Training in progress, step 273

model-00001-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:243de2276529eadec36d7d5e8d3dcbaa89326a8872e9b5d659cbe4250032a864
+oid sha256:5b4241b416b5fca87541fc548410ba16fe21633b4b03374c83fdf4cbcc74246f
 size 4891730992

model-00002-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58f817725244d171dfc8626fbcd72457a7cd931bb9f7de96cfa2f72e45b9d9e8
+oid sha256:1f2af299f24f6fbd5dbe89436a418e91991b48b82a16cb3e826682b03b8254aa
 size 4876059352

model-00003-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c63131c16f91372f31005277cb17eb74c2a32d1690418feb0bf72239232526c8
+oid sha256:09836acb0485bb517326f3bca182bd5130321cb98828b47857fc0a8662307989
 size 4876059384

model-00004-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c039915170604a7f87a22a1b638aa2ccc10cd95a32e6f2458fe49a4460cc167
+oid sha256:1ddca811b47b4e2afccfbf24b942dc7a74a7288b901ca4188e95a908bb16c2d0
 size 4876059416

model-00005-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e5021f316cc23ccee03d2658e8bc98c37e5de05d41201131ce0bb6b9768e1a8
+oid sha256:d262282f992b23243aa1b2ca15f949d7469ea4a63353d3f3506522e44971724a
 size 4876059416

model-00006-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5f6d4448875ea03eecf5d30800ad12bc8e3183ea3e89dfd867b4b9034300ca6
+oid sha256:782cfc179860cb3661ce0a65efa454d360c41f3fc2891e4185536c214fc20cfc
 size 4876059416

model-00007-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7671a0171343e0a3a46441ee06d27d0f1995d6cd59c2904245b8c783e75b93b
+oid sha256:00154b4f4108239b98075ff00063e90701421be877f81b3b276e9e0a01c0fa49
 size 4876059416

model-00008-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:442f8fe09dac3b9e42ff1855fbcfe27baea15a0ca37474e95284770db94cce5d
+oid sha256:d95b93ed84dad7a7a31558b9cfc3c5f1f6941a4ecaf4e5637827d8012a8fad90
 size 4876059416

model-00009-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cf0ba6575a763dc665aa6dbeb658217f4e5c2cf2fe5fcd6bd7ef783e470c90b
+oid sha256:9c165a55faf9d4852ea4b329fa4eb7f4226aeeb1fc4904991f7dc00992b3aa26
 size 4876059416

model-00010-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e45b2447db5c7d5f9a26a3839690fac77655459698993dbb92acd55db4459656
+oid sha256:5834cfa71f41bdb87ac95533218326dfceecaa837dec76e04d19c58903ba4d56
 size 4876059416

model-00011-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7aa3a093f50e4dbd496210d1f8e00625fb6ab55c31fd72e03d37f1af58f9637
+oid sha256:4294fd249a262dfeb3ef31d952f1d6354a5837f31303afed264a3061312a826f
 size 4876059416

model-00012-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3776acc12be290756b5aa2cd5a2e5d418d8d100a969026837a4cd971ed43c5e
+oid sha256:b248c36618ac8cb067dd109d32af693d6b529ae33e2d36908384c3b8d1f1b453
 size 4876059416

model-00013-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bfd92b73d631697d90421cdd1ada8ea90bd44abca6833b69fbd37dbdee0e9e2
+oid sha256:98e2585b326b0d2163e7ee4184966a182dcff45cf7b45bc01d698c964c76bac9
 size 4876059416

model-00014-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67f0835f7947b8025f56381cadbae8b0c80e895e99ce8d0e89ba87216252df6e
+oid sha256:8da1a7633d6c609729bcba723334174b198384895acb2a5766122cdf9edc61c4
 size 2123397800

trainer_log.jsonl

@@ -200,3 +200,75 @@
 {"current_steps": 200, "total_steps": 273, "loss": 1.0781, "lr": 9.176822866112988e-06, "epoch": 0.7315957933241883, "percentage": 73.26, "elapsed_time": "12:01:03", "remaining_time": "4:23:11"}
 {"current_steps": 201, "total_steps": 273, "loss": 1.0589, "lr": 8.943218808746603e-06, "epoch": 0.7352537722908093, "percentage": 73.63, "elapsed_time": "12:12:10", "remaining_time": "4:22:16"}
 {"current_steps": 202, "total_steps": 273, "loss": 1.0627, "lr": 8.711977151095524e-06, "epoch": 0.7389117512574302, "percentage": 73.99, "elapsed_time": "12:15:45", "remaining_time": "4:18:36"}
+{"current_steps": 203, "total_steps": 273, "loss": 1.0707, "lr": 8.483131915247968e-06, "epoch": 0.7425697302240513, "percentage": 74.36, "elapsed_time": "12:19:21", "remaining_time": "4:14:56"}
+{"current_steps": 204, "total_steps": 273, "loss": 1.0637, "lr": 8.256716770711764e-06, "epoch": 0.7462277091906722, "percentage": 74.73, "elapsed_time": "12:22:55", "remaining_time": "4:11:16"}
+{"current_steps": 205, "total_steps": 273, "loss": 1.0806, "lr": 8.032765029460625e-06, "epoch": 0.7498856881572931, "percentage": 75.09, "elapsed_time": "12:26:29", "remaining_time": "4:07:37"}
+{"current_steps": 206, "total_steps": 273, "loss": 1.0466, "lr": 7.811309641033041e-06, "epoch": 0.7535436671239141, "percentage": 75.46, "elapsed_time": "12:30:08", "remaining_time": "4:03:58"}
+{"current_steps": 207, "total_steps": 273, "loss": 1.0805, "lr": 7.592383187684457e-06, "epoch": 0.757201646090535, "percentage": 75.82, "elapsed_time": "12:33:43", "remaining_time": "4:00:19"}
+{"current_steps": 208, "total_steps": 273, "loss": 1.098, "lr": 7.376017879593553e-06, "epoch": 0.7608596250571559, "percentage": 76.19, "elapsed_time": "12:37:19", "remaining_time": "3:56:39"}
+{"current_steps": 209, "total_steps": 273, "loss": 1.0872, "lr": 7.1622455501231925e-06, "epoch": 0.7645176040237769, "percentage": 76.56, "elapsed_time": "12:40:53", "remaining_time": "3:53:00"}
+{"current_steps": 210, "total_steps": 273, "loss": 1.0892, "lr": 6.951097651136889e-06, "epoch": 0.7681755829903978, "percentage": 76.92, "elapsed_time": "12:44:28", "remaining_time": "3:49:20"}
+{"current_steps": 211, "total_steps": 273, "loss": 1.0703, "lr": 6.74260524837132e-06, "epoch": 0.7718335619570188, "percentage": 77.29, "elapsed_time": "12:48:06", "remaining_time": "3:45:42"}
+{"current_steps": 212, "total_steps": 273, "loss": 1.0825, "lr": 6.536799016865713e-06, "epoch": 0.7754915409236397, "percentage": 77.66, "elapsed_time": "12:51:40", "remaining_time": "3:42:02"}
+{"current_steps": 213, "total_steps": 273, "loss": 1.054, "lr": 6.333709236448693e-06, "epoch": 0.7791495198902606, "percentage": 78.02, "elapsed_time": "12:55:18", "remaining_time": "3:38:23"}
+{"current_steps": 214, "total_steps": 273, "loss": 1.0677, "lr": 6.133365787283268e-06, "epoch": 0.7828074988568816, "percentage": 78.39, "elapsed_time": "12:58:54", "remaining_time": "3:34:44"}
+{"current_steps": 215, "total_steps": 273, "loss": 1.0539, "lr": 5.935798145470639e-06, "epoch": 0.7864654778235025, "percentage": 78.75, "elapsed_time": "13:02:30", "remaining_time": "3:31:05"}
+{"current_steps": 216, "total_steps": 273, "loss": 1.0623, "lr": 5.741035378713428e-06, "epoch": 0.7901234567901234, "percentage": 79.12, "elapsed_time": "13:06:06", "remaining_time": "3:27:26"}
+{"current_steps": 217, "total_steps": 273, "loss": 1.0866, "lr": 5.549106142039018e-06, "epoch": 0.7937814357567444, "percentage": 79.49, "elapsed_time": "13:09:43", "remaining_time": "3:23:48"}
+{"current_steps": 218, "total_steps": 273, "loss": 1.0728, "lr": 5.360038673583601e-06, "epoch": 0.7974394147233653, "percentage": 79.85, "elapsed_time": "13:13:22", "remaining_time": "3:20:09"}
+{"current_steps": 219, "total_steps": 273, "loss": 1.0333, "lr": 5.173860790437563e-06, "epoch": 0.8010973936899863, "percentage": 80.22, "elapsed_time": "13:17:00", "remaining_time": "3:16:31"}
+{"current_steps": 220, "total_steps": 273, "loss": 1.0556, "lr": 4.990599884552802e-06, "epoch": 0.8047553726566072, "percentage": 80.59, "elapsed_time": "13:20:36", "remaining_time": "3:12:52"}
+{"current_steps": 221, "total_steps": 273, "loss": 1.0908, "lr": 4.8102829187126355e-06, "epoch": 0.8084133516232281, "percentage": 80.95, "elapsed_time": "13:24:15", "remaining_time": "3:09:14"}
+{"current_steps": 222, "total_steps": 273, "loss": 1.0702, "lr": 4.632936422564785e-06, "epoch": 0.8120713305898491, "percentage": 81.32, "elapsed_time": "13:27:51", "remaining_time": "3:05:35"}
+{"current_steps": 223, "total_steps": 273, "loss": 1.0651, "lr": 4.458586488718178e-06, "epoch": 0.81572930955647, "percentage": 81.68, "elapsed_time": "13:31:28", "remaining_time": "3:01:56"}
+{"current_steps": 224, "total_steps": 273, "loss": 1.0798, "lr": 4.2872587689039484e-06, "epoch": 0.819387288523091, "percentage": 82.05, "elapsed_time": "13:35:05", "remaining_time": "2:58:18"}
+{"current_steps": 225, "total_steps": 273, "loss": 1.0739, "lr": 4.118978470201379e-06, "epoch": 0.823045267489712, "percentage": 82.42, "elapsed_time": "13:38:42", "remaining_time": "2:54:39"}
+{"current_steps": 226, "total_steps": 273, "loss": 1.0608, "lr": 3.953770351329228e-06, "epoch": 0.8267032464563329, "percentage": 82.78, "elapsed_time": "13:42:18", "remaining_time": "2:51:00"}
+{"current_steps": 227, "total_steps": 273, "loss": 1.0827, "lr": 3.7916587190030467e-06, "epoch": 0.8303612254229538, "percentage": 83.15, "elapsed_time": "13:45:54", "remaining_time": "2:47:21"}
+{"current_steps": 228, "total_steps": 273, "loss": 1.0715, "lr": 3.6326674243589653e-06, "epoch": 0.8340192043895748, "percentage": 83.52, "elapsed_time": "13:49:29", "remaining_time": "2:43:42"}
+{"current_steps": 229, "total_steps": 273, "loss": 1.068, "lr": 3.476819859444538e-06, "epoch": 0.8376771833561957, "percentage": 83.88, "elapsed_time": "13:53:09", "remaining_time": "2:40:05"}
+{"current_steps": 230, "total_steps": 273, "loss": 1.0859, "lr": 3.3241389537771174e-06, "epoch": 0.8413351623228167, "percentage": 84.25, "elapsed_time": "13:56:42", "remaining_time": "2:36:25"}
+{"current_steps": 231, "total_steps": 273, "loss": 1.0818, "lr": 3.1746471709702964e-06, "epoch": 0.8449931412894376, "percentage": 84.62, "elapsed_time": "14:00:16", "remaining_time": "2:32:46"}
+{"current_steps": 232, "total_steps": 273, "loss": 1.0371, "lr": 3.028366505428856e-06, "epoch": 0.8486511202560585, "percentage": 84.98, "elapsed_time": "14:03:48", "remaining_time": "2:29:07"}
+{"current_steps": 233, "total_steps": 273, "loss": 1.1001, "lr": 2.8853184791128086e-06, "epoch": 0.8523090992226795, "percentage": 85.35, "elapsed_time": "14:07:21", "remaining_time": "2:25:28"}
+{"current_steps": 234, "total_steps": 273, "loss": 1.0495, "lr": 2.745524138370892e-06, "epoch": 0.8559670781893004, "percentage": 85.71, "elapsed_time": "14:10:53", "remaining_time": "2:21:48"}
+{"current_steps": 235, "total_steps": 273, "loss": 1.0614, "lr": 2.6090040508440857e-06, "epoch": 0.8596250571559213, "percentage": 86.08, "elapsed_time": "14:14:25", "remaining_time": "2:18:09"}
+{"current_steps": 236, "total_steps": 273, "loss": 1.0881, "lr": 2.475778302439524e-06, "epoch": 0.8632830361225423, "percentage": 86.45, "elapsed_time": "14:17:58", "remaining_time": "2:14:30"}
+{"current_steps": 237, "total_steps": 273, "loss": 1.0753, "lr": 2.345866494375307e-06, "epoch": 0.8669410150891632, "percentage": 86.81, "elapsed_time": "14:21:38", "remaining_time": "2:10:52"}
+{"current_steps": 238, "total_steps": 273, "loss": 1.0512, "lr": 2.219287740296605e-06, "epoch": 0.8705989940557842, "percentage": 87.18, "elapsed_time": "14:25:10", "remaining_time": "2:07:13"}
+{"current_steps": 239, "total_steps": 273, "loss": 1.085, "lr": 2.0960606634635365e-06, "epoch": 0.8742569730224051, "percentage": 87.55, "elapsed_time": "14:28:48", "remaining_time": "2:03:35"}
+{"current_steps": 240, "total_steps": 273, "loss": 1.0602, "lr": 1.9762033940111335e-06, "epoch": 0.877914951989026, "percentage": 87.91, "elapsed_time": "14:32:21", "remaining_time": "1:59:56"}
+{"current_steps": 241, "total_steps": 273, "loss": 1.0696, "lr": 1.8597335662819099e-06, "epoch": 0.881572930955647, "percentage": 88.28, "elapsed_time": "14:35:55", "remaining_time": "1:56:18"}
+{"current_steps": 242, "total_steps": 273, "loss": 1.0706, "lr": 1.746668316231359e-06, "epoch": 0.8852309099222679, "percentage": 88.64, "elapsed_time": "14:39:27", "remaining_time": "1:52:39"}
+{"current_steps": 243, "total_steps": 273, "loss": 1.103, "lr": 1.6370242789067764e-06, "epoch": 0.8888888888888888, "percentage": 89.01, "elapsed_time": "14:43:03", "remaining_time": "1:49:01"}
+{"current_steps": 244, "total_steps": 273, "loss": 1.0722, "lr": 1.530817585999783e-06, "epoch": 0.8925468678555099, "percentage": 89.38, "elapsed_time": "14:46:37", "remaining_time": "1:45:22"}
+{"current_steps": 245, "total_steps": 273, "loss": 1.0671, "lr": 1.428063863472895e-06, "epoch": 0.8962048468221308, "percentage": 89.74, "elapsed_time": "14:50:10", "remaining_time": "1:41:44"}
+{"current_steps": 246, "total_steps": 273, "loss": 1.0957, "lr": 1.3287782292605245e-06, "epoch": 0.8998628257887518, "percentage": 90.11, "elapsed_time": "14:53:48", "remaining_time": "1:38:06"}
+{"current_steps": 247, "total_steps": 273, "loss": 1.0343, "lr": 1.2329752910446913e-06, "epoch": 0.9035208047553727, "percentage": 90.48, "elapsed_time": "14:57:22", "remaining_time": "1:34:27"}
+{"current_steps": 248, "total_steps": 273, "loss": 1.0584, "lr": 1.1406691441058493e-06, "epoch": 0.9071787837219936, "percentage": 90.84, "elapsed_time": "15:00:54", "remaining_time": "1:30:49"}
+{"current_steps": 249, "total_steps": 273, "loss": 1.0421, "lr": 1.0518733692490513e-06, "epoch": 0.9108367626886146, "percentage": 91.21, "elapsed_time": "15:04:26", "remaining_time": "1:27:10"}
+{"current_steps": 250, "total_steps": 273, "loss": 1.057, "lr": 9.66601030805861e-07, "epoch": 0.9144947416552355, "percentage": 91.58, "elapsed_time": "15:08:05", "remaining_time": "1:23:32"}
+{"current_steps": 251, "total_steps": 273, "loss": 1.0751, "lr": 8.848646747122075e-07, "epoch": 0.9181527206218564, "percentage": 91.94, "elapsed_time": "15:11:43", "remaining_time": "1:19:54"}
+{"current_steps": 252, "total_steps": 273, "loss": 1.0533, "lr": 8.066763266625282e-07, "epoch": 0.9218106995884774, "percentage": 92.31, "elapsed_time": "15:15:20", "remaining_time": "1:16:16"}
+{"current_steps": 253, "total_steps": 273, "loss": 1.0718, "lr": 7.320474903404762e-07, "epoch": 0.9254686785550983, "percentage": 92.67, "elapsed_time": "15:18:54", "remaining_time": "1:12:38"}
+{"current_steps": 254, "total_steps": 273, "loss": 1.0668, "lr": 6.609891457263817e-07, "epoch": 0.9291266575217193, "percentage": 93.04, "elapsed_time": "15:22:32", "remaining_time": "1:09:00"}
+{"current_steps": 255, "total_steps": 273, "loss": 1.0688, "lr": 5.935117474818036e-07, "epoch": 0.9327846364883402, "percentage": 93.41, "elapsed_time": "15:26:12", "remaining_time": "1:05:22"}
+{"current_steps": 256, "total_steps": 273, "loss": 1.0612, "lr": 5.296252234113564e-07, "epoch": 0.9364426154549611, "percentage": 93.77, "elapsed_time": "15:29:49", "remaining_time": "1:01:44"}
+{"current_steps": 257, "total_steps": 273, "loss": 1.0607, "lr": 4.6933897300205085e-07, "epoch": 0.9401005944215821, "percentage": 94.14, "elapsed_time": "15:33:24", "remaining_time": "0:58:06"}
+{"current_steps": 258, "total_steps": 273, "loss": 1.0678, "lr": 4.1266186604037307e-07, "epoch": 0.943758573388203, "percentage": 94.51, "elapsed_time": "15:36:57", "remaining_time": "0:54:28"}
+{"current_steps": 259, "total_steps": 273, "loss": 1.0511, "lr": 3.5960224130728857e-07, "epoch": 0.9474165523548239, "percentage": 94.87, "elapsed_time": "15:40:32", "remaining_time": "0:50:50"}
+{"current_steps": 260, "total_steps": 273, "loss": 1.0586, "lr": 3.101679053513745e-07, "epoch": 0.9510745313214449, "percentage": 95.24, "elapsed_time": "15:44:04", "remaining_time": "0:47:12"}
+{"current_steps": 261, "total_steps": 273, "loss": 1.0655, "lr": 2.643661313402601e-07, "epoch": 0.9547325102880658, "percentage": 95.6, "elapsed_time": "15:47:37", "remaining_time": "0:43:34"}
+{"current_steps": 262, "total_steps": 273, "loss": 1.0519, "lr": 2.2220365799053843e-07, "epoch": 0.9583904892546868, "percentage": 95.97, "elapsed_time": "15:51:10", "remaining_time": "0:39:56"}
+{"current_steps": 263, "total_steps": 273, "loss": 1.097, "lr": 1.836866885763233e-07, "epoch": 0.9620484682213077, "percentage": 96.34, "elapsed_time": "15:54:48", "remaining_time": "0:36:18"}
+{"current_steps": 264, "total_steps": 273, "loss": 1.0564, "lr": 1.488208900165572e-07, "epoch": 0.9657064471879286, "percentage": 96.7, "elapsed_time": "15:58:21", "remaining_time": "0:32:40"}
+{"current_steps": 265, "total_steps": 273, "loss": 1.0683, "lr": 1.176113920412697e-07, "epoch": 0.9693644261545497, "percentage": 97.07, "elapsed_time": "16:01:53", "remaining_time": "0:29:02"}
+{"current_steps": 266, "total_steps": 273, "loss": 1.0648, "lr": 9.006278643683696e-08, "epoch": 0.9730224051211706, "percentage": 97.44, "elapsed_time": "16:05:25", "remaining_time": "0:25:24"}
+{"current_steps": 267, "total_steps": 273, "loss": 1.0781, "lr": 6.617912637040812e-08, "epoch": 0.9766803840877915, "percentage": 97.8, "elapsed_time": "16:09:02", "remaining_time": "0:21:46"}
+{"current_steps": 268, "total_steps": 273, "loss": 1.0615, "lr": 4.596392579356845e-08, "epoch": 0.9803383630544125, "percentage": 98.17, "elapsed_time": "16:12:34", "remaining_time": "0:18:08"}
+{"current_steps": 269, "total_steps": 273, "loss": 1.0623, "lr": 2.9420158925341777e-08, "epoch": 0.9839963420210334, "percentage": 98.53, "elapsed_time": "16:16:07", "remaining_time": "0:14:30"}
+{"current_steps": 270, "total_steps": 273, "loss": 1.0464, "lr": 1.6550259814601676e-08, "epoch": 0.9876543209876543, "percentage": 98.9, "elapsed_time": "16:19:40", "remaining_time": "0:10:53"}
+{"current_steps": 271, "total_steps": 273, "loss": 1.0607, "lr": 7.356121981946795e-09, "epoch": 0.9913122999542753, "percentage": 99.27, "elapsed_time": "16:23:15", "remaining_time": "0:07:15"}
+{"current_steps": 272, "total_steps": 273, "loss": 1.0465, "lr": 1.8390981411264829e-09, "epoch": 0.9949702789208962, "percentage": 99.63, "elapsed_time": "16:26:47", "remaining_time": "0:03:37"}
+{"current_steps": 273, "total_steps": 273, "loss": 1.0636, "lr": 0.0, "epoch": 0.9986282578875172, "percentage": 100.0, "elapsed_time": "16:30:21", "remaining_time": "0:00:00"}
+{"current_steps": 273, "total_steps": 273, "epoch": 0.9986282578875172, "percentage": 100.0, "elapsed_time": "16:37:51", "remaining_time": "0:00:00"}