sedrickkeh
commited on
Commit
•
3014e63
1
Parent(s):
ff891e3
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:c059aefc2eaa34ee9a27b9e85533807049ff7f8c65dcebdaa903227337c338fd
|
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:d2f4f5418eeff63061cbedf9814221ce40d0d811a870af493eeda761f814d164
|
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 sha256:7350bdeb69bf1256d991134d4cde9c08d04f533e3896e93af5ab1c47150cc8be
|
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:dca60044bc93c56416dd6be874ef8c133ae2c659bcff3c33d7dfeb091600726e
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -87,3 +87,47 @@
|
|
87 |
{"current_steps": 860, "total_steps": 1314, "loss": 0.5986, "learning_rate": 5e-06, "epoch": 1.9606837606837608, "percentage": 65.45, "elapsed_time": "12:41:38", "remaining_time": "6:42:04"}
|
88 |
{"current_steps": 870, "total_steps": 1314, "loss": 0.596, "learning_rate": 5e-06, "epoch": 1.9834757834757835, "percentage": 66.21, "elapsed_time": "12:50:23", "remaining_time": "6:33:10"}
|
89 |
{"current_steps": 877, "total_steps": 1314, "eval_loss": 0.6187179088592529, "epoch": 1.9994301994301993, "percentage": 66.74, "elapsed_time": "13:03:54", "remaining_time": "6:30:36"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
87 |
{"current_steps": 860, "total_steps": 1314, "loss": 0.5986, "learning_rate": 5e-06, "epoch": 1.9606837606837608, "percentage": 65.45, "elapsed_time": "12:41:38", "remaining_time": "6:42:04"}
|
88 |
{"current_steps": 870, "total_steps": 1314, "loss": 0.596, "learning_rate": 5e-06, "epoch": 1.9834757834757835, "percentage": 66.21, "elapsed_time": "12:50:23", "remaining_time": "6:33:10"}
|
89 |
{"current_steps": 877, "total_steps": 1314, "eval_loss": 0.6187179088592529, "epoch": 1.9994301994301993, "percentage": 66.74, "elapsed_time": "13:03:54", "remaining_time": "6:30:36"}
|
90 |
+
{"current_steps": 880, "total_steps": 1314, "loss": 0.6154, "learning_rate": 5e-06, "epoch": 2.006837606837607, "percentage": 66.97, "elapsed_time": "13:07:39", "remaining_time": "6:28:27"}
|
91 |
+
{"current_steps": 890, "total_steps": 1314, "loss": 0.5546, "learning_rate": 5e-06, "epoch": 2.0296296296296297, "percentage": 67.73, "elapsed_time": "13:16:25", "remaining_time": "6:19:25"}
|
92 |
+
{"current_steps": 900, "total_steps": 1314, "loss": 0.5697, "learning_rate": 5e-06, "epoch": 2.0524216524216525, "percentage": 68.49, "elapsed_time": "13:25:11", "remaining_time": "6:10:23"}
|
93 |
+
{"current_steps": 910, "total_steps": 1314, "loss": 0.5678, "learning_rate": 5e-06, "epoch": 2.0752136752136754, "percentage": 69.25, "elapsed_time": "13:33:57", "remaining_time": "6:01:21"}
|
94 |
+
{"current_steps": 920, "total_steps": 1314, "loss": 0.5709, "learning_rate": 5e-06, "epoch": 2.098005698005698, "percentage": 70.02, "elapsed_time": "13:42:43", "remaining_time": "5:52:20"}
|
95 |
+
{"current_steps": 930, "total_steps": 1314, "loss": 0.569, "learning_rate": 5e-06, "epoch": 2.1207977207977207, "percentage": 70.78, "elapsed_time": "13:51:29", "remaining_time": "5:43:19"}
|
96 |
+
{"current_steps": 940, "total_steps": 1314, "loss": 0.5636, "learning_rate": 5e-06, "epoch": 2.1435897435897435, "percentage": 71.54, "elapsed_time": "14:00:15", "remaining_time": "5:34:18"}
|
97 |
+
{"current_steps": 950, "total_steps": 1314, "loss": 0.5646, "learning_rate": 5e-06, "epoch": 2.1663817663817664, "percentage": 72.3, "elapsed_time": "14:09:01", "remaining_time": "5:25:18"}
|
98 |
+
{"current_steps": 960, "total_steps": 1314, "loss": 0.5696, "learning_rate": 5e-06, "epoch": 2.1891737891737892, "percentage": 73.06, "elapsed_time": "14:17:47", "remaining_time": "5:16:18"}
|
99 |
+
{"current_steps": 970, "total_steps": 1314, "loss": 0.569, "learning_rate": 5e-06, "epoch": 2.211965811965812, "percentage": 73.82, "elapsed_time": "14:26:32", "remaining_time": "5:07:18"}
|
100 |
+
{"current_steps": 980, "total_steps": 1314, "loss": 0.5587, "learning_rate": 5e-06, "epoch": 2.234757834757835, "percentage": 74.58, "elapsed_time": "14:35:18", "remaining_time": "4:58:19"}
|
101 |
+
{"current_steps": 990, "total_steps": 1314, "loss": 0.5678, "learning_rate": 5e-06, "epoch": 2.2575498575498574, "percentage": 75.34, "elapsed_time": "14:44:04", "remaining_time": "4:49:20"}
|
102 |
+
{"current_steps": 1000, "total_steps": 1314, "loss": 0.5681, "learning_rate": 5e-06, "epoch": 2.2803418803418802, "percentage": 76.1, "elapsed_time": "14:52:50", "remaining_time": "4:40:21"}
|
103 |
+
{"current_steps": 1010, "total_steps": 1314, "loss": 0.5656, "learning_rate": 5e-06, "epoch": 2.303133903133903, "percentage": 76.86, "elapsed_time": "15:01:36", "remaining_time": "4:31:22"}
|
104 |
+
{"current_steps": 1020, "total_steps": 1314, "loss": 0.5686, "learning_rate": 5e-06, "epoch": 2.325925925925926, "percentage": 77.63, "elapsed_time": "15:10:21", "remaining_time": "4:22:23"}
|
105 |
+
{"current_steps": 1030, "total_steps": 1314, "loss": 0.5699, "learning_rate": 5e-06, "epoch": 2.348717948717949, "percentage": 78.39, "elapsed_time": "15:19:07", "remaining_time": "4:13:25"}
|
106 |
+
{"current_steps": 1040, "total_steps": 1314, "loss": 0.5679, "learning_rate": 5e-06, "epoch": 2.3715099715099717, "percentage": 79.15, "elapsed_time": "15:27:52", "remaining_time": "4:04:27"}
|
107 |
+
{"current_steps": 1050, "total_steps": 1314, "loss": 0.5672, "learning_rate": 5e-06, "epoch": 2.394301994301994, "percentage": 79.91, "elapsed_time": "15:36:38", "remaining_time": "3:55:29"}
|
108 |
+
{"current_steps": 1060, "total_steps": 1314, "loss": 0.5756, "learning_rate": 5e-06, "epoch": 2.417094017094017, "percentage": 80.67, "elapsed_time": "15:45:24", "remaining_time": "3:46:32"}
|
109 |
+
{"current_steps": 1070, "total_steps": 1314, "loss": 0.5784, "learning_rate": 5e-06, "epoch": 2.43988603988604, "percentage": 81.43, "elapsed_time": "15:54:10", "remaining_time": "3:37:35"}
|
110 |
+
{"current_steps": 1080, "total_steps": 1314, "loss": 0.5737, "learning_rate": 5e-06, "epoch": 2.4626780626780627, "percentage": 82.19, "elapsed_time": "16:02:57", "remaining_time": "3:28:38"}
|
111 |
+
{"current_steps": 1090, "total_steps": 1314, "loss": 0.5713, "learning_rate": 5e-06, "epoch": 2.4854700854700855, "percentage": 82.95, "elapsed_time": "16:11:42", "remaining_time": "3:19:41"}
|
112 |
+
{"current_steps": 1100, "total_steps": 1314, "loss": 0.5777, "learning_rate": 5e-06, "epoch": 2.5082621082621084, "percentage": 83.71, "elapsed_time": "16:20:28", "remaining_time": "3:10:44"}
|
113 |
+
{"current_steps": 1110, "total_steps": 1314, "loss": 0.5713, "learning_rate": 5e-06, "epoch": 2.5310541310541312, "percentage": 84.47, "elapsed_time": "16:29:14", "remaining_time": "3:01:48"}
|
114 |
+
{"current_steps": 1120, "total_steps": 1314, "loss": 0.5694, "learning_rate": 5e-06, "epoch": 2.5538461538461537, "percentage": 85.24, "elapsed_time": "16:38:00", "remaining_time": "2:52:52"}
|
115 |
+
{"current_steps": 1130, "total_steps": 1314, "loss": 0.5688, "learning_rate": 5e-06, "epoch": 2.5766381766381765, "percentage": 86.0, "elapsed_time": "16:46:46", "remaining_time": "2:43:56"}
|
116 |
+
{"current_steps": 1140, "total_steps": 1314, "loss": 0.5685, "learning_rate": 5e-06, "epoch": 2.5994301994301994, "percentage": 86.76, "elapsed_time": "16:55:32", "remaining_time": "2:35:00"}
|
117 |
+
{"current_steps": 1150, "total_steps": 1314, "loss": 0.5688, "learning_rate": 5e-06, "epoch": 2.6222222222222222, "percentage": 87.52, "elapsed_time": "17:04:18", "remaining_time": "2:26:04"}
|
118 |
+
{"current_steps": 1160, "total_steps": 1314, "loss": 0.57, "learning_rate": 5e-06, "epoch": 2.645014245014245, "percentage": 88.28, "elapsed_time": "17:13:04", "remaining_time": "2:17:08"}
|
119 |
+
{"current_steps": 1170, "total_steps": 1314, "loss": 0.5727, "learning_rate": 5e-06, "epoch": 2.667806267806268, "percentage": 89.04, "elapsed_time": "17:21:50", "remaining_time": "2:08:13"}
|
120 |
+
{"current_steps": 1180, "total_steps": 1314, "loss": 0.5679, "learning_rate": 5e-06, "epoch": 2.690598290598291, "percentage": 89.8, "elapsed_time": "17:30:36", "remaining_time": "1:59:18"}
|
121 |
+
{"current_steps": 1190, "total_steps": 1314, "loss": 0.569, "learning_rate": 5e-06, "epoch": 2.7133903133903132, "percentage": 90.56, "elapsed_time": "17:39:22", "remaining_time": "1:50:23"}
|
122 |
+
{"current_steps": 1200, "total_steps": 1314, "loss": 0.5721, "learning_rate": 5e-06, "epoch": 2.736182336182336, "percentage": 91.32, "elapsed_time": "17:48:08", "remaining_time": "1:41:28"}
|
123 |
+
{"current_steps": 1210, "total_steps": 1314, "loss": 0.5755, "learning_rate": 5e-06, "epoch": 2.758974358974359, "percentage": 92.09, "elapsed_time": "17:56:54", "remaining_time": "1:32:33"}
|
124 |
+
{"current_steps": 1220, "total_steps": 1314, "loss": 0.5653, "learning_rate": 5e-06, "epoch": 2.781766381766382, "percentage": 92.85, "elapsed_time": "18:05:40", "remaining_time": "1:23:39"}
|
125 |
+
{"current_steps": 1230, "total_steps": 1314, "loss": 0.5638, "learning_rate": 5e-06, "epoch": 2.8045584045584047, "percentage": 93.61, "elapsed_time": "18:14:27", "remaining_time": "1:14:44"}
|
126 |
+
{"current_steps": 1240, "total_steps": 1314, "loss": 0.5787, "learning_rate": 5e-06, "epoch": 2.827350427350427, "percentage": 94.37, "elapsed_time": "18:23:12", "remaining_time": "1:05:50"}
|
127 |
+
{"current_steps": 1250, "total_steps": 1314, "loss": 0.5753, "learning_rate": 5e-06, "epoch": 2.8501424501424504, "percentage": 95.13, "elapsed_time": "18:31:58", "remaining_time": "0:56:55"}
|
128 |
+
{"current_steps": 1260, "total_steps": 1314, "loss": 0.5725, "learning_rate": 5e-06, "epoch": 2.872934472934473, "percentage": 95.89, "elapsed_time": "18:40:44", "remaining_time": "0:48:01"}
|
129 |
+
{"current_steps": 1270, "total_steps": 1314, "loss": 0.5734, "learning_rate": 5e-06, "epoch": 2.8957264957264957, "percentage": 96.65, "elapsed_time": "18:49:30", "remaining_time": "0:39:07"}
|
130 |
+
{"current_steps": 1280, "total_steps": 1314, "loss": 0.5636, "learning_rate": 5e-06, "epoch": 2.9185185185185185, "percentage": 97.41, "elapsed_time": "18:58:15", "remaining_time": "0:30:14"}
|
131 |
+
{"current_steps": 1290, "total_steps": 1314, "loss": 0.5638, "learning_rate": 5e-06, "epoch": 2.9413105413105414, "percentage": 98.17, "elapsed_time": "19:07:01", "remaining_time": "0:21:20"}
|
132 |
+
{"current_steps": 1300, "total_steps": 1314, "loss": 0.565, "learning_rate": 5e-06, "epoch": 2.9641025641025642, "percentage": 98.93, "elapsed_time": "19:15:47", "remaining_time": "0:12:26"}
|
133 |
+
{"current_steps": 1310, "total_steps": 1314, "loss": 0.5748, "learning_rate": 5e-06, "epoch": 2.9868945868945866, "percentage": 99.7, "elapsed_time": "19:24:33", "remaining_time": "0:03:33"}
|