sedrickkeh
commited on
Commit
•
ff08041
1
Parent(s):
72cf443
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 4877660776
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4a557b439e19fd3312e5449d26332e7126d7be30b9aaeda956ab75268bba0f5
|
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:a6ff230f0b878fc540b11b5fe8527edaa00d97b49ed1e15b797f8e7fa7e93fce
|
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 sha256:19faf55767a16b0cffa80f0704903a6dbcf4cd080fc6e5b5277693015b8e73d5
|
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:d365d4444b2187c7ffeb7a29909a0e220056db3e2e33c2beebe8327095c4e510
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -88,3 +88,46 @@
|
|
88 |
{"current_steps": 870, "total_steps": 1314, "loss": 0.596, "learning_rate": 5e-06, "epoch": 1.9834757834757835, "percentage": 66.21, "elapsed_time": "12:48:48", "remaining_time": "6:32:21"}
|
89 |
{"current_steps": 877, "total_steps": 1314, "eval_loss": 0.6186895370483398, "epoch": 1.9994301994301993, "percentage": 66.74, "elapsed_time": "13:02:11", "remaining_time": "6:29:45"}
|
90 |
{"current_steps": 880, "total_steps": 1314, "loss": 0.6154, "learning_rate": 5e-06, "epoch": 2.006837606837607, "percentage": 66.97, "elapsed_time": "13:05:53", "remaining_time": "6:27:35"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
88 |
{"current_steps": 870, "total_steps": 1314, "loss": 0.596, "learning_rate": 5e-06, "epoch": 1.9834757834757835, "percentage": 66.21, "elapsed_time": "12:48:48", "remaining_time": "6:32:21"}
|
89 |
{"current_steps": 877, "total_steps": 1314, "eval_loss": 0.6186895370483398, "epoch": 1.9994301994301993, "percentage": 66.74, "elapsed_time": "13:02:11", "remaining_time": "6:29:45"}
|
90 |
{"current_steps": 880, "total_steps": 1314, "loss": 0.6154, "learning_rate": 5e-06, "epoch": 2.006837606837607, "percentage": 66.97, "elapsed_time": "13:05:53", "remaining_time": "6:27:35"}
|
91 |
+
{"current_steps": 890, "total_steps": 1314, "loss": 0.5545, "learning_rate": 5e-06, "epoch": 2.0296296296296297, "percentage": 67.73, "elapsed_time": "13:14:37", "remaining_time": "6:18:33"}
|
92 |
+
{"current_steps": 900, "total_steps": 1314, "loss": 0.5696, "learning_rate": 5e-06, "epoch": 2.0524216524216525, "percentage": 68.49, "elapsed_time": "13:23:22", "remaining_time": "6:09:32"}
|
93 |
+
{"current_steps": 910, "total_steps": 1314, "loss": 0.5678, "learning_rate": 5e-06, "epoch": 2.0752136752136754, "percentage": 69.25, "elapsed_time": "13:32:07", "remaining_time": "6:00:32"}
|
94 |
+
{"current_steps": 920, "total_steps": 1314, "loss": 0.5709, "learning_rate": 5e-06, "epoch": 2.098005698005698, "percentage": 70.02, "elapsed_time": "13:40:51", "remaining_time": "5:51:32"}
|
95 |
+
{"current_steps": 930, "total_steps": 1314, "loss": 0.5689, "learning_rate": 5e-06, "epoch": 2.1207977207977207, "percentage": 70.78, "elapsed_time": "13:49:37", "remaining_time": "5:42:33"}
|
96 |
+
{"current_steps": 940, "total_steps": 1314, "loss": 0.5636, "learning_rate": 5e-06, "epoch": 2.1435897435897435, "percentage": 71.54, "elapsed_time": "13:58:22", "remaining_time": "5:33:33"}
|
97 |
+
{"current_steps": 950, "total_steps": 1314, "loss": 0.5645, "learning_rate": 5e-06, "epoch": 2.1663817663817664, "percentage": 72.3, "elapsed_time": "14:07:07", "remaining_time": "5:24:34"}
|
98 |
+
{"current_steps": 960, "total_steps": 1314, "loss": 0.5696, "learning_rate": 5e-06, "epoch": 2.1891737891737892, "percentage": 73.06, "elapsed_time": "14:15:51", "remaining_time": "5:15:36"}
|
99 |
+
{"current_steps": 970, "total_steps": 1314, "loss": 0.569, "learning_rate": 5e-06, "epoch": 2.211965811965812, "percentage": 73.82, "elapsed_time": "14:24:36", "remaining_time": "5:06:37"}
|
100 |
+
{"current_steps": 980, "total_steps": 1314, "loss": 0.5587, "learning_rate": 5e-06, "epoch": 2.234757834757835, "percentage": 74.58, "elapsed_time": "14:33:21", "remaining_time": "4:57:39"}
|
101 |
+
{"current_steps": 990, "total_steps": 1314, "loss": 0.5677, "learning_rate": 5e-06, "epoch": 2.2575498575498574, "percentage": 75.34, "elapsed_time": "14:42:05", "remaining_time": "4:48:40"}
|
102 |
+
{"current_steps": 1000, "total_steps": 1314, "loss": 0.5681, "learning_rate": 5e-06, "epoch": 2.2803418803418802, "percentage": 76.1, "elapsed_time": "14:50:49", "remaining_time": "4:39:43"}
|
103 |
+
{"current_steps": 1010, "total_steps": 1314, "loss": 0.5655, "learning_rate": 5e-06, "epoch": 2.303133903133903, "percentage": 76.86, "elapsed_time": "14:59:34", "remaining_time": "4:30:45"}
|
104 |
+
{"current_steps": 1020, "total_steps": 1314, "loss": 0.5686, "learning_rate": 5e-06, "epoch": 2.325925925925926, "percentage": 77.63, "elapsed_time": "15:08:18", "remaining_time": "4:21:48"}
|
105 |
+
{"current_steps": 1030, "total_steps": 1314, "loss": 0.5699, "learning_rate": 5e-06, "epoch": 2.348717948717949, "percentage": 78.39, "elapsed_time": "15:17:02", "remaining_time": "4:12:51"}
|
106 |
+
{"current_steps": 1040, "total_steps": 1314, "loss": 0.5678, "learning_rate": 5e-06, "epoch": 2.3715099715099717, "percentage": 79.15, "elapsed_time": "15:25:46", "remaining_time": "4:03:54"}
|
107 |
+
{"current_steps": 1050, "total_steps": 1314, "loss": 0.5672, "learning_rate": 5e-06, "epoch": 2.394301994301994, "percentage": 79.91, "elapsed_time": "15:34:31", "remaining_time": "3:54:57"}
|
108 |
+
{"current_steps": 1060, "total_steps": 1314, "loss": 0.5755, "learning_rate": 5e-06, "epoch": 2.417094017094017, "percentage": 80.67, "elapsed_time": "15:43:15", "remaining_time": "3:46:01"}
|
109 |
+
{"current_steps": 1070, "total_steps": 1314, "loss": 0.5784, "learning_rate": 5e-06, "epoch": 2.43988603988604, "percentage": 81.43, "elapsed_time": "15:52:00", "remaining_time": "3:37:05"}
|
110 |
+
{"current_steps": 1080, "total_steps": 1314, "loss": 0.5736, "learning_rate": 5e-06, "epoch": 2.4626780626780627, "percentage": 82.19, "elapsed_time": "16:00:44", "remaining_time": "3:28:09"}
|
111 |
+
{"current_steps": 1090, "total_steps": 1314, "loss": 0.5713, "learning_rate": 5e-06, "epoch": 2.4854700854700855, "percentage": 82.95, "elapsed_time": "16:09:29", "remaining_time": "3:19:14"}
|
112 |
+
{"current_steps": 1100, "total_steps": 1314, "loss": 0.5777, "learning_rate": 5e-06, "epoch": 2.5082621082621084, "percentage": 83.71, "elapsed_time": "16:18:14", "remaining_time": "3:10:18"}
|
113 |
+
{"current_steps": 1110, "total_steps": 1314, "loss": 0.5712, "learning_rate": 5e-06, "epoch": 2.5310541310541312, "percentage": 84.47, "elapsed_time": "16:26:59", "remaining_time": "3:01:23"}
|
114 |
+
{"current_steps": 1120, "total_steps": 1314, "loss": 0.5693, "learning_rate": 5e-06, "epoch": 2.5538461538461537, "percentage": 85.24, "elapsed_time": "16:35:42", "remaining_time": "2:52:28"}
|
115 |
+
{"current_steps": 1130, "total_steps": 1314, "loss": 0.5688, "learning_rate": 5e-06, "epoch": 2.5766381766381765, "percentage": 86.0, "elapsed_time": "16:44:25", "remaining_time": "2:43:33"}
|
116 |
+
{"current_steps": 1140, "total_steps": 1314, "loss": 0.5684, "learning_rate": 5e-06, "epoch": 2.5994301994301994, "percentage": 86.76, "elapsed_time": "16:53:08", "remaining_time": "2:34:38"}
|
117 |
+
{"current_steps": 1150, "total_steps": 1314, "loss": 0.5687, "learning_rate": 5e-06, "epoch": 2.6222222222222222, "percentage": 87.52, "elapsed_time": "17:01:52", "remaining_time": "2:25:43"}
|
118 |
+
{"current_steps": 1160, "total_steps": 1314, "loss": 0.5699, "learning_rate": 5e-06, "epoch": 2.645014245014245, "percentage": 88.28, "elapsed_time": "17:10:36", "remaining_time": "2:16:49"}
|
119 |
+
{"current_steps": 1170, "total_steps": 1314, "loss": 0.5726, "learning_rate": 5e-06, "epoch": 2.667806267806268, "percentage": 89.04, "elapsed_time": "17:19:20", "remaining_time": "2:07:55"}
|
120 |
+
{"current_steps": 1180, "total_steps": 1314, "loss": 0.5678, "learning_rate": 5e-06, "epoch": 2.690598290598291, "percentage": 89.8, "elapsed_time": "17:28:03", "remaining_time": "1:59:01"}
|
121 |
+
{"current_steps": 1190, "total_steps": 1314, "loss": 0.5689, "learning_rate": 5e-06, "epoch": 2.7133903133903132, "percentage": 90.56, "elapsed_time": "17:36:48", "remaining_time": "1:50:07"}
|
122 |
+
{"current_steps": 1200, "total_steps": 1314, "loss": 0.5721, "learning_rate": 5e-06, "epoch": 2.736182336182336, "percentage": 91.32, "elapsed_time": "17:45:32", "remaining_time": "1:41:13"}
|
123 |
+
{"current_steps": 1210, "total_steps": 1314, "loss": 0.5755, "learning_rate": 5e-06, "epoch": 2.758974358974359, "percentage": 92.09, "elapsed_time": "17:54:16", "remaining_time": "1:32:20"}
|
124 |
+
{"current_steps": 1220, "total_steps": 1314, "loss": 0.5653, "learning_rate": 5e-06, "epoch": 2.781766381766382, "percentage": 92.85, "elapsed_time": "18:03:01", "remaining_time": "1:23:26"}
|
125 |
+
{"current_steps": 1230, "total_steps": 1314, "loss": 0.5638, "learning_rate": 5e-06, "epoch": 2.8045584045584047, "percentage": 93.61, "elapsed_time": "18:11:45", "remaining_time": "1:14:33"}
|
126 |
+
{"current_steps": 1240, "total_steps": 1314, "loss": 0.5786, "learning_rate": 5e-06, "epoch": 2.827350427350427, "percentage": 94.37, "elapsed_time": "18:20:30", "remaining_time": "1:05:40"}
|
127 |
+
{"current_steps": 1250, "total_steps": 1314, "loss": 0.5753, "learning_rate": 5e-06, "epoch": 2.8501424501424504, "percentage": 95.13, "elapsed_time": "18:29:14", "remaining_time": "0:56:47"}
|
128 |
+
{"current_steps": 1260, "total_steps": 1314, "loss": 0.5724, "learning_rate": 5e-06, "epoch": 2.872934472934473, "percentage": 95.89, "elapsed_time": "18:37:58", "remaining_time": "0:47:54"}
|
129 |
+
{"current_steps": 1270, "total_steps": 1314, "loss": 0.5734, "learning_rate": 5e-06, "epoch": 2.8957264957264957, "percentage": 96.65, "elapsed_time": "18:46:41", "remaining_time": "0:39:02"}
|
130 |
+
{"current_steps": 1280, "total_steps": 1314, "loss": 0.5636, "learning_rate": 5e-06, "epoch": 2.9185185185185185, "percentage": 97.41, "elapsed_time": "18:55:26", "remaining_time": "0:30:09"}
|
131 |
+
{"current_steps": 1290, "total_steps": 1314, "loss": 0.5638, "learning_rate": 5e-06, "epoch": 2.9413105413105414, "percentage": 98.17, "elapsed_time": "19:04:10", "remaining_time": "0:21:17"}
|
132 |
+
{"current_steps": 1300, "total_steps": 1314, "loss": 0.5649, "learning_rate": 5e-06, "epoch": 2.9641025641025642, "percentage": 98.93, "elapsed_time": "19:12:55", "remaining_time": "0:12:24"}
|
133 |
+
{"current_steps": 1310, "total_steps": 1314, "loss": 0.5748, "learning_rate": 5e-06, "epoch": 2.9868945868945866, "percentage": 99.7, "elapsed_time": "19:21:39", "remaining_time": "0:03:32"}
|