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 4976698672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:982f1c5b42195d197dbb3331de198374ff61835fe9ab6d78caf4f61007d76185
|
3 |
size 4976698672
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999802720
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b97af9d4b86001d7affa3555abe036f95c9aea8d732ec3d80230d8da8a52689
|
3 |
size 4999802720
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4915916176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a990d9454e170744a40253e045ed580824a99dfc09ca1a408395684d7674408
|
3 |
size 4915916176
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1168138808
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:434b04fe3e7aa39def57253dc62adc0f80b16bba66fea26b5d9fdadc016eb86d
|
3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
@@ -43,3 +43,47 @@
|
|
43 |
{"current_steps": 423, "total_steps": 1269, "eval_loss": 0.6508128643035889, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:44:54", "remaining_time": "1:29:49"}
|
44 |
{"current_steps": 430, "total_steps": 1269, "loss": 0.6168, "learning_rate": 5e-06, "epoch": 1.016548463356974, "percentage": 33.88, "elapsed_time": "0:49:50", "remaining_time": "1:37:15"}
|
45 |
{"current_steps": 440, "total_steps": 1269, "loss": 0.6076, "learning_rate": 5e-06, "epoch": 1.0401891252955082, "percentage": 34.67, "elapsed_time": "0:50:54", "remaining_time": "1:35:55"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
{"current_steps": 423, "total_steps": 1269, "eval_loss": 0.6508128643035889, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:44:54", "remaining_time": "1:29:49"}
|
44 |
{"current_steps": 430, "total_steps": 1269, "loss": 0.6168, "learning_rate": 5e-06, "epoch": 1.016548463356974, "percentage": 33.88, "elapsed_time": "0:49:50", "remaining_time": "1:37:15"}
|
45 |
{"current_steps": 440, "total_steps": 1269, "loss": 0.6076, "learning_rate": 5e-06, "epoch": 1.0401891252955082, "percentage": 34.67, "elapsed_time": "0:50:54", "remaining_time": "1:35:55"}
|
46 |
+
{"current_steps": 450, "total_steps": 1269, "loss": 0.607, "learning_rate": 5e-06, "epoch": 1.0638297872340425, "percentage": 35.46, "elapsed_time": "0:52:17", "remaining_time": "1:35:10"}
|
47 |
+
{"current_steps": 460, "total_steps": 1269, "loss": 0.6053, "learning_rate": 5e-06, "epoch": 1.0874704491725768, "percentage": 36.25, "elapsed_time": "0:53:19", "remaining_time": "1:33:47"}
|
48 |
+
{"current_steps": 470, "total_steps": 1269, "loss": 0.6125, "learning_rate": 5e-06, "epoch": 1.1111111111111112, "percentage": 37.04, "elapsed_time": "0:54:23", "remaining_time": "1:32:27"}
|
49 |
+
{"current_steps": 480, "total_steps": 1269, "loss": 0.6075, "learning_rate": 5e-06, "epoch": 1.1347517730496455, "percentage": 37.83, "elapsed_time": "0:55:35", "remaining_time": "1:31:23"}
|
50 |
+
{"current_steps": 490, "total_steps": 1269, "loss": 0.6149, "learning_rate": 5e-06, "epoch": 1.1583924349881798, "percentage": 38.61, "elapsed_time": "0:56:38", "remaining_time": "1:30:02"}
|
51 |
+
{"current_steps": 500, "total_steps": 1269, "loss": 0.6081, "learning_rate": 5e-06, "epoch": 1.1820330969267139, "percentage": 39.4, "elapsed_time": "0:57:46", "remaining_time": "1:28:51"}
|
52 |
+
{"current_steps": 510, "total_steps": 1269, "loss": 0.6079, "learning_rate": 5e-06, "epoch": 1.2056737588652482, "percentage": 40.19, "elapsed_time": "0:58:58", "remaining_time": "1:27:46"}
|
53 |
+
{"current_steps": 520, "total_steps": 1269, "loss": 0.6036, "learning_rate": 5e-06, "epoch": 1.2293144208037825, "percentage": 40.98, "elapsed_time": "1:00:01", "remaining_time": "1:26:26"}
|
54 |
+
{"current_steps": 530, "total_steps": 1269, "loss": 0.6045, "learning_rate": 5e-06, "epoch": 1.2529550827423168, "percentage": 41.77, "elapsed_time": "1:01:03", "remaining_time": "1:25:08"}
|
55 |
+
{"current_steps": 540, "total_steps": 1269, "loss": 0.6064, "learning_rate": 5e-06, "epoch": 1.2765957446808511, "percentage": 42.55, "elapsed_time": "1:02:05", "remaining_time": "1:23:49"}
|
56 |
+
{"current_steps": 550, "total_steps": 1269, "loss": 0.6081, "learning_rate": 5e-06, "epoch": 1.3002364066193852, "percentage": 43.34, "elapsed_time": "1:03:08", "remaining_time": "1:22:32"}
|
57 |
+
{"current_steps": 560, "total_steps": 1269, "loss": 0.6055, "learning_rate": 5e-06, "epoch": 1.3238770685579198, "percentage": 44.13, "elapsed_time": "1:04:10", "remaining_time": "1:21:15"}
|
58 |
+
{"current_steps": 570, "total_steps": 1269, "loss": 0.6107, "learning_rate": 5e-06, "epoch": 1.3475177304964538, "percentage": 44.92, "elapsed_time": "1:05:13", "remaining_time": "1:19:58"}
|
59 |
+
{"current_steps": 580, "total_steps": 1269, "loss": 0.6052, "learning_rate": 5e-06, "epoch": 1.3711583924349882, "percentage": 45.71, "elapsed_time": "1:06:15", "remaining_time": "1:18:42"}
|
60 |
+
{"current_steps": 590, "total_steps": 1269, "loss": 0.6051, "learning_rate": 5e-06, "epoch": 1.3947990543735225, "percentage": 46.49, "elapsed_time": "1:07:28", "remaining_time": "1:17:39"}
|
61 |
+
{"current_steps": 600, "total_steps": 1269, "loss": 0.6057, "learning_rate": 5e-06, "epoch": 1.4184397163120568, "percentage": 47.28, "elapsed_time": "1:08:31", "remaining_time": "1:16:24"}
|
62 |
+
{"current_steps": 610, "total_steps": 1269, "loss": 0.6043, "learning_rate": 5e-06, "epoch": 1.442080378250591, "percentage": 48.07, "elapsed_time": "1:09:33", "remaining_time": "1:15:09"}
|
63 |
+
{"current_steps": 620, "total_steps": 1269, "loss": 0.6033, "learning_rate": 5e-06, "epoch": 1.4657210401891252, "percentage": 48.86, "elapsed_time": "1:10:36", "remaining_time": "1:13:54"}
|
64 |
+
{"current_steps": 630, "total_steps": 1269, "loss": 0.6132, "learning_rate": 5e-06, "epoch": 1.4893617021276595, "percentage": 49.65, "elapsed_time": "1:11:38", "remaining_time": "1:12:39"}
|
65 |
+
{"current_steps": 640, "total_steps": 1269, "loss": 0.6047, "learning_rate": 5e-06, "epoch": 1.5130023640661938, "percentage": 50.43, "elapsed_time": "1:12:40", "remaining_time": "1:11:25"}
|
66 |
+
{"current_steps": 650, "total_steps": 1269, "loss": 0.6073, "learning_rate": 5e-06, "epoch": 1.5366430260047281, "percentage": 51.22, "elapsed_time": "1:13:43", "remaining_time": "1:10:12"}
|
67 |
+
{"current_steps": 660, "total_steps": 1269, "loss": 0.608, "learning_rate": 5e-06, "epoch": 1.5602836879432624, "percentage": 52.01, "elapsed_time": "1:14:52", "remaining_time": "1:09:05"}
|
68 |
+
{"current_steps": 670, "total_steps": 1269, "loss": 0.6004, "learning_rate": 5e-06, "epoch": 1.5839243498817965, "percentage": 52.8, "elapsed_time": "1:16:03", "remaining_time": "1:08:00"}
|
69 |
+
{"current_steps": 680, "total_steps": 1269, "loss": 0.6019, "learning_rate": 5e-06, "epoch": 1.607565011820331, "percentage": 53.59, "elapsed_time": "1:17:06", "remaining_time": "1:06:47"}
|
70 |
+
{"current_steps": 690, "total_steps": 1269, "loss": 0.6055, "learning_rate": 5e-06, "epoch": 1.6312056737588652, "percentage": 54.37, "elapsed_time": "1:18:09", "remaining_time": "1:05:34"}
|
71 |
+
{"current_steps": 700, "total_steps": 1269, "loss": 0.6074, "learning_rate": 5e-06, "epoch": 1.6548463356973995, "percentage": 55.16, "elapsed_time": "1:19:11", "remaining_time": "1:04:22"}
|
72 |
+
{"current_steps": 710, "total_steps": 1269, "loss": 0.6051, "learning_rate": 5e-06, "epoch": 1.6784869976359338, "percentage": 55.95, "elapsed_time": "1:20:13", "remaining_time": "1:03:10"}
|
73 |
+
{"current_steps": 720, "total_steps": 1269, "loss": 0.5994, "learning_rate": 5e-06, "epoch": 1.702127659574468, "percentage": 56.74, "elapsed_time": "1:21:16", "remaining_time": "1:01:58"}
|
74 |
+
{"current_steps": 730, "total_steps": 1269, "loss": 0.6044, "learning_rate": 5e-06, "epoch": 1.7257683215130024, "percentage": 57.53, "elapsed_time": "1:22:18", "remaining_time": "1:00:46"}
|
75 |
+
{"current_steps": 740, "total_steps": 1269, "loss": 0.6089, "learning_rate": 5e-06, "epoch": 1.7494089834515365, "percentage": 58.31, "elapsed_time": "1:23:21", "remaining_time": "0:59:35"}
|
76 |
+
{"current_steps": 750, "total_steps": 1269, "loss": 0.6003, "learning_rate": 5e-06, "epoch": 1.773049645390071, "percentage": 59.1, "elapsed_time": "1:24:23", "remaining_time": "0:58:23"}
|
77 |
+
{"current_steps": 760, "total_steps": 1269, "loss": 0.5998, "learning_rate": 5e-06, "epoch": 1.7966903073286051, "percentage": 59.89, "elapsed_time": "1:25:25", "remaining_time": "0:57:12"}
|
78 |
+
{"current_steps": 770, "total_steps": 1269, "loss": 0.6096, "learning_rate": 5e-06, "epoch": 1.8203309692671394, "percentage": 60.68, "elapsed_time": "1:26:28", "remaining_time": "0:56:02"}
|
79 |
+
{"current_steps": 780, "total_steps": 1269, "loss": 0.6062, "learning_rate": 5e-06, "epoch": 1.8439716312056738, "percentage": 61.47, "elapsed_time": "1:27:35", "remaining_time": "0:54:54"}
|
80 |
+
{"current_steps": 790, "total_steps": 1269, "loss": 0.6082, "learning_rate": 5e-06, "epoch": 1.867612293144208, "percentage": 62.25, "elapsed_time": "1:28:43", "remaining_time": "0:53:47"}
|
81 |
+
{"current_steps": 800, "total_steps": 1269, "loss": 0.5968, "learning_rate": 5e-06, "epoch": 1.8912529550827424, "percentage": 63.04, "elapsed_time": "1:29:45", "remaining_time": "0:52:37"}
|
82 |
+
{"current_steps": 810, "total_steps": 1269, "loss": 0.5955, "learning_rate": 5e-06, "epoch": 1.9148936170212765, "percentage": 63.83, "elapsed_time": "1:30:48", "remaining_time": "0:51:27"}
|
83 |
+
{"current_steps": 820, "total_steps": 1269, "loss": 0.606, "learning_rate": 5e-06, "epoch": 1.938534278959811, "percentage": 64.62, "elapsed_time": "1:31:50", "remaining_time": "0:50:17"}
|
84 |
+
{"current_steps": 830, "total_steps": 1269, "loss": 0.6028, "learning_rate": 5e-06, "epoch": 1.962174940898345, "percentage": 65.41, "elapsed_time": "1:32:53", "remaining_time": "0:49:07"}
|
85 |
+
{"current_steps": 840, "total_steps": 1269, "loss": 0.6057, "learning_rate": 5e-06, "epoch": 1.9858156028368794, "percentage": 66.19, "elapsed_time": "1:33:55", "remaining_time": "0:47:58"}
|
86 |
+
{"current_steps": 846, "total_steps": 1269, "eval_loss": 0.6412354111671448, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:35:10", "remaining_time": "0:47:35"}
|
87 |
+
{"current_steps": 850, "total_steps": 1269, "loss": 0.5827, "learning_rate": 5e-06, "epoch": 2.0094562647754137, "percentage": 66.98, "elapsed_time": "1:39:32", "remaining_time": "0:49:04"}
|
88 |
+
{"current_steps": 860, "total_steps": 1269, "loss": 0.5511, "learning_rate": 5e-06, "epoch": 2.033096926713948, "percentage": 67.77, "elapsed_time": "1:40:35", "remaining_time": "0:47:50"}
|
89 |
+
{"current_steps": 870, "total_steps": 1269, "loss": 0.5581, "learning_rate": 5e-06, "epoch": 2.0567375886524824, "percentage": 68.56, "elapsed_time": "1:41:48", "remaining_time": "0:46:41"}
|