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 4976698672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:009abdc51cd07f4018a03450fa794de70214793ed84090bb31403492957f4c6b
|
3 |
size 4976698672
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999802720
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:afbc4b25f59d3f9347cb7e001b706598385395f1dd8b0611130417411c709081
|
3 |
size 4999802720
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4915916176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45c9f4ee9e856c4bb2b23666200d16a5550ef1bccfe6bd1d19631ddf6b68a121
|
3 |
size 4915916176
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1168138808
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6da094a723a4fa4a2fee6405c0b6e6e1c7de94cb4fb7c3fb37d87c0fc03e62a
|
3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
@@ -18,3 +18,14 @@
|
|
18 |
{"current_steps": 170, "total_steps": 276, "loss": 0.6653, "lr": 5e-06, "epoch": 1.8478260869565217, "percentage": 61.59, "elapsed_time": "2:45:41", "remaining_time": "1:43:18"}
|
19 |
{"current_steps": 180, "total_steps": 276, "loss": 0.6578, "lr": 5e-06, "epoch": 1.9565217391304348, "percentage": 65.22, "elapsed_time": "2:55:15", "remaining_time": "1:33:28"}
|
20 |
{"current_steps": 184, "total_steps": 276, "eval_loss": 0.6927142143249512, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "3:00:42", "remaining_time": "1:30:21"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
{"current_steps": 170, "total_steps": 276, "loss": 0.6653, "lr": 5e-06, "epoch": 1.8478260869565217, "percentage": 61.59, "elapsed_time": "2:45:41", "remaining_time": "1:43:18"}
|
19 |
{"current_steps": 180, "total_steps": 276, "loss": 0.6578, "lr": 5e-06, "epoch": 1.9565217391304348, "percentage": 65.22, "elapsed_time": "2:55:15", "remaining_time": "1:33:28"}
|
20 |
{"current_steps": 184, "total_steps": 276, "eval_loss": 0.6927142143249512, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "3:00:42", "remaining_time": "1:30:21"}
|
21 |
+
{"current_steps": 190, "total_steps": 276, "loss": 0.6373, "lr": 5e-06, "epoch": 2.0652173913043477, "percentage": 68.84, "elapsed_time": "3:07:37", "remaining_time": "1:24:55"}
|
22 |
+
{"current_steps": 200, "total_steps": 276, "loss": 0.6138, "lr": 5e-06, "epoch": 2.1739130434782608, "percentage": 72.46, "elapsed_time": "3:17:12", "remaining_time": "1:14:56"}
|
23 |
+
{"current_steps": 210, "total_steps": 276, "loss": 0.6095, "lr": 5e-06, "epoch": 2.282608695652174, "percentage": 76.09, "elapsed_time": "3:26:47", "remaining_time": "1:04:59"}
|
24 |
+
{"current_steps": 220, "total_steps": 276, "loss": 0.614, "lr": 5e-06, "epoch": 2.391304347826087, "percentage": 79.71, "elapsed_time": "3:36:23", "remaining_time": "0:55:04"}
|
25 |
+
{"current_steps": 230, "total_steps": 276, "loss": 0.6139, "lr": 5e-06, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "3:45:59", "remaining_time": "0:45:11"}
|
26 |
+
{"current_steps": 240, "total_steps": 276, "loss": 0.6113, "lr": 5e-06, "epoch": 2.608695652173913, "percentage": 86.96, "elapsed_time": "3:55:33", "remaining_time": "0:35:20"}
|
27 |
+
{"current_steps": 250, "total_steps": 276, "loss": 0.6127, "lr": 5e-06, "epoch": 2.717391304347826, "percentage": 90.58, "elapsed_time": "4:05:09", "remaining_time": "0:25:29"}
|
28 |
+
{"current_steps": 260, "total_steps": 276, "loss": 0.6186, "lr": 5e-06, "epoch": 2.8260869565217392, "percentage": 94.2, "elapsed_time": "4:14:45", "remaining_time": "0:15:40"}
|
29 |
+
{"current_steps": 270, "total_steps": 276, "loss": 0.616, "lr": 5e-06, "epoch": 2.9347826086956523, "percentage": 97.83, "elapsed_time": "4:24:20", "remaining_time": "0:05:52"}
|
30 |
+
{"current_steps": 276, "total_steps": 276, "eval_loss": 0.6901357173919678, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "4:32:55", "remaining_time": "0:00:00"}
|
31 |
+
{"current_steps": 276, "total_steps": 276, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "4:34:12", "remaining_time": "0:00:00"}
|