Upload folder using huggingface_hub
Browse files- conds.pt +3 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- s3gen.safetensors +3 -0
- scheduler.pt +3 -0
- t3_cfg.safetensors +3 -0
- tokenizer.json +1435 -0
- trainer_state.json +1923 -0
- training_args.bin +3 -0
- ve.safetensors +3 -0
conds.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6552d70568833628ba019c6b03459e77fe71ca197d5c560cef9411bee9d87f4e
|
| 3 |
+
size 107374
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:124c430cd7cbb85ba7d9981a7bbae032b7b2e655c22dcd35f7f79beeadffdacb
|
| 3 |
+
size 2129654648
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:427f2d90bb72f9af91eae0df1070a0620c8e0860c6b9e79e5ff3a194457aff97
|
| 3 |
+
size 4259421963
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:777940f94385b4bcd2af00fd0e4fdc0aafcac5f34ddb0b107b8396f79cb8ba56
|
| 3 |
+
size 14645
|
s3gen.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b78103c654207393955e4900aac14a12de8ef25f4b09424f1ef91941f161d4e
|
| 3 |
+
size 1056484620
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb68af34417121f1f3a3518a567c5ccf8f07990cbc83b85f3bed894c554af616
|
| 3 |
+
size 1465
|
t3_cfg.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03d635376a2048b4c898e16570e550af61d73e1930ccd73661ba7e003aaf7541
|
| 3 |
+
size 2129653744
|
tokenizer.json
ADDED
|
@@ -0,0 +1,1435 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 0,
|
| 8 |
+
"special": true,
|
| 9 |
+
"content": "[STOP]",
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"normalized": false
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"id": 1,
|
| 17 |
+
"special": true,
|
| 18 |
+
"content": "[UNK]",
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"lstrip": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"normalized": false
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"id": 2,
|
| 26 |
+
"special": true,
|
| 27 |
+
"content": "[SPACE]",
|
| 28 |
+
"single_word": false,
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"normalized": false
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": 255,
|
| 35 |
+
"special": true,
|
| 36 |
+
"content": "[START]",
|
| 37 |
+
"single_word": false,
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"normalized": false
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"id": 604,
|
| 44 |
+
"content": "[UH]",
|
| 45 |
+
"single_word": false,
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"id": 605,
|
| 53 |
+
"content": "[UM]",
|
| 54 |
+
"single_word": false,
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"id": 606,
|
| 62 |
+
"content": "[giggle]",
|
| 63 |
+
"single_word": false,
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"normalized": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"id": 607,
|
| 71 |
+
"content": "[laughter]",
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"lstrip": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"normalized": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"id": 608,
|
| 80 |
+
"content": "[guffaw]",
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"lstrip": false,
|
| 83 |
+
"rstrip": false,
|
| 84 |
+
"normalized": false,
|
| 85 |
+
"special": true
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"id": 609,
|
| 89 |
+
"content": "[inhale]",
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"lstrip": false,
|
| 92 |
+
"rstrip": false,
|
| 93 |
+
"normalized": false,
|
| 94 |
+
"special": true
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"id": 610,
|
| 98 |
+
"content": "[exhale]",
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"lstrip": false,
|
| 101 |
+
"rstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"special": true
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"id": 611,
|
| 107 |
+
"content": "[sigh]",
|
| 108 |
+
"single_word": false,
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"rstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"special": true
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"id": 612,
|
| 116 |
+
"content": "[cry]",
|
| 117 |
+
"single_word": false,
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"id": 613,
|
| 125 |
+
"content": "[bark]",
|
| 126 |
+
"single_word": false,
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"id": 614,
|
| 134 |
+
"content": "[howl]",
|
| 135 |
+
"single_word": false,
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"normalized": false,
|
| 139 |
+
"special": true
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"id": 615,
|
| 143 |
+
"content": "[meow]",
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"lstrip": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"normalized": false,
|
| 148 |
+
"special": true
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"id": 616,
|
| 152 |
+
"content": "[singing]",
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"lstrip": false,
|
| 155 |
+
"rstrip": false,
|
| 156 |
+
"normalized": false,
|
| 157 |
+
"special": true
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"id": 617,
|
| 161 |
+
"content": "[music]",
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"lstrip": false,
|
| 164 |
+
"rstrip": false,
|
| 165 |
+
"normalized": false,
|
| 166 |
+
"special": true
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"id": 618,
|
| 170 |
+
"content": "[whistle]",
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"lstrip": false,
|
| 173 |
+
"rstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"special": true
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"id": 619,
|
| 179 |
+
"content": "[humming]",
|
| 180 |
+
"single_word": false,
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"rstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"special": true
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"id": 620,
|
| 188 |
+
"content": "[gasp]",
|
| 189 |
+
"single_word": false,
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"id": 621,
|
| 197 |
+
"content": "[groan]",
|
| 198 |
+
"single_word": false,
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"normalized": false,
|
| 202 |
+
"special": true
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"id": 622,
|
| 206 |
+
"content": "[whisper]",
|
| 207 |
+
"single_word": false,
|
| 208 |
+
"lstrip": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"normalized": false,
|
| 211 |
+
"special": true
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"id": 623,
|
| 215 |
+
"content": "[mumble]",
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"lstrip": false,
|
| 218 |
+
"rstrip": false,
|
| 219 |
+
"normalized": false,
|
| 220 |
+
"special": true
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"id": 624,
|
| 224 |
+
"content": "[sniff]",
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"lstrip": false,
|
| 227 |
+
"rstrip": false,
|
| 228 |
+
"normalized": false,
|
| 229 |
+
"special": true
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"id": 625,
|
| 233 |
+
"content": "[sneeze]",
|
| 234 |
+
"single_word": false,
|
| 235 |
+
"lstrip": false,
|
| 236 |
+
"rstrip": false,
|
| 237 |
+
"normalized": false,
|
| 238 |
+
"special": true
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"id": 626,
|
| 242 |
+
"content": "[cough]",
|
| 243 |
+
"single_word": false,
|
| 244 |
+
"lstrip": false,
|
| 245 |
+
"rstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"special": true
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"id": 627,
|
| 251 |
+
"content": "[snore]",
|
| 252 |
+
"single_word": false,
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"rstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"special": true
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"id": 628,
|
| 260 |
+
"content": "[chew]",
|
| 261 |
+
"single_word": false,
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"normalized": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"id": 629,
|
| 269 |
+
"content": "[sip]",
|
| 270 |
+
"single_word": false,
|
| 271 |
+
"lstrip": false,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"normalized": false,
|
| 274 |
+
"special": true
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"id": 630,
|
| 278 |
+
"content": "[clear_throat]",
|
| 279 |
+
"single_word": false,
|
| 280 |
+
"lstrip": false,
|
| 281 |
+
"rstrip": false,
|
| 282 |
+
"normalized": false,
|
| 283 |
+
"special": true
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"id": 631,
|
| 287 |
+
"content": "[kiss]",
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"lstrip": false,
|
| 290 |
+
"rstrip": false,
|
| 291 |
+
"normalized": false,
|
| 292 |
+
"special": true
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"id": 632,
|
| 296 |
+
"content": "[shhh]",
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"lstrip": false,
|
| 299 |
+
"rstrip": false,
|
| 300 |
+
"normalized": false,
|
| 301 |
+
"special": true
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"id": 633,
|
| 305 |
+
"content": "[gibberish]",
|
| 306 |
+
"single_word": false,
|
| 307 |
+
"lstrip": false,
|
| 308 |
+
"rstrip": false,
|
| 309 |
+
"normalized": false,
|
| 310 |
+
"special": true
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"id": 634,
|
| 314 |
+
"content": "[fr]",
|
| 315 |
+
"single_word": false,
|
| 316 |
+
"lstrip": false,
|
| 317 |
+
"rstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"special": true
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"id": 635,
|
| 323 |
+
"content": "[es]",
|
| 324 |
+
"single_word": false,
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"rstrip": false,
|
| 327 |
+
"normalized": false,
|
| 328 |
+
"special": true
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"id": 636,
|
| 332 |
+
"content": "[de]",
|
| 333 |
+
"single_word": false,
|
| 334 |
+
"lstrip": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"normalized": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"id": 637,
|
| 341 |
+
"content": "[it]",
|
| 342 |
+
"single_word": false,
|
| 343 |
+
"lstrip": false,
|
| 344 |
+
"rstrip": false,
|
| 345 |
+
"normalized": false,
|
| 346 |
+
"special": true
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"id": 638,
|
| 350 |
+
"content": "[ipa]",
|
| 351 |
+
"single_word": false,
|
| 352 |
+
"lstrip": false,
|
| 353 |
+
"rstrip": false,
|
| 354 |
+
"normalized": false,
|
| 355 |
+
"special": true
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"id": 639,
|
| 359 |
+
"content": "[end_of_label]",
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"lstrip": false,
|
| 362 |
+
"rstrip": false,
|
| 363 |
+
"normalized": false,
|
| 364 |
+
"special": true
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"id": 695,
|
| 368 |
+
"content": "[PLACEHOLDER55]",
|
| 369 |
+
"single_word": false,
|
| 370 |
+
"lstrip": false,
|
| 371 |
+
"rstrip": false,
|
| 372 |
+
"normalized": false,
|
| 373 |
+
"special": true
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"id": 696,
|
| 377 |
+
"content": "[PLACEHOLDER56]",
|
| 378 |
+
"single_word": false,
|
| 379 |
+
"lstrip": false,
|
| 380 |
+
"rstrip": false,
|
| 381 |
+
"normalized": false,
|
| 382 |
+
"special": true
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"id": 697,
|
| 386 |
+
"content": "[PLACEHOLDER57]",
|
| 387 |
+
"single_word": false,
|
| 388 |
+
"lstrip": false,
|
| 389 |
+
"rstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"special": true
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"id": 698,
|
| 395 |
+
"content": "[PLACEHOLDER58]",
|
| 396 |
+
"single_word": false,
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"rstrip": false,
|
| 399 |
+
"normalized": false,
|
| 400 |
+
"special": true
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"id": 699,
|
| 404 |
+
"content": "[PLACEHOLDER59]",
|
| 405 |
+
"single_word": false,
|
| 406 |
+
"lstrip": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"normalized": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"id": 700,
|
| 413 |
+
"content": "[PLACEHOLDER60]",
|
| 414 |
+
"single_word": false,
|
| 415 |
+
"lstrip": false,
|
| 416 |
+
"rstrip": false,
|
| 417 |
+
"normalized": false,
|
| 418 |
+
"special": true
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"id": 701,
|
| 422 |
+
"content": "[PLACEHOLDER61]",
|
| 423 |
+
"single_word": false,
|
| 424 |
+
"lstrip": false,
|
| 425 |
+
"rstrip": false,
|
| 426 |
+
"normalized": false,
|
| 427 |
+
"special": true
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"id": 702,
|
| 431 |
+
"content": "[PLACEHOLDER62]",
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"lstrip": false,
|
| 434 |
+
"rstrip": false,
|
| 435 |
+
"normalized": false,
|
| 436 |
+
"special": true
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"id": 703,
|
| 440 |
+
"content": "[PLACEHOLDER63]",
|
| 441 |
+
"single_word": false,
|
| 442 |
+
"lstrip": false,
|
| 443 |
+
"rstrip": false,
|
| 444 |
+
"normalized": false,
|
| 445 |
+
"special": true
|
| 446 |
+
}
|
| 447 |
+
],
|
| 448 |
+
"normalizer": null,
|
| 449 |
+
"pre_tokenizer": {
|
| 450 |
+
"type": "Whitespace"
|
| 451 |
+
},
|
| 452 |
+
"post_processor": null,
|
| 453 |
+
"decoder": null,
|
| 454 |
+
"model": {
|
| 455 |
+
"type": "BPE",
|
| 456 |
+
"dropout": null,
|
| 457 |
+
"unk_token": "[UNK]",
|
| 458 |
+
"continuing_subword_prefix": null,
|
| 459 |
+
"end_of_word_suffix": null,
|
| 460 |
+
"fuse_unk": false,
|
| 461 |
+
"vocab": {
|
| 462 |
+
"[STOP]": 0,
|
| 463 |
+
"[UNK]": 1,
|
| 464 |
+
"[SPACE]": 2,
|
| 465 |
+
"!": 3,
|
| 466 |
+
"'": 4,
|
| 467 |
+
"(": 5,
|
| 468 |
+
")": 6,
|
| 469 |
+
",": 7,
|
| 470 |
+
"-": 8,
|
| 471 |
+
".": 9,
|
| 472 |
+
"/": 10,
|
| 473 |
+
":": 11,
|
| 474 |
+
";": 12,
|
| 475 |
+
"?": 13,
|
| 476 |
+
"a": 14,
|
| 477 |
+
"b": 15,
|
| 478 |
+
"c": 16,
|
| 479 |
+
"d": 17,
|
| 480 |
+
"e": 18,
|
| 481 |
+
"f": 19,
|
| 482 |
+
"g": 20,
|
| 483 |
+
"h": 21,
|
| 484 |
+
"i": 22,
|
| 485 |
+
"j": 23,
|
| 486 |
+
"k": 24,
|
| 487 |
+
"l": 25,
|
| 488 |
+
"m": 26,
|
| 489 |
+
"n": 27,
|
| 490 |
+
"o": 28,
|
| 491 |
+
"p": 29,
|
| 492 |
+
"q": 30,
|
| 493 |
+
"r": 31,
|
| 494 |
+
"s": 32,
|
| 495 |
+
"t": 33,
|
| 496 |
+
"u": 34,
|
| 497 |
+
"v": 35,
|
| 498 |
+
"w": 36,
|
| 499 |
+
"x": 37,
|
| 500 |
+
"y": 38,
|
| 501 |
+
"z": 39,
|
| 502 |
+
"th": 40,
|
| 503 |
+
"in": 41,
|
| 504 |
+
"the": 42,
|
| 505 |
+
"an": 43,
|
| 506 |
+
"er": 44,
|
| 507 |
+
"ou": 45,
|
| 508 |
+
"re": 46,
|
| 509 |
+
"on": 47,
|
| 510 |
+
"at": 48,
|
| 511 |
+
"ed": 49,
|
| 512 |
+
"en": 50,
|
| 513 |
+
"to": 51,
|
| 514 |
+
"ing": 52,
|
| 515 |
+
"and": 53,
|
| 516 |
+
"is": 54,
|
| 517 |
+
"as": 55,
|
| 518 |
+
"al": 56,
|
| 519 |
+
"or": 57,
|
| 520 |
+
"of": 58,
|
| 521 |
+
"ar": 59,
|
| 522 |
+
"it": 60,
|
| 523 |
+
"es": 61,
|
| 524 |
+
"he": 62,
|
| 525 |
+
"st": 63,
|
| 526 |
+
"le": 64,
|
| 527 |
+
"om": 65,
|
| 528 |
+
"se": 66,
|
| 529 |
+
"be": 67,
|
| 530 |
+
"ad": 68,
|
| 531 |
+
"ow": 69,
|
| 532 |
+
"ly": 70,
|
| 533 |
+
"ch": 71,
|
| 534 |
+
"wh": 72,
|
| 535 |
+
"that": 73,
|
| 536 |
+
"you": 74,
|
| 537 |
+
"li": 75,
|
| 538 |
+
"ve": 76,
|
| 539 |
+
"ac": 77,
|
| 540 |
+
"ti": 78,
|
| 541 |
+
"ld": 79,
|
| 542 |
+
"me": 80,
|
| 543 |
+
"was": 81,
|
| 544 |
+
"gh": 82,
|
| 545 |
+
"id": 83,
|
| 546 |
+
"ll": 84,
|
| 547 |
+
"wi": 85,
|
| 548 |
+
"ent": 86,
|
| 549 |
+
"for": 87,
|
| 550 |
+
"ay": 88,
|
| 551 |
+
"ro": 89,
|
| 552 |
+
"ver": 90,
|
| 553 |
+
"ic": 91,
|
| 554 |
+
"her": 92,
|
| 555 |
+
"ke": 93,
|
| 556 |
+
"his": 94,
|
| 557 |
+
"no": 95,
|
| 558 |
+
"ut": 96,
|
| 559 |
+
"un": 97,
|
| 560 |
+
"ir": 98,
|
| 561 |
+
"lo": 99,
|
| 562 |
+
"we": 100,
|
| 563 |
+
"ri": 101,
|
| 564 |
+
"ha": 102,
|
| 565 |
+
"with": 103,
|
| 566 |
+
"ght": 104,
|
| 567 |
+
"out": 105,
|
| 568 |
+
"im": 106,
|
| 569 |
+
"ion": 107,
|
| 570 |
+
"all": 108,
|
| 571 |
+
"ab": 109,
|
| 572 |
+
"one": 110,
|
| 573 |
+
"ne": 111,
|
| 574 |
+
"ge": 112,
|
| 575 |
+
"ould": 113,
|
| 576 |
+
"ter": 114,
|
| 577 |
+
"mo": 115,
|
| 578 |
+
"had": 116,
|
| 579 |
+
"ce": 117,
|
| 580 |
+
"she": 118,
|
| 581 |
+
"go": 119,
|
| 582 |
+
"sh": 120,
|
| 583 |
+
"ur": 121,
|
| 584 |
+
"am": 122,
|
| 585 |
+
"so": 123,
|
| 586 |
+
"pe": 124,
|
| 587 |
+
"my": 125,
|
| 588 |
+
"de": 126,
|
| 589 |
+
"are": 127,
|
| 590 |
+
"but": 128,
|
| 591 |
+
"ome": 129,
|
| 592 |
+
"fr": 130,
|
| 593 |
+
"ther": 131,
|
| 594 |
+
"fe": 132,
|
| 595 |
+
"su": 133,
|
| 596 |
+
"do": 134,
|
| 597 |
+
"con": 135,
|
| 598 |
+
"te": 136,
|
| 599 |
+
"ain": 137,
|
| 600 |
+
"ere": 138,
|
| 601 |
+
"po": 139,
|
| 602 |
+
"if": 140,
|
| 603 |
+
"they": 141,
|
| 604 |
+
"us": 142,
|
| 605 |
+
"ag": 143,
|
| 606 |
+
"tr": 144,
|
| 607 |
+
"now": 145,
|
| 608 |
+
"oun": 146,
|
| 609 |
+
"this": 147,
|
| 610 |
+
"have": 148,
|
| 611 |
+
"not": 149,
|
| 612 |
+
"sa": 150,
|
| 613 |
+
"il": 151,
|
| 614 |
+
"up": 152,
|
| 615 |
+
"thing": 153,
|
| 616 |
+
"from": 154,
|
| 617 |
+
"ap": 155,
|
| 618 |
+
"him": 156,
|
| 619 |
+
"ack": 157,
|
| 620 |
+
"ation": 158,
|
| 621 |
+
"ant": 159,
|
| 622 |
+
"our": 160,
|
| 623 |
+
"op": 161,
|
| 624 |
+
"like": 162,
|
| 625 |
+
"ust": 163,
|
| 626 |
+
"ess": 164,
|
| 627 |
+
"bo": 165,
|
| 628 |
+
"ok": 166,
|
| 629 |
+
"ul": 167,
|
| 630 |
+
"ind": 168,
|
| 631 |
+
"ex": 169,
|
| 632 |
+
"com": 170,
|
| 633 |
+
"some": 171,
|
| 634 |
+
"there": 172,
|
| 635 |
+
"ers": 173,
|
| 636 |
+
"co": 174,
|
| 637 |
+
"res": 175,
|
| 638 |
+
"man": 176,
|
| 639 |
+
"ard": 177,
|
| 640 |
+
"pl": 178,
|
| 641 |
+
"wor": 179,
|
| 642 |
+
"way": 180,
|
| 643 |
+
"tion": 181,
|
| 644 |
+
"fo": 182,
|
| 645 |
+
"ca": 183,
|
| 646 |
+
"were": 184,
|
| 647 |
+
"by": 185,
|
| 648 |
+
"ate": 186,
|
| 649 |
+
"pro": 187,
|
| 650 |
+
"ted": 188,
|
| 651 |
+
"ound": 189,
|
| 652 |
+
"own": 190,
|
| 653 |
+
"would": 191,
|
| 654 |
+
"ts": 192,
|
| 655 |
+
"what": 193,
|
| 656 |
+
"qu": 194,
|
| 657 |
+
"ally": 195,
|
| 658 |
+
"ight": 196,
|
| 659 |
+
"ck": 197,
|
| 660 |
+
"gr": 198,
|
| 661 |
+
"when": 199,
|
| 662 |
+
"ven": 200,
|
| 663 |
+
"can": 201,
|
| 664 |
+
"ough": 202,
|
| 665 |
+
"ine": 203,
|
| 666 |
+
"end": 204,
|
| 667 |
+
"per": 205,
|
| 668 |
+
"ous": 206,
|
| 669 |
+
"od": 207,
|
| 670 |
+
"ide": 208,
|
| 671 |
+
"know": 209,
|
| 672 |
+
"ty": 210,
|
| 673 |
+
"very": 211,
|
| 674 |
+
"si": 212,
|
| 675 |
+
"ak": 213,
|
| 676 |
+
"who": 214,
|
| 677 |
+
"about": 215,
|
| 678 |
+
"ill": 216,
|
| 679 |
+
"them": 217,
|
| 680 |
+
"est": 218,
|
| 681 |
+
"red": 219,
|
| 682 |
+
"ye": 220,
|
| 683 |
+
"could": 221,
|
| 684 |
+
"ong": 222,
|
| 685 |
+
"your": 223,
|
| 686 |
+
"their": 224,
|
| 687 |
+
"em": 225,
|
| 688 |
+
"just": 226,
|
| 689 |
+
"other": 227,
|
| 690 |
+
"into": 228,
|
| 691 |
+
"any": 229,
|
| 692 |
+
"whi": 230,
|
| 693 |
+
"um": 231,
|
| 694 |
+
"tw": 232,
|
| 695 |
+
"ast": 233,
|
| 696 |
+
"der": 234,
|
| 697 |
+
"did": 235,
|
| 698 |
+
"ie": 236,
|
| 699 |
+
"been": 237,
|
| 700 |
+
"ace": 238,
|
| 701 |
+
"ink": 239,
|
| 702 |
+
"ity": 240,
|
| 703 |
+
"back": 241,
|
| 704 |
+
"ting": 242,
|
| 705 |
+
"br": 243,
|
| 706 |
+
"more": 244,
|
| 707 |
+
"ake": 245,
|
| 708 |
+
"pp": 246,
|
| 709 |
+
"then": 247,
|
| 710 |
+
"sp": 248,
|
| 711 |
+
"el": 249,
|
| 712 |
+
"use": 250,
|
| 713 |
+
"bl": 251,
|
| 714 |
+
"said": 252,
|
| 715 |
+
"over": 253,
|
| 716 |
+
"get": 254,
|
| 717 |
+
"[START]": 255,
|
| 718 |
+
"\"": 256,
|
| 719 |
+
"#": 257,
|
| 720 |
+
"$": 258,
|
| 721 |
+
"%": 259,
|
| 722 |
+
"&": 260,
|
| 723 |
+
"*": 261,
|
| 724 |
+
"+": 262,
|
| 725 |
+
"0": 263,
|
| 726 |
+
"1": 264,
|
| 727 |
+
"2": 265,
|
| 728 |
+
"3": 266,
|
| 729 |
+
"4": 267,
|
| 730 |
+
"5": 268,
|
| 731 |
+
"6": 269,
|
| 732 |
+
"7": 270,
|
| 733 |
+
"8": 271,
|
| 734 |
+
"9": 272,
|
| 735 |
+
"<": 273,
|
| 736 |
+
"=": 274,
|
| 737 |
+
">": 275,
|
| 738 |
+
"@": 276,
|
| 739 |
+
"A": 277,
|
| 740 |
+
"B": 278,
|
| 741 |
+
"C": 279,
|
| 742 |
+
"D": 280,
|
| 743 |
+
"E": 281,
|
| 744 |
+
"F": 282,
|
| 745 |
+
"G": 283,
|
| 746 |
+
"H": 284,
|
| 747 |
+
"I": 285,
|
| 748 |
+
"J": 286,
|
| 749 |
+
"K": 287,
|
| 750 |
+
"L": 288,
|
| 751 |
+
"M": 289,
|
| 752 |
+
"N": 290,
|
| 753 |
+
"O": 291,
|
| 754 |
+
"P": 292,
|
| 755 |
+
"Q": 293,
|
| 756 |
+
"R": 294,
|
| 757 |
+
"S": 295,
|
| 758 |
+
"T": 296,
|
| 759 |
+
"U": 297,
|
| 760 |
+
"V": 298,
|
| 761 |
+
"W": 299,
|
| 762 |
+
"X": 300,
|
| 763 |
+
"Y": 301,
|
| 764 |
+
"Z": 302,
|
| 765 |
+
"[": 303,
|
| 766 |
+
"\\": 304,
|
| 767 |
+
"]": 305,
|
| 768 |
+
"^": 306,
|
| 769 |
+
"_": 307,
|
| 770 |
+
"`": 308,
|
| 771 |
+
"{": 309,
|
| 772 |
+
"|": 310,
|
| 773 |
+
"}": 311,
|
| 774 |
+
"~": 312,
|
| 775 |
+
"‐": 313,
|
| 776 |
+
"‑": 314,
|
| 777 |
+
"‒": 315,
|
| 778 |
+
"–": 316,
|
| 779 |
+
"—": 317,
|
| 780 |
+
"―": 318,
|
| 781 |
+
"‖": 319,
|
| 782 |
+
"‗": 320,
|
| 783 |
+
"‘": 321,
|
| 784 |
+
"’": 322,
|
| 785 |
+
"‚": 323,
|
| 786 |
+
"‛": 324,
|
| 787 |
+
"“": 325,
|
| 788 |
+
"”": 326,
|
| 789 |
+
"„": 327,
|
| 790 |
+
"‟": 328,
|
| 791 |
+
" ": 329,
|
| 792 |
+
"¡": 330,
|
| 793 |
+
"¢": 331,
|
| 794 |
+
"£": 332,
|
| 795 |
+
"¤": 333,
|
| 796 |
+
"¥": 334,
|
| 797 |
+
"¦": 335,
|
| 798 |
+
"§": 336,
|
| 799 |
+
"¨": 337,
|
| 800 |
+
"©": 338,
|
| 801 |
+
"ª": 339,
|
| 802 |
+
"«": 340,
|
| 803 |
+
"¬": 341,
|
| 804 |
+
"": 342,
|
| 805 |
+
"®": 343,
|
| 806 |
+
"¯": 344,
|
| 807 |
+
"°": 345,
|
| 808 |
+
"±": 346,
|
| 809 |
+
"²": 347,
|
| 810 |
+
"³": 348,
|
| 811 |
+
"´": 349,
|
| 812 |
+
"µ": 350,
|
| 813 |
+
"¶": 351,
|
| 814 |
+
"·": 352,
|
| 815 |
+
"¸": 353,
|
| 816 |
+
"¹": 354,
|
| 817 |
+
"º": 355,
|
| 818 |
+
"»": 356,
|
| 819 |
+
"¼": 357,
|
| 820 |
+
"½": 358,
|
| 821 |
+
"¾": 359,
|
| 822 |
+
"¿": 360,
|
| 823 |
+
"À": 361,
|
| 824 |
+
"Á": 362,
|
| 825 |
+
"Â": 363,
|
| 826 |
+
"Ã": 364,
|
| 827 |
+
"Ä": 365,
|
| 828 |
+
"Å": 366,
|
| 829 |
+
"Æ": 367,
|
| 830 |
+
"Ç": 368,
|
| 831 |
+
"È": 369,
|
| 832 |
+
"É": 370,
|
| 833 |
+
"Ê": 371,
|
| 834 |
+
"Ë": 372,
|
| 835 |
+
"Ì": 373,
|
| 836 |
+
"Í": 374,
|
| 837 |
+
"Î": 375,
|
| 838 |
+
"Ï": 376,
|
| 839 |
+
"Ð": 377,
|
| 840 |
+
"Ñ": 378,
|
| 841 |
+
"Ò": 379,
|
| 842 |
+
"Ó": 380,
|
| 843 |
+
"Ô": 381,
|
| 844 |
+
"Õ": 382,
|
| 845 |
+
"Ö": 383,
|
| 846 |
+
"×": 384,
|
| 847 |
+
"Ø": 385,
|
| 848 |
+
"Ù": 386,
|
| 849 |
+
"Ú": 387,
|
| 850 |
+
"Û": 388,
|
| 851 |
+
"Ü": 389,
|
| 852 |
+
"Ý": 390,
|
| 853 |
+
"Þ": 391,
|
| 854 |
+
"ß": 392,
|
| 855 |
+
"à": 393,
|
| 856 |
+
"á": 394,
|
| 857 |
+
"â": 395,
|
| 858 |
+
"ã": 396,
|
| 859 |
+
"ä": 397,
|
| 860 |
+
"å": 398,
|
| 861 |
+
"æ": 399,
|
| 862 |
+
"ç": 400,
|
| 863 |
+
"è": 401,
|
| 864 |
+
"é": 402,
|
| 865 |
+
"ê": 403,
|
| 866 |
+
"ë": 404,
|
| 867 |
+
"ì": 405,
|
| 868 |
+
"í": 406,
|
| 869 |
+
"î": 407,
|
| 870 |
+
"ï": 408,
|
| 871 |
+
"ð": 409,
|
| 872 |
+
"ñ": 410,
|
| 873 |
+
"ò": 411,
|
| 874 |
+
"ó": 412,
|
| 875 |
+
"ô": 413,
|
| 876 |
+
"õ": 414,
|
| 877 |
+
"ö": 415,
|
| 878 |
+
"÷": 416,
|
| 879 |
+
"ø": 417,
|
| 880 |
+
"ù": 418,
|
| 881 |
+
"ú": 419,
|
| 882 |
+
"û": 420,
|
| 883 |
+
"ü": 421,
|
| 884 |
+
"ý": 422,
|
| 885 |
+
"þ": 423,
|
| 886 |
+
"ÿ": 424,
|
| 887 |
+
"ɐ": 425,
|
| 888 |
+
"ɑ": 426,
|
| 889 |
+
"ɒ": 427,
|
| 890 |
+
"ɓ": 428,
|
| 891 |
+
"ɔ": 429,
|
| 892 |
+
"ɕ": 430,
|
| 893 |
+
"ɖ": 431,
|
| 894 |
+
"ɗ": 432,
|
| 895 |
+
"ɘ": 433,
|
| 896 |
+
"ə": 434,
|
| 897 |
+
"ɚ": 435,
|
| 898 |
+
"ɛ": 436,
|
| 899 |
+
"ɜ": 437,
|
| 900 |
+
"ɝ": 438,
|
| 901 |
+
"ɞ": 439,
|
| 902 |
+
"ɟ": 440,
|
| 903 |
+
"ɠ": 441,
|
| 904 |
+
"ɡ": 442,
|
| 905 |
+
"ɢ": 443,
|
| 906 |
+
"ɣ": 444,
|
| 907 |
+
"ɤ": 445,
|
| 908 |
+
"ɥ": 446,
|
| 909 |
+
"ɦ": 447,
|
| 910 |
+
"ɧ": 448,
|
| 911 |
+
"ɨ": 449,
|
| 912 |
+
"ɩ": 450,
|
| 913 |
+
"ɪ": 451,
|
| 914 |
+
"ɫ": 452,
|
| 915 |
+
"ɬ": 453,
|
| 916 |
+
"ɭ": 454,
|
| 917 |
+
"ɮ": 455,
|
| 918 |
+
"ɯ": 456,
|
| 919 |
+
"ɰ": 457,
|
| 920 |
+
"ɱ": 458,
|
| 921 |
+
"ɲ": 459,
|
| 922 |
+
"ɳ": 460,
|
| 923 |
+
"ɴ": 461,
|
| 924 |
+
"ɵ": 462,
|
| 925 |
+
"ɶ": 463,
|
| 926 |
+
"ɷ": 464,
|
| 927 |
+
"ɸ": 465,
|
| 928 |
+
"ɹ": 466,
|
| 929 |
+
"ɺ": 467,
|
| 930 |
+
"ɻ": 468,
|
| 931 |
+
"ɼ": 469,
|
| 932 |
+
"ɽ": 470,
|
| 933 |
+
"ɾ": 471,
|
| 934 |
+
"ɿ": 472,
|
| 935 |
+
"ʀ": 473,
|
| 936 |
+
"ʁ": 474,
|
| 937 |
+
"ʂ": 475,
|
| 938 |
+
"ʃ": 476,
|
| 939 |
+
"ʄ": 477,
|
| 940 |
+
"ʅ": 478,
|
| 941 |
+
"ʆ": 479,
|
| 942 |
+
"ʇ": 480,
|
| 943 |
+
"ʈ": 481,
|
| 944 |
+
"ʉ": 482,
|
| 945 |
+
"ʊ": 483,
|
| 946 |
+
"ʋ": 484,
|
| 947 |
+
"ʌ": 485,
|
| 948 |
+
"ʍ": 486,
|
| 949 |
+
"ʎ": 487,
|
| 950 |
+
"ʏ": 488,
|
| 951 |
+
"ʐ": 489,
|
| 952 |
+
"ʑ": 490,
|
| 953 |
+
"ʒ": 491,
|
| 954 |
+
"ʓ": 492,
|
| 955 |
+
"ʔ": 493,
|
| 956 |
+
"ʕ": 494,
|
| 957 |
+
"ʖ": 495,
|
| 958 |
+
"ʗ": 496,
|
| 959 |
+
"ʘ": 497,
|
| 960 |
+
"ʙ": 498,
|
| 961 |
+
"ʚ": 499,
|
| 962 |
+
"ʛ": 500,
|
| 963 |
+
"ʜ": 501,
|
| 964 |
+
"ʝ": 502,
|
| 965 |
+
"ʞ": 503,
|
| 966 |
+
"ʟ": 504,
|
| 967 |
+
"ʠ": 505,
|
| 968 |
+
"ʡ": 506,
|
| 969 |
+
"ʢ": 507,
|
| 970 |
+
"ʣ": 508,
|
| 971 |
+
"ʤ": 509,
|
| 972 |
+
"ʥ": 510,
|
| 973 |
+
"ʦ": 511,
|
| 974 |
+
"ʧ": 512,
|
| 975 |
+
"ʨ": 513,
|
| 976 |
+
"ʩ": 514,
|
| 977 |
+
"ʪ": 515,
|
| 978 |
+
"ʫ": 516,
|
| 979 |
+
"ʬ": 517,
|
| 980 |
+
"ʭ": 518,
|
| 981 |
+
"ʮ": 519,
|
| 982 |
+
"ʯ": 520,
|
| 983 |
+
"ʰ": 521,
|
| 984 |
+
"ʱ": 522,
|
| 985 |
+
"ʲ": 523,
|
| 986 |
+
"ʳ": 524,
|
| 987 |
+
"ʴ": 525,
|
| 988 |
+
"ʵ": 526,
|
| 989 |
+
"ʶ": 527,
|
| 990 |
+
"ʷ": 528,
|
| 991 |
+
"ʸ": 529,
|
| 992 |
+
"ʹ": 530,
|
| 993 |
+
"ʺ": 531,
|
| 994 |
+
"ʻ": 532,
|
| 995 |
+
"ʼ": 533,
|
| 996 |
+
"ʽ": 534,
|
| 997 |
+
"ʾ": 535,
|
| 998 |
+
"ʿ": 536,
|
| 999 |
+
"ˀ": 537,
|
| 1000 |
+
"ˁ": 538,
|
| 1001 |
+
"˂": 539,
|
| 1002 |
+
"˃": 540,
|
| 1003 |
+
"˄": 541,
|
| 1004 |
+
"˅": 542,
|
| 1005 |
+
"ˆ": 543,
|
| 1006 |
+
"ˇ": 544,
|
| 1007 |
+
"ˈ": 545,
|
| 1008 |
+
"ˉ": 546,
|
| 1009 |
+
"ˊ": 547,
|
| 1010 |
+
"ˋ": 548,
|
| 1011 |
+
"ˌ": 549,
|
| 1012 |
+
"ˍ": 550,
|
| 1013 |
+
"ˎ": 551,
|
| 1014 |
+
"ˏ": 552,
|
| 1015 |
+
"ː": 553,
|
| 1016 |
+
"ˑ": 554,
|
| 1017 |
+
"˒": 555,
|
| 1018 |
+
"˓": 556,
|
| 1019 |
+
"˔": 557,
|
| 1020 |
+
"˕": 558,
|
| 1021 |
+
"˖": 559,
|
| 1022 |
+
"˗": 560,
|
| 1023 |
+
"˘": 561,
|
| 1024 |
+
"˙": 562,
|
| 1025 |
+
"˚": 563,
|
| 1026 |
+
"˛": 564,
|
| 1027 |
+
"˜": 565,
|
| 1028 |
+
"˝": 566,
|
| 1029 |
+
"˞": 567,
|
| 1030 |
+
"˟": 568,
|
| 1031 |
+
"ˠ": 569,
|
| 1032 |
+
"ˡ": 570,
|
| 1033 |
+
"ˢ": 571,
|
| 1034 |
+
"ˣ": 572,
|
| 1035 |
+
"ˤ": 573,
|
| 1036 |
+
"˥": 574,
|
| 1037 |
+
"˦": 575,
|
| 1038 |
+
"˧": 576,
|
| 1039 |
+
"˨": 577,
|
| 1040 |
+
"˩": 578,
|
| 1041 |
+
"˪": 579,
|
| 1042 |
+
"˫": 580,
|
| 1043 |
+
"ˬ": 581,
|
| 1044 |
+
"˭": 582,
|
| 1045 |
+
"ˮ": 583,
|
| 1046 |
+
"˯": 584,
|
| 1047 |
+
"˰": 585,
|
| 1048 |
+
"˱": 586,
|
| 1049 |
+
"˲": 587,
|
| 1050 |
+
"˳": 588,
|
| 1051 |
+
"˴": 589,
|
| 1052 |
+
"˵": 590,
|
| 1053 |
+
"˶": 591,
|
| 1054 |
+
"˷": 592,
|
| 1055 |
+
"˸": 593,
|
| 1056 |
+
"˹": 594,
|
| 1057 |
+
"˺": 595,
|
| 1058 |
+
"˻": 596,
|
| 1059 |
+
"˼": 597,
|
| 1060 |
+
"˽": 598,
|
| 1061 |
+
"˾": 599,
|
| 1062 |
+
"˿": 600,
|
| 1063 |
+
"ā": 601,
|
| 1064 |
+
"ō": 602,
|
| 1065 |
+
"…": 603,
|
| 1066 |
+
"[UH]": 604,
|
| 1067 |
+
"[UM]": 605,
|
| 1068 |
+
"[giggle]": 606,
|
| 1069 |
+
"[laughter]": 607,
|
| 1070 |
+
"[guffaw]": 608,
|
| 1071 |
+
"[inhale]": 609,
|
| 1072 |
+
"[exhale]": 610,
|
| 1073 |
+
"[sigh]": 611,
|
| 1074 |
+
"[cry]": 612,
|
| 1075 |
+
"[bark]": 613,
|
| 1076 |
+
"[howl]": 614,
|
| 1077 |
+
"[meow]": 615,
|
| 1078 |
+
"[singing]": 616,
|
| 1079 |
+
"[music]": 617,
|
| 1080 |
+
"[whistle]": 618,
|
| 1081 |
+
"[humming]": 619,
|
| 1082 |
+
"[gasp]": 620,
|
| 1083 |
+
"[groan]": 621,
|
| 1084 |
+
"[whisper]": 622,
|
| 1085 |
+
"[mumble]": 623,
|
| 1086 |
+
"[sniff]": 624,
|
| 1087 |
+
"[sneeze]": 625,
|
| 1088 |
+
"[cough]": 626,
|
| 1089 |
+
"[snore]": 627,
|
| 1090 |
+
"[chew]": 628,
|
| 1091 |
+
"[sip]": 629,
|
| 1092 |
+
"[clear_throat]": 630,
|
| 1093 |
+
"[kiss]": 631,
|
| 1094 |
+
"[shhh]": 632,
|
| 1095 |
+
"[gibberish]": 633,
|
| 1096 |
+
"[fr]": 634,
|
| 1097 |
+
"[es]": 635,
|
| 1098 |
+
"[de]": 636,
|
| 1099 |
+
"[it]": 637,
|
| 1100 |
+
"[ipa]": 638,
|
| 1101 |
+
"[end_of_label]": 639,
|
| 1102 |
+
"ŋ": 640,
|
| 1103 |
+
"ᵻ": 641,
|
| 1104 |
+
"θ": 642,
|
| 1105 |
+
"̩": 643,
|
| 1106 |
+
"\u0303": 644,
|
| 1107 |
+
"ɑː": 645,
|
| 1108 |
+
"iː": 646,
|
| 1109 |
+
"uː": 647,
|
| 1110 |
+
"ɜː": 648,
|
| 1111 |
+
"ɔː": 649,
|
| 1112 |
+
"oː": 650,
|
| 1113 |
+
"eɪ": 651,
|
| 1114 |
+
"oʊ": 652,
|
| 1115 |
+
"aɪ": 653,
|
| 1116 |
+
"aʊ": 654,
|
| 1117 |
+
"ɔɪ": 655,
|
| 1118 |
+
"dʒ": 656,
|
| 1119 |
+
"tʃ": 657,
|
| 1120 |
+
"ɪŋ": 658,
|
| 1121 |
+
"ᵻd": 659,
|
| 1122 |
+
"ˈiː": 660,
|
| 1123 |
+
"ˌiː": 661,
|
| 1124 |
+
"ˈɪ": 662,
|
| 1125 |
+
"ˌɪ": 663,
|
| 1126 |
+
"ˈeɪ": 664,
|
| 1127 |
+
"ˌeɪ": 665,
|
| 1128 |
+
"ˈɛ": 666,
|
| 1129 |
+
"ˌɛ": 667,
|
| 1130 |
+
"ˈæ": 668,
|
| 1131 |
+
"ˌæ": 669,
|
| 1132 |
+
"ˈɑː": 670,
|
| 1133 |
+
"ˌɑː": 671,
|
| 1134 |
+
"ˈɔː": 672,
|
| 1135 |
+
"ˌɔː": 673,
|
| 1136 |
+
"oːɹ": 674,
|
| 1137 |
+
"ˈoːɹ": 675,
|
| 1138 |
+
"ˌoːɹ": 676,
|
| 1139 |
+
"ˈoʊ": 677,
|
| 1140 |
+
"ˌoʊ": 678,
|
| 1141 |
+
"ˈʊ": 679,
|
| 1142 |
+
"ˌʊ": 680,
|
| 1143 |
+
"ˈuː": 681,
|
| 1144 |
+
"ˌuː": 682,
|
| 1145 |
+
"ˈɜː": 683,
|
| 1146 |
+
"ˌɜː": 684,
|
| 1147 |
+
"ˈʌ": 685,
|
| 1148 |
+
"ˌʌ": 686,
|
| 1149 |
+
"ˈaɪ": 687,
|
| 1150 |
+
"ˌaɪ": 688,
|
| 1151 |
+
"ˈaʊ": 689,
|
| 1152 |
+
"ˌaʊ": 690,
|
| 1153 |
+
"ˈɔɪ": 691,
|
| 1154 |
+
"ˌɔɪ": 692,
|
| 1155 |
+
"ˈɚ": 693,
|
| 1156 |
+
"ˌɐ": 694,
|
| 1157 |
+
"[PLACEHOLDER55]": 695,
|
| 1158 |
+
"[PLACEHOLDER56]": 696,
|
| 1159 |
+
"[PLACEHOLDER57]": 697,
|
| 1160 |
+
"[PLACEHOLDER58]": 698,
|
| 1161 |
+
"[PLACEHOLDER59]": 699,
|
| 1162 |
+
"[PLACEHOLDER60]": 700,
|
| 1163 |
+
"[PLACEHOLDER61]": 701,
|
| 1164 |
+
"[PLACEHOLDER62]": 702,
|
| 1165 |
+
"[PLACEHOLDER63]": 703
|
| 1166 |
+
},
|
| 1167 |
+
"merges": [
|
| 1168 |
+
"t h",
|
| 1169 |
+
"i n",
|
| 1170 |
+
"th e",
|
| 1171 |
+
"a n",
|
| 1172 |
+
"e r",
|
| 1173 |
+
"o u",
|
| 1174 |
+
"r e",
|
| 1175 |
+
"o n",
|
| 1176 |
+
"a t",
|
| 1177 |
+
"e d",
|
| 1178 |
+
"e n",
|
| 1179 |
+
"t o",
|
| 1180 |
+
"in g",
|
| 1181 |
+
"an d",
|
| 1182 |
+
"i s",
|
| 1183 |
+
"a s",
|
| 1184 |
+
"a l",
|
| 1185 |
+
"o r",
|
| 1186 |
+
"o f",
|
| 1187 |
+
"a r",
|
| 1188 |
+
"i t",
|
| 1189 |
+
"e s",
|
| 1190 |
+
"h e",
|
| 1191 |
+
"s t",
|
| 1192 |
+
"l e",
|
| 1193 |
+
"o m",
|
| 1194 |
+
"s e",
|
| 1195 |
+
"b e",
|
| 1196 |
+
"a d",
|
| 1197 |
+
"o w",
|
| 1198 |
+
"l y",
|
| 1199 |
+
"c h",
|
| 1200 |
+
"w h",
|
| 1201 |
+
"th at",
|
| 1202 |
+
"y ou",
|
| 1203 |
+
"l i",
|
| 1204 |
+
"v e",
|
| 1205 |
+
"a c",
|
| 1206 |
+
"t i",
|
| 1207 |
+
"l d",
|
| 1208 |
+
"m e",
|
| 1209 |
+
"w as",
|
| 1210 |
+
"g h",
|
| 1211 |
+
"i d",
|
| 1212 |
+
"l l",
|
| 1213 |
+
"w i",
|
| 1214 |
+
"en t",
|
| 1215 |
+
"f or",
|
| 1216 |
+
"a y",
|
| 1217 |
+
"r o",
|
| 1218 |
+
"v er",
|
| 1219 |
+
"i c",
|
| 1220 |
+
"h er",
|
| 1221 |
+
"k e",
|
| 1222 |
+
"h is",
|
| 1223 |
+
"n o",
|
| 1224 |
+
"u t",
|
| 1225 |
+
"u n",
|
| 1226 |
+
"i r",
|
| 1227 |
+
"l o",
|
| 1228 |
+
"w e",
|
| 1229 |
+
"r i",
|
| 1230 |
+
"h a",
|
| 1231 |
+
"wi th",
|
| 1232 |
+
"gh t",
|
| 1233 |
+
"ou t",
|
| 1234 |
+
"i m",
|
| 1235 |
+
"i on",
|
| 1236 |
+
"al l",
|
| 1237 |
+
"a b",
|
| 1238 |
+
"on e",
|
| 1239 |
+
"n e",
|
| 1240 |
+
"g e",
|
| 1241 |
+
"ou ld",
|
| 1242 |
+
"t er",
|
| 1243 |
+
"m o",
|
| 1244 |
+
"h ad",
|
| 1245 |
+
"c e",
|
| 1246 |
+
"s he",
|
| 1247 |
+
"g o",
|
| 1248 |
+
"s h",
|
| 1249 |
+
"u r",
|
| 1250 |
+
"a m",
|
| 1251 |
+
"s o",
|
| 1252 |
+
"p e",
|
| 1253 |
+
"m y",
|
| 1254 |
+
"d e",
|
| 1255 |
+
"a re",
|
| 1256 |
+
"b ut",
|
| 1257 |
+
"om e",
|
| 1258 |
+
"f r",
|
| 1259 |
+
"the r",
|
| 1260 |
+
"f e",
|
| 1261 |
+
"s u",
|
| 1262 |
+
"d o",
|
| 1263 |
+
"c on",
|
| 1264 |
+
"t e",
|
| 1265 |
+
"a in",
|
| 1266 |
+
"er e",
|
| 1267 |
+
"p o",
|
| 1268 |
+
"i f",
|
| 1269 |
+
"the y",
|
| 1270 |
+
"u s",
|
| 1271 |
+
"a g",
|
| 1272 |
+
"t r",
|
| 1273 |
+
"n ow",
|
| 1274 |
+
"ou n",
|
| 1275 |
+
"th is",
|
| 1276 |
+
"ha ve",
|
| 1277 |
+
"no t",
|
| 1278 |
+
"s a",
|
| 1279 |
+
"i l",
|
| 1280 |
+
"u p",
|
| 1281 |
+
"th ing",
|
| 1282 |
+
"fr om",
|
| 1283 |
+
"a p",
|
| 1284 |
+
"h im",
|
| 1285 |
+
"ac k",
|
| 1286 |
+
"at ion",
|
| 1287 |
+
"an t",
|
| 1288 |
+
"ou r",
|
| 1289 |
+
"o p",
|
| 1290 |
+
"li ke",
|
| 1291 |
+
"u st",
|
| 1292 |
+
"es s",
|
| 1293 |
+
"b o",
|
| 1294 |
+
"o k",
|
| 1295 |
+
"u l",
|
| 1296 |
+
"in d",
|
| 1297 |
+
"e x",
|
| 1298 |
+
"c om",
|
| 1299 |
+
"s ome",
|
| 1300 |
+
"the re",
|
| 1301 |
+
"er s",
|
| 1302 |
+
"c o",
|
| 1303 |
+
"re s",
|
| 1304 |
+
"m an",
|
| 1305 |
+
"ar d",
|
| 1306 |
+
"p l",
|
| 1307 |
+
"w or",
|
| 1308 |
+
"w ay",
|
| 1309 |
+
"ti on",
|
| 1310 |
+
"f o",
|
| 1311 |
+
"c a",
|
| 1312 |
+
"w ere",
|
| 1313 |
+
"b y",
|
| 1314 |
+
"at e",
|
| 1315 |
+
"p ro",
|
| 1316 |
+
"t ed",
|
| 1317 |
+
"oun d",
|
| 1318 |
+
"ow n",
|
| 1319 |
+
"w ould",
|
| 1320 |
+
"t s",
|
| 1321 |
+
"wh at",
|
| 1322 |
+
"q u",
|
| 1323 |
+
"al ly",
|
| 1324 |
+
"i ght",
|
| 1325 |
+
"c k",
|
| 1326 |
+
"g r",
|
| 1327 |
+
"wh en",
|
| 1328 |
+
"v en",
|
| 1329 |
+
"c an",
|
| 1330 |
+
"ou gh",
|
| 1331 |
+
"in e",
|
| 1332 |
+
"en d",
|
| 1333 |
+
"p er",
|
| 1334 |
+
"ou s",
|
| 1335 |
+
"o d",
|
| 1336 |
+
"id e",
|
| 1337 |
+
"k now",
|
| 1338 |
+
"t y",
|
| 1339 |
+
"ver y",
|
| 1340 |
+
"s i",
|
| 1341 |
+
"a k",
|
| 1342 |
+
"wh o",
|
| 1343 |
+
"ab out",
|
| 1344 |
+
"i ll",
|
| 1345 |
+
"the m",
|
| 1346 |
+
"es t",
|
| 1347 |
+
"re d",
|
| 1348 |
+
"y e",
|
| 1349 |
+
"c ould",
|
| 1350 |
+
"on g",
|
| 1351 |
+
"you r",
|
| 1352 |
+
"the ir",
|
| 1353 |
+
"e m",
|
| 1354 |
+
"j ust",
|
| 1355 |
+
"o ther",
|
| 1356 |
+
"in to",
|
| 1357 |
+
"an y",
|
| 1358 |
+
"wh i",
|
| 1359 |
+
"u m",
|
| 1360 |
+
"t w",
|
| 1361 |
+
"as t",
|
| 1362 |
+
"d er",
|
| 1363 |
+
"d id",
|
| 1364 |
+
"i e",
|
| 1365 |
+
"be en",
|
| 1366 |
+
"ac e",
|
| 1367 |
+
"in k",
|
| 1368 |
+
"it y",
|
| 1369 |
+
"b ack",
|
| 1370 |
+
"t ing",
|
| 1371 |
+
"b r",
|
| 1372 |
+
"mo re",
|
| 1373 |
+
"a ke",
|
| 1374 |
+
"p p",
|
| 1375 |
+
"the n",
|
| 1376 |
+
"s p",
|
| 1377 |
+
"e l",
|
| 1378 |
+
"u se",
|
| 1379 |
+
"b l",
|
| 1380 |
+
"sa id",
|
| 1381 |
+
"o ver",
|
| 1382 |
+
"ge t",
|
| 1383 |
+
"ɑ ː",
|
| 1384 |
+
"i ː",
|
| 1385 |
+
"u ː",
|
| 1386 |
+
"ɜ ː",
|
| 1387 |
+
"ɔ ː",
|
| 1388 |
+
"o ː",
|
| 1389 |
+
"e ɪ",
|
| 1390 |
+
"o ʊ",
|
| 1391 |
+
"a ɪ",
|
| 1392 |
+
"a ʊ",
|
| 1393 |
+
"ɔ ɪ",
|
| 1394 |
+
"d ʒ",
|
| 1395 |
+
"t ʃ",
|
| 1396 |
+
"ɪ ŋ",
|
| 1397 |
+
"ᵻ d",
|
| 1398 |
+
"ˈ iː",
|
| 1399 |
+
"ˌ iː",
|
| 1400 |
+
"ˈ ɪ",
|
| 1401 |
+
"ˌ ɪ",
|
| 1402 |
+
"ˈ eɪ",
|
| 1403 |
+
"ˌ eɪ",
|
| 1404 |
+
"ˈ ɛ",
|
| 1405 |
+
"ˌ ɛ",
|
| 1406 |
+
"ˈ æ",
|
| 1407 |
+
"ˌ æ",
|
| 1408 |
+
"ˈ ɑː",
|
| 1409 |
+
"ˌ ɑː",
|
| 1410 |
+
"ˈ ɔː",
|
| 1411 |
+
"ˌ ɔː",
|
| 1412 |
+
"oː ɹ",
|
| 1413 |
+
"ˈ oːɹ",
|
| 1414 |
+
"ˌ oːɹ",
|
| 1415 |
+
"ˈ oʊ",
|
| 1416 |
+
"ˌ oʊ",
|
| 1417 |
+
"ˈ ʊ",
|
| 1418 |
+
"ˌ ʊ",
|
| 1419 |
+
"ˈ uː",
|
| 1420 |
+
"ˌ uː",
|
| 1421 |
+
"ˈ ɜː",
|
| 1422 |
+
"ˌ ɜː",
|
| 1423 |
+
"ˈ ʌ",
|
| 1424 |
+
"ˌ ʌ",
|
| 1425 |
+
"ˈ aɪ",
|
| 1426 |
+
"ˌ aɪ",
|
| 1427 |
+
"ˈ aʊ",
|
| 1428 |
+
"ˌ aʊ",
|
| 1429 |
+
"ˈ ɔɪ",
|
| 1430 |
+
"ˌ ɔɪ",
|
| 1431 |
+
"ˈ ɚ",
|
| 1432 |
+
"ˌ ɐ"
|
| 1433 |
+
]
|
| 1434 |
+
}
|
| 1435 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1923 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 41.328125,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2645,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0,
|
| 13 |
+
"eval_runtime": 2.9591,
|
| 14 |
+
"eval_samples_per_second": 0.338,
|
| 15 |
+
"eval_steps_per_second": 0.338,
|
| 16 |
+
"step": 0
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.15625,
|
| 20 |
+
"grad_norm": 8.098007202148438,
|
| 21 |
+
"learning_rate": 4.000000000000001e-06,
|
| 22 |
+
"loss": 8.5142,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.3125,
|
| 27 |
+
"grad_norm": 6.856651306152344,
|
| 28 |
+
"learning_rate": 9e-06,
|
| 29 |
+
"loss": 7.9708,
|
| 30 |
+
"step": 20
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.46875,
|
| 34 |
+
"grad_norm": 5.80125093460083,
|
| 35 |
+
"learning_rate": 1.4000000000000001e-05,
|
| 36 |
+
"loss": 8.01,
|
| 37 |
+
"step": 30
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.625,
|
| 41 |
+
"grad_norm": 5.687861442565918,
|
| 42 |
+
"learning_rate": 1.9e-05,
|
| 43 |
+
"loss": 7.6212,
|
| 44 |
+
"step": 40
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.78125,
|
| 48 |
+
"grad_norm": 6.117136478424072,
|
| 49 |
+
"learning_rate": 2.4e-05,
|
| 50 |
+
"loss": 7.3311,
|
| 51 |
+
"step": 50
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.9375,
|
| 55 |
+
"grad_norm": 5.861077785491943,
|
| 56 |
+
"learning_rate": 2.9e-05,
|
| 57 |
+
"loss": 7.5553,
|
| 58 |
+
"step": 60
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.09375,
|
| 62 |
+
"grad_norm": 6.021880149841309,
|
| 63 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 64 |
+
"loss": 7.05,
|
| 65 |
+
"step": 70
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.25,
|
| 69 |
+
"grad_norm": 7.620683670043945,
|
| 70 |
+
"learning_rate": 3.9000000000000006e-05,
|
| 71 |
+
"loss": 6.7186,
|
| 72 |
+
"step": 80
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.40625,
|
| 76 |
+
"grad_norm": 7.098018169403076,
|
| 77 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 78 |
+
"loss": 6.5668,
|
| 79 |
+
"step": 90
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.5625,
|
| 83 |
+
"grad_norm": 7.157684326171875,
|
| 84 |
+
"learning_rate": 4.9e-05,
|
| 85 |
+
"loss": 6.6148,
|
| 86 |
+
"step": 100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.71875,
|
| 90 |
+
"grad_norm": 7.009696006774902,
|
| 91 |
+
"learning_rate": 4.9936507936507936e-05,
|
| 92 |
+
"loss": 6.5017,
|
| 93 |
+
"step": 110
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.875,
|
| 97 |
+
"grad_norm": 7.6622467041015625,
|
| 98 |
+
"learning_rate": 4.985714285714286e-05,
|
| 99 |
+
"loss": 6.53,
|
| 100 |
+
"step": 120
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 2.03125,
|
| 104 |
+
"grad_norm": 8.221333503723145,
|
| 105 |
+
"learning_rate": 4.977777777777778e-05,
|
| 106 |
+
"loss": 6.306,
|
| 107 |
+
"step": 130
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 2.1875,
|
| 111 |
+
"grad_norm": 8.832132339477539,
|
| 112 |
+
"learning_rate": 4.96984126984127e-05,
|
| 113 |
+
"loss": 4.8787,
|
| 114 |
+
"step": 140
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.34375,
|
| 118 |
+
"grad_norm": 9.245682716369629,
|
| 119 |
+
"learning_rate": 4.961904761904762e-05,
|
| 120 |
+
"loss": 4.7796,
|
| 121 |
+
"step": 150
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 2.5,
|
| 125 |
+
"grad_norm": 9.249746322631836,
|
| 126 |
+
"learning_rate": 4.953968253968254e-05,
|
| 127 |
+
"loss": 4.79,
|
| 128 |
+
"step": 160
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.65625,
|
| 132 |
+
"grad_norm": 8.098647117614746,
|
| 133 |
+
"learning_rate": 4.9460317460317465e-05,
|
| 134 |
+
"loss": 4.8157,
|
| 135 |
+
"step": 170
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 2.8125,
|
| 139 |
+
"grad_norm": 9.594801902770996,
|
| 140 |
+
"learning_rate": 4.9380952380952386e-05,
|
| 141 |
+
"loss": 4.5135,
|
| 142 |
+
"step": 180
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 2.96875,
|
| 146 |
+
"grad_norm": 9.500739097595215,
|
| 147 |
+
"learning_rate": 4.930158730158731e-05,
|
| 148 |
+
"loss": 4.9346,
|
| 149 |
+
"step": 190
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 3.125,
|
| 153 |
+
"grad_norm": 10.759628295898438,
|
| 154 |
+
"learning_rate": 4.922222222222222e-05,
|
| 155 |
+
"loss": 3.4195,
|
| 156 |
+
"step": 200
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 3.28125,
|
| 160 |
+
"grad_norm": 12.300085067749023,
|
| 161 |
+
"learning_rate": 4.9142857142857144e-05,
|
| 162 |
+
"loss": 3.136,
|
| 163 |
+
"step": 210
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 3.4375,
|
| 167 |
+
"grad_norm": 9.825932502746582,
|
| 168 |
+
"learning_rate": 4.9063492063492065e-05,
|
| 169 |
+
"loss": 3.0981,
|
| 170 |
+
"step": 220
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 3.59375,
|
| 174 |
+
"grad_norm": 10.764175415039062,
|
| 175 |
+
"learning_rate": 4.898412698412699e-05,
|
| 176 |
+
"loss": 3.0372,
|
| 177 |
+
"step": 230
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 3.75,
|
| 181 |
+
"grad_norm": 10.330010414123535,
|
| 182 |
+
"learning_rate": 4.890476190476191e-05,
|
| 183 |
+
"loss": 3.0934,
|
| 184 |
+
"step": 240
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 3.90625,
|
| 188 |
+
"grad_norm": 10.405282020568848,
|
| 189 |
+
"learning_rate": 4.882539682539683e-05,
|
| 190 |
+
"loss": 3.135,
|
| 191 |
+
"step": 250
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 4.0625,
|
| 195 |
+
"grad_norm": 9.842012405395508,
|
| 196 |
+
"learning_rate": 4.874603174603175e-05,
|
| 197 |
+
"loss": 2.7457,
|
| 198 |
+
"step": 260
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 4.21875,
|
| 202 |
+
"grad_norm": 10.659170150756836,
|
| 203 |
+
"learning_rate": 4.866666666666667e-05,
|
| 204 |
+
"loss": 1.981,
|
| 205 |
+
"step": 270
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 4.375,
|
| 209 |
+
"grad_norm": 9.820462226867676,
|
| 210 |
+
"learning_rate": 4.858730158730159e-05,
|
| 211 |
+
"loss": 2.0881,
|
| 212 |
+
"step": 280
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 4.53125,
|
| 216 |
+
"grad_norm": 9.645284652709961,
|
| 217 |
+
"learning_rate": 4.850793650793651e-05,
|
| 218 |
+
"loss": 1.9438,
|
| 219 |
+
"step": 290
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 4.6875,
|
| 223 |
+
"grad_norm": 9.881282806396484,
|
| 224 |
+
"learning_rate": 4.842857142857143e-05,
|
| 225 |
+
"loss": 1.8556,
|
| 226 |
+
"step": 300
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 4.84375,
|
| 230 |
+
"grad_norm": 10.5478515625,
|
| 231 |
+
"learning_rate": 4.834920634920635e-05,
|
| 232 |
+
"loss": 2.0494,
|
| 233 |
+
"step": 310
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 5.0,
|
| 237 |
+
"grad_norm": 19.77553939819336,
|
| 238 |
+
"learning_rate": 4.8269841269841274e-05,
|
| 239 |
+
"loss": 2.0695,
|
| 240 |
+
"step": 320
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 5.15625,
|
| 244 |
+
"grad_norm": 8.124504089355469,
|
| 245 |
+
"learning_rate": 4.819047619047619e-05,
|
| 246 |
+
"loss": 1.1424,
|
| 247 |
+
"step": 330
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 5.3125,
|
| 251 |
+
"grad_norm": 9.63291072845459,
|
| 252 |
+
"learning_rate": 4.811111111111111e-05,
|
| 253 |
+
"loss": 1.1688,
|
| 254 |
+
"step": 340
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 5.46875,
|
| 258 |
+
"grad_norm": 8.620952606201172,
|
| 259 |
+
"learning_rate": 4.803174603174603e-05,
|
| 260 |
+
"loss": 1.2346,
|
| 261 |
+
"step": 350
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 5.625,
|
| 265 |
+
"grad_norm": 8.060315132141113,
|
| 266 |
+
"learning_rate": 4.795238095238095e-05,
|
| 267 |
+
"loss": 1.176,
|
| 268 |
+
"step": 360
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 5.78125,
|
| 272 |
+
"grad_norm": 7.583358287811279,
|
| 273 |
+
"learning_rate": 4.7873015873015874e-05,
|
| 274 |
+
"loss": 1.2118,
|
| 275 |
+
"step": 370
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 5.9375,
|
| 279 |
+
"grad_norm": 10.535112380981445,
|
| 280 |
+
"learning_rate": 4.7793650793650796e-05,
|
| 281 |
+
"loss": 1.2446,
|
| 282 |
+
"step": 380
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 6.09375,
|
| 286 |
+
"grad_norm": 7.170854568481445,
|
| 287 |
+
"learning_rate": 4.771428571428572e-05,
|
| 288 |
+
"loss": 1.0445,
|
| 289 |
+
"step": 390
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 6.25,
|
| 293 |
+
"grad_norm": 6.0907392501831055,
|
| 294 |
+
"learning_rate": 4.763492063492064e-05,
|
| 295 |
+
"loss": 0.7688,
|
| 296 |
+
"step": 400
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 6.40625,
|
| 300 |
+
"grad_norm": 7.953549385070801,
|
| 301 |
+
"learning_rate": 4.755555555555556e-05,
|
| 302 |
+
"loss": 0.7333,
|
| 303 |
+
"step": 410
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 6.5625,
|
| 307 |
+
"grad_norm": 10.276406288146973,
|
| 308 |
+
"learning_rate": 4.747619047619048e-05,
|
| 309 |
+
"loss": 0.8645,
|
| 310 |
+
"step": 420
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 6.71875,
|
| 314 |
+
"grad_norm": 7.596552848815918,
|
| 315 |
+
"learning_rate": 4.73968253968254e-05,
|
| 316 |
+
"loss": 0.7799,
|
| 317 |
+
"step": 430
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 6.875,
|
| 321 |
+
"grad_norm": 6.478920936584473,
|
| 322 |
+
"learning_rate": 4.7317460317460325e-05,
|
| 323 |
+
"loss": 0.8262,
|
| 324 |
+
"step": 440
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.03125,
|
| 328 |
+
"grad_norm": 4.837390422821045,
|
| 329 |
+
"learning_rate": 4.723809523809524e-05,
|
| 330 |
+
"loss": 0.7218,
|
| 331 |
+
"step": 450
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 7.1875,
|
| 335 |
+
"grad_norm": 5.8777289390563965,
|
| 336 |
+
"learning_rate": 4.715873015873016e-05,
|
| 337 |
+
"loss": 0.5238,
|
| 338 |
+
"step": 460
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 7.34375,
|
| 342 |
+
"grad_norm": 4.988452434539795,
|
| 343 |
+
"learning_rate": 4.707936507936508e-05,
|
| 344 |
+
"loss": 0.5285,
|
| 345 |
+
"step": 470
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 7.5,
|
| 349 |
+
"grad_norm": 5.605051517486572,
|
| 350 |
+
"learning_rate": 4.7e-05,
|
| 351 |
+
"loss": 0.5368,
|
| 352 |
+
"step": 480
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 7.65625,
|
| 356 |
+
"grad_norm": 7.234042644500732,
|
| 357 |
+
"learning_rate": 4.692063492063492e-05,
|
| 358 |
+
"loss": 0.5803,
|
| 359 |
+
"step": 490
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 7.8125,
|
| 363 |
+
"grad_norm": 6.273004055023193,
|
| 364 |
+
"learning_rate": 4.684126984126984e-05,
|
| 365 |
+
"loss": 0.519,
|
| 366 |
+
"step": 500
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 7.8125,
|
| 370 |
+
"eval_runtime": 2.3062,
|
| 371 |
+
"eval_samples_per_second": 0.434,
|
| 372 |
+
"eval_steps_per_second": 0.434,
|
| 373 |
+
"step": 500
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 7.96875,
|
| 377 |
+
"grad_norm": 4.803182125091553,
|
| 378 |
+
"learning_rate": 4.676190476190476e-05,
|
| 379 |
+
"loss": 0.5611,
|
| 380 |
+
"step": 510
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 8.125,
|
| 384 |
+
"grad_norm": 4.977607727050781,
|
| 385 |
+
"learning_rate": 4.668253968253968e-05,
|
| 386 |
+
"loss": 0.3616,
|
| 387 |
+
"step": 520
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 8.28125,
|
| 391 |
+
"grad_norm": 4.4240336418151855,
|
| 392 |
+
"learning_rate": 4.6603174603174605e-05,
|
| 393 |
+
"loss": 0.4303,
|
| 394 |
+
"step": 530
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 8.4375,
|
| 398 |
+
"grad_norm": 5.406126022338867,
|
| 399 |
+
"learning_rate": 4.6523809523809526e-05,
|
| 400 |
+
"loss": 0.384,
|
| 401 |
+
"step": 540
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 8.59375,
|
| 405 |
+
"grad_norm": 4.34033203125,
|
| 406 |
+
"learning_rate": 4.644444444444445e-05,
|
| 407 |
+
"loss": 0.3784,
|
| 408 |
+
"step": 550
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 8.75,
|
| 412 |
+
"grad_norm": 5.256556034088135,
|
| 413 |
+
"learning_rate": 4.636507936507937e-05,
|
| 414 |
+
"loss": 0.4345,
|
| 415 |
+
"step": 560
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 8.90625,
|
| 419 |
+
"grad_norm": 5.054710388183594,
|
| 420 |
+
"learning_rate": 4.628571428571429e-05,
|
| 421 |
+
"loss": 0.4257,
|
| 422 |
+
"step": 570
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 9.0625,
|
| 426 |
+
"grad_norm": 5.220774173736572,
|
| 427 |
+
"learning_rate": 4.6206349206349205e-05,
|
| 428 |
+
"loss": 0.3146,
|
| 429 |
+
"step": 580
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 9.21875,
|
| 433 |
+
"grad_norm": 4.420045375823975,
|
| 434 |
+
"learning_rate": 4.612698412698413e-05,
|
| 435 |
+
"loss": 0.298,
|
| 436 |
+
"step": 590
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 9.375,
|
| 440 |
+
"grad_norm": 4.474491596221924,
|
| 441 |
+
"learning_rate": 4.604761904761905e-05,
|
| 442 |
+
"loss": 0.3023,
|
| 443 |
+
"step": 600
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 9.53125,
|
| 447 |
+
"grad_norm": 4.131107807159424,
|
| 448 |
+
"learning_rate": 4.596825396825397e-05,
|
| 449 |
+
"loss": 0.2846,
|
| 450 |
+
"step": 610
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 9.6875,
|
| 454 |
+
"grad_norm": 4.535623550415039,
|
| 455 |
+
"learning_rate": 4.588888888888889e-05,
|
| 456 |
+
"loss": 0.3244,
|
| 457 |
+
"step": 620
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 9.84375,
|
| 461 |
+
"grad_norm": 4.365594387054443,
|
| 462 |
+
"learning_rate": 4.580952380952381e-05,
|
| 463 |
+
"loss": 0.2925,
|
| 464 |
+
"step": 630
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 10.0,
|
| 468 |
+
"grad_norm": 7.354922294616699,
|
| 469 |
+
"learning_rate": 4.5730158730158734e-05,
|
| 470 |
+
"loss": 0.3234,
|
| 471 |
+
"step": 640
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 10.15625,
|
| 475 |
+
"grad_norm": 3.916835308074951,
|
| 476 |
+
"learning_rate": 4.5650793650793656e-05,
|
| 477 |
+
"loss": 0.236,
|
| 478 |
+
"step": 650
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 10.3125,
|
| 482 |
+
"grad_norm": 4.322419166564941,
|
| 483 |
+
"learning_rate": 4.557142857142858e-05,
|
| 484 |
+
"loss": 0.2353,
|
| 485 |
+
"step": 660
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 10.46875,
|
| 489 |
+
"grad_norm": 5.4846038818359375,
|
| 490 |
+
"learning_rate": 4.54920634920635e-05,
|
| 491 |
+
"loss": 0.2422,
|
| 492 |
+
"step": 670
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 10.625,
|
| 496 |
+
"grad_norm": 4.341657638549805,
|
| 497 |
+
"learning_rate": 4.5412698412698414e-05,
|
| 498 |
+
"loss": 0.2592,
|
| 499 |
+
"step": 680
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 10.78125,
|
| 503 |
+
"grad_norm": 4.786070346832275,
|
| 504 |
+
"learning_rate": 4.5333333333333335e-05,
|
| 505 |
+
"loss": 0.2501,
|
| 506 |
+
"step": 690
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 10.9375,
|
| 510 |
+
"grad_norm": 3.9264745712280273,
|
| 511 |
+
"learning_rate": 4.525396825396826e-05,
|
| 512 |
+
"loss": 0.2683,
|
| 513 |
+
"step": 700
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 11.09375,
|
| 517 |
+
"grad_norm": 3.851856231689453,
|
| 518 |
+
"learning_rate": 4.517460317460318e-05,
|
| 519 |
+
"loss": 0.1978,
|
| 520 |
+
"step": 710
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 11.25,
|
| 524 |
+
"grad_norm": 4.643581390380859,
|
| 525 |
+
"learning_rate": 4.509523809523809e-05,
|
| 526 |
+
"loss": 0.1841,
|
| 527 |
+
"step": 720
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 11.40625,
|
| 531 |
+
"grad_norm": 4.105888843536377,
|
| 532 |
+
"learning_rate": 4.5015873015873014e-05,
|
| 533 |
+
"loss": 0.1976,
|
| 534 |
+
"step": 730
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 11.5625,
|
| 538 |
+
"grad_norm": 3.809528350830078,
|
| 539 |
+
"learning_rate": 4.4936507936507936e-05,
|
| 540 |
+
"loss": 0.1896,
|
| 541 |
+
"step": 740
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 11.71875,
|
| 545 |
+
"grad_norm": 4.457248687744141,
|
| 546 |
+
"learning_rate": 4.485714285714286e-05,
|
| 547 |
+
"loss": 0.2125,
|
| 548 |
+
"step": 750
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 11.875,
|
| 552 |
+
"grad_norm": 3.7699806690216064,
|
| 553 |
+
"learning_rate": 4.477777777777778e-05,
|
| 554 |
+
"loss": 0.2212,
|
| 555 |
+
"step": 760
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 12.03125,
|
| 559 |
+
"grad_norm": 4.643237590789795,
|
| 560 |
+
"learning_rate": 4.46984126984127e-05,
|
| 561 |
+
"loss": 0.2235,
|
| 562 |
+
"step": 770
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 12.1875,
|
| 566 |
+
"grad_norm": 4.064443588256836,
|
| 567 |
+
"learning_rate": 4.461904761904762e-05,
|
| 568 |
+
"loss": 0.1503,
|
| 569 |
+
"step": 780
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 12.34375,
|
| 573 |
+
"grad_norm": 4.605109691619873,
|
| 574 |
+
"learning_rate": 4.4539682539682543e-05,
|
| 575 |
+
"loss": 0.172,
|
| 576 |
+
"step": 790
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 12.5,
|
| 580 |
+
"grad_norm": 3.8005576133728027,
|
| 581 |
+
"learning_rate": 4.4460317460317465e-05,
|
| 582 |
+
"loss": 0.1713,
|
| 583 |
+
"step": 800
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 12.65625,
|
| 587 |
+
"grad_norm": 4.829875469207764,
|
| 588 |
+
"learning_rate": 4.4380952380952386e-05,
|
| 589 |
+
"loss": 0.1783,
|
| 590 |
+
"step": 810
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 12.8125,
|
| 594 |
+
"grad_norm": 4.428802490234375,
|
| 595 |
+
"learning_rate": 4.430158730158731e-05,
|
| 596 |
+
"loss": 0.1742,
|
| 597 |
+
"step": 820
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 12.96875,
|
| 601 |
+
"grad_norm": 5.068906307220459,
|
| 602 |
+
"learning_rate": 4.422222222222222e-05,
|
| 603 |
+
"loss": 0.1797,
|
| 604 |
+
"step": 830
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 13.125,
|
| 608 |
+
"grad_norm": 3.3268795013427734,
|
| 609 |
+
"learning_rate": 4.4142857142857144e-05,
|
| 610 |
+
"loss": 0.1389,
|
| 611 |
+
"step": 840
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 13.28125,
|
| 615 |
+
"grad_norm": 3.312582015991211,
|
| 616 |
+
"learning_rate": 4.4063492063492066e-05,
|
| 617 |
+
"loss": 0.1191,
|
| 618 |
+
"step": 850
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 13.4375,
|
| 622 |
+
"grad_norm": 3.7299697399139404,
|
| 623 |
+
"learning_rate": 4.398412698412699e-05,
|
| 624 |
+
"loss": 0.1432,
|
| 625 |
+
"step": 860
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 13.59375,
|
| 629 |
+
"grad_norm": 4.627827167510986,
|
| 630 |
+
"learning_rate": 4.39047619047619e-05,
|
| 631 |
+
"loss": 0.1672,
|
| 632 |
+
"step": 870
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 13.75,
|
| 636 |
+
"grad_norm": 4.645421981811523,
|
| 637 |
+
"learning_rate": 4.3825396825396823e-05,
|
| 638 |
+
"loss": 0.1503,
|
| 639 |
+
"step": 880
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 13.90625,
|
| 643 |
+
"grad_norm": 5.321810245513916,
|
| 644 |
+
"learning_rate": 4.3746031746031745e-05,
|
| 645 |
+
"loss": 0.1486,
|
| 646 |
+
"step": 890
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 14.0625,
|
| 650 |
+
"grad_norm": 2.487105369567871,
|
| 651 |
+
"learning_rate": 4.3666666666666666e-05,
|
| 652 |
+
"loss": 0.1193,
|
| 653 |
+
"step": 900
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 14.21875,
|
| 657 |
+
"grad_norm": 4.098151683807373,
|
| 658 |
+
"learning_rate": 4.358730158730159e-05,
|
| 659 |
+
"loss": 0.1182,
|
| 660 |
+
"step": 910
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 14.375,
|
| 664 |
+
"grad_norm": 3.2538163661956787,
|
| 665 |
+
"learning_rate": 4.350793650793651e-05,
|
| 666 |
+
"loss": 0.1145,
|
| 667 |
+
"step": 920
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 14.53125,
|
| 671 |
+
"grad_norm": 3.7881181240081787,
|
| 672 |
+
"learning_rate": 4.342857142857143e-05,
|
| 673 |
+
"loss": 0.1255,
|
| 674 |
+
"step": 930
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 14.6875,
|
| 678 |
+
"grad_norm": 2.861689567565918,
|
| 679 |
+
"learning_rate": 4.334920634920635e-05,
|
| 680 |
+
"loss": 0.144,
|
| 681 |
+
"step": 940
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 14.84375,
|
| 685 |
+
"grad_norm": 3.1621310710906982,
|
| 686 |
+
"learning_rate": 4.3269841269841274e-05,
|
| 687 |
+
"loss": 0.1293,
|
| 688 |
+
"step": 950
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 15.0,
|
| 692 |
+
"grad_norm": 11.439355850219727,
|
| 693 |
+
"learning_rate": 4.3190476190476195e-05,
|
| 694 |
+
"loss": 0.1553,
|
| 695 |
+
"step": 960
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 15.15625,
|
| 699 |
+
"grad_norm": 3.6791841983795166,
|
| 700 |
+
"learning_rate": 4.311111111111111e-05,
|
| 701 |
+
"loss": 0.0949,
|
| 702 |
+
"step": 970
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 15.3125,
|
| 706 |
+
"grad_norm": 2.71702241897583,
|
| 707 |
+
"learning_rate": 4.303174603174603e-05,
|
| 708 |
+
"loss": 0.1125,
|
| 709 |
+
"step": 980
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 15.46875,
|
| 713 |
+
"grad_norm": 2.713571786880493,
|
| 714 |
+
"learning_rate": 4.295238095238095e-05,
|
| 715 |
+
"loss": 0.137,
|
| 716 |
+
"step": 990
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 15.625,
|
| 720 |
+
"grad_norm": 2.975768804550171,
|
| 721 |
+
"learning_rate": 4.2873015873015875e-05,
|
| 722 |
+
"loss": 0.108,
|
| 723 |
+
"step": 1000
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 15.625,
|
| 727 |
+
"eval_runtime": 2.2622,
|
| 728 |
+
"eval_samples_per_second": 0.442,
|
| 729 |
+
"eval_steps_per_second": 0.442,
|
| 730 |
+
"step": 1000
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 15.78125,
|
| 734 |
+
"grad_norm": 3.5744853019714355,
|
| 735 |
+
"learning_rate": 4.2793650793650796e-05,
|
| 736 |
+
"loss": 0.1207,
|
| 737 |
+
"step": 1010
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 15.9375,
|
| 741 |
+
"grad_norm": 1.8845595121383667,
|
| 742 |
+
"learning_rate": 4.271428571428572e-05,
|
| 743 |
+
"loss": 0.1013,
|
| 744 |
+
"step": 1020
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 16.09375,
|
| 748 |
+
"grad_norm": 4.227961540222168,
|
| 749 |
+
"learning_rate": 4.263492063492064e-05,
|
| 750 |
+
"loss": 0.112,
|
| 751 |
+
"step": 1030
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 16.25,
|
| 755 |
+
"grad_norm": 3.289071798324585,
|
| 756 |
+
"learning_rate": 4.255555555555556e-05,
|
| 757 |
+
"loss": 0.1054,
|
| 758 |
+
"step": 1040
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 16.40625,
|
| 762 |
+
"grad_norm": 1.9135278463363647,
|
| 763 |
+
"learning_rate": 4.247619047619048e-05,
|
| 764 |
+
"loss": 0.0933,
|
| 765 |
+
"step": 1050
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 16.5625,
|
| 769 |
+
"grad_norm": 2.586151599884033,
|
| 770 |
+
"learning_rate": 4.2396825396825404e-05,
|
| 771 |
+
"loss": 0.1205,
|
| 772 |
+
"step": 1060
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 16.71875,
|
| 776 |
+
"grad_norm": 3.5681819915771484,
|
| 777 |
+
"learning_rate": 4.231746031746032e-05,
|
| 778 |
+
"loss": 0.1015,
|
| 779 |
+
"step": 1070
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 16.875,
|
| 783 |
+
"grad_norm": 3.7675039768218994,
|
| 784 |
+
"learning_rate": 4.223809523809524e-05,
|
| 785 |
+
"loss": 0.128,
|
| 786 |
+
"step": 1080
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 17.03125,
|
| 790 |
+
"grad_norm": 2.631277322769165,
|
| 791 |
+
"learning_rate": 4.215873015873016e-05,
|
| 792 |
+
"loss": 0.107,
|
| 793 |
+
"step": 1090
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 17.1875,
|
| 797 |
+
"grad_norm": 3.59251070022583,
|
| 798 |
+
"learning_rate": 4.2079365079365076e-05,
|
| 799 |
+
"loss": 0.0918,
|
| 800 |
+
"step": 1100
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 17.34375,
|
| 804 |
+
"grad_norm": 3.785374641418457,
|
| 805 |
+
"learning_rate": 4.2e-05,
|
| 806 |
+
"loss": 0.1031,
|
| 807 |
+
"step": 1110
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 17.5,
|
| 811 |
+
"grad_norm": 3.6201488971710205,
|
| 812 |
+
"learning_rate": 4.192063492063492e-05,
|
| 813 |
+
"loss": 0.0965,
|
| 814 |
+
"step": 1120
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 17.65625,
|
| 818 |
+
"grad_norm": 3.608516216278076,
|
| 819 |
+
"learning_rate": 4.184126984126984e-05,
|
| 820 |
+
"loss": 0.1046,
|
| 821 |
+
"step": 1130
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 17.8125,
|
| 825 |
+
"grad_norm": 3.3631608486175537,
|
| 826 |
+
"learning_rate": 4.176190476190476e-05,
|
| 827 |
+
"loss": 0.1047,
|
| 828 |
+
"step": 1140
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 17.96875,
|
| 832 |
+
"grad_norm": 2.2599599361419678,
|
| 833 |
+
"learning_rate": 4.1682539682539684e-05,
|
| 834 |
+
"loss": 0.0976,
|
| 835 |
+
"step": 1150
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 18.125,
|
| 839 |
+
"grad_norm": 3.3925111293792725,
|
| 840 |
+
"learning_rate": 4.1603174603174605e-05,
|
| 841 |
+
"loss": 0.081,
|
| 842 |
+
"step": 1160
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 18.28125,
|
| 846 |
+
"grad_norm": 2.5443062782287598,
|
| 847 |
+
"learning_rate": 4.152380952380953e-05,
|
| 848 |
+
"loss": 0.0917,
|
| 849 |
+
"step": 1170
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 18.4375,
|
| 853 |
+
"grad_norm": 4.180214881896973,
|
| 854 |
+
"learning_rate": 4.144444444444445e-05,
|
| 855 |
+
"loss": 0.0913,
|
| 856 |
+
"step": 1180
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 18.59375,
|
| 860 |
+
"grad_norm": 2.3229408264160156,
|
| 861 |
+
"learning_rate": 4.136507936507937e-05,
|
| 862 |
+
"loss": 0.081,
|
| 863 |
+
"step": 1190
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 18.75,
|
| 867 |
+
"grad_norm": 3.885908603668213,
|
| 868 |
+
"learning_rate": 4.128571428571429e-05,
|
| 869 |
+
"loss": 0.1078,
|
| 870 |
+
"step": 1200
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 18.90625,
|
| 874 |
+
"grad_norm": 3.1222493648529053,
|
| 875 |
+
"learning_rate": 4.120634920634921e-05,
|
| 876 |
+
"loss": 0.1177,
|
| 877 |
+
"step": 1210
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 19.0625,
|
| 881 |
+
"grad_norm": 3.3118879795074463,
|
| 882 |
+
"learning_rate": 4.112698412698413e-05,
|
| 883 |
+
"loss": 0.0775,
|
| 884 |
+
"step": 1220
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 19.21875,
|
| 888 |
+
"grad_norm": 1.8756282329559326,
|
| 889 |
+
"learning_rate": 4.104761904761905e-05,
|
| 890 |
+
"loss": 0.0906,
|
| 891 |
+
"step": 1230
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 19.375,
|
| 895 |
+
"grad_norm": 3.6675071716308594,
|
| 896 |
+
"learning_rate": 4.096825396825397e-05,
|
| 897 |
+
"loss": 0.0938,
|
| 898 |
+
"step": 1240
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 19.53125,
|
| 902 |
+
"grad_norm": 2.8696744441986084,
|
| 903 |
+
"learning_rate": 4.088888888888889e-05,
|
| 904 |
+
"loss": 0.0821,
|
| 905 |
+
"step": 1250
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 19.6875,
|
| 909 |
+
"grad_norm": 3.246438980102539,
|
| 910 |
+
"learning_rate": 4.0809523809523813e-05,
|
| 911 |
+
"loss": 0.1216,
|
| 912 |
+
"step": 1260
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 19.84375,
|
| 916 |
+
"grad_norm": 2.579602003097534,
|
| 917 |
+
"learning_rate": 4.073015873015873e-05,
|
| 918 |
+
"loss": 0.0705,
|
| 919 |
+
"step": 1270
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 20.0,
|
| 923 |
+
"grad_norm": 14.062989234924316,
|
| 924 |
+
"learning_rate": 4.065079365079365e-05,
|
| 925 |
+
"loss": 0.1125,
|
| 926 |
+
"step": 1280
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 20.15625,
|
| 930 |
+
"grad_norm": 2.5907585620880127,
|
| 931 |
+
"learning_rate": 4.057142857142857e-05,
|
| 932 |
+
"loss": 0.0764,
|
| 933 |
+
"step": 1290
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 20.3125,
|
| 937 |
+
"grad_norm": 4.850607872009277,
|
| 938 |
+
"learning_rate": 4.049206349206349e-05,
|
| 939 |
+
"loss": 0.0882,
|
| 940 |
+
"step": 1300
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 20.46875,
|
| 944 |
+
"grad_norm": 2.3619115352630615,
|
| 945 |
+
"learning_rate": 4.0412698412698414e-05,
|
| 946 |
+
"loss": 0.0833,
|
| 947 |
+
"step": 1310
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 20.625,
|
| 951 |
+
"grad_norm": 3.1803815364837646,
|
| 952 |
+
"learning_rate": 4.0333333333333336e-05,
|
| 953 |
+
"loss": 0.0894,
|
| 954 |
+
"step": 1320
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 20.78125,
|
| 958 |
+
"grad_norm": 15.570907592773438,
|
| 959 |
+
"learning_rate": 4.025396825396826e-05,
|
| 960 |
+
"loss": 0.2225,
|
| 961 |
+
"step": 1330
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 20.9375,
|
| 965 |
+
"grad_norm": 2.721440076828003,
|
| 966 |
+
"learning_rate": 4.018253968253968e-05,
|
| 967 |
+
"loss": 0.1233,
|
| 968 |
+
"step": 1340
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 21.09375,
|
| 972 |
+
"grad_norm": 1.798134446144104,
|
| 973 |
+
"learning_rate": 4.01031746031746e-05,
|
| 974 |
+
"loss": 0.067,
|
| 975 |
+
"step": 1350
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 21.25,
|
| 979 |
+
"grad_norm": 3.387782335281372,
|
| 980 |
+
"learning_rate": 4.0023809523809524e-05,
|
| 981 |
+
"loss": 0.0692,
|
| 982 |
+
"step": 1360
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 21.40625,
|
| 986 |
+
"grad_norm": 2.723196029663086,
|
| 987 |
+
"learning_rate": 3.9944444444444446e-05,
|
| 988 |
+
"loss": 0.0683,
|
| 989 |
+
"step": 1370
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 21.5625,
|
| 993 |
+
"grad_norm": 3.666444778442383,
|
| 994 |
+
"learning_rate": 3.986507936507937e-05,
|
| 995 |
+
"loss": 0.0883,
|
| 996 |
+
"step": 1380
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 21.71875,
|
| 1000 |
+
"grad_norm": 1.9571526050567627,
|
| 1001 |
+
"learning_rate": 3.978571428571429e-05,
|
| 1002 |
+
"loss": 0.0802,
|
| 1003 |
+
"step": 1390
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 21.875,
|
| 1007 |
+
"grad_norm": 2.5271904468536377,
|
| 1008 |
+
"learning_rate": 3.970634920634921e-05,
|
| 1009 |
+
"loss": 0.0737,
|
| 1010 |
+
"step": 1400
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 22.03125,
|
| 1014 |
+
"grad_norm": 3.5426900386810303,
|
| 1015 |
+
"learning_rate": 3.962698412698413e-05,
|
| 1016 |
+
"loss": 0.0838,
|
| 1017 |
+
"step": 1410
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 22.1875,
|
| 1021 |
+
"grad_norm": 1.7901580333709717,
|
| 1022 |
+
"learning_rate": 3.954761904761905e-05,
|
| 1023 |
+
"loss": 0.0671,
|
| 1024 |
+
"step": 1420
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 22.34375,
|
| 1028 |
+
"grad_norm": 3.4260764122009277,
|
| 1029 |
+
"learning_rate": 3.946825396825397e-05,
|
| 1030 |
+
"loss": 0.0775,
|
| 1031 |
+
"step": 1430
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 22.5,
|
| 1035 |
+
"grad_norm": 2.499107837677002,
|
| 1036 |
+
"learning_rate": 3.938888888888889e-05,
|
| 1037 |
+
"loss": 0.0826,
|
| 1038 |
+
"step": 1440
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 22.65625,
|
| 1042 |
+
"grad_norm": 2.7331862449645996,
|
| 1043 |
+
"learning_rate": 3.930952380952381e-05,
|
| 1044 |
+
"loss": 0.0771,
|
| 1045 |
+
"step": 1450
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 22.8125,
|
| 1049 |
+
"grad_norm": 3.2004685401916504,
|
| 1050 |
+
"learning_rate": 3.923015873015873e-05,
|
| 1051 |
+
"loss": 0.088,
|
| 1052 |
+
"step": 1460
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 22.96875,
|
| 1056 |
+
"grad_norm": 3.175179958343506,
|
| 1057 |
+
"learning_rate": 3.9150793650793654e-05,
|
| 1058 |
+
"loss": 0.0861,
|
| 1059 |
+
"step": 1470
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 23.125,
|
| 1063 |
+
"grad_norm": 2.032646417617798,
|
| 1064 |
+
"learning_rate": 3.9071428571428575e-05,
|
| 1065 |
+
"loss": 0.0682,
|
| 1066 |
+
"step": 1480
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 23.28125,
|
| 1070 |
+
"grad_norm": 1.5635634660720825,
|
| 1071 |
+
"learning_rate": 3.89920634920635e-05,
|
| 1072 |
+
"loss": 0.0833,
|
| 1073 |
+
"step": 1490
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 23.4375,
|
| 1077 |
+
"grad_norm": 1.8121321201324463,
|
| 1078 |
+
"learning_rate": 3.891269841269842e-05,
|
| 1079 |
+
"loss": 0.0965,
|
| 1080 |
+
"step": 1500
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 23.4375,
|
| 1084 |
+
"eval_runtime": 2.0794,
|
| 1085 |
+
"eval_samples_per_second": 0.481,
|
| 1086 |
+
"eval_steps_per_second": 0.481,
|
| 1087 |
+
"step": 1500
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 23.59375,
|
| 1091 |
+
"grad_norm": 1.8793394565582275,
|
| 1092 |
+
"learning_rate": 3.883333333333333e-05,
|
| 1093 |
+
"loss": 0.0887,
|
| 1094 |
+
"step": 1510
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 23.75,
|
| 1098 |
+
"grad_norm": 2.1231632232666016,
|
| 1099 |
+
"learning_rate": 3.8753968253968255e-05,
|
| 1100 |
+
"loss": 0.0879,
|
| 1101 |
+
"step": 1520
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 23.90625,
|
| 1105 |
+
"grad_norm": 3.5764803886413574,
|
| 1106 |
+
"learning_rate": 3.8674603174603176e-05,
|
| 1107 |
+
"loss": 0.0861,
|
| 1108 |
+
"step": 1530
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 24.0625,
|
| 1112 |
+
"grad_norm": 2.105710029602051,
|
| 1113 |
+
"learning_rate": 3.85952380952381e-05,
|
| 1114 |
+
"loss": 0.07,
|
| 1115 |
+
"step": 1540
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 24.21875,
|
| 1119 |
+
"grad_norm": 2.8722870349884033,
|
| 1120 |
+
"learning_rate": 3.851587301587302e-05,
|
| 1121 |
+
"loss": 0.076,
|
| 1122 |
+
"step": 1550
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 24.375,
|
| 1126 |
+
"grad_norm": 2.6126277446746826,
|
| 1127 |
+
"learning_rate": 3.843650793650794e-05,
|
| 1128 |
+
"loss": 0.0983,
|
| 1129 |
+
"step": 1560
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 24.53125,
|
| 1133 |
+
"grad_norm": 2.2635769844055176,
|
| 1134 |
+
"learning_rate": 3.8357142857142855e-05,
|
| 1135 |
+
"loss": 0.0864,
|
| 1136 |
+
"step": 1570
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 24.6875,
|
| 1140 |
+
"grad_norm": 2.11098313331604,
|
| 1141 |
+
"learning_rate": 3.827777777777778e-05,
|
| 1142 |
+
"loss": 0.0923,
|
| 1143 |
+
"step": 1580
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 24.84375,
|
| 1147 |
+
"grad_norm": 1.6163533926010132,
|
| 1148 |
+
"learning_rate": 3.81984126984127e-05,
|
| 1149 |
+
"loss": 0.0711,
|
| 1150 |
+
"step": 1590
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 25.0,
|
| 1154 |
+
"grad_norm": 2.54638671875,
|
| 1155 |
+
"learning_rate": 3.811904761904762e-05,
|
| 1156 |
+
"loss": 0.0705,
|
| 1157 |
+
"step": 1600
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 25.15625,
|
| 1161 |
+
"grad_norm": 2.592470407485962,
|
| 1162 |
+
"learning_rate": 3.803968253968254e-05,
|
| 1163 |
+
"loss": 0.0765,
|
| 1164 |
+
"step": 1610
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 25.3125,
|
| 1168 |
+
"grad_norm": 2.1981208324432373,
|
| 1169 |
+
"learning_rate": 3.796031746031746e-05,
|
| 1170 |
+
"loss": 0.0856,
|
| 1171 |
+
"step": 1620
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 25.46875,
|
| 1175 |
+
"grad_norm": 1.384098768234253,
|
| 1176 |
+
"learning_rate": 3.7880952380952384e-05,
|
| 1177 |
+
"loss": 0.0951,
|
| 1178 |
+
"step": 1630
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 25.625,
|
| 1182 |
+
"grad_norm": 1.502350091934204,
|
| 1183 |
+
"learning_rate": 3.7801587301587306e-05,
|
| 1184 |
+
"loss": 0.0858,
|
| 1185 |
+
"step": 1640
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 25.78125,
|
| 1189 |
+
"grad_norm": 1.4763522148132324,
|
| 1190 |
+
"learning_rate": 3.772222222222223e-05,
|
| 1191 |
+
"loss": 0.0647,
|
| 1192 |
+
"step": 1650
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 25.9375,
|
| 1196 |
+
"grad_norm": 1.7555052042007446,
|
| 1197 |
+
"learning_rate": 3.764285714285715e-05,
|
| 1198 |
+
"loss": 0.0874,
|
| 1199 |
+
"step": 1660
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 26.09375,
|
| 1203 |
+
"grad_norm": 1.0187015533447266,
|
| 1204 |
+
"learning_rate": 3.756349206349207e-05,
|
| 1205 |
+
"loss": 0.0635,
|
| 1206 |
+
"step": 1670
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 26.25,
|
| 1210 |
+
"grad_norm": 1.7138936519622803,
|
| 1211 |
+
"learning_rate": 3.7484126984126985e-05,
|
| 1212 |
+
"loss": 0.0772,
|
| 1213 |
+
"step": 1680
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 26.40625,
|
| 1217 |
+
"grad_norm": 2.3353724479675293,
|
| 1218 |
+
"learning_rate": 3.7404761904761907e-05,
|
| 1219 |
+
"loss": 0.0892,
|
| 1220 |
+
"step": 1690
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 26.5625,
|
| 1224 |
+
"grad_norm": 2.6141700744628906,
|
| 1225 |
+
"learning_rate": 3.732539682539682e-05,
|
| 1226 |
+
"loss": 0.0897,
|
| 1227 |
+
"step": 1700
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 26.71875,
|
| 1231 |
+
"grad_norm": 1.7785848379135132,
|
| 1232 |
+
"learning_rate": 3.724603174603174e-05,
|
| 1233 |
+
"loss": 0.0899,
|
| 1234 |
+
"step": 1710
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 26.875,
|
| 1238 |
+
"grad_norm": 2.6693010330200195,
|
| 1239 |
+
"learning_rate": 3.7166666666666664e-05,
|
| 1240 |
+
"loss": 0.0901,
|
| 1241 |
+
"step": 1720
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 27.03125,
|
| 1245 |
+
"grad_norm": 2.059981346130371,
|
| 1246 |
+
"learning_rate": 3.7087301587301586e-05,
|
| 1247 |
+
"loss": 0.0822,
|
| 1248 |
+
"step": 1730
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 27.1875,
|
| 1252 |
+
"grad_norm": 1.6238901615142822,
|
| 1253 |
+
"learning_rate": 3.700793650793651e-05,
|
| 1254 |
+
"loss": 0.0777,
|
| 1255 |
+
"step": 1740
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 27.34375,
|
| 1259 |
+
"grad_norm": 2.782425880432129,
|
| 1260 |
+
"learning_rate": 3.692857142857143e-05,
|
| 1261 |
+
"loss": 0.0782,
|
| 1262 |
+
"step": 1750
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 27.5,
|
| 1266 |
+
"grad_norm": 1.8468166589736938,
|
| 1267 |
+
"learning_rate": 3.684920634920635e-05,
|
| 1268 |
+
"loss": 0.0835,
|
| 1269 |
+
"step": 1760
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 27.65625,
|
| 1273 |
+
"grad_norm": 1.3156135082244873,
|
| 1274 |
+
"learning_rate": 3.676984126984127e-05,
|
| 1275 |
+
"loss": 0.1072,
|
| 1276 |
+
"step": 1770
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 27.8125,
|
| 1280 |
+
"grad_norm": 3.260084390640259,
|
| 1281 |
+
"learning_rate": 3.669047619047619e-05,
|
| 1282 |
+
"loss": 0.0939,
|
| 1283 |
+
"step": 1780
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 27.96875,
|
| 1287 |
+
"grad_norm": 2.518204689025879,
|
| 1288 |
+
"learning_rate": 3.6611111111111115e-05,
|
| 1289 |
+
"loss": 0.0884,
|
| 1290 |
+
"step": 1790
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 28.125,
|
| 1294 |
+
"grad_norm": 2.598057985305786,
|
| 1295 |
+
"learning_rate": 3.6531746031746036e-05,
|
| 1296 |
+
"loss": 0.0683,
|
| 1297 |
+
"step": 1800
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 28.28125,
|
| 1301 |
+
"grad_norm": 1.8533433675765991,
|
| 1302 |
+
"learning_rate": 3.645238095238096e-05,
|
| 1303 |
+
"loss": 0.0833,
|
| 1304 |
+
"step": 1810
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 28.4375,
|
| 1308 |
+
"grad_norm": 1.2828975915908813,
|
| 1309 |
+
"learning_rate": 3.637301587301587e-05,
|
| 1310 |
+
"loss": 0.0832,
|
| 1311 |
+
"step": 1820
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 28.59375,
|
| 1315 |
+
"grad_norm": 1.7714905738830566,
|
| 1316 |
+
"learning_rate": 3.6293650793650794e-05,
|
| 1317 |
+
"loss": 0.0901,
|
| 1318 |
+
"step": 1830
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 28.75,
|
| 1322 |
+
"grad_norm": 2.098923921585083,
|
| 1323 |
+
"learning_rate": 3.6214285714285716e-05,
|
| 1324 |
+
"loss": 0.0954,
|
| 1325 |
+
"step": 1840
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 28.90625,
|
| 1329 |
+
"grad_norm": 2.298226833343506,
|
| 1330 |
+
"learning_rate": 3.613492063492064e-05,
|
| 1331 |
+
"loss": 0.0888,
|
| 1332 |
+
"step": 1850
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 29.0625,
|
| 1336 |
+
"grad_norm": 1.5519624948501587,
|
| 1337 |
+
"learning_rate": 3.605555555555556e-05,
|
| 1338 |
+
"loss": 0.0664,
|
| 1339 |
+
"step": 1860
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 29.21875,
|
| 1343 |
+
"grad_norm": 2.015573501586914,
|
| 1344 |
+
"learning_rate": 3.597619047619048e-05,
|
| 1345 |
+
"loss": 0.0637,
|
| 1346 |
+
"step": 1870
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 29.375,
|
| 1350 |
+
"grad_norm": 1.925529956817627,
|
| 1351 |
+
"learning_rate": 3.58968253968254e-05,
|
| 1352 |
+
"loss": 0.0803,
|
| 1353 |
+
"step": 1880
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 29.53125,
|
| 1357 |
+
"grad_norm": 2.4342522621154785,
|
| 1358 |
+
"learning_rate": 3.581746031746032e-05,
|
| 1359 |
+
"loss": 0.0911,
|
| 1360 |
+
"step": 1890
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 29.6875,
|
| 1364 |
+
"grad_norm": 1.8124195337295532,
|
| 1365 |
+
"learning_rate": 3.573809523809524e-05,
|
| 1366 |
+
"loss": 0.0803,
|
| 1367 |
+
"step": 1900
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 29.84375,
|
| 1371 |
+
"grad_norm": 2.3409860134124756,
|
| 1372 |
+
"learning_rate": 3.565873015873016e-05,
|
| 1373 |
+
"loss": 0.0943,
|
| 1374 |
+
"step": 1910
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 30.0,
|
| 1378 |
+
"grad_norm": 1.2545162439346313,
|
| 1379 |
+
"learning_rate": 3.557936507936508e-05,
|
| 1380 |
+
"loss": 0.0853,
|
| 1381 |
+
"step": 1920
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 30.15625,
|
| 1385 |
+
"grad_norm": 1.9356091022491455,
|
| 1386 |
+
"learning_rate": 3.55e-05,
|
| 1387 |
+
"loss": 0.0585,
|
| 1388 |
+
"step": 1930
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 30.3125,
|
| 1392 |
+
"grad_norm": 1.6294385194778442,
|
| 1393 |
+
"learning_rate": 3.5420634920634924e-05,
|
| 1394 |
+
"loss": 0.0876,
|
| 1395 |
+
"step": 1940
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 30.46875,
|
| 1399 |
+
"grad_norm": 2.081688165664673,
|
| 1400 |
+
"learning_rate": 3.534126984126984e-05,
|
| 1401 |
+
"loss": 0.0827,
|
| 1402 |
+
"step": 1950
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 30.625,
|
| 1406 |
+
"grad_norm": 1.7468382120132446,
|
| 1407 |
+
"learning_rate": 3.526190476190476e-05,
|
| 1408 |
+
"loss": 0.0732,
|
| 1409 |
+
"step": 1960
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 30.78125,
|
| 1413 |
+
"grad_norm": 2.1742124557495117,
|
| 1414 |
+
"learning_rate": 3.518253968253968e-05,
|
| 1415 |
+
"loss": 0.084,
|
| 1416 |
+
"step": 1970
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 30.9375,
|
| 1420 |
+
"grad_norm": 2.147754430770874,
|
| 1421 |
+
"learning_rate": 3.51031746031746e-05,
|
| 1422 |
+
"loss": 0.0856,
|
| 1423 |
+
"step": 1980
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 31.09375,
|
| 1427 |
+
"grad_norm": 2.1251964569091797,
|
| 1428 |
+
"learning_rate": 3.5023809523809525e-05,
|
| 1429 |
+
"loss": 0.0762,
|
| 1430 |
+
"step": 1990
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 31.25,
|
| 1434 |
+
"grad_norm": 2.6378941535949707,
|
| 1435 |
+
"learning_rate": 3.4944444444444446e-05,
|
| 1436 |
+
"loss": 0.071,
|
| 1437 |
+
"step": 2000
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 31.25,
|
| 1441 |
+
"eval_runtime": 2.0743,
|
| 1442 |
+
"eval_samples_per_second": 0.482,
|
| 1443 |
+
"eval_steps_per_second": 0.482,
|
| 1444 |
+
"step": 2000
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 31.40625,
|
| 1448 |
+
"grad_norm": 2.126807689666748,
|
| 1449 |
+
"learning_rate": 3.486507936507937e-05,
|
| 1450 |
+
"loss": 0.0785,
|
| 1451 |
+
"step": 2010
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 31.5625,
|
| 1455 |
+
"grad_norm": 2.4585835933685303,
|
| 1456 |
+
"learning_rate": 3.478571428571429e-05,
|
| 1457 |
+
"loss": 0.1053,
|
| 1458 |
+
"step": 2020
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 31.71875,
|
| 1462 |
+
"grad_norm": 1.9649542570114136,
|
| 1463 |
+
"learning_rate": 3.470634920634921e-05,
|
| 1464 |
+
"loss": 0.0734,
|
| 1465 |
+
"step": 2030
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 31.875,
|
| 1469 |
+
"grad_norm": 2.3006460666656494,
|
| 1470 |
+
"learning_rate": 3.462698412698413e-05,
|
| 1471 |
+
"loss": 0.0858,
|
| 1472 |
+
"step": 2040
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 32.03125,
|
| 1476 |
+
"grad_norm": 2.163447856903076,
|
| 1477 |
+
"learning_rate": 3.4547619047619054e-05,
|
| 1478 |
+
"loss": 0.0826,
|
| 1479 |
+
"step": 2050
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 32.1875,
|
| 1483 |
+
"grad_norm": 2.0441508293151855,
|
| 1484 |
+
"learning_rate": 3.4468253968253975e-05,
|
| 1485 |
+
"loss": 0.0712,
|
| 1486 |
+
"step": 2060
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 32.34375,
|
| 1490 |
+
"grad_norm": 1.5795445442199707,
|
| 1491 |
+
"learning_rate": 3.438888888888889e-05,
|
| 1492 |
+
"loss": 0.056,
|
| 1493 |
+
"step": 2070
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 32.5,
|
| 1497 |
+
"grad_norm": 3.5661540031433105,
|
| 1498 |
+
"learning_rate": 3.430952380952381e-05,
|
| 1499 |
+
"loss": 0.069,
|
| 1500 |
+
"step": 2080
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 32.65625,
|
| 1504 |
+
"grad_norm": 1.6884055137634277,
|
| 1505 |
+
"learning_rate": 3.423015873015873e-05,
|
| 1506 |
+
"loss": 0.0899,
|
| 1507 |
+
"step": 2090
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 32.8125,
|
| 1511 |
+
"grad_norm": 2.421724557876587,
|
| 1512 |
+
"learning_rate": 3.415079365079365e-05,
|
| 1513 |
+
"loss": 0.0768,
|
| 1514 |
+
"step": 2100
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 32.96875,
|
| 1518 |
+
"grad_norm": 1.1584899425506592,
|
| 1519 |
+
"learning_rate": 3.407142857142857e-05,
|
| 1520 |
+
"loss": 0.0763,
|
| 1521 |
+
"step": 2110
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 33.125,
|
| 1525 |
+
"grad_norm": 2.069801092147827,
|
| 1526 |
+
"learning_rate": 3.399206349206349e-05,
|
| 1527 |
+
"loss": 0.0636,
|
| 1528 |
+
"step": 2120
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 33.28125,
|
| 1532 |
+
"grad_norm": 2.5826573371887207,
|
| 1533 |
+
"learning_rate": 3.391269841269841e-05,
|
| 1534 |
+
"loss": 0.0676,
|
| 1535 |
+
"step": 2130
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 33.4375,
|
| 1539 |
+
"grad_norm": 1.119449496269226,
|
| 1540 |
+
"learning_rate": 3.3833333333333334e-05,
|
| 1541 |
+
"loss": 0.0613,
|
| 1542 |
+
"step": 2140
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 33.59375,
|
| 1546 |
+
"grad_norm": 1.6656103134155273,
|
| 1547 |
+
"learning_rate": 3.3753968253968255e-05,
|
| 1548 |
+
"loss": 0.0598,
|
| 1549 |
+
"step": 2150
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 33.75,
|
| 1553 |
+
"grad_norm": 1.7956265211105347,
|
| 1554 |
+
"learning_rate": 3.3674603174603177e-05,
|
| 1555 |
+
"loss": 0.0778,
|
| 1556 |
+
"step": 2160
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 33.90625,
|
| 1560 |
+
"grad_norm": 2.2106685638427734,
|
| 1561 |
+
"learning_rate": 3.35952380952381e-05,
|
| 1562 |
+
"loss": 0.0737,
|
| 1563 |
+
"step": 2170
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 34.0625,
|
| 1567 |
+
"grad_norm": 2.4478724002838135,
|
| 1568 |
+
"learning_rate": 3.351587301587302e-05,
|
| 1569 |
+
"loss": 0.0642,
|
| 1570 |
+
"step": 2180
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 34.21875,
|
| 1574 |
+
"grad_norm": 2.3334341049194336,
|
| 1575 |
+
"learning_rate": 3.343650793650794e-05,
|
| 1576 |
+
"loss": 0.0697,
|
| 1577 |
+
"step": 2190
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 34.375,
|
| 1581 |
+
"grad_norm": 1.870275855064392,
|
| 1582 |
+
"learning_rate": 3.3357142857142856e-05,
|
| 1583 |
+
"loss": 0.0523,
|
| 1584 |
+
"step": 2200
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 34.53125,
|
| 1588 |
+
"grad_norm": 1.283444881439209,
|
| 1589 |
+
"learning_rate": 3.327777777777778e-05,
|
| 1590 |
+
"loss": 0.0619,
|
| 1591 |
+
"step": 2210
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 34.6875,
|
| 1595 |
+
"grad_norm": 1.7918671369552612,
|
| 1596 |
+
"learning_rate": 3.31984126984127e-05,
|
| 1597 |
+
"loss": 0.061,
|
| 1598 |
+
"step": 2220
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 34.84375,
|
| 1602 |
+
"grad_norm": 1.6546680927276611,
|
| 1603 |
+
"learning_rate": 3.311904761904762e-05,
|
| 1604 |
+
"loss": 0.058,
|
| 1605 |
+
"step": 2230
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 35.0,
|
| 1609 |
+
"grad_norm": 3.8063647747039795,
|
| 1610 |
+
"learning_rate": 3.303968253968254e-05,
|
| 1611 |
+
"loss": 0.0605,
|
| 1612 |
+
"step": 2240
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 35.15625,
|
| 1616 |
+
"grad_norm": 1.8701483011245728,
|
| 1617 |
+
"learning_rate": 3.296031746031746e-05,
|
| 1618 |
+
"loss": 0.0652,
|
| 1619 |
+
"step": 2250
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 35.3125,
|
| 1623 |
+
"grad_norm": 0.48190346360206604,
|
| 1624 |
+
"learning_rate": 3.2880952380952385e-05,
|
| 1625 |
+
"loss": 0.0443,
|
| 1626 |
+
"step": 2260
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 35.46875,
|
| 1630 |
+
"grad_norm": 1.0227997303009033,
|
| 1631 |
+
"learning_rate": 3.2801587301587306e-05,
|
| 1632 |
+
"loss": 0.0397,
|
| 1633 |
+
"step": 2270
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 35.625,
|
| 1637 |
+
"grad_norm": 1.4256937503814697,
|
| 1638 |
+
"learning_rate": 3.272222222222223e-05,
|
| 1639 |
+
"loss": 0.0541,
|
| 1640 |
+
"step": 2280
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 35.78125,
|
| 1644 |
+
"grad_norm": 2.3451199531555176,
|
| 1645 |
+
"learning_rate": 3.264285714285714e-05,
|
| 1646 |
+
"loss": 0.0568,
|
| 1647 |
+
"step": 2290
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 35.9375,
|
| 1651 |
+
"grad_norm": 1.3683526515960693,
|
| 1652 |
+
"learning_rate": 3.2563492063492064e-05,
|
| 1653 |
+
"loss": 0.0587,
|
| 1654 |
+
"step": 2300
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 36.09375,
|
| 1658 |
+
"grad_norm": 1.4543867111206055,
|
| 1659 |
+
"learning_rate": 3.2484126984126986e-05,
|
| 1660 |
+
"loss": 0.0394,
|
| 1661 |
+
"step": 2310
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 36.25,
|
| 1665 |
+
"grad_norm": 1.9606877565383911,
|
| 1666 |
+
"learning_rate": 3.240476190476191e-05,
|
| 1667 |
+
"loss": 0.0545,
|
| 1668 |
+
"step": 2320
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 36.40625,
|
| 1672 |
+
"grad_norm": 1.6910959482192993,
|
| 1673 |
+
"learning_rate": 3.232539682539683e-05,
|
| 1674 |
+
"loss": 0.0638,
|
| 1675 |
+
"step": 2330
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 36.5625,
|
| 1679 |
+
"grad_norm": 1.735841155052185,
|
| 1680 |
+
"learning_rate": 3.224603174603174e-05,
|
| 1681 |
+
"loss": 0.0569,
|
| 1682 |
+
"step": 2340
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 36.71875,
|
| 1686 |
+
"grad_norm": 1.5598944425582886,
|
| 1687 |
+
"learning_rate": 3.2166666666666665e-05,
|
| 1688 |
+
"loss": 0.0649,
|
| 1689 |
+
"step": 2350
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 36.875,
|
| 1693 |
+
"grad_norm": 1.5700335502624512,
|
| 1694 |
+
"learning_rate": 3.2087301587301586e-05,
|
| 1695 |
+
"loss": 0.0689,
|
| 1696 |
+
"step": 2360
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 37.03125,
|
| 1700 |
+
"grad_norm": 1.0767812728881836,
|
| 1701 |
+
"learning_rate": 3.200793650793651e-05,
|
| 1702 |
+
"loss": 0.0535,
|
| 1703 |
+
"step": 2370
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 37.1875,
|
| 1707 |
+
"grad_norm": 2.505707263946533,
|
| 1708 |
+
"learning_rate": 3.192857142857143e-05,
|
| 1709 |
+
"loss": 0.0486,
|
| 1710 |
+
"step": 2380
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 37.34375,
|
| 1714 |
+
"grad_norm": 2.1414477825164795,
|
| 1715 |
+
"learning_rate": 3.184920634920635e-05,
|
| 1716 |
+
"loss": 0.0462,
|
| 1717 |
+
"step": 2390
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 37.5,
|
| 1721 |
+
"grad_norm": 1.0493581295013428,
|
| 1722 |
+
"learning_rate": 3.176984126984127e-05,
|
| 1723 |
+
"loss": 0.0515,
|
| 1724 |
+
"step": 2400
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 37.65625,
|
| 1728 |
+
"grad_norm": 1.5255446434020996,
|
| 1729 |
+
"learning_rate": 3.1690476190476194e-05,
|
| 1730 |
+
"loss": 0.0485,
|
| 1731 |
+
"step": 2410
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 37.8125,
|
| 1735 |
+
"grad_norm": 1.3334754705429077,
|
| 1736 |
+
"learning_rate": 3.1611111111111115e-05,
|
| 1737 |
+
"loss": 0.056,
|
| 1738 |
+
"step": 2420
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 37.96875,
|
| 1742 |
+
"grad_norm": 1.745110273361206,
|
| 1743 |
+
"learning_rate": 3.153174603174604e-05,
|
| 1744 |
+
"loss": 0.0473,
|
| 1745 |
+
"step": 2430
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 38.125,
|
| 1749 |
+
"grad_norm": 1.4413131475448608,
|
| 1750 |
+
"learning_rate": 3.145238095238096e-05,
|
| 1751 |
+
"loss": 0.0317,
|
| 1752 |
+
"step": 2440
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 38.28125,
|
| 1756 |
+
"grad_norm": 1.6811962127685547,
|
| 1757 |
+
"learning_rate": 3.137301587301587e-05,
|
| 1758 |
+
"loss": 0.0496,
|
| 1759 |
+
"step": 2450
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 38.4375,
|
| 1763 |
+
"grad_norm": 1.2820957899093628,
|
| 1764 |
+
"learning_rate": 3.1293650793650795e-05,
|
| 1765 |
+
"loss": 0.0369,
|
| 1766 |
+
"step": 2460
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 38.59375,
|
| 1770 |
+
"grad_norm": 1.7850005626678467,
|
| 1771 |
+
"learning_rate": 3.1214285714285716e-05,
|
| 1772 |
+
"loss": 0.0478,
|
| 1773 |
+
"step": 2470
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 38.75,
|
| 1777 |
+
"grad_norm": 2.456017255783081,
|
| 1778 |
+
"learning_rate": 3.113492063492064e-05,
|
| 1779 |
+
"loss": 0.0507,
|
| 1780 |
+
"step": 2480
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 38.90625,
|
| 1784 |
+
"grad_norm": 2.1933865547180176,
|
| 1785 |
+
"learning_rate": 3.105555555555555e-05,
|
| 1786 |
+
"loss": 0.0436,
|
| 1787 |
+
"step": 2490
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 39.0625,
|
| 1791 |
+
"grad_norm": 0.9716876745223999,
|
| 1792 |
+
"learning_rate": 3.0976190476190474e-05,
|
| 1793 |
+
"loss": 0.0439,
|
| 1794 |
+
"step": 2500
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 39.0625,
|
| 1798 |
+
"eval_runtime": 2.0072,
|
| 1799 |
+
"eval_samples_per_second": 0.498,
|
| 1800 |
+
"eval_steps_per_second": 0.498,
|
| 1801 |
+
"step": 2500
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 39.21875,
|
| 1805 |
+
"grad_norm": 2.0628113746643066,
|
| 1806 |
+
"learning_rate": 3.0896825396825395e-05,
|
| 1807 |
+
"loss": 0.0408,
|
| 1808 |
+
"step": 2510
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 39.375,
|
| 1812 |
+
"grad_norm": 1.5137745141983032,
|
| 1813 |
+
"learning_rate": 3.081746031746032e-05,
|
| 1814 |
+
"loss": 0.0445,
|
| 1815 |
+
"step": 2520
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 39.53125,
|
| 1819 |
+
"grad_norm": 1.6775884628295898,
|
| 1820 |
+
"learning_rate": 3.073809523809524e-05,
|
| 1821 |
+
"loss": 0.051,
|
| 1822 |
+
"step": 2530
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 39.6875,
|
| 1826 |
+
"grad_norm": 1.440619707107544,
|
| 1827 |
+
"learning_rate": 3.065873015873016e-05,
|
| 1828 |
+
"loss": 0.0387,
|
| 1829 |
+
"step": 2540
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 39.84375,
|
| 1833 |
+
"grad_norm": 2.1149260997772217,
|
| 1834 |
+
"learning_rate": 3.057936507936508e-05,
|
| 1835 |
+
"loss": 0.0387,
|
| 1836 |
+
"step": 2550
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 40.0,
|
| 1840 |
+
"grad_norm": 2.163191318511963,
|
| 1841 |
+
"learning_rate": 3.05e-05,
|
| 1842 |
+
"loss": 0.0363,
|
| 1843 |
+
"step": 2560
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 40.15625,
|
| 1847 |
+
"grad_norm": 3.246634006500244,
|
| 1848 |
+
"learning_rate": 3.042063492063492e-05,
|
| 1849 |
+
"loss": 0.0429,
|
| 1850 |
+
"step": 2570
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 40.3125,
|
| 1854 |
+
"grad_norm": 1.188644289970398,
|
| 1855 |
+
"learning_rate": 3.0341269841269842e-05,
|
| 1856 |
+
"loss": 0.0316,
|
| 1857 |
+
"step": 2580
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 40.46875,
|
| 1861 |
+
"grad_norm": 2.2617383003234863,
|
| 1862 |
+
"learning_rate": 3.0261904761904764e-05,
|
| 1863 |
+
"loss": 0.0406,
|
| 1864 |
+
"step": 2590
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 40.625,
|
| 1868 |
+
"grad_norm": 0.6037064790725708,
|
| 1869 |
+
"learning_rate": 3.0182539682539685e-05,
|
| 1870 |
+
"loss": 0.031,
|
| 1871 |
+
"step": 2600
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 40.78125,
|
| 1875 |
+
"grad_norm": 1.1936763525009155,
|
| 1876 |
+
"learning_rate": 3.0103174603174607e-05,
|
| 1877 |
+
"loss": 0.0401,
|
| 1878 |
+
"step": 2610
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 40.9375,
|
| 1882 |
+
"grad_norm": 3.0310215950012207,
|
| 1883 |
+
"learning_rate": 3.0023809523809525e-05,
|
| 1884 |
+
"loss": 0.0339,
|
| 1885 |
+
"step": 2620
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 41.09375,
|
| 1889 |
+
"grad_norm": 0.6716585755348206,
|
| 1890 |
+
"learning_rate": 2.9944444444444446e-05,
|
| 1891 |
+
"loss": 0.0338,
|
| 1892 |
+
"step": 2630
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 41.25,
|
| 1896 |
+
"grad_norm": 0.5010519623756409,
|
| 1897 |
+
"learning_rate": 2.9865079365079368e-05,
|
| 1898 |
+
"loss": 0.0315,
|
| 1899 |
+
"step": 2640
|
| 1900 |
+
}
|
| 1901 |
+
],
|
| 1902 |
+
"logging_steps": 10,
|
| 1903 |
+
"max_steps": 6400,
|
| 1904 |
+
"num_input_tokens_seen": 0,
|
| 1905 |
+
"num_train_epochs": 100,
|
| 1906 |
+
"save_steps": 115,
|
| 1907 |
+
"stateful_callbacks": {
|
| 1908 |
+
"TrainerControl": {
|
| 1909 |
+
"args": {
|
| 1910 |
+
"should_epoch_stop": false,
|
| 1911 |
+
"should_evaluate": false,
|
| 1912 |
+
"should_log": false,
|
| 1913 |
+
"should_save": true,
|
| 1914 |
+
"should_training_stop": false
|
| 1915 |
+
},
|
| 1916 |
+
"attributes": {}
|
| 1917 |
+
}
|
| 1918 |
+
},
|
| 1919 |
+
"total_flos": 0.0,
|
| 1920 |
+
"train_batch_size": 8,
|
| 1921 |
+
"trial_name": null,
|
| 1922 |
+
"trial_params": null
|
| 1923 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ffe8194a454fde0f449eb7c7e43672ffa6b49ff9ee6aba76958f32161079d0b
|
| 3 |
+
size 5713
|
ve.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0921cab452fa278bc25cd23ffd59d36f816d7dc5181dd1bef9751a7fb61f63c
|
| 3 |
+
size 5695784
|