penfever commited on
Commit
31d1cc5
·
verified ·
1 Parent(s): 77138a0

Training in progress, step 6400

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87bbd19b2ccb69af85de2a0cf4ba1914c1db8a0d78b0112bdd446e608beaf7a1
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d548a2ee9fc642d02fd9085888be8affca91fdf00f3b652764c781fb0c568c71
3
  size 4902257696
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a81ffeed483f542bab9a55860c931e7a1f8ea0932fee684a2d4dd39cf154f2e
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21a145f956812dc85d700625ce766231970fd84ab5bad5a2c5d1b1dd30a82ffe
3
  size 4915960368
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0b037cb5fa7d20f5e27e90f7808267159fc6624b524b2196c32dfcbb46968e7
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e454dafbdd6b83d09445c352c1c2ba7b562bd661ac2d4d72df2fe21948da26b
3
  size 4983068496
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0720b1e53a639717f69adf8c263a538a84cc23653d848ca3f378af550dfe7cdd
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33a2537d08aa5dcb9cdcacd97fab3c10ade90003d223e61bed18c9d86e374fea
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -1240,3 +1240,45 @@
1240
  {"current_steps": 6200, "total_steps": 9128, "loss": 0.2022, "lr": 1.1288377878377514e-05, "epoch": 4.754890678941312, "percentage": 67.92, "elapsed_time": "1 day, 14:24:18", "remaining_time": "18:08:13"}
1241
  {"current_steps": 6205, "total_steps": 9128, "loss": 0.2003, "lr": 1.1253970172802276e-05, "epoch": 4.758726505561949, "percentage": 67.98, "elapsed_time": "1 day, 14:27:11", "remaining_time": "18:06:51"}
1242
  {"current_steps": 6210, "total_steps": 9128, "loss": 0.1865, "lr": 1.121959444405941e-05, "epoch": 4.762562332182585, "percentage": 68.03, "elapsed_time": "1 day, 14:28:52", "remaining_time": "18:04:54"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1240
  {"current_steps": 6200, "total_steps": 9128, "loss": 0.2022, "lr": 1.1288377878377514e-05, "epoch": 4.754890678941312, "percentage": 67.92, "elapsed_time": "1 day, 14:24:18", "remaining_time": "18:08:13"}
1241
  {"current_steps": 6205, "total_steps": 9128, "loss": 0.2003, "lr": 1.1253970172802276e-05, "epoch": 4.758726505561949, "percentage": 67.98, "elapsed_time": "1 day, 14:27:11", "remaining_time": "18:06:51"}
1242
  {"current_steps": 6210, "total_steps": 9128, "loss": 0.1865, "lr": 1.121959444405941e-05, "epoch": 4.762562332182585, "percentage": 68.03, "elapsed_time": "1 day, 14:28:52", "remaining_time": "18:04:54"}
1243
+ {"current_steps": 6215, "total_steps": 9128, "loss": 0.2209, "lr": 1.1185250817831879e-05, "epoch": 4.766398158803222, "percentage": 68.09, "elapsed_time": "1 day, 14:30:33", "remaining_time": "18:02:58"}
1244
+ {"current_steps": 6220, "total_steps": 9128, "loss": 0.2005, "lr": 1.1150939419685268e-05, "epoch": 4.770233985423859, "percentage": 68.14, "elapsed_time": "1 day, 14:32:22", "remaining_time": "18:01:05"}
1245
+ {"current_steps": 6225, "total_steps": 9128, "loss": 0.2163, "lr": 1.1116660375067336e-05, "epoch": 4.7740698120444955, "percentage": 68.2, "elapsed_time": "1 day, 14:34:07", "remaining_time": "17:59:11"}
1246
+ {"current_steps": 6230, "total_steps": 9128, "loss": 0.2083, "lr": 1.1082413809307551e-05, "epoch": 4.777905638665132, "percentage": 68.25, "elapsed_time": "1 day, 14:35:53", "remaining_time": "17:57:16"}
1247
+ {"current_steps": 6235, "total_steps": 9128, "loss": 0.2147, "lr": 1.1048199847616634e-05, "epoch": 4.781741465285769, "percentage": 68.31, "elapsed_time": "1 day, 14:37:34", "remaining_time": "17:55:20"}
1248
+ {"current_steps": 6240, "total_steps": 9128, "loss": 0.2073, "lr": 1.10140186150861e-05, "epoch": 4.785577291906406, "percentage": 68.36, "elapsed_time": "1 day, 14:39:16", "remaining_time": "17:53:24"}
1249
+ {"current_steps": 6245, "total_steps": 9128, "loss": 0.2007, "lr": 1.0979870236687798e-05, "epoch": 4.789413118527042, "percentage": 68.42, "elapsed_time": "1 day, 14:40:55", "remaining_time": "17:51:27"}
1250
+ {"current_steps": 6250, "total_steps": 9128, "loss": 0.1979, "lr": 1.0945754837273461e-05, "epoch": 4.793248945147679, "percentage": 68.47, "elapsed_time": "1 day, 14:42:33", "remaining_time": "17:49:29"}
1251
+ {"current_steps": 6255, "total_steps": 9128, "loss": 0.1968, "lr": 1.0911672541574245e-05, "epoch": 4.797084771768316, "percentage": 68.53, "elapsed_time": "1 day, 14:44:10", "remaining_time": "17:47:31"}
1252
+ {"current_steps": 6260, "total_steps": 9128, "loss": 0.1927, "lr": 1.0877623474200273e-05, "epoch": 4.800920598388953, "percentage": 68.58, "elapsed_time": "1 day, 14:45:49", "remaining_time": "17:45:34"}
1253
+ {"current_steps": 6265, "total_steps": 9128, "loss": 0.1942, "lr": 1.0843607759640182e-05, "epoch": 4.8047564250095895, "percentage": 68.63, "elapsed_time": "1 day, 14:47:32", "remaining_time": "17:43:39"}
1254
+ {"current_steps": 6270, "total_steps": 9128, "loss": 0.1821, "lr": 1.0809625522260663e-05, "epoch": 4.808592251630226, "percentage": 68.69, "elapsed_time": "1 day, 14:49:09", "remaining_time": "17:41:40"}
1255
+ {"current_steps": 6275, "total_steps": 9128, "loss": 0.1983, "lr": 1.0775676886306013e-05, "epoch": 4.812428078250863, "percentage": 68.74, "elapsed_time": "1 day, 14:50:48", "remaining_time": "17:39:43"}
1256
+ {"current_steps": 6280, "total_steps": 9128, "loss": 0.2244, "lr": 1.0741761975897671e-05, "epoch": 4.8162639048715, "percentage": 68.8, "elapsed_time": "1 day, 14:52:26", "remaining_time": "17:37:46"}
1257
+ {"current_steps": 6285, "total_steps": 9128, "loss": 0.1976, "lr": 1.0707880915033777e-05, "epoch": 4.820099731492137, "percentage": 68.85, "elapsed_time": "1 day, 14:54:06", "remaining_time": "17:35:49"}
1258
+ {"current_steps": 6290, "total_steps": 9128, "loss": 0.2066, "lr": 1.067403382758871e-05, "epoch": 4.823935558112773, "percentage": 68.91, "elapsed_time": "1 day, 14:55:44", "remaining_time": "17:33:52"}
1259
+ {"current_steps": 6295, "total_steps": 9128, "loss": 0.1995, "lr": 1.0640220837312634e-05, "epoch": 4.82777138473341, "percentage": 68.96, "elapsed_time": "1 day, 14:57:23", "remaining_time": "17:31:55"}
1260
+ {"current_steps": 6300, "total_steps": 9128, "loss": 0.2079, "lr": 1.060644206783105e-05, "epoch": 4.831607211354047, "percentage": 69.02, "elapsed_time": "1 day, 14:59:06", "remaining_time": "17:30:00"}
1261
+ {"current_steps": 6305, "total_steps": 9128, "loss": 0.2012, "lr": 1.057269764264434e-05, "epoch": 4.8354430379746836, "percentage": 69.07, "elapsed_time": "1 day, 15:00:52", "remaining_time": "17:28:06"}
1262
+ {"current_steps": 6310, "total_steps": 9128, "loss": 0.1915, "lr": 1.053898768512732e-05, "epoch": 4.83927886459532, "percentage": 69.13, "elapsed_time": "1 day, 15:02:34", "remaining_time": "17:26:10"}
1263
+ {"current_steps": 6315, "total_steps": 9128, "loss": 0.207, "lr": 1.0505312318528804e-05, "epoch": 4.843114691215957, "percentage": 69.18, "elapsed_time": "1 day, 15:04:14", "remaining_time": "17:24:14"}
1264
+ {"current_steps": 6320, "total_steps": 9128, "loss": 0.1947, "lr": 1.0471671665971104e-05, "epoch": 4.846950517836594, "percentage": 69.24, "elapsed_time": "1 day, 15:05:54", "remaining_time": "17:22:17"}
1265
+ {"current_steps": 6325, "total_steps": 9128, "loss": 0.2014, "lr": 1.0438065850449624e-05, "epoch": 4.85078634445723, "percentage": 69.29, "elapsed_time": "1 day, 15:07:30", "remaining_time": "17:20:19"}
1266
+ {"current_steps": 6330, "total_steps": 9128, "loss": 0.2148, "lr": 1.0404494994832421e-05, "epoch": 4.854622171077867, "percentage": 69.35, "elapsed_time": "1 day, 15:09:15", "remaining_time": "17:18:25"}
1267
+ {"current_steps": 6335, "total_steps": 9128, "loss": 0.2072, "lr": 1.0370959221859702e-05, "epoch": 4.858457997698504, "percentage": 69.4, "elapsed_time": "1 day, 15:10:54", "remaining_time": "17:16:28"}
1268
+ {"current_steps": 6340, "total_steps": 9128, "loss": 0.2148, "lr": 1.0337458654143417e-05, "epoch": 4.862293824319141, "percentage": 69.46, "elapsed_time": "1 day, 15:12:31", "remaining_time": "17:14:31"}
1269
+ {"current_steps": 6345, "total_steps": 9128, "loss": 0.2078, "lr": 1.0303993414166808e-05, "epoch": 4.866129650939778, "percentage": 69.51, "elapsed_time": "1 day, 15:14:07", "remaining_time": "17:12:33"}
1270
+ {"current_steps": 6350, "total_steps": 9128, "loss": 0.2198, "lr": 1.027056362428394e-05, "epoch": 4.869965477560414, "percentage": 69.57, "elapsed_time": "1 day, 15:15:50", "remaining_time": "17:10:37"}
1271
+ {"current_steps": 6355, "total_steps": 9128, "loss": 0.213, "lr": 1.0237169406719296e-05, "epoch": 4.873801304181051, "percentage": 69.62, "elapsed_time": "1 day, 15:17:31", "remaining_time": "17:08:42"}
1272
+ {"current_steps": 6360, "total_steps": 9128, "loss": 0.2142, "lr": 1.0203810883567255e-05, "epoch": 4.877637130801688, "percentage": 69.68, "elapsed_time": "1 day, 15:19:08", "remaining_time": "17:06:44"}
1273
+ {"current_steps": 6365, "total_steps": 9128, "loss": 0.2156, "lr": 1.0170488176791721e-05, "epoch": 4.881472957422325, "percentage": 69.73, "elapsed_time": "1 day, 15:20:56", "remaining_time": "17:04:51"}
1274
+ {"current_steps": 6370, "total_steps": 9128, "loss": 0.2047, "lr": 1.0137201408225663e-05, "epoch": 4.885308784042961, "percentage": 69.79, "elapsed_time": "1 day, 15:22:33", "remaining_time": "17:02:54"}
1275
+ {"current_steps": 6375, "total_steps": 9128, "loss": 0.2108, "lr": 1.0103950699570615e-05, "epoch": 4.889144610663598, "percentage": 69.84, "elapsed_time": "1 day, 15:24:10", "remaining_time": "17:00:57"}
1276
+ {"current_steps": 6380, "total_steps": 9128, "loss": 0.2141, "lr": 1.0070736172396286e-05, "epoch": 4.892980437284235, "percentage": 69.89, "elapsed_time": "1 day, 15:25:47", "remaining_time": "16:58:59"}
1277
+ {"current_steps": 6385, "total_steps": 9128, "loss": 0.2029, "lr": 1.0037557948140124e-05, "epoch": 4.896816263904872, "percentage": 69.95, "elapsed_time": "1 day, 15:27:27", "remaining_time": "16:57:03"}
1278
+ {"current_steps": 6390, "total_steps": 9128, "loss": 0.1935, "lr": 1.0004416148106808e-05, "epoch": 4.900652090525508, "percentage": 70.0, "elapsed_time": "1 day, 15:29:15", "remaining_time": "16:55:11"}
1279
+ {"current_steps": 6395, "total_steps": 9128, "loss": 0.2105, "lr": 9.97131089346788e-06, "epoch": 4.904487917146145, "percentage": 70.06, "elapsed_time": "1 day, 15:30:58", "remaining_time": "16:53:16"}
1280
+ {"current_steps": 6400, "total_steps": 9128, "loss": 0.1977, "lr": 9.938242305261253e-06, "epoch": 4.908323743766782, "percentage": 70.11, "elapsed_time": "1 day, 15:32:38", "remaining_time": "16:51:20"}
1281
+ {"current_steps": 6405, "total_steps": 9128, "loss": 0.2149, "lr": 9.905210504390755e-06, "epoch": 4.912159570387418, "percentage": 70.17, "elapsed_time": "1 day, 15:35:29", "remaining_time": "16:49:54"}
1282
+ {"current_steps": 6410, "total_steps": 9128, "loss": 0.2062, "lr": 9.87221561162577e-06, "epoch": 4.915995397008055, "percentage": 70.22, "elapsed_time": "1 day, 15:37:10", "remaining_time": "16:47:58"}
1283
+ {"current_steps": 6415, "total_steps": 9128, "loss": 0.2098, "lr": 9.83925774760068e-06, "epoch": 4.919831223628692, "percentage": 70.28, "elapsed_time": "1 day, 15:38:52", "remaining_time": "16:46:03"}
1284
+ {"current_steps": 6420, "total_steps": 9128, "loss": 0.2053, "lr": 9.806337032814533e-06, "epoch": 4.923667050249328, "percentage": 70.33, "elapsed_time": "1 day, 15:40:28", "remaining_time": "16:44:06"}