:06"}
+{"current_steps": 285, "total_steps": 288, "loss": 0.2618, "lr": 5.884031785068356e-09, "epoch": 2.9628990509059534, "percentage": 98.96, "elapsed_time": "9:37:53", "remaining_time": "0:06:04"}
+{"current_steps": 286, "total_steps": 288, "loss": 0.2675, "lr": 3.3100519629203353e-09, "epoch": 2.9732528041415014, "percentage": 99.31, "elapsed_time": "9:40:00", "remaining_time": "0:04:03"}
+{"current_steps": 287, "total_steps": 288, "loss": 0.2651, "lr": 1.471224396389359e-09, "epoch": 2.9836065573770494, "percentage": 99.65, "elapsed_time": "9:41:56", "remaining_time": "0:02:01"}
+{"current_steps": 288, "total_steps": 288, "loss": 0.2605, "lr": 3.678196282252966e-10, "epoch": 2.993960310612597, "percentage": 100.0, "elapsed_time": "9:44:00", "remaining_time": "0:00:00"}
+{"current_steps": 288, "total_steps": 288, "epoch": 2.993960310612597, "percentage": 100.0, "elapsed_time": "9:48:49", "remaining_time": "0:00:00"}