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:c5129d9980a74deee350a2ff7af2a16de91617d687cfea6b1752c4b28bd5f974
|
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:c5fdfc0d225d3555cd95de38aabd1ab73ee32e8ed7f7f948dac87ef28d140eba
|
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 sha256:9a14a6b7466770676282df38a1f105292e70d5393cc17a09a86131611fa52074
|
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:d81599d194c43fb679fbfc78afa346838b3df4f9e4eab8f083d7ec591b51f137
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -66,3 +66,29 @@
|
|
66 |
{"current_steps": 66, "total_steps": 93, "loss": 0.505, "lr": 1.195771226998789e-06, "epoch": 2.112, "percentage": 70.97, "elapsed_time": "0:37:49", "remaining_time": "0:15:28"}
|
67 |
{"current_steps": 67, "total_steps": 93, "loss": 0.5505, "lr": 1.1159957293262888e-06, "epoch": 2.144, "percentage": 72.04, "elapsed_time": "0:38:27", "remaining_time": "0:14:55"}
|
68 |
{"current_steps": 68, "total_steps": 93, "loss": 0.4181, "lr": 1.0382028044398823e-06, "epoch": 2.176, "percentage": 73.12, "elapsed_time": "0:38:59", "remaining_time": "0:14:20"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
66 |
{"current_steps": 66, "total_steps": 93, "loss": 0.505, "lr": 1.195771226998789e-06, "epoch": 2.112, "percentage": 70.97, "elapsed_time": "0:37:49", "remaining_time": "0:15:28"}
|
67 |
{"current_steps": 67, "total_steps": 93, "loss": 0.5505, "lr": 1.1159957293262888e-06, "epoch": 2.144, "percentage": 72.04, "elapsed_time": "0:38:27", "remaining_time": "0:14:55"}
|
68 |
{"current_steps": 68, "total_steps": 93, "loss": 0.4181, "lr": 1.0382028044398823e-06, "epoch": 2.176, "percentage": 73.12, "elapsed_time": "0:38:59", "remaining_time": "0:14:20"}
|
69 |
+
{"current_steps": 69, "total_steps": 93, "loss": 0.5063, "lr": 9.625038899551162e-07, "epoch": 2.208, "percentage": 74.19, "elapsed_time": "0:39:31", "remaining_time": "0:13:44"}
|
70 |
+
{"current_steps": 70, "total_steps": 93, "loss": 0.5717, "lr": 8.890074238378074e-07, "epoch": 2.24, "percentage": 75.27, "elapsed_time": "0:40:02", "remaining_time": "0:13:09"}
|
71 |
+
{"current_steps": 71, "total_steps": 93, "loss": 0.5182, "lr": 8.178186890677029e-07, "epoch": 2.2720000000000002, "percentage": 76.34, "elapsed_time": "0:40:30", "remaining_time": "0:12:33"}
|
72 |
+
{"current_steps": 72, "total_steps": 93, "loss": 0.5755, "lr": 7.490396628216237e-07, "epoch": 2.304, "percentage": 77.42, "elapsed_time": "0:41:02", "remaining_time": "0:11:58"}
|
73 |
+
{"current_steps": 73, "total_steps": 93, "loss": 0.4823, "lr": 6.827688703921407e-07, "epoch": 2.336, "percentage": 78.49, "elapsed_time": "0:41:32", "remaining_time": "0:11:22"}
|
74 |
+
{"current_steps": 74, "total_steps": 93, "loss": 0.53, "lr": 6.191012440510469e-07, "epoch": 2.368, "percentage": 79.57, "elapsed_time": "0:42:07", "remaining_time": "0:10:48"}
|
75 |
+
{"current_steps": 75, "total_steps": 93, "loss": 0.4502, "lr": 5.581279870597866e-07, "epoch": 2.4, "percentage": 80.65, "elapsed_time": "0:42:35", "remaining_time": "0:10:13"}
|
76 |
+
{"current_steps": 76, "total_steps": 93, "loss": 0.6202, "lr": 4.999364430216639e-07, "epoch": 2.432, "percentage": 81.72, "elapsed_time": "0:43:09", "remaining_time": "0:09:39"}
|
77 |
+
{"current_steps": 77, "total_steps": 93, "loss": 0.4654, "lr": 4.4460997076297504e-07, "epoch": 2.464, "percentage": 82.8, "elapsed_time": "0:43:36", "remaining_time": "0:09:03"}
|
78 |
+
{"current_steps": 78, "total_steps": 93, "loss": 0.4881, "lr": 3.922278249222894e-07, "epoch": 2.496, "percentage": 83.87, "elapsed_time": "0:44:20", "remaining_time": "0:08:31"}
|
79 |
+
{"current_steps": 79, "total_steps": 93, "loss": 0.4975, "lr": 3.4286504241894283e-07, "epoch": 2.528, "percentage": 84.95, "elapsed_time": "0:44:54", "remaining_time": "0:07:57"}
|
80 |
+
{"current_steps": 80, "total_steps": 93, "loss": 0.605, "lr": 2.965923349633779e-07, "epoch": 2.56, "percentage": 86.02, "elapsed_time": "0:45:18", "remaining_time": "0:07:21"}
|
81 |
+
{"current_steps": 81, "total_steps": 93, "loss": 0.5747, "lr": 2.53475987763295e-07, "epoch": 2.592, "percentage": 87.1, "elapsed_time": "0:45:48", "remaining_time": "0:06:47"}
|
82 |
+
{"current_steps": 82, "total_steps": 93, "loss": 0.4929, "lr": 2.135777645707318e-07, "epoch": 2.624, "percentage": 88.17, "elapsed_time": "0:46:18", "remaining_time": "0:06:12"}
|
83 |
+
{"current_steps": 83, "total_steps": 93, "loss": 0.5086, "lr": 1.7695481920608716e-07, "epoch": 2.656, "percentage": 89.25, "elapsed_time": "0:46:54", "remaining_time": "0:05:39"}
|
84 |
+
{"current_steps": 84, "total_steps": 93, "loss": 0.565, "lr": 1.4365961368581844e-07, "epoch": 2.6879999999999997, "percentage": 90.32, "elapsed_time": "0:47:37", "remaining_time": "0:05:06"}
|
85 |
+
{"current_steps": 85, "total_steps": 93, "loss": 0.603, "lr": 1.137398430711123e-07, "epoch": 2.7199999999999998, "percentage": 91.4, "elapsed_time": "0:48:12", "remaining_time": "0:04:32"}
|
86 |
+
{"current_steps": 86, "total_steps": 93, "loss": 0.3893, "lr": 8.723836714516681e-08, "epoch": 2.752, "percentage": 92.47, "elapsed_time": "0:48:46", "remaining_time": "0:03:58"}
|
87 |
+
{"current_steps": 87, "total_steps": 93, "loss": 0.5293, "lr": 6.419314901696671e-08, "epoch": 2.784, "percentage": 93.55, "elapsed_time": "0:49:22", "remaining_time": "0:03:24"}
|
88 |
+
{"current_steps": 88, "total_steps": 93, "loss": 0.5167, "lr": 4.4637200739493514e-08, "epoch": 2.816, "percentage": 94.62, "elapsed_time": "0:49:49", "remaining_time": "0:02:49"}
|
89 |
+
{"current_steps": 89, "total_steps": 93, "loss": 0.4821, "lr": 2.8598536020278678e-08, "epoch": 2.848, "percentage": 95.7, "elapsed_time": "0:50:14", "remaining_time": "0:02:15"}
|
90 |
+
{"current_steps": 90, "total_steps": 93, "loss": 0.645, "lr": 1.6100130092037704e-08, "epoch": 2.88, "percentage": 96.77, "elapsed_time": "0:50:51", "remaining_time": "0:01:41"}
|
91 |
+
{"current_steps": 91, "total_steps": 93, "loss": 0.4611, "lr": 7.159886800869875e-09, "epoch": 2.912, "percentage": 97.85, "elapsed_time": "0:51:25", "remaining_time": "0:01:07"}
|
92 |
+
{"current_steps": 92, "total_steps": 93, "loss": 0.5646, "lr": 1.7906129591713228e-09, "epoch": 2.944, "percentage": 98.92, "elapsed_time": "0:51:54", "remaining_time": "0:00:33"}
|
93 |
+
{"current_steps": 93, "total_steps": 93, "loss": 0.4423, "lr": 0.0, "epoch": 2.976, "percentage": 100.0, "elapsed_time": "0:52:21", "remaining_time": "0:00:00"}
|
94 |
+
{"current_steps": 93, "total_steps": 93, "epoch": 2.976, "percentage": 100.0, "elapsed_time": "0:54:43", "remaining_time": "0:00:00"}
|