Training in progress, epoch 4
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:ab3534aca13ea374da186dc350ccdc2fdd66e588b0303e9f7c71cb38e611eaf7
|
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 sha256:06fcbe120dcd874f1345e056bcbc1553cc238b5436c0a2e6a84aabda3449c298
|
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 sha256:1d7d42b4758fe81de56ae7ec8c3d6a0f4771f4a20b097b49895342f685701bc1
|
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 sha256:3372d59239326c94079f3eae9b8977a2ae3d4abefaae4a0415460d33b9054a61
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -347,3 +347,37 @@
|
|
347 |
{"current_steps": 145, "total_steps": 180, "loss": 0.5049, "lr": 8.8654035230336e-06, "epoch": 4.020689655172414, "percentage": 80.56, "elapsed_time": "1:07:46", "remaining_time": "0:16:21"}
|
348 |
{"current_steps": 146, "total_steps": 180, "loss": 0.4855, "lr": 8.384293219249633e-06, "epoch": 4.048275862068966, "percentage": 81.11, "elapsed_time": "1:09:28", "remaining_time": "0:16:10"}
|
349 |
{"current_steps": 147, "total_steps": 180, "loss": 0.4838, "lr": 7.915072289798247e-06, "epoch": 4.075862068965518, "percentage": 81.67, "elapsed_time": "1:11:11", "remaining_time": "0:15:59"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
347 |
{"current_steps": 145, "total_steps": 180, "loss": 0.5049, "lr": 8.8654035230336e-06, "epoch": 4.020689655172414, "percentage": 80.56, "elapsed_time": "1:07:46", "remaining_time": "0:16:21"}
|
348 |
{"current_steps": 146, "total_steps": 180, "loss": 0.4855, "lr": 8.384293219249633e-06, "epoch": 4.048275862068966, "percentage": 81.11, "elapsed_time": "1:09:28", "remaining_time": "0:16:10"}
|
349 |
{"current_steps": 147, "total_steps": 180, "loss": 0.4838, "lr": 7.915072289798247e-06, "epoch": 4.075862068965518, "percentage": 81.67, "elapsed_time": "1:11:11", "remaining_time": "0:15:59"}
|
350 |
+
{"current_steps": 148, "total_steps": 180, "loss": 0.4859, "lr": 7.457917189481301e-06, "epoch": 4.103448275862069, "percentage": 82.22, "elapsed_time": "1:12:54", "remaining_time": "0:15:45"}
|
351 |
+
{"current_steps": 149, "total_steps": 180, "loss": 0.492, "lr": 7.0129998356357295e-06, "epoch": 4.13103448275862, "percentage": 82.78, "elapsed_time": "1:14:37", "remaining_time": "0:15:31"}
|
352 |
+
{"current_steps": 150, "total_steps": 180, "loss": 0.4879, "lr": 6.58048754348255e-06, "epoch": 4.158620689655172, "percentage": 83.33, "elapsed_time": "1:16:19", "remaining_time": "0:15:15"}
|
353 |
+
{"current_steps": 151, "total_steps": 180, "loss": 0.4934, "lr": 6.160542963206357e-06, "epoch": 4.186206896551724, "percentage": 83.89, "elapsed_time": "1:18:04", "remaining_time": "0:14:59"}
|
354 |
+
{"current_steps": 152, "total_steps": 180, "loss": 0.4947, "lr": 5.753324018789346e-06, "epoch": 4.213793103448276, "percentage": 84.44, "elapsed_time": "1:19:46", "remaining_time": "0:14:41"}
|
355 |
+
{"current_steps": 153, "total_steps": 180, "loss": 0.4898, "lr": 5.358983848622452e-06, "epoch": 4.241379310344827, "percentage": 85.0, "elapsed_time": "1:21:31", "remaining_time": "0:14:23"}
|
356 |
+
{"current_steps": 154, "total_steps": 180, "loss": 0.4971, "lr": 4.97767074791637e-06, "epoch": 4.268965517241379, "percentage": 85.56, "elapsed_time": "1:23:13", "remaining_time": "0:14:03"}
|
357 |
+
{"current_steps": 155, "total_steps": 180, "loss": 0.4827, "lr": 4.609528112933688e-06, "epoch": 4.296551724137931, "percentage": 86.11, "elapsed_time": "1:24:56", "remaining_time": "0:13:41"}
|
358 |
+
{"current_steps": 156, "total_steps": 180, "loss": 0.4881, "lr": 4.254694387063514e-06, "epoch": 4.324137931034483, "percentage": 86.67, "elapsed_time": "1:26:39", "remaining_time": "0:13:19"}
|
359 |
+
{"current_steps": 157, "total_steps": 180, "loss": 0.5004, "lr": 3.913303008758491e-06, "epoch": 4.3517241379310345, "percentage": 87.22, "elapsed_time": "1:28:22", "remaining_time": "0:12:56"}
|
360 |
+
{"current_steps": 158, "total_steps": 180, "loss": 0.4957, "lr": 3.585482361354138e-06, "epoch": 4.379310344827586, "percentage": 87.78, "elapsed_time": "1:30:05", "remaining_time": "0:12:32"}
|
361 |
+
{"current_steps": 159, "total_steps": 180, "loss": 0.4872, "lr": 3.2713557247890447e-06, "epoch": 4.406896551724138, "percentage": 88.33, "elapsed_time": "1:31:50", "remaining_time": "0:12:07"}
|
362 |
+
{"current_steps": 160, "total_steps": 180, "loss": 0.4883, "lr": 2.9710412292443868e-06, "epoch": 4.43448275862069, "percentage": 88.89, "elapsed_time": "1:33:38", "remaining_time": "0:11:42"}
|
363 |
+
{"current_steps": 161, "total_steps": 180, "loss": 0.4875, "lr": 2.6846518107199782e-06, "epoch": 4.462068965517242, "percentage": 89.44, "elapsed_time": "1:35:23", "remaining_time": "0:11:15"}
|
364 |
+
{"current_steps": 162, "total_steps": 180, "loss": 0.4958, "lr": 2.4122951685636674e-06, "epoch": 4.489655172413793, "percentage": 90.0, "elapsed_time": "1:37:05", "remaining_time": "0:10:47"}
|
365 |
+
{"current_steps": 163, "total_steps": 180, "loss": 0.5004, "lr": 2.1540737249699893e-06, "epoch": 4.517241379310345, "percentage": 90.56, "elapsed_time": "1:38:48", "remaining_time": "0:10:18"}
|
366 |
+
{"current_steps": 164, "total_steps": 180, "loss": 0.4908, "lr": 1.9100845864633875e-06, "epoch": 4.544827586206896, "percentage": 91.11, "elapsed_time": "1:40:31", "remaining_time": "0:09:48"}
|
367 |
+
{"current_steps": 165, "total_steps": 180, "loss": 0.4966, "lr": 1.6804195073804442e-06, "epoch": 4.572413793103449, "percentage": 91.67, "elapsed_time": "1:42:14", "remaining_time": "0:09:17"}
|
368 |
+
{"current_steps": 166, "total_steps": 180, "loss": 0.4848, "lr": 1.4651648553647869e-06, "epoch": 4.6, "percentage": 92.22, "elapsed_time": "1:43:56", "remaining_time": "0:08:45"}
|
369 |
+
{"current_steps": 167, "total_steps": 180, "loss": 0.4854, "lr": 1.2644015788877684e-06, "epoch": 4.627586206896551, "percentage": 92.78, "elapsed_time": "1:45:39", "remaining_time": "0:08:13"}
|
370 |
+
{"current_steps": 168, "total_steps": 180, "loss": 0.4979, "lr": 1.0782051768070477e-06, "epoch": 4.655172413793103, "percentage": 93.33, "elapsed_time": "1:47:21", "remaining_time": "0:07:40"}
|
371 |
+
{"current_steps": 169, "total_steps": 180, "loss": 0.4942, "lr": 9.066456699745774e-07, "epoch": 4.682758620689655, "percentage": 93.89, "elapsed_time": "1:49:02", "remaining_time": "0:07:05"}
|
372 |
+
{"current_steps": 170, "total_steps": 180, "loss": 0.4942, "lr": 7.497875749046124e-07, "epoch": 4.710344827586207, "percentage": 94.44, "elapsed_time": "1:50:44", "remaining_time": "0:06:30"}
|
373 |
+
{"current_steps": 171, "total_steps": 180, "loss": 0.4924, "lr": 6.076898795116792e-07, "epoch": 4.7379310344827585, "percentage": 95.0, "elapsed_time": "1:52:27", "remaining_time": "0:05:55"}
|
374 |
+
{"current_steps": 172, "total_steps": 180, "loss": 0.4908, "lr": 4.804060209276396e-07, "epoch": 4.76551724137931, "percentage": 95.56, "elapsed_time": "1:54:09", "remaining_time": "0:05:18"}
|
375 |
+
{"current_steps": 173, "total_steps": 180, "loss": 0.4942, "lr": 3.679838654061874e-07, "epoch": 4.793103448275862, "percentage": 96.11, "elapsed_time": "1:55:51", "remaining_time": "0:04:41"}
|
376 |
+
{"current_steps": 174, "total_steps": 180, "loss": 0.488, "lr": 2.704656903222791e-07, "epoch": 4.820689655172414, "percentage": 96.67, "elapsed_time": "1:57:34", "remaining_time": "0:04:03"}
|
377 |
+
{"current_steps": 175, "total_steps": 180, "loss": 0.4953, "lr": 1.8788816827336686e-07, "epoch": 4.848275862068966, "percentage": 97.22, "elapsed_time": "1:59:16", "remaining_time": "0:03:24"}
|
378 |
+
{"current_steps": 176, "total_steps": 180, "loss": 0.4922, "lr": 1.2028235328831906e-07, "epoch": 4.875862068965517, "percentage": 97.78, "elapsed_time": "2:00:59", "remaining_time": "0:02:44"}
|
379 |
+
{"current_steps": 177, "total_steps": 180, "loss": 0.5023, "lr": 6.767366914927298e-08, "epoch": 4.903448275862069, "percentage": 98.33, "elapsed_time": "2:02:41", "remaining_time": "0:02:04"}
|
380 |
+
{"current_steps": 178, "total_steps": 180, "loss": 0.494, "lr": 3.0081899830798345e-08, "epoch": 4.931034482758621, "percentage": 98.89, "elapsed_time": "2:04:28", "remaining_time": "0:01:23"}
|
381 |
+
{"current_steps": 179, "total_steps": 180, "loss": 0.4894, "lr": 7.521182059946342e-09, "epoch": 4.958620689655173, "percentage": 99.44, "elapsed_time": "2:06:17", "remaining_time": "0:00:42"}
|
382 |
+
{"current_steps": 180, "total_steps": 180, "loss": 0.4915, "lr": 0.0, "epoch": 4.9862068965517246, "percentage": 100.0, "elapsed_time": "2:08:01", "remaining_time": "0:00:00"}
|
383 |
+
{"current_steps": 180, "total_steps": 180, "epoch": 4.9862068965517246, "percentage": 100.0, "elapsed_time": "2:10:56", "remaining_time": "0:00:00"}
|