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 |
-
"k_proj",
|
24 |
-
"o_proj",
|
25 |
"down_proj",
|
|
|
|
|
26 |
"q_proj",
|
27 |
-
"
|
28 |
"gate_proj",
|
29 |
-
"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
|
|
23 |
"down_proj",
|
24 |
+
"k_proj",
|
25 |
+
"up_proj",
|
26 |
"q_proj",
|
27 |
+
"o_proj",
|
28 |
"gate_proj",
|
29 |
+
"v_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 sha256:454be7f7f42b3e391e4d71e4a03ac934e965c5588a2abca69e5c3ecaa121b08c
|
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 sha256:98722f9ad59cde468c2aa1cfc46d8eed2571ab3acf464dbc61558dcd9d5e61ce
|
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:bed3f715fcccea0289952a1e65e1e9fa153b90ddb88681ade1a90a533910eef6
|
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 sha256:605f443006a4ec282d31183e68111e42bcb6bf1598125189906d2c7084eda57f
|
3 |
size 15024
|
last-checkpoint/trainer_state.json
CHANGED
@@ -18,9 +18,9 @@
|
|
18 |
{
|
19 |
"epoch": 0.002835873803615739,
|
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": 0.07089684509039348,
|
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": 0.14179369018078697,
|
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": 0.002835873803615739,
|
20 |
"eval_loss": NaN,
|
21 |
+
"eval_runtime": 130.4225,
|
22 |
+
"eval_samples_per_second": 18.218,
|
23 |
+
"eval_steps_per_second": 2.277,
|
24 |
"step": 1
|
25 |
},
|
26 |
{
|
|
|
194 |
{
|
195 |
"epoch": 0.07089684509039348,
|
196 |
"eval_loss": NaN,
|
197 |
+
"eval_runtime": 130.0655,
|
198 |
+
"eval_samples_per_second": 18.268,
|
199 |
+
"eval_steps_per_second": 2.283,
|
200 |
"step": 25
|
201 |
},
|
202 |
{
|
|
|
377 |
{
|
378 |
"epoch": 0.14179369018078697,
|
379 |
"eval_loss": NaN,
|
380 |
+
"eval_runtime": 130.2643,
|
381 |
+
"eval_samples_per_second": 18.24,
|
382 |
+
"eval_steps_per_second": 2.28,
|
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 sha256:71bebcc0519cae1e60b4d19cf548f5635e381b6f19a5338cc9ecce64ea4992a8
|
3 |
size 6776
|