DeepDream2045
commited on
Commit
•
e727ba0
1
Parent(s):
db8db30
Training in progress, step 50, checkpoint
Browse files
last-checkpoint/adapter_config.json
CHANGED
@@ -20,12 +20,12 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"k_proj",
|
24 |
-
"o_proj",
|
25 |
-
"q_proj",
|
26 |
"v_proj",
|
27 |
-
"up_proj",
|
28 |
"down_proj",
|
|
|
|
|
|
|
|
|
29 |
"gate_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
|
|
|
|
23 |
"v_proj",
|
|
|
24 |
"down_proj",
|
25 |
+
"o_proj",
|
26 |
+
"up_proj",
|
27 |
+
"q_proj",
|
28 |
+
"k_proj",
|
29 |
"gate_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c647c2477ac1dcbfa262b6d94265b8ece9372898d971e0a1e0e3d61e1487774d
|
3 |
size 15024
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e942d3b76267ccff9412a67588ace8e831a40ed4ffa7b9653f973988ab67767
|
3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7174cc4497573ac0d8d963f8dc44392ddf278521acba7aab1f03e52160becb9
|
3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:583b5a377bcf6fdd1e35c8c34141403b0f2c35d03df4322059db8ae36a32b85d
|
3 |
size 15024
|
last-checkpoint/trainer_state.json
CHANGED
@@ -18,9 +18,9 @@
|
|
18 |
{
|
19 |
"epoch": 0.006771053745239103,
|
20 |
"eval_loss": NaN,
|
21 |
-
"eval_runtime":
|
22 |
-
"eval_samples_per_second":
|
23 |
-
"eval_steps_per_second":
|
24 |
"step": 1
|
25 |
},
|
26 |
{
|
@@ -194,9 +194,9 @@
|
|
194 |
{
|
195 |
"epoch": 0.16927634363097757,
|
196 |
"eval_loss": NaN,
|
197 |
-
"eval_runtime":
|
198 |
-
"eval_samples_per_second":
|
199 |
-
"eval_steps_per_second":
|
200 |
"step": 25
|
201 |
},
|
202 |
{
|
@@ -377,9 +377,9 @@
|
|
377 |
{
|
378 |
"epoch": 0.33855268726195514,
|
379 |
"eval_loss": NaN,
|
380 |
-
"eval_runtime":
|
381 |
-
"eval_samples_per_second":
|
382 |
-
"eval_steps_per_second":
|
383 |
"step": 50
|
384 |
}
|
385 |
],
|
|
|
18 |
{
|
19 |
"epoch": 0.006771053745239103,
|
20 |
"eval_loss": NaN,
|
21 |
+
"eval_runtime": 100.0237,
|
22 |
+
"eval_samples_per_second": 9.948,
|
23 |
+
"eval_steps_per_second": 1.25,
|
24 |
"step": 1
|
25 |
},
|
26 |
{
|
|
|
194 |
{
|
195 |
"epoch": 0.16927634363097757,
|
196 |
"eval_loss": NaN,
|
197 |
+
"eval_runtime": 100.0356,
|
198 |
+
"eval_samples_per_second": 9.946,
|
199 |
+
"eval_steps_per_second": 1.25,
|
200 |
"step": 25
|
201 |
},
|
202 |
{
|
|
|
377 |
{
|
378 |
"epoch": 0.33855268726195514,
|
379 |
"eval_loss": NaN,
|
380 |
+
"eval_runtime": 99.9005,
|
381 |
+
"eval_samples_per_second": 9.96,
|
382 |
+
"eval_steps_per_second": 1.251,
|
383 |
"step": 50
|
384 |
}
|
385 |
],
|
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 sha256:1e793f9bd3dc57265c50bdadd53647d6243f3824ac2e90ff1aae17dbba3f746b
|
3 |
size 6776
|