Training in progress, step 291, checkpoint
Browse files
checkpoint-291/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1415329032
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7644d37c8337ff124c044cb3ded5bee2190760e3f93b7182c1a45349b83a5de
|
3 |
size 1415329032
|
checkpoint-291/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2830833850
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34399dc784eb6a9c418c1403cc4067357863542c80e62722eeaac1729d7a98a0
|
3 |
size 2830833850
|
checkpoint-291/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22e1f228c5f91c32a551f03c547e2753f195f7168d247ce88741efb49afe64fd
|
3 |
size 1064
|
checkpoint-291/tokenizer.json
CHANGED
@@ -2,7 +2,7 @@
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
-
"max_length":
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
+
"max_length": 580,
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
checkpoint-291/trainer_state.json
CHANGED
@@ -10,25 +10,25 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.06891798759476224,
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate": 9.
|
15 |
-
"loss": 0.
|
16 |
"step": 100
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.13783597518952448,
|
20 |
-
"grad_norm":
|
21 |
-
"learning_rate": 9.
|
22 |
-
"loss": 0.
|
23 |
"step": 200
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.2005513439007581,
|
27 |
-
"eval_accuracy": 0.
|
28 |
-
"eval_loss": 0.
|
29 |
-
"eval_runtime":
|
30 |
-
"eval_samples_per_second": 72.
|
31 |
-
"eval_steps_per_second": 9.
|
32 |
"step": 291
|
33 |
}
|
34 |
],
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.06891798759476224,
|
13 |
+
"grad_norm": 8.768977165222168,
|
14 |
+
"learning_rate": 9.88557738007169e-06,
|
15 |
+
"loss": 0.6099,
|
16 |
"step": 100
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.13783597518952448,
|
20 |
+
"grad_norm": 13.488529205322266,
|
21 |
+
"learning_rate": 9.547546534667266e-06,
|
22 |
+
"loss": 0.5507,
|
23 |
"step": 200
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.2005513439007581,
|
27 |
+
"eval_accuracy": 0.7176081716426815,
|
28 |
+
"eval_loss": 0.5506236553192139,
|
29 |
+
"eval_runtime": 1151.562,
|
30 |
+
"eval_samples_per_second": 72.772,
|
31 |
+
"eval_steps_per_second": 9.097,
|
32 |
"step": 291
|
33 |
}
|
34 |
],
|
checkpoint-291/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5304
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17ac0abd3be3c7ffa5c103daf33aa2dc3687beb22a067b1ddae465234d558ea1
|
3 |
size 5304
|