Training in progress, epoch 3
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:e18581019544b7e0a38f70c94e23d34c7506be74f6b472c3a057c010f04b8c7d
|
| 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:dd23f24c60ad29c483b3aa58677bf40ae6520e99a8af0c1ff3561a54556ea11a
|
| 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:aba91b37d725d288c1916b22a59e650bcd6bfb6f7fbc5fc140c4d315675398be
|
| 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 sha256:2d52da07ceba6d1e540d5acf01fc04592bd66168ab63859551ba3720d239ebdc
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
@@ -70,3 +70,28 @@
|
|
| 70 |
{"current_steps": 70, "total_steps": 96, "loss": 0.127, "lr": 2.0907054222102367e-06, "epoch": 2.1875, "percentage": 72.92, "elapsed_time": "0:04:22", "remaining_time": "0:01:37"}
|
| 71 |
{"current_steps": 71, "total_steps": 96, "loss": 0.131, "lr": 1.944131429510754e-06, "epoch": 2.21875, "percentage": 73.96, "elapsed_time": "0:04:25", "remaining_time": "0:01:33"}
|
| 72 |
{"current_steps": 72, "total_steps": 96, "loss": 0.1119, "lr": 1.8016348922055448e-06, "epoch": 2.25, "percentage": 75.0, "elapsed_time": "0:04:27", "remaining_time": "0:01:29"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 70 |
{"current_steps": 70, "total_steps": 96, "loss": 0.127, "lr": 2.0907054222102367e-06, "epoch": 2.1875, "percentage": 72.92, "elapsed_time": "0:04:22", "remaining_time": "0:01:37"}
|
| 71 |
{"current_steps": 71, "total_steps": 96, "loss": 0.131, "lr": 1.944131429510754e-06, "epoch": 2.21875, "percentage": 73.96, "elapsed_time": "0:04:25", "remaining_time": "0:01:33"}
|
| 72 |
{"current_steps": 72, "total_steps": 96, "loss": 0.1119, "lr": 1.8016348922055448e-06, "epoch": 2.25, "percentage": 75.0, "elapsed_time": "0:04:27", "remaining_time": "0:01:29"}
|
| 73 |
+
{"current_steps": 73, "total_steps": 96, "loss": 0.1131, "lr": 1.6634059438888034e-06, "epoch": 2.28125, "percentage": 76.04, "elapsed_time": "0:04:30", "remaining_time": "0:01:25"}
|
| 74 |
+
{"current_steps": 74, "total_steps": 96, "loss": 0.1147, "lr": 1.5296290238968303e-06, "epoch": 2.3125, "percentage": 77.08, "elapsed_time": "0:04:33", "remaining_time": "0:01:21"}
|
| 75 |
+
{"current_steps": 75, "total_steps": 96, "loss": 0.1219, "lr": 1.4004826312100218e-06, "epoch": 2.34375, "percentage": 78.12, "elapsed_time": "0:04:35", "remaining_time": "0:01:17"}
|
| 76 |
+
{"current_steps": 76, "total_steps": 96, "loss": 0.1178, "lr": 1.2761390862810907e-06, "epoch": 2.375, "percentage": 79.17, "elapsed_time": "0:04:37", "remaining_time": "0:01:13"}
|
| 77 |
+
{"current_steps": 77, "total_steps": 96, "loss": 0.1102, "lr": 1.1567643011073393e-06, "epoch": 2.40625, "percentage": 80.21, "elapsed_time": "0:04:40", "remaining_time": "0:01:09"}
|
| 78 |
+
{"current_steps": 78, "total_steps": 96, "loss": 0.1077, "lr": 1.04251755785373e-06, "epoch": 2.4375, "percentage": 81.25, "elapsed_time": "0:04:42", "remaining_time": "0:01:05"}
|
| 79 |
+
{"current_steps": 79, "total_steps": 96, "loss": 0.1045, "lr": 9.335512963221732e-07, "epoch": 2.46875, "percentage": 82.29, "elapsed_time": "0:04:45", "remaining_time": "0:01:01"}
|
| 80 |
+
{"current_steps": 80, "total_steps": 96, "loss": 0.1298, "lr": 8.30010910550611e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "0:04:47", "remaining_time": "0:00:57"}
|
| 81 |
+
{"current_steps": 81, "total_steps": 96, "loss": 0.1336, "lr": 7.320345548132679e-07, "epoch": 2.53125, "percentage": 84.38, "elapsed_time": "0:04:50", "remaining_time": "0:00:53"}
|
| 82 |
+
{"current_steps": 82, "total_steps": 96, "loss": 0.1017, "lr": 6.397529592809615e-07, "epoch": 2.5625, "percentage": 85.42, "elapsed_time": "0:04:52", "remaining_time": "0:00:49"}
|
| 83 |
+
{"current_steps": 83, "total_steps": 96, "loss": 0.1058, "lr": 5.532892555874059e-07, "epoch": 2.59375, "percentage": 86.46, "elapsed_time": "0:04:54", "remaining_time": "0:00:46"}
|
| 84 |
+
{"current_steps": 84, "total_steps": 96, "loss": 0.1174, "lr": 4.727588125342669e-07, "epoch": 2.625, "percentage": 87.5, "elapsed_time": "0:04:57", "remaining_time": "0:00:42"}
|
| 85 |
+
{"current_steps": 85, "total_steps": 96, "loss": 0.1076, "lr": 3.9826908215420344e-07, "epoch": 2.65625, "percentage": 88.54, "elapsed_time": "0:04:59", "remaining_time": "0:00:38"}
|
| 86 |
+
{"current_steps": 86, "total_steps": 96, "loss": 0.1411, "lr": 3.299194563372604e-07, "epoch": 2.6875, "percentage": 89.58, "elapsed_time": "0:05:02", "remaining_time": "0:00:35"}
|
| 87 |
+
{"current_steps": 87, "total_steps": 96, "loss": 0.1101, "lr": 2.67801134211953e-07, "epoch": 2.71875, "percentage": 90.62, "elapsed_time": "0:05:04", "remaining_time": "0:00:31"}
|
| 88 |
+
{"current_steps": 88, "total_steps": 96, "loss": 0.1397, "lr": 2.1199700045797077e-07, "epoch": 2.75, "percentage": 91.67, "elapsed_time": "0:05:06", "remaining_time": "0:00:27"}
|
| 89 |
+
{"current_steps": 89, "total_steps": 96, "loss": 0.1053, "lr": 1.6258151471287397e-07, "epoch": 2.78125, "percentage": 92.71, "elapsed_time": "0:05:09", "remaining_time": "0:00:24"}
|
| 90 |
+
{"current_steps": 90, "total_steps": 96, "loss": 0.1197, "lr": 1.196206122203647e-07, "epoch": 2.8125, "percentage": 93.75, "elapsed_time": "0:05:11", "remaining_time": "0:00:20"}
|
| 91 |
+
{"current_steps": 91, "total_steps": 96, "loss": 0.1004, "lr": 8.317161585266964e-08, "epoch": 2.84375, "percentage": 94.79, "elapsed_time": "0:05:14", "remaining_time": "0:00:17"}
|
| 92 |
+
{"current_steps": 92, "total_steps": 96, "loss": 0.1161, "lr": 5.3283159624448745e-08, "epoch": 2.875, "percentage": 95.83, "elapsed_time": "0:05:16", "remaining_time": "0:00:13"}
|
| 93 |
+
{"current_steps": 93, "total_steps": 96, "loss": 0.1109, "lr": 2.9995123800270476e-08, "epoch": 2.90625, "percentage": 96.88, "elapsed_time": "0:05:19", "remaining_time": "0:00:10"}
|
| 94 |
+
{"current_steps": 94, "total_steps": 96, "loss": 0.109, "lr": 1.333858168224178e-08, "epoch": 2.9375, "percentage": 97.92, "elapsed_time": "0:05:21", "remaining_time": "0:00:06"}
|
| 95 |
+
{"current_steps": 95, "total_steps": 96, "loss": 0.1002, "lr": 3.3357581488030476e-09, "epoch": 2.96875, "percentage": 98.96, "elapsed_time": "0:05:23", "remaining_time": "0:00:03"}
|
| 96 |
+
{"current_steps": 96, "total_steps": 96, "loss": 0.0853, "lr": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:05:26", "remaining_time": "0:00:00"}
|
| 97 |
+
{"current_steps": 96, "total_steps": 96, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:07:00", "remaining_time": "0:00:00"}
|