Training in progress, epoch 1
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:f96f3359a87a35e1490e1a3c0a7e10a0ec7c05162cde9c83437f28c91240996a
|
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 sha256:65d1a542baf7278c5fccb986417c728990ed27160977333590d105e4d9f0b561
|
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 sha256:084744618bf02ff228956a52e721dc28947fd6da55f8e37bd92c4d8f0cf27df3
|
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:b561870ac8a3b9765be80f8d429100d3f2e97abe96664145c882d2f25730f8c3
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -32,3 +32,35 @@
|
|
32 |
{"current_steps": 32, "total_steps": 224, "loss": 0.6935, "lr": 1.990122514534651e-05, "epoch": 0.9721518987341772, "percentage": 14.29, "elapsed_time": "1:02:57", "remaining_time": "6:17:45"}
|
33 |
{"current_steps": 33, "total_steps": 224, "loss": 0.6756, "lr": 1.9878102910595097e-05, "epoch": 1.010126582278481, "percentage": 14.73, "elapsed_time": "1:05:40", "remaining_time": "6:20:06"}
|
34 |
{"current_steps": 34, "total_steps": 224, "loss": 0.6422, "lr": 1.985256759242359e-05, "epoch": 1.040506329113924, "percentage": 15.18, "elapsed_time": "1:07:50", "remaining_time": "6:19:04"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
{"current_steps": 32, "total_steps": 224, "loss": 0.6935, "lr": 1.990122514534651e-05, "epoch": 0.9721518987341772, "percentage": 14.29, "elapsed_time": "1:02:57", "remaining_time": "6:17:45"}
|
33 |
{"current_steps": 33, "total_steps": 224, "loss": 0.6756, "lr": 1.9878102910595097e-05, "epoch": 1.010126582278481, "percentage": 14.73, "elapsed_time": "1:05:40", "remaining_time": "6:20:06"}
|
34 |
{"current_steps": 34, "total_steps": 224, "loss": 0.6422, "lr": 1.985256759242359e-05, "epoch": 1.040506329113924, "percentage": 15.18, "elapsed_time": "1:07:50", "remaining_time": "6:19:04"}
|
35 |
+
{"current_steps": 35, "total_steps": 224, "loss": 0.6543, "lr": 1.982462542875576e-05, "epoch": 1.070886075949367, "percentage": 15.62, "elapsed_time": "1:09:41", "remaining_time": "6:16:20"}
|
36 |
+
{"current_steps": 36, "total_steps": 224, "loss": 0.6559, "lr": 1.979428324547432e-05, "epoch": 1.1012658227848102, "percentage": 16.07, "elapsed_time": "1:11:36", "remaining_time": "6:13:58"}
|
37 |
+
{"current_steps": 37, "total_steps": 224, "loss": 0.646, "lr": 1.9761548454753455e-05, "epoch": 1.1316455696202532, "percentage": 16.52, "elapsed_time": "1:13:45", "remaining_time": "6:12:45"}
|
38 |
+
{"current_steps": 38, "total_steps": 224, "loss": 0.6541, "lr": 1.972642905324813e-05, "epoch": 1.1620253164556962, "percentage": 16.96, "elapsed_time": "1:15:44", "remaining_time": "6:10:43"}
|
39 |
+
{"current_steps": 39, "total_steps": 224, "loss": 0.6481, "lr": 1.9688933620140638e-05, "epoch": 1.1924050632911392, "percentage": 17.41, "elapsed_time": "1:17:38", "remaining_time": "6:08:17"}
|
40 |
+
{"current_steps": 40, "total_steps": 224, "loss": 0.6208, "lr": 1.96490713150448e-05, "epoch": 1.2227848101265824, "percentage": 17.86, "elapsed_time": "1:19:42", "remaining_time": "6:06:37"}
|
41 |
+
{"current_steps": 41, "total_steps": 224, "loss": 0.6275, "lr": 1.9606851875768404e-05, "epoch": 1.2531645569620253, "percentage": 18.3, "elapsed_time": "1:21:39", "remaining_time": "6:04:27"}
|
42 |
+
{"current_steps": 42, "total_steps": 224, "loss": 0.6349, "lr": 1.956228561593441e-05, "epoch": 1.2835443037974683, "percentage": 18.75, "elapsed_time": "1:23:46", "remaining_time": "6:03:03"}
|
43 |
+
{"current_steps": 43, "total_steps": 224, "loss": 0.6382, "lr": 1.9515383422461457e-05, "epoch": 1.3139240506329113, "percentage": 19.2, "elapsed_time": "1:25:29", "remaining_time": "5:59:51"}
|
44 |
+
{"current_steps": 44, "total_steps": 224, "loss": 0.6355, "lr": 1.9466156752904344e-05, "epoch": 1.3443037974683545, "percentage": 19.64, "elapsed_time": "1:27:19", "remaining_time": "5:57:12"}
|
45 |
+
{"current_steps": 45, "total_steps": 224, "loss": 0.6337, "lr": 1.9414617632655114e-05, "epoch": 1.3746835443037975, "percentage": 20.09, "elapsed_time": "1:29:10", "remaining_time": "5:54:44"}
|
46 |
+
{"current_steps": 46, "total_steps": 224, "loss": 0.6389, "lr": 1.9360778652005416e-05, "epoch": 1.4050632911392404, "percentage": 20.54, "elapsed_time": "1:31:04", "remaining_time": "5:52:26"}
|
47 |
+
{"current_steps": 47, "total_steps": 224, "loss": 0.6189, "lr": 1.9304652963070868e-05, "epoch": 1.4354430379746836, "percentage": 20.98, "elapsed_time": "1:32:53", "remaining_time": "5:49:49"}
|
48 |
+
{"current_steps": 48, "total_steps": 224, "loss": 0.6312, "lr": 1.9246254276578175e-05, "epoch": 1.4658227848101266, "percentage": 21.43, "elapsed_time": "1:34:51", "remaining_time": "5:47:48"}
|
49 |
+
{"current_steps": 49, "total_steps": 224, "loss": 0.6214, "lr": 1.9185596858515797e-05, "epoch": 1.4962025316455696, "percentage": 21.88, "elapsed_time": "1:36:53", "remaining_time": "5:46:01"}
|
50 |
+
{"current_steps": 50, "total_steps": 224, "loss": 0.6256, "lr": 1.9122695526648968e-05, "epoch": 1.5265822784810128, "percentage": 22.32, "elapsed_time": "1:38:51", "remaining_time": "5:44:00"}
|
51 |
+
{"current_steps": 51, "total_steps": 224, "loss": 0.6372, "lr": 1.905756564689991e-05, "epoch": 1.5569620253164556, "percentage": 22.77, "elapsed_time": "1:40:47", "remaining_time": "5:41:53"}
|
52 |
+
{"current_steps": 52, "total_steps": 224, "loss": 0.608, "lr": 1.8990223129594146e-05, "epoch": 1.5873417721518988, "percentage": 23.21, "elapsed_time": "1:42:50", "remaining_time": "5:40:10"}
|
53 |
+
{"current_steps": 53, "total_steps": 224, "loss": 0.6256, "lr": 1.8920684425573865e-05, "epoch": 1.6177215189873417, "percentage": 23.66, "elapsed_time": "1:44:46", "remaining_time": "5:38:02"}
|
54 |
+
{"current_steps": 54, "total_steps": 224, "loss": 0.6205, "lr": 1.884896652217917e-05, "epoch": 1.6481012658227847, "percentage": 24.11, "elapsed_time": "1:46:40", "remaining_time": "5:35:49"}
|
55 |
+
{"current_steps": 55, "total_steps": 224, "loss": 0.6123, "lr": 1.877508693909831e-05, "epoch": 1.678481012658228, "percentage": 24.55, "elapsed_time": "1:48:35", "remaining_time": "5:33:41"}
|
56 |
+
{"current_steps": 56, "total_steps": 224, "loss": 0.608, "lr": 1.8699063724087905e-05, "epoch": 1.7088607594936709, "percentage": 25.0, "elapsed_time": "1:50:22", "remaining_time": "5:31:08"}
|
57 |
+
{"current_steps": 57, "total_steps": 224, "loss": 0.6074, "lr": 1.862091544856407e-05, "epoch": 1.7392405063291139, "percentage": 25.45, "elapsed_time": "1:52:29", "remaining_time": "5:29:34"}
|
58 |
+
{"current_steps": 58, "total_steps": 224, "loss": 0.6225, "lr": 1.854066120306571e-05, "epoch": 1.769620253164557, "percentage": 25.89, "elapsed_time": "1:54:32", "remaining_time": "5:27:50"}
|
59 |
+
{"current_steps": 59, "total_steps": 224, "loss": 0.6276, "lr": 1.8458320592590976e-05, "epoch": 1.8, "percentage": 26.34, "elapsed_time": "1:56:43", "remaining_time": "5:26:25"}
|
60 |
+
{"current_steps": 60, "total_steps": 224, "loss": 0.6109, "lr": 1.837391373180801e-05, "epoch": 1.830379746835443, "percentage": 26.79, "elapsed_time": "1:58:34", "remaining_time": "5:24:06"}
|
61 |
+
{"current_steps": 61, "total_steps": 224, "loss": 0.6203, "lr": 1.8287461240141217e-05, "epoch": 1.8607594936708862, "percentage": 27.23, "elapsed_time": "2:00:38", "remaining_time": "5:22:21"}
|
62 |
+
{"current_steps": 62, "total_steps": 224, "loss": 0.6078, "lr": 1.8198984236734246e-05, "epoch": 1.891139240506329, "percentage": 27.68, "elapsed_time": "2:02:31", "remaining_time": "5:20:09"}
|
63 |
+
{"current_steps": 63, "total_steps": 224, "loss": 0.612, "lr": 1.8108504335290852e-05, "epoch": 1.9215189873417722, "percentage": 28.12, "elapsed_time": "2:04:27", "remaining_time": "5:18:02"}
|
64 |
+
{"current_steps": 64, "total_steps": 224, "loss": 0.6187, "lr": 1.8016043638794975e-05, "epoch": 1.9518987341772152, "percentage": 28.57, "elapsed_time": "2:06:30", "remaining_time": "5:16:15"}
|
65 |
+
{"current_steps": 65, "total_steps": 224, "loss": 0.6125, "lr": 1.7921624734111292e-05, "epoch": 1.9822784810126581, "percentage": 29.02, "elapsed_time": "2:08:32", "remaining_time": "5:14:25"}
|
66 |
+
{"current_steps": 66, "total_steps": 224, "loss": 0.584, "lr": 1.7825270686467567e-05, "epoch": 2.020253164556962, "percentage": 29.46, "elapsed_time": "2:11:25", "remaining_time": "5:14:37"}
|