Training in progress, epoch 0, checkpoint
Browse files
last-checkpoint/adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
-
"up_proj",
|
25 |
-
"v_proj",
|
26 |
"o_proj",
|
|
|
|
|
|
|
27 |
"gate_proj",
|
28 |
-
"
|
29 |
-
"down_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"k_proj",
|
|
|
|
|
24 |
"o_proj",
|
25 |
+
"v_proj",
|
26 |
+
"down_proj",
|
27 |
+
"q_proj",
|
28 |
"gate_proj",
|
29 |
+
"up_proj"
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 80013120
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35b87eb078b45683cae3b6afe67507eec7c4e65d31f954cb725267409650db44
|
3 |
size 80013120
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 160173306
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f483aa7902c5af727bae154802674efccc3c46a20e593aa34b52400cc96d6807
|
3 |
size 160173306
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fabe555e426d29ce39e0d57d059e8ad3c6f264a2ad9a601533f26c69b61418a
|
3 |
size 14244
|
last-checkpoint/trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6776
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:236de30e9969c5e6bd7c6f1ce5795a9c3cd8937a91a4bb16877c4eb246ae6cde
|
3 |
size 6776
|