DeepDream2045
commited on
Training in progress, step 50, 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 |
-
"k_proj",
|
26 |
"q_proj",
|
|
|
27 |
"down_proj",
|
28 |
-
"
|
29 |
-
"o_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"o_proj",
|
24 |
+
"gate_proj",
|
25 |
"up_proj",
|
|
|
26 |
"q_proj",
|
27 |
+
"v_proj",
|
28 |
"down_proj",
|
29 |
+
"k_proj"
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
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 sha256:2a8d735d93da067cc3ccdb9a8e8e4d49b9fceb542ffc03c787355b6eeff56eb2
|
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 sha256:07efa5c19205375d87c02c816e12d03f5250fb27dedbfe4d7cb06c7a45ef0d3f
|
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 sha256:588fec7999e72266ca0262df6747867f6494bbb7637d6d4ce97bf6270aeb201d
|
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 sha256:0acb2d2f6e013687fc9c12063171d9a55a42733377b5936e0a722f683f9fb682
|
3 |
size 15024
|
last-checkpoint/trainer_state.json
CHANGED
@@ -18,9 +18,9 @@
|
|
18 |
{
|
19 |
"epoch": 0.0005198011760501609,
|
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": 0.01299502940125402,
|
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": 0.02599005880250804,
|
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": 0.0005198011760501609,
|
20 |
"eval_loss": NaN,
|
21 |
+
"eval_runtime": 191.1407,
|
22 |
+
"eval_samples_per_second": 67.809,
|
23 |
+
"eval_steps_per_second": 8.481,
|
24 |
"step": 1
|
25 |
},
|
26 |
{
|
|
|
194 |
{
|
195 |
"epoch": 0.01299502940125402,
|
196 |
"eval_loss": NaN,
|
197 |
+
"eval_runtime": 124.4962,
|
198 |
+
"eval_samples_per_second": 104.108,
|
199 |
+
"eval_steps_per_second": 13.02,
|
200 |
"step": 25
|
201 |
},
|
202 |
{
|
|
|
377 |
{
|
378 |
"epoch": 0.02599005880250804,
|
379 |
"eval_loss": NaN,
|
380 |
+
"eval_runtime": 166.0337,
|
381 |
+
"eval_samples_per_second": 78.062,
|
382 |
+
"eval_steps_per_second": 9.763,
|
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 sha256:6aa37725226041eb549cada138c82982136a64a4485aaea3339df266058c2f57
|
3 |
size 6776
|