DeepDream2045
commited on
Commit
•
64ee151
1
Parent(s):
0708242
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 |
"up_proj",
|
24 |
-
"
|
25 |
"q_proj",
|
|
|
26 |
"gate_proj",
|
27 |
-
"k_proj",
|
28 |
-
"v_proj",
|
29 |
"down_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"v_proj",
|
24 |
"up_proj",
|
25 |
+
"k_proj",
|
26 |
"q_proj",
|
27 |
+
"o_proj",
|
28 |
"gate_proj",
|
|
|
|
|
29 |
"down_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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c6dddbc65c5cc1386be476a93923b429fef687cdb9e3b507a44aa41fec87b17
|
3 |
+
size 14960
|
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 sha256:578f89f36c2119627429fdb12293c5a7bcbb70a50fe92bf4c060d05eba122910
|
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 sha256:7ee59a279c4d01e637361bcde2f9028b0b6a5ba713f055bc740870e0390f08a9
|
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 sha256:4cb1f1f5ebe2245fc110ccc2866f5e52ee7b1c05e80c67e68a48848dd3941ebf
|
3 |
size 15024
|
last-checkpoint/trainer_state.json
CHANGED
@@ -18,9 +18,9 @@
|
|
18 |
{
|
19 |
"epoch": 0.024922118380062305,
|
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": 0.6230529595015576,
|
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": 1.2461059190031152,
|
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": 0.024922118380062305,
|
20 |
"eval_loss": NaN,
|
21 |
+
"eval_runtime": 5.6431,
|
22 |
+
"eval_samples_per_second": 47.846,
|
23 |
+
"eval_steps_per_second": 6.025,
|
24 |
"step": 1
|
25 |
},
|
26 |
{
|
|
|
194 |
{
|
195 |
"epoch": 0.6230529595015576,
|
196 |
"eval_loss": NaN,
|
197 |
+
"eval_runtime": 5.5286,
|
198 |
+
"eval_samples_per_second": 48.837,
|
199 |
+
"eval_steps_per_second": 6.15,
|
200 |
"step": 25
|
201 |
},
|
202 |
{
|
|
|
377 |
{
|
378 |
"epoch": 1.2461059190031152,
|
379 |
"eval_loss": NaN,
|
380 |
+
"eval_runtime": 5.5255,
|
381 |
+
"eval_samples_per_second": 48.865,
|
382 |
+
"eval_steps_per_second": 6.153,
|
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 sha256:372431cf5d215cc9cbc0915c2e3f7c9cedcc04697ee854b92077999ee82a49b4
|
3 |
size 6776
|