Training in progress, epoch 2
Browse files
model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4877660776
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f406e427db2ee5fd85b7accb10c474cc852ead0978e3e32f60a4bc1e9144ef92
|
| 3 |
size 4877660776
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4932751008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2634917eba0e153b4c8b966c76ab2fc66b5e2ecb5dd9bdbba594173272a0410d
|
| 3 |
size 4932751008
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4330865200
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:187b2cc977c6be9af46776a92b5e269c3b5765c389fde595d48ad9e5f289a6e0
|
| 3 |
size 4330865200
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1089994880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b119ae34d7b7b2e18ae4b5248a87af5dda251d05f3ff75cfc7b50125ca6ba5c
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
@@ -281,3 +281,33 @@
|
|
| 281 |
{"current_steps": 281, "total_steps": 312, "loss": 0.4307, "lr": 2.9940862715390483e-07, "epoch": 2.693290734824281, "percentage": 90.06, "elapsed_time": "1:17:46", "remaining_time": "0:08:34"}
|
| 282 |
{"current_steps": 282, "total_steps": 312, "loss": 0.441, "lr": 2.8058334845816214e-07, "epoch": 2.702875399361022, "percentage": 90.38, "elapsed_time": "1:17:59", "remaining_time": "0:08:17"}
|
| 283 |
{"current_steps": 283, "total_steps": 312, "loss": 0.4231, "lr": 2.6235218056235633e-07, "epoch": 2.7124600638977636, "percentage": 90.71, "elapsed_time": "1:18:17", "remaining_time": "0:08:01"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 281 |
{"current_steps": 281, "total_steps": 312, "loss": 0.4307, "lr": 2.9940862715390483e-07, "epoch": 2.693290734824281, "percentage": 90.06, "elapsed_time": "1:17:46", "remaining_time": "0:08:34"}
|
| 282 |
{"current_steps": 282, "total_steps": 312, "loss": 0.441, "lr": 2.8058334845816214e-07, "epoch": 2.702875399361022, "percentage": 90.38, "elapsed_time": "1:17:59", "remaining_time": "0:08:17"}
|
| 283 |
{"current_steps": 283, "total_steps": 312, "loss": 0.4231, "lr": 2.6235218056235633e-07, "epoch": 2.7124600638977636, "percentage": 90.71, "elapsed_time": "1:18:17", "remaining_time": "0:08:01"}
|
| 284 |
+
{"current_steps": 284, "total_steps": 312, "loss": 0.46, "lr": 2.447174185242324e-07, "epoch": 2.722044728434505, "percentage": 91.03, "elapsed_time": "1:18:35", "remaining_time": "0:07:44"}
|
| 285 |
+
{"current_steps": 285, "total_steps": 312, "loss": 0.3886, "lr": 2.276812823220964e-07, "epoch": 2.731629392971246, "percentage": 91.35, "elapsed_time": "1:18:52", "remaining_time": "0:07:28"}
|
| 286 |
+
{"current_steps": 286, "total_steps": 312, "loss": 0.4617, "lr": 2.1124591657534776e-07, "epoch": 2.741214057507987, "percentage": 91.67, "elapsed_time": "1:19:07", "remaining_time": "0:07:11"}
|
| 287 |
+
{"current_steps": 287, "total_steps": 312, "loss": 0.4317, "lr": 1.9541339027450256e-07, "epoch": 2.7507987220447285, "percentage": 91.99, "elapsed_time": "1:19:23", "remaining_time": "0:06:54"}
|
| 288 |
+
{"current_steps": 288, "total_steps": 312, "loss": 0.3958, "lr": 1.801856965207338e-07, "epoch": 2.7603833865814695, "percentage": 92.31, "elapsed_time": "1:19:41", "remaining_time": "0:06:38"}
|
| 289 |
+
{"current_steps": 289, "total_steps": 312, "loss": 0.4189, "lr": 1.6556475227496816e-07, "epoch": 2.769968051118211, "percentage": 92.63, "elapsed_time": "1:19:58", "remaining_time": "0:06:21"}
|
| 290 |
+
{"current_steps": 290, "total_steps": 312, "loss": 0.4475, "lr": 1.5155239811656562e-07, "epoch": 2.779552715654952, "percentage": 92.95, "elapsed_time": "1:20:12", "remaining_time": "0:06:05"}
|
| 291 |
+
{"current_steps": 291, "total_steps": 312, "loss": 0.4039, "lr": 1.3815039801161723e-07, "epoch": 2.7891373801916934, "percentage": 93.27, "elapsed_time": "1:20:29", "remaining_time": "0:05:48"}
|
| 292 |
+
{"current_steps": 292, "total_steps": 312, "loss": 0.3835, "lr": 1.253604390908819e-07, "epoch": 2.7987220447284344, "percentage": 93.59, "elapsed_time": "1:20:45", "remaining_time": "0:05:31"}
|
| 293 |
+
{"current_steps": 293, "total_steps": 312, "loss": 0.4825, "lr": 1.1318413143740436e-07, "epoch": 2.8083067092651754, "percentage": 93.91, "elapsed_time": "1:21:03", "remaining_time": "0:05:15"}
|
| 294 |
+
{"current_steps": 294, "total_steps": 312, "loss": 0.4142, "lr": 1.0162300788382263e-07, "epoch": 2.817891373801917, "percentage": 94.23, "elapsed_time": "1:21:19", "remaining_time": "0:04:58"}
|
| 295 |
+
{"current_steps": 295, "total_steps": 312, "loss": 0.3933, "lr": 9.0678523819408e-08, "epoch": 2.8274760383386583, "percentage": 94.55, "elapsed_time": "1:21:36", "remaining_time": "0:04:42"}
|
| 296 |
+
{"current_steps": 296, "total_steps": 312, "loss": 0.4562, "lr": 8.035205700685167e-08, "epoch": 2.8370607028753994, "percentage": 94.87, "elapsed_time": "1:21:52", "remaining_time": "0:04:25"}
|
| 297 |
+
{"current_steps": 297, "total_steps": 312, "loss": 0.42, "lr": 7.064490740882057e-08, "epoch": 2.8466453674121404, "percentage": 95.19, "elapsed_time": "1:22:10", "remaining_time": "0:04:09"}
|
| 298 |
+
{"current_steps": 298, "total_steps": 312, "loss": 0.4289, "lr": 6.15582970243117e-08, "epoch": 2.856230031948882, "percentage": 95.51, "elapsed_time": "1:22:28", "remaining_time": "0:03:52"}
|
| 299 |
+
{"current_steps": 299, "total_steps": 312, "loss": 0.4808, "lr": 5.3093369734816824e-08, "epoch": 2.8658146964856233, "percentage": 95.83, "elapsed_time": "1:22:46", "remaining_time": "0:03:35"}
|
| 300 |
+
{"current_steps": 300, "total_steps": 312, "loss": 0.4643, "lr": 4.52511911603265e-08, "epoch": 2.8753993610223643, "percentage": 96.15, "elapsed_time": "1:23:02", "remaining_time": "0:03:19"}
|
| 301 |
+
{"current_steps": 301, "total_steps": 312, "loss": 0.3762, "lr": 3.8032748525179684e-08, "epoch": 2.8849840255591053, "percentage": 96.47, "elapsed_time": "1:23:17", "remaining_time": "0:03:02"}
|
| 302 |
+
{"current_steps": 302, "total_steps": 312, "loss": 0.4528, "lr": 3.143895053378698e-08, "epoch": 2.8945686900958467, "percentage": 96.79, "elapsed_time": "1:23:34", "remaining_time": "0:02:46"}
|
| 303 |
+
{"current_steps": 303, "total_steps": 312, "loss": 0.3986, "lr": 2.547062725623828e-08, "epoch": 2.9041533546325877, "percentage": 97.12, "elapsed_time": "1:23:51", "remaining_time": "0:02:29"}
|
| 304 |
+
{"current_steps": 304, "total_steps": 312, "loss": 0.4257, "lr": 2.012853002380466e-08, "epoch": 2.913738019169329, "percentage": 97.44, "elapsed_time": "1:24:07", "remaining_time": "0:02:12"}
|
| 305 |
+
{"current_steps": 305, "total_steps": 312, "loss": 0.4584, "lr": 1.541333133436018e-08, "epoch": 2.92332268370607, "percentage": 97.76, "elapsed_time": "1:24:22", "remaining_time": "0:01:56"}
|
| 306 |
+
{"current_steps": 306, "total_steps": 312, "loss": 0.4506, "lr": 1.132562476771959e-08, "epoch": 2.9329073482428116, "percentage": 98.08, "elapsed_time": "1:24:38", "remaining_time": "0:01:39"}
|
| 307 |
+
{"current_steps": 307, "total_steps": 312, "loss": 0.4184, "lr": 7.865924910916977e-09, "epoch": 2.9424920127795526, "percentage": 98.4, "elapsed_time": "1:24:52", "remaining_time": "0:01:22"}
|
| 308 |
+
{"current_steps": 308, "total_steps": 312, "loss": 0.3951, "lr": 5.034667293427053e-09, "epoch": 2.952076677316294, "percentage": 98.72, "elapsed_time": "1:25:10", "remaining_time": "0:01:06"}
|
| 309 |
+
{"current_steps": 309, "total_steps": 312, "loss": 0.4028, "lr": 2.8322083323334417e-09, "epoch": 2.961661341853035, "percentage": 99.04, "elapsed_time": "1:25:27", "remaining_time": "0:00:49"}
|
| 310 |
+
{"current_steps": 310, "total_steps": 312, "loss": 0.4171, "lr": 1.2588252874673469e-09, "epoch": 2.9712460063897765, "percentage": 99.36, "elapsed_time": "1:25:42", "remaining_time": "0:00:33"}
|
| 311 |
+
{"current_steps": 311, "total_steps": 312, "loss": 0.3893, "lr": 3.147162264971471e-10, "epoch": 2.9808306709265175, "percentage": 99.68, "elapsed_time": "1:25:59", "remaining_time": "0:00:16"}
|
| 312 |
+
{"current_steps": 312, "total_steps": 312, "loss": 0.4427, "lr": 0.0, "epoch": 2.9904153354632586, "percentage": 100.0, "elapsed_time": "1:26:16", "remaining_time": "0:00:00"}
|
| 313 |
+
{"current_steps": 312, "total_steps": 312, "epoch": 2.9904153354632586, "percentage": 100.0, "elapsed_time": "1:29:11", "remaining_time": "0:00:00"}
|