sedrickkeh
commited on
Commit
•
8270d2b
1
Parent(s):
009b8f4
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 4903351912
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce614322d4c7502d6ea514dab94c32beaad72289947c0e127ded3b6201c5fe4d
|
3 |
size 4903351912
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4947570872
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12298323e3a73554d6d031b5a69ef7069fa6fe4fdec714c57f48144d41f518c5
|
3 |
size 4947570872
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4962221464
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7bb3f84bad64081c9b226a5988cdd3f503179ae025023afb5f3c72fb80d18b51
|
3 |
size 4962221464
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3670322200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa302bcf3785ed7d6ac4638bdb04d8249034e56a1d27dbfc3317e1554bff0a59
|
3 |
size 3670322200
|
trainer_log.jsonl
CHANGED
@@ -43,3 +43,48 @@
|
|
43 |
{"current_steps": 430, "total_steps": 1329, "loss": 0.5886, "learning_rate": 5e-06, "epoch": 0.9703808180535967, "percentage": 32.36, "elapsed_time": "10:44:10", "remaining_time": "22:26:46"}
|
44 |
{"current_steps": 440, "total_steps": 1329, "loss": 0.5934, "learning_rate": 5e-06, "epoch": 0.9929478138222849, "percentage": 33.11, "elapsed_time": "10:59:10", "remaining_time": "22:11:49"}
|
45 |
{"current_steps": 443, "total_steps": 1329, "eval_loss": 0.5912763476371765, "epoch": 0.9997179125528914, "percentage": 33.33, "elapsed_time": "11:15:28", "remaining_time": "22:30:57"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
{"current_steps": 430, "total_steps": 1329, "loss": 0.5886, "learning_rate": 5e-06, "epoch": 0.9703808180535967, "percentage": 32.36, "elapsed_time": "10:44:10", "remaining_time": "22:26:46"}
|
44 |
{"current_steps": 440, "total_steps": 1329, "loss": 0.5934, "learning_rate": 5e-06, "epoch": 0.9929478138222849, "percentage": 33.11, "elapsed_time": "10:59:10", "remaining_time": "22:11:49"}
|
45 |
{"current_steps": 443, "total_steps": 1329, "eval_loss": 0.5912763476371765, "epoch": 0.9997179125528914, "percentage": 33.33, "elapsed_time": "11:15:28", "remaining_time": "22:30:57"}
|
46 |
+
{"current_steps": 450, "total_steps": 1329, "loss": 0.6009, "learning_rate": 5e-06, "epoch": 1.0155148095909732, "percentage": 33.86, "elapsed_time": "11:27:02", "remaining_time": "22:22:00"}
|
47 |
+
{"current_steps": 460, "total_steps": 1329, "loss": 0.5282, "learning_rate": 5e-06, "epoch": 1.0380818053596614, "percentage": 34.61, "elapsed_time": "11:42:01", "remaining_time": "22:06:13"}
|
48 |
+
{"current_steps": 470, "total_steps": 1329, "loss": 0.543, "learning_rate": 5e-06, "epoch": 1.0606488011283497, "percentage": 35.36, "elapsed_time": "11:57:00", "remaining_time": "21:50:26"}
|
49 |
+
{"current_steps": 480, "total_steps": 1329, "loss": 0.5308, "learning_rate": 5e-06, "epoch": 1.0832157968970382, "percentage": 36.12, "elapsed_time": "12:11:59", "remaining_time": "21:34:42"}
|
50 |
+
{"current_steps": 490, "total_steps": 1329, "loss": 0.5411, "learning_rate": 5e-06, "epoch": 1.1057827926657264, "percentage": 36.87, "elapsed_time": "12:26:57", "remaining_time": "21:18:59"}
|
51 |
+
{"current_steps": 500, "total_steps": 1329, "loss": 0.5399, "learning_rate": 5e-06, "epoch": 1.1283497884344147, "percentage": 37.62, "elapsed_time": "12:41:56", "remaining_time": "21:03:18"}
|
52 |
+
{"current_steps": 510, "total_steps": 1329, "loss": 0.5411, "learning_rate": 5e-06, "epoch": 1.150916784203103, "percentage": 38.37, "elapsed_time": "12:56:55", "remaining_time": "20:47:39"}
|
53 |
+
{"current_steps": 520, "total_steps": 1329, "loss": 0.5336, "learning_rate": 5e-06, "epoch": 1.1734837799717912, "percentage": 39.13, "elapsed_time": "13:11:54", "remaining_time": "20:32:01"}
|
54 |
+
{"current_steps": 530, "total_steps": 1329, "loss": 0.5399, "learning_rate": 5e-06, "epoch": 1.1960507757404795, "percentage": 39.88, "elapsed_time": "13:26:53", "remaining_time": "20:16:26"}
|
55 |
+
{"current_steps": 540, "total_steps": 1329, "loss": 0.5373, "learning_rate": 5e-06, "epoch": 1.2186177715091677, "percentage": 40.63, "elapsed_time": "13:41:52", "remaining_time": "20:00:51"}
|
56 |
+
{"current_steps": 550, "total_steps": 1329, "loss": 0.5421, "learning_rate": 5e-06, "epoch": 1.2411847672778562, "percentage": 41.38, "elapsed_time": "13:56:51", "remaining_time": "19:45:17"}
|
57 |
+
{"current_steps": 560, "total_steps": 1329, "loss": 0.544, "learning_rate": 5e-06, "epoch": 1.2637517630465445, "percentage": 42.14, "elapsed_time": "14:11:50", "remaining_time": "19:29:45"}
|
58 |
+
{"current_steps": 570, "total_steps": 1329, "loss": 0.5412, "learning_rate": 5e-06, "epoch": 1.2863187588152327, "percentage": 42.89, "elapsed_time": "14:26:50", "remaining_time": "19:14:15"}
|
59 |
+
{"current_steps": 580, "total_steps": 1329, "loss": 0.5411, "learning_rate": 5e-06, "epoch": 1.308885754583921, "percentage": 43.64, "elapsed_time": "14:41:49", "remaining_time": "18:58:45"}
|
60 |
+
{"current_steps": 590, "total_steps": 1329, "loss": 0.5411, "learning_rate": 5e-06, "epoch": 1.3314527503526092, "percentage": 44.39, "elapsed_time": "14:56:48", "remaining_time": "18:43:17"}
|
61 |
+
{"current_steps": 600, "total_steps": 1329, "loss": 0.5464, "learning_rate": 5e-06, "epoch": 1.3540197461212977, "percentage": 45.15, "elapsed_time": "15:11:47", "remaining_time": "18:27:49"}
|
62 |
+
{"current_steps": 610, "total_steps": 1329, "loss": 0.5391, "learning_rate": 5e-06, "epoch": 1.376586741889986, "percentage": 45.9, "elapsed_time": "15:26:46", "remaining_time": "18:12:23"}
|
63 |
+
{"current_steps": 620, "total_steps": 1329, "loss": 0.5434, "learning_rate": 5e-06, "epoch": 1.3991537376586742, "percentage": 46.65, "elapsed_time": "15:41:46", "remaining_time": "17:56:57"}
|
64 |
+
{"current_steps": 630, "total_steps": 1329, "loss": 0.5415, "learning_rate": 5e-06, "epoch": 1.4217207334273625, "percentage": 47.4, "elapsed_time": "15:56:45", "remaining_time": "17:41:32"}
|
65 |
+
{"current_steps": 640, "total_steps": 1329, "loss": 0.5412, "learning_rate": 5e-06, "epoch": 1.4442877291960508, "percentage": 48.16, "elapsed_time": "16:11:44", "remaining_time": "17:26:08"}
|
66 |
+
{"current_steps": 650, "total_steps": 1329, "loss": 0.5421, "learning_rate": 5e-06, "epoch": 1.466854724964739, "percentage": 48.91, "elapsed_time": "16:26:43", "remaining_time": "17:10:44"}
|
67 |
+
{"current_steps": 660, "total_steps": 1329, "loss": 0.5459, "learning_rate": 5e-06, "epoch": 1.4894217207334273, "percentage": 49.66, "elapsed_time": "16:41:42", "remaining_time": "16:55:22"}
|
68 |
+
{"current_steps": 670, "total_steps": 1329, "loss": 0.5405, "learning_rate": 5e-06, "epoch": 1.5119887165021155, "percentage": 50.41, "elapsed_time": "16:56:41", "remaining_time": "16:40:00"}
|
69 |
+
{"current_steps": 680, "total_steps": 1329, "loss": 0.5346, "learning_rate": 5e-06, "epoch": 1.5345557122708038, "percentage": 51.17, "elapsed_time": "17:11:41", "remaining_time": "16:24:39"}
|
70 |
+
{"current_steps": 690, "total_steps": 1329, "loss": 0.5368, "learning_rate": 5e-06, "epoch": 1.5571227080394923, "percentage": 51.92, "elapsed_time": "17:26:40", "remaining_time": "16:09:18"}
|
71 |
+
{"current_steps": 700, "total_steps": 1329, "loss": 0.5411, "learning_rate": 5e-06, "epoch": 1.5796897038081805, "percentage": 52.67, "elapsed_time": "17:41:39", "remaining_time": "15:53:58"}
|
72 |
+
{"current_steps": 710, "total_steps": 1329, "loss": 0.5438, "learning_rate": 5e-06, "epoch": 1.6022566995768688, "percentage": 53.42, "elapsed_time": "17:56:38", "remaining_time": "15:38:39"}
|
73 |
+
{"current_steps": 720, "total_steps": 1329, "loss": 0.5518, "learning_rate": 5e-06, "epoch": 1.6248236953455573, "percentage": 54.18, "elapsed_time": "18:11:38", "remaining_time": "15:23:20"}
|
74 |
+
{"current_steps": 730, "total_steps": 1329, "loss": 0.535, "learning_rate": 5e-06, "epoch": 1.6473906911142455, "percentage": 54.93, "elapsed_time": "18:26:37", "remaining_time": "15:08:02"}
|
75 |
+
{"current_steps": 740, "total_steps": 1329, "loss": 0.5509, "learning_rate": 5e-06, "epoch": 1.6699576868829338, "percentage": 55.68, "elapsed_time": "18:41:36", "remaining_time": "14:52:44"}
|
76 |
+
{"current_steps": 750, "total_steps": 1329, "loss": 0.5422, "learning_rate": 5e-06, "epoch": 1.692524682651622, "percentage": 56.43, "elapsed_time": "18:56:35", "remaining_time": "14:37:27"}
|
77 |
+
{"current_steps": 760, "total_steps": 1329, "loss": 0.5411, "learning_rate": 5e-06, "epoch": 1.7150916784203103, "percentage": 57.19, "elapsed_time": "19:11:34", "remaining_time": "14:22:10"}
|
78 |
+
{"current_steps": 770, "total_steps": 1329, "loss": 0.5418, "learning_rate": 5e-06, "epoch": 1.7376586741889986, "percentage": 57.94, "elapsed_time": "19:26:34", "remaining_time": "14:06:54"}
|
79 |
+
{"current_steps": 780, "total_steps": 1329, "loss": 0.5377, "learning_rate": 5e-06, "epoch": 1.7602256699576868, "percentage": 58.69, "elapsed_time": "19:41:34", "remaining_time": "13:51:38"}
|
80 |
+
{"current_steps": 790, "total_steps": 1329, "loss": 0.5413, "learning_rate": 5e-06, "epoch": 1.782792665726375, "percentage": 59.44, "elapsed_time": "19:56:33", "remaining_time": "13:36:22"}
|
81 |
+
{"current_steps": 800, "total_steps": 1329, "loss": 0.5363, "learning_rate": 5e-06, "epoch": 1.8053596614950633, "percentage": 60.2, "elapsed_time": "20:11:32", "remaining_time": "13:21:08"}
|
82 |
+
{"current_steps": 810, "total_steps": 1329, "loss": 0.547, "learning_rate": 5e-06, "epoch": 1.8279266572637518, "percentage": 60.95, "elapsed_time": "20:26:32", "remaining_time": "13:05:53"}
|
83 |
+
{"current_steps": 820, "total_steps": 1329, "loss": 0.5344, "learning_rate": 5e-06, "epoch": 1.85049365303244, "percentage": 61.7, "elapsed_time": "20:41:31", "remaining_time": "12:50:39"}
|
84 |
+
{"current_steps": 830, "total_steps": 1329, "loss": 0.5467, "learning_rate": 5e-06, "epoch": 1.8730606488011283, "percentage": 62.45, "elapsed_time": "20:56:31", "remaining_time": "12:35:25"}
|
85 |
+
{"current_steps": 840, "total_steps": 1329, "loss": 0.5465, "learning_rate": 5e-06, "epoch": 1.8956276445698168, "percentage": 63.21, "elapsed_time": "21:11:30", "remaining_time": "12:20:12"}
|
86 |
+
{"current_steps": 850, "total_steps": 1329, "loss": 0.5343, "learning_rate": 5e-06, "epoch": 1.918194640338505, "percentage": 63.96, "elapsed_time": "21:26:30", "remaining_time": "12:04:59"}
|
87 |
+
{"current_steps": 860, "total_steps": 1329, "loss": 0.5394, "learning_rate": 5e-06, "epoch": 1.9407616361071933, "percentage": 64.71, "elapsed_time": "21:41:29", "remaining_time": "11:49:46"}
|
88 |
+
{"current_steps": 870, "total_steps": 1329, "loss": 0.5457, "learning_rate": 5e-06, "epoch": 1.9633286318758816, "percentage": 65.46, "elapsed_time": "21:56:28", "remaining_time": "11:34:33"}
|
89 |
+
{"current_steps": 880, "total_steps": 1329, "loss": 0.5441, "learning_rate": 5e-06, "epoch": 1.9858956276445698, "percentage": 66.22, "elapsed_time": "22:11:27", "remaining_time": "11:19:20"}
|
90 |
+
{"current_steps": 886, "total_steps": 1329, "eval_loss": 0.587400496006012, "epoch": 1.9994358251057829, "percentage": 66.67, "elapsed_time": "22:32:23", "remaining_time": "11:16:11"}
|