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 sha256:2c5b9a6c9e61fcb190145af232d948855cc7e78db0b15d2c1cc5877bb9b1e6d8
|
| 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 sha256:72ff27f13b5997f10b4e6d90a9e4595376f4f15108812221081643729ed651b7
|
| 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:ba56e82d2668d74423b9db3a005478ec531f26fa517d106270c6f02808938283
|
| 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 sha256:6344d87e73b8567f5cb759aa28d43e646ef126a2016e3561288bbfa349d772df
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
@@ -66,3 +66,29 @@
|
|
| 66 |
{"current_steps": 66, "total_steps": 93, "loss": 0.3972, "lr": 2.391542453997578e-06, "epoch": 2.112, "percentage": 70.97, "elapsed_time": "0:40:59", "remaining_time": "0:16:46"}
|
| 67 |
{"current_steps": 67, "total_steps": 93, "loss": 0.4317, "lr": 2.2319914586525776e-06, "epoch": 2.144, "percentage": 72.04, "elapsed_time": "0:41:36", "remaining_time": "0:16:08"}
|
| 68 |
{"current_steps": 68, "total_steps": 93, "loss": 0.3826, "lr": 2.0764056088797646e-06, "epoch": 2.176, "percentage": 73.12, "elapsed_time": "0:42:06", "remaining_time": "0:15:28"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 66 |
{"current_steps": 66, "total_steps": 93, "loss": 0.3972, "lr": 2.391542453997578e-06, "epoch": 2.112, "percentage": 70.97, "elapsed_time": "0:40:59", "remaining_time": "0:16:46"}
|
| 67 |
{"current_steps": 67, "total_steps": 93, "loss": 0.4317, "lr": 2.2319914586525776e-06, "epoch": 2.144, "percentage": 72.04, "elapsed_time": "0:41:36", "remaining_time": "0:16:08"}
|
| 68 |
{"current_steps": 68, "total_steps": 93, "loss": 0.3826, "lr": 2.0764056088797646e-06, "epoch": 2.176, "percentage": 73.12, "elapsed_time": "0:42:06", "remaining_time": "0:15:28"}
|
| 69 |
+
{"current_steps": 69, "total_steps": 93, "loss": 0.4041, "lr": 1.9250077799102323e-06, "epoch": 2.208, "percentage": 74.19, "elapsed_time": "0:42:38", "remaining_time": "0:14:49"}
|
| 70 |
+
{"current_steps": 70, "total_steps": 93, "loss": 0.4387, "lr": 1.7780148476756148e-06, "epoch": 2.24, "percentage": 75.27, "elapsed_time": "0:43:08", "remaining_time": "0:14:10"}
|
| 71 |
+
{"current_steps": 71, "total_steps": 93, "loss": 0.4334, "lr": 1.6356373781354058e-06, "epoch": 2.2720000000000002, "percentage": 76.34, "elapsed_time": "0:43:35", "remaining_time": "0:13:30"}
|
| 72 |
+
{"current_steps": 72, "total_steps": 93, "loss": 0.4368, "lr": 1.4980793256432474e-06, "epoch": 2.304, "percentage": 77.42, "elapsed_time": "0:44:06", "remaining_time": "0:12:51"}
|
| 73 |
+
{"current_steps": 73, "total_steps": 93, "loss": 0.4073, "lr": 1.3655377407842813e-06, "epoch": 2.336, "percentage": 78.49, "elapsed_time": "0:44:35", "remaining_time": "0:12:12"}
|
| 74 |
+
{"current_steps": 74, "total_steps": 93, "loss": 0.4026, "lr": 1.2382024881020937e-06, "epoch": 2.368, "percentage": 79.57, "elapsed_time": "0:45:09", "remaining_time": "0:11:35"}
|
| 75 |
+
{"current_steps": 75, "total_steps": 93, "loss": 0.3788, "lr": 1.1162559741195733e-06, "epoch": 2.4, "percentage": 80.65, "elapsed_time": "0:45:36", "remaining_time": "0:10:56"}
|
| 76 |
+
{"current_steps": 76, "total_steps": 93, "loss": 0.414, "lr": 9.998728860433277e-07, "epoch": 2.432, "percentage": 81.72, "elapsed_time": "0:46:08", "remaining_time": "0:10:19"}
|
| 77 |
+
{"current_steps": 77, "total_steps": 93, "loss": 0.3815, "lr": 8.892199415259501e-07, "epoch": 2.464, "percentage": 82.8, "elapsed_time": "0:46:35", "remaining_time": "0:09:40"}
|
| 78 |
+
{"current_steps": 78, "total_steps": 93, "loss": 0.3731, "lr": 7.844556498445788e-07, "epoch": 2.496, "percentage": 83.87, "elapsed_time": "0:47:17", "remaining_time": "0:09:05"}
|
| 79 |
+
{"current_steps": 79, "total_steps": 93, "loss": 0.4096, "lr": 6.857300848378857e-07, "epoch": 2.528, "percentage": 84.95, "elapsed_time": "0:47:51", "remaining_time": "0:08:28"}
|
| 80 |
+
{"current_steps": 80, "total_steps": 93, "loss": 0.4437, "lr": 5.931846699267558e-07, "epoch": 2.56, "percentage": 86.02, "elapsed_time": "0:48:14", "remaining_time": "0:07:50"}
|
| 81 |
+
{"current_steps": 81, "total_steps": 93, "loss": 0.4076, "lr": 5.0695197552659e-07, "epoch": 2.592, "percentage": 87.1, "elapsed_time": "0:48:43", "remaining_time": "0:07:13"}
|
| 82 |
+
{"current_steps": 82, "total_steps": 93, "loss": 0.3967, "lr": 4.271555291414636e-07, "epoch": 2.624, "percentage": 88.17, "elapsed_time": "0:49:12", "remaining_time": "0:06:36"}
|
| 83 |
+
{"current_steps": 83, "total_steps": 93, "loss": 0.3843, "lr": 3.539096384121743e-07, "epoch": 2.656, "percentage": 89.25, "elapsed_time": "0:49:46", "remaining_time": "0:05:59"}
|
| 84 |
+
{"current_steps": 84, "total_steps": 93, "loss": 0.3836, "lr": 2.873192273716369e-07, "epoch": 2.6879999999999997, "percentage": 90.32, "elapsed_time": "0:50:28", "remaining_time": "0:05:24"}
|
| 85 |
+
{"current_steps": 85, "total_steps": 93, "loss": 0.4543, "lr": 2.274796861422246e-07, "epoch": 2.7199999999999998, "percentage": 91.4, "elapsed_time": "0:51:02", "remaining_time": "0:04:48"}
|
| 86 |
+
{"current_steps": 86, "total_steps": 93, "loss": 0.3527, "lr": 1.7447673429033361e-07, "epoch": 2.752, "percentage": 92.47, "elapsed_time": "0:51:35", "remaining_time": "0:04:11"}
|
| 87 |
+
{"current_steps": 87, "total_steps": 93, "loss": 0.3922, "lr": 1.2838629803393343e-07, "epoch": 2.784, "percentage": 93.55, "elapsed_time": "0:52:09", "remaining_time": "0:03:35"}
|
| 88 |
+
{"current_steps": 88, "total_steps": 93, "loss": 0.3972, "lr": 8.927440147898703e-08, "epoch": 2.816, "percentage": 94.62, "elapsed_time": "0:52:35", "remaining_time": "0:02:59"}
|
| 89 |
+
{"current_steps": 89, "total_steps": 93, "loss": 0.4262, "lr": 5.7197072040557356e-08, "epoch": 2.848, "percentage": 95.7, "elapsed_time": "0:53:00", "remaining_time": "0:02:22"}
|
| 90 |
+
{"current_steps": 90, "total_steps": 93, "loss": 0.4841, "lr": 3.220026018407541e-08, "epoch": 2.88, "percentage": 96.77, "elapsed_time": "0:53:36", "remaining_time": "0:01:47"}
|
| 91 |
+
{"current_steps": 91, "total_steps": 93, "loss": 0.3779, "lr": 1.431977360173975e-08, "epoch": 2.912, "percentage": 97.85, "elapsed_time": "0:54:08", "remaining_time": "0:01:11"}
|
| 92 |
+
{"current_steps": 92, "total_steps": 93, "loss": 0.4023, "lr": 3.5812259183426457e-09, "epoch": 2.944, "percentage": 98.92, "elapsed_time": "0:54:37", "remaining_time": "0:00:35"}
|
| 93 |
+
{"current_steps": 93, "total_steps": 93, "loss": 0.3697, "lr": 0.0, "epoch": 2.976, "percentage": 100.0, "elapsed_time": "0:55:03", "remaining_time": "0:00:00"}
|
| 94 |
+
{"current_steps": 93, "total_steps": 93, "epoch": 2.976, "percentage": 100.0, "elapsed_time": "1:16:48", "remaining_time": "0:00:00"}
|