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 sha256:1c026e62176e5b9a993fb7aa7c76ac445258a16704f658833ae9eb7731679f7c
|
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 sha256:5d14774b38adbc53ba45db329d128a4c10ca720630f4ef54da6c17509dcb334e
|
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 sha256:5e0bc343a2ad6cd87e14477a220f8cb40220c79d51a60e3f83f30db62c3d251d
|
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:bdc57bf406e736ba754c2e602bd130ef5f5789836320d45cd1675e5108bb6f5f
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -28,3 +28,30 @@
|
|
28 |
{"current_steps": 28, "total_steps": 78, "loss": 1.0453, "lr": 8.117449009293668e-06, "epoch": 1.0632911392405062, "percentage": 35.9, "elapsed_time": "0:11:11", "remaining_time": "0:19:59"}
|
29 |
{"current_steps": 29, "total_steps": 78, "loss": 0.9382, "lr": 7.938926261462366e-06, "epoch": 1.1012658227848102, "percentage": 37.18, "elapsed_time": "0:11:33", "remaining_time": "0:19:32"}
|
30 |
{"current_steps": 30, "total_steps": 78, "loss": 0.9047, "lr": 7.754484907260513e-06, "epoch": 1.139240506329114, "percentage": 38.46, "elapsed_time": "0:11:54", "remaining_time": "0:19:02"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
{"current_steps": 28, "total_steps": 78, "loss": 1.0453, "lr": 8.117449009293668e-06, "epoch": 1.0632911392405062, "percentage": 35.9, "elapsed_time": "0:11:11", "remaining_time": "0:19:59"}
|
29 |
{"current_steps": 29, "total_steps": 78, "loss": 0.9382, "lr": 7.938926261462366e-06, "epoch": 1.1012658227848102, "percentage": 37.18, "elapsed_time": "0:11:33", "remaining_time": "0:19:32"}
|
30 |
{"current_steps": 30, "total_steps": 78, "loss": 0.9047, "lr": 7.754484907260513e-06, "epoch": 1.139240506329114, "percentage": 38.46, "elapsed_time": "0:11:54", "remaining_time": "0:19:02"}
|
31 |
+
{"current_steps": 31, "total_steps": 78, "loss": 0.9878, "lr": 7.564496387029532e-06, "epoch": 1.1772151898734178, "percentage": 39.74, "elapsed_time": "0:12:15", "remaining_time": "0:18:35"}
|
32 |
+
{"current_steps": 32, "total_steps": 78, "loss": 0.8767, "lr": 7.369343312364994e-06, "epoch": 1.2151898734177216, "percentage": 41.03, "elapsed_time": "0:12:37", "remaining_time": "0:18:08"}
|
33 |
+
{"current_steps": 33, "total_steps": 78, "loss": 0.9205, "lr": 7.169418695587791e-06, "epoch": 1.2531645569620253, "percentage": 42.31, "elapsed_time": "0:12:58", "remaining_time": "0:17:41"}
|
34 |
+
{"current_steps": 34, "total_steps": 78, "loss": 1.0082, "lr": 6.965125158269619e-06, "epoch": 1.2911392405063291, "percentage": 43.59, "elapsed_time": "0:13:20", "remaining_time": "0:17:15"}
|
35 |
+
{"current_steps": 35, "total_steps": 78, "loss": 0.9122, "lr": 6.7568741204067145e-06, "epoch": 1.3291139240506329, "percentage": 44.87, "elapsed_time": "0:13:43", "remaining_time": "0:16:51"}
|
36 |
+
{"current_steps": 36, "total_steps": 78, "loss": 0.8857, "lr": 6.545084971874738e-06, "epoch": 1.3670886075949367, "percentage": 46.15, "elapsed_time": "0:14:02", "remaining_time": "0:16:22"}
|
37 |
+
{"current_steps": 37, "total_steps": 78, "loss": 0.9377, "lr": 6.330184227833376e-06, "epoch": 1.4050632911392404, "percentage": 47.44, "elapsed_time": "0:14:22", "remaining_time": "0:15:55"}
|
38 |
+
{"current_steps": 38, "total_steps": 78, "loss": 0.9129, "lr": 6.112604669781572e-06, "epoch": 1.4430379746835442, "percentage": 48.72, "elapsed_time": "0:14:41", "remaining_time": "0:15:27"}
|
39 |
+
{"current_steps": 39, "total_steps": 78, "loss": 0.951, "lr": 5.892784473993184e-06, "epoch": 1.481012658227848, "percentage": 50.0, "elapsed_time": "0:15:04", "remaining_time": "0:15:04"}
|
40 |
+
{"current_steps": 40, "total_steps": 78, "loss": 0.9992, "lr": 5.671166329088278e-06, "epoch": 1.518987341772152, "percentage": 51.28, "elapsed_time": "0:15:25", "remaining_time": "0:14:39"}
|
41 |
+
{"current_steps": 41, "total_steps": 78, "loss": 0.9643, "lr": 5.448196544517168e-06, "epoch": 1.5569620253164556, "percentage": 52.56, "elapsed_time": "0:15:47", "remaining_time": "0:14:14"}
|
42 |
+
{"current_steps": 42, "total_steps": 78, "loss": 0.8755, "lr": 5.224324151752575e-06, "epoch": 1.5949367088607596, "percentage": 53.85, "elapsed_time": "0:16:08", "remaining_time": "0:13:50"}
|
43 |
+
{"current_steps": 43, "total_steps": 78, "loss": 0.9582, "lr": 5e-06, "epoch": 1.6329113924050633, "percentage": 55.13, "elapsed_time": "0:16:29", "remaining_time": "0:13:25"}
|
44 |
+
{"current_steps": 44, "total_steps": 78, "loss": 0.9069, "lr": 4.775675848247427e-06, "epoch": 1.6708860759493671, "percentage": 56.41, "elapsed_time": "0:16:47", "remaining_time": "0:12:58"}
|
45 |
+
{"current_steps": 45, "total_steps": 78, "loss": 0.9026, "lr": 4.551803455482833e-06, "epoch": 1.7088607594936709, "percentage": 57.69, "elapsed_time": "0:17:09", "remaining_time": "0:12:35"}
|
46 |
+
{"current_steps": 46, "total_steps": 78, "loss": 0.9127, "lr": 4.3288336709117246e-06, "epoch": 1.7468354430379747, "percentage": 58.97, "elapsed_time": "0:17:31", "remaining_time": "0:12:11"}
|
47 |
+
{"current_steps": 47, "total_steps": 78, "loss": 0.95, "lr": 4.107215526006818e-06, "epoch": 1.7848101265822784, "percentage": 60.26, "elapsed_time": "0:17:51", "remaining_time": "0:11:46"}
|
48 |
+
{"current_steps": 48, "total_steps": 78, "loss": 0.9351, "lr": 3.887395330218429e-06, "epoch": 1.8227848101265822, "percentage": 61.54, "elapsed_time": "0:18:12", "remaining_time": "0:11:22"}
|
49 |
+
{"current_steps": 49, "total_steps": 78, "loss": 0.8573, "lr": 3.669815772166625e-06, "epoch": 1.8607594936708862, "percentage": 62.82, "elapsed_time": "0:18:32", "remaining_time": "0:10:58"}
|
50 |
+
{"current_steps": 50, "total_steps": 78, "loss": 1.0057, "lr": 3.4549150281252635e-06, "epoch": 1.8987341772151898, "percentage": 64.1, "elapsed_time": "0:18:52", "remaining_time": "0:10:34"}
|
51 |
+
{"current_steps": 51, "total_steps": 78, "loss": 0.9267, "lr": 3.2431258795932863e-06, "epoch": 1.9367088607594938, "percentage": 65.38, "elapsed_time": "0:19:12", "remaining_time": "0:10:10"}
|
52 |
+
{"current_steps": 52, "total_steps": 78, "loss": 0.9172, "lr": 3.0348748417303826e-06, "epoch": 1.9746835443037973, "percentage": 66.67, "elapsed_time": "0:19:34", "remaining_time": "0:09:47"}
|
53 |
+
{"current_steps": 53, "total_steps": 78, "loss": 1.4886, "lr": 2.83058130441221e-06, "epoch": 2.0126582278481013, "percentage": 67.95, "elapsed_time": "0:20:48", "remaining_time": "0:09:48"}
|
54 |
+
{"current_steps": 54, "total_steps": 78, "loss": 0.8463, "lr": 2.6306566876350072e-06, "epoch": 2.050632911392405, "percentage": 69.23, "elapsed_time": "0:21:09", "remaining_time": "0:09:24"}
|
55 |
+
{"current_steps": 55, "total_steps": 78, "loss": 0.9339, "lr": 2.43550361297047e-06, "epoch": 2.088607594936709, "percentage": 70.51, "elapsed_time": "0:21:30", "remaining_time": "0:08:59"}
|
56 |
+
{"current_steps": 56, "total_steps": 78, "loss": 0.9372, "lr": 2.245515092739488e-06, "epoch": 2.1265822784810124, "percentage": 71.79, "elapsed_time": "0:21:52", "remaining_time": "0:08:35"}
|
57 |
+
{"current_steps": 57, "total_steps": 78, "loss": 0.895, "lr": 2.061073738537635e-06, "epoch": 2.1645569620253164, "percentage": 73.08, "elapsed_time": "0:22:14", "remaining_time": "0:08:11"}
|