Training in progress, step 10255, checkpoint
Browse files- checkpoint-10255/model.safetensors +3 -0
- checkpoint-10255/optimizer.pt +3 -0
- checkpoint-10255/rng_state_0.pth +3 -0
- checkpoint-10255/rng_state_1.pth +3 -0
- checkpoint-10255/rng_state_2.pth +3 -0
- checkpoint-10255/rng_state_3.pth +3 -0
- checkpoint-10255/rng_state_4.pth +3 -0
- checkpoint-10255/rng_state_5.pth +3 -0
- checkpoint-10255/rng_state_6.pth +3 -0
- checkpoint-10255/rng_state_7.pth +3 -0
- checkpoint-10255/scheduler.pt +3 -0
- checkpoint-10255/special_tokens_map.json +37 -0
- checkpoint-10255/tokenizer.json +0 -0
- checkpoint-10255/tokenizer_config.json +945 -0
- checkpoint-10255/trainer_state.json +1148 -0
- checkpoint-10255/training_args.bin +3 -0
checkpoint-10255/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7d66ffce10f7b8ea15aafb97972f9563f133899c2df52e9cd88e769ec3258f4
|
| 3 |
+
size 737629736
|
checkpoint-10255/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7afba24e227ca8f331a71b60603ff846065d1334cf47088dc17685bae75fe676
|
| 3 |
+
size 601335051
|
checkpoint-10255/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce3d262d7b4281fcd65f2efbdf76d173c86db77bbb36630a1cf9502ada887e98
|
| 3 |
+
size 16325
|
checkpoint-10255/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a913f9c3a662a864a8c3b9f267fdf8e8876d5aea3bbb521bfe2807d5ded7ad3
|
| 3 |
+
size 16325
|
checkpoint-10255/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d434cef17549ef12778e5ae86aa11e16f10a8810dd5dd9d3162682aa1ac6e37
|
| 3 |
+
size 16325
|
checkpoint-10255/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d43f6fa2b57c3a1c60c85abc3457522befe5974b7ef72299c79b5e43baea974
|
| 3 |
+
size 16325
|
checkpoint-10255/rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35ebfb771b355c149f1e2e93c1d5f0b6de1bbcbb11450123e12806b0447246c7
|
| 3 |
+
size 16325
|
checkpoint-10255/rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cada01f435e94416b7d6a2ff9e945a1f1bd40005eae6953bd8dddf6015d6058b
|
| 3 |
+
size 16325
|
checkpoint-10255/rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b80178ff7c7865caa4192af3cade19499b8ffdf4b5e711e50f386b5bd716a57c
|
| 3 |
+
size 16325
|
checkpoint-10255/rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62602e8f3517562f942a8e55137351b407a8083bac251def4129993070fe4097
|
| 3 |
+
size 16325
|
checkpoint-10255/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec1a355bfbdb6153501bdb2fecd845b4b2fe79d6d3d9bb1a41fa223618db251a
|
| 3 |
+
size 1465
|
checkpoint-10255/special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": true,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
checkpoint-10255/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-10255/tokenizer_config.json
ADDED
|
@@ -0,0 +1,945 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "|||IP_ADDRESS|||",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": false
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<|padding|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"50254": {
|
| 20 |
+
"content": " ",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": true,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": false
|
| 26 |
+
},
|
| 27 |
+
"50255": {
|
| 28 |
+
"content": " ",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": false
|
| 34 |
+
},
|
| 35 |
+
"50256": {
|
| 36 |
+
"content": " ",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": true,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": false
|
| 42 |
+
},
|
| 43 |
+
"50257": {
|
| 44 |
+
"content": " ",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": true,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": false
|
| 50 |
+
},
|
| 51 |
+
"50258": {
|
| 52 |
+
"content": " ",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": true,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": false
|
| 58 |
+
},
|
| 59 |
+
"50259": {
|
| 60 |
+
"content": " ",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": true,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": false
|
| 66 |
+
},
|
| 67 |
+
"50260": {
|
| 68 |
+
"content": " ",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": true,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": false
|
| 74 |
+
},
|
| 75 |
+
"50261": {
|
| 76 |
+
"content": " ",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": true,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": false
|
| 82 |
+
},
|
| 83 |
+
"50262": {
|
| 84 |
+
"content": " ",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": true,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": false
|
| 90 |
+
},
|
| 91 |
+
"50263": {
|
| 92 |
+
"content": " ",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": true,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": false
|
| 98 |
+
},
|
| 99 |
+
"50264": {
|
| 100 |
+
"content": " ",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": true,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": false
|
| 106 |
+
},
|
| 107 |
+
"50265": {
|
| 108 |
+
"content": " ",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": true,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": false
|
| 114 |
+
},
|
| 115 |
+
"50266": {
|
| 116 |
+
"content": " ",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": true,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": false
|
| 122 |
+
},
|
| 123 |
+
"50267": {
|
| 124 |
+
"content": " ",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": true,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": false
|
| 130 |
+
},
|
| 131 |
+
"50268": {
|
| 132 |
+
"content": " ",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": true,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": false
|
| 138 |
+
},
|
| 139 |
+
"50269": {
|
| 140 |
+
"content": " ",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": true,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": false
|
| 146 |
+
},
|
| 147 |
+
"50270": {
|
| 148 |
+
"content": " ",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": true,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": false
|
| 154 |
+
},
|
| 155 |
+
"50271": {
|
| 156 |
+
"content": " ",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": true,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": false
|
| 162 |
+
},
|
| 163 |
+
"50272": {
|
| 164 |
+
"content": " ",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": true,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": false
|
| 170 |
+
},
|
| 171 |
+
"50273": {
|
| 172 |
+
"content": " ",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": true,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": false
|
| 178 |
+
},
|
| 179 |
+
"50274": {
|
| 180 |
+
"content": " ",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": true,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": false
|
| 186 |
+
},
|
| 187 |
+
"50275": {
|
| 188 |
+
"content": " ",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": true,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": false
|
| 194 |
+
},
|
| 195 |
+
"50276": {
|
| 196 |
+
"content": " ",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": true,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": false
|
| 202 |
+
},
|
| 203 |
+
"50277": {
|
| 204 |
+
"content": "|||EMAIL_ADDRESS|||",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": true,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": false
|
| 210 |
+
},
|
| 211 |
+
"50278": {
|
| 212 |
+
"content": "|||PHONE_NUMBER|||",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": true,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": false
|
| 218 |
+
},
|
| 219 |
+
"50279": {
|
| 220 |
+
"content": "<|endoftext|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"50280": {
|
| 228 |
+
"content": "[UNK]",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"50281": {
|
| 236 |
+
"content": "[CLS]",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"50282": {
|
| 244 |
+
"content": "[SEP]",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"50283": {
|
| 252 |
+
"content": "[PAD]",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"50284": {
|
| 260 |
+
"content": "[MASK]",
|
| 261 |
+
"lstrip": true,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"50285": {
|
| 268 |
+
"content": "[unused0]",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": true,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": false
|
| 274 |
+
},
|
| 275 |
+
"50286": {
|
| 276 |
+
"content": "[unused1]",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": true,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": false
|
| 282 |
+
},
|
| 283 |
+
"50287": {
|
| 284 |
+
"content": "[unused2]",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": true,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": false
|
| 290 |
+
},
|
| 291 |
+
"50288": {
|
| 292 |
+
"content": "[unused3]",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": true,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": false
|
| 298 |
+
},
|
| 299 |
+
"50289": {
|
| 300 |
+
"content": "[unused4]",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": true,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": false
|
| 306 |
+
},
|
| 307 |
+
"50290": {
|
| 308 |
+
"content": "[unused5]",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": true,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": false
|
| 314 |
+
},
|
| 315 |
+
"50291": {
|
| 316 |
+
"content": "[unused6]",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": true,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": false
|
| 322 |
+
},
|
| 323 |
+
"50292": {
|
| 324 |
+
"content": "[unused7]",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": true,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": false
|
| 330 |
+
},
|
| 331 |
+
"50293": {
|
| 332 |
+
"content": "[unused8]",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": true,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": false
|
| 338 |
+
},
|
| 339 |
+
"50294": {
|
| 340 |
+
"content": "[unused9]",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": true,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": false
|
| 346 |
+
},
|
| 347 |
+
"50295": {
|
| 348 |
+
"content": "[unused10]",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": true,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": false
|
| 354 |
+
},
|
| 355 |
+
"50296": {
|
| 356 |
+
"content": "[unused11]",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": true,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": false
|
| 362 |
+
},
|
| 363 |
+
"50297": {
|
| 364 |
+
"content": "[unused12]",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": true,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": false
|
| 370 |
+
},
|
| 371 |
+
"50298": {
|
| 372 |
+
"content": "[unused13]",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": true,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": false
|
| 378 |
+
},
|
| 379 |
+
"50299": {
|
| 380 |
+
"content": "[unused14]",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": true,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": false
|
| 386 |
+
},
|
| 387 |
+
"50300": {
|
| 388 |
+
"content": "[unused15]",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": true,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": false
|
| 394 |
+
},
|
| 395 |
+
"50301": {
|
| 396 |
+
"content": "[unused16]",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": true,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": false
|
| 402 |
+
},
|
| 403 |
+
"50302": {
|
| 404 |
+
"content": "[unused17]",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": true,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": false
|
| 410 |
+
},
|
| 411 |
+
"50303": {
|
| 412 |
+
"content": "[unused18]",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": true,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": false
|
| 418 |
+
},
|
| 419 |
+
"50304": {
|
| 420 |
+
"content": "[unused19]",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": true,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": false
|
| 426 |
+
},
|
| 427 |
+
"50305": {
|
| 428 |
+
"content": "[unused20]",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": true,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": false
|
| 434 |
+
},
|
| 435 |
+
"50306": {
|
| 436 |
+
"content": "[unused21]",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": true,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": false
|
| 442 |
+
},
|
| 443 |
+
"50307": {
|
| 444 |
+
"content": "[unused22]",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": true,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": false
|
| 450 |
+
},
|
| 451 |
+
"50308": {
|
| 452 |
+
"content": "[unused23]",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": true,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": false
|
| 458 |
+
},
|
| 459 |
+
"50309": {
|
| 460 |
+
"content": "[unused24]",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": true,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": false
|
| 466 |
+
},
|
| 467 |
+
"50310": {
|
| 468 |
+
"content": "[unused25]",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": true,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": false
|
| 474 |
+
},
|
| 475 |
+
"50311": {
|
| 476 |
+
"content": "[unused26]",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": true,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": false
|
| 482 |
+
},
|
| 483 |
+
"50312": {
|
| 484 |
+
"content": "[unused27]",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": true,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": false
|
| 490 |
+
},
|
| 491 |
+
"50313": {
|
| 492 |
+
"content": "[unused28]",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": true,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": false
|
| 498 |
+
},
|
| 499 |
+
"50314": {
|
| 500 |
+
"content": "[unused29]",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": true,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": false
|
| 506 |
+
},
|
| 507 |
+
"50315": {
|
| 508 |
+
"content": "[unused30]",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": true,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": false
|
| 514 |
+
},
|
| 515 |
+
"50316": {
|
| 516 |
+
"content": "[unused31]",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": true,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": false
|
| 522 |
+
},
|
| 523 |
+
"50317": {
|
| 524 |
+
"content": "[unused32]",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": true,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": false
|
| 530 |
+
},
|
| 531 |
+
"50318": {
|
| 532 |
+
"content": "[unused33]",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": true,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": false
|
| 538 |
+
},
|
| 539 |
+
"50319": {
|
| 540 |
+
"content": "[unused34]",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": true,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": false
|
| 546 |
+
},
|
| 547 |
+
"50320": {
|
| 548 |
+
"content": "[unused35]",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": true,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": false
|
| 554 |
+
},
|
| 555 |
+
"50321": {
|
| 556 |
+
"content": "[unused36]",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": true,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": false
|
| 562 |
+
},
|
| 563 |
+
"50322": {
|
| 564 |
+
"content": "[unused37]",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": true,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": false
|
| 570 |
+
},
|
| 571 |
+
"50323": {
|
| 572 |
+
"content": "[unused38]",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": true,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": false
|
| 578 |
+
},
|
| 579 |
+
"50324": {
|
| 580 |
+
"content": "[unused39]",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": true,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": false
|
| 586 |
+
},
|
| 587 |
+
"50325": {
|
| 588 |
+
"content": "[unused40]",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": true,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": false
|
| 594 |
+
},
|
| 595 |
+
"50326": {
|
| 596 |
+
"content": "[unused41]",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": true,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": false
|
| 602 |
+
},
|
| 603 |
+
"50327": {
|
| 604 |
+
"content": "[unused42]",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": true,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": false
|
| 610 |
+
},
|
| 611 |
+
"50328": {
|
| 612 |
+
"content": "[unused43]",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": true,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": false
|
| 618 |
+
},
|
| 619 |
+
"50329": {
|
| 620 |
+
"content": "[unused44]",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": true,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": false
|
| 626 |
+
},
|
| 627 |
+
"50330": {
|
| 628 |
+
"content": "[unused45]",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": true,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": false
|
| 634 |
+
},
|
| 635 |
+
"50331": {
|
| 636 |
+
"content": "[unused46]",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": true,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": false
|
| 642 |
+
},
|
| 643 |
+
"50332": {
|
| 644 |
+
"content": "[unused47]",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": true,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": false
|
| 650 |
+
},
|
| 651 |
+
"50333": {
|
| 652 |
+
"content": "[unused48]",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": true,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": false
|
| 658 |
+
},
|
| 659 |
+
"50334": {
|
| 660 |
+
"content": "[unused49]",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": true,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": false
|
| 666 |
+
},
|
| 667 |
+
"50335": {
|
| 668 |
+
"content": "[unused50]",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": true,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": false
|
| 674 |
+
},
|
| 675 |
+
"50336": {
|
| 676 |
+
"content": "[unused51]",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": true,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": false
|
| 682 |
+
},
|
| 683 |
+
"50337": {
|
| 684 |
+
"content": "[unused52]",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": true,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": false
|
| 690 |
+
},
|
| 691 |
+
"50338": {
|
| 692 |
+
"content": "[unused53]",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": true,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": false
|
| 698 |
+
},
|
| 699 |
+
"50339": {
|
| 700 |
+
"content": "[unused54]",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": true,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": false
|
| 706 |
+
},
|
| 707 |
+
"50340": {
|
| 708 |
+
"content": "[unused55]",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": true,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": false
|
| 714 |
+
},
|
| 715 |
+
"50341": {
|
| 716 |
+
"content": "[unused56]",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": true,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": false
|
| 722 |
+
},
|
| 723 |
+
"50342": {
|
| 724 |
+
"content": "[unused57]",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": true,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": false
|
| 730 |
+
},
|
| 731 |
+
"50343": {
|
| 732 |
+
"content": "[unused58]",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": true,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": false
|
| 738 |
+
},
|
| 739 |
+
"50344": {
|
| 740 |
+
"content": "[unused59]",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": true,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": false
|
| 746 |
+
},
|
| 747 |
+
"50345": {
|
| 748 |
+
"content": "[unused60]",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": true,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": false
|
| 754 |
+
},
|
| 755 |
+
"50346": {
|
| 756 |
+
"content": "[unused61]",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": true,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": false
|
| 762 |
+
},
|
| 763 |
+
"50347": {
|
| 764 |
+
"content": "[unused62]",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": true,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": false
|
| 770 |
+
},
|
| 771 |
+
"50348": {
|
| 772 |
+
"content": "[unused63]",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": true,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": false
|
| 778 |
+
},
|
| 779 |
+
"50349": {
|
| 780 |
+
"content": "[unused64]",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": true,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": false
|
| 786 |
+
},
|
| 787 |
+
"50350": {
|
| 788 |
+
"content": "[unused65]",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": true,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": false
|
| 794 |
+
},
|
| 795 |
+
"50351": {
|
| 796 |
+
"content": "[unused66]",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": true,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": false
|
| 802 |
+
},
|
| 803 |
+
"50352": {
|
| 804 |
+
"content": "[unused67]",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": true,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": false
|
| 810 |
+
},
|
| 811 |
+
"50353": {
|
| 812 |
+
"content": "[unused68]",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": true,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": false
|
| 818 |
+
},
|
| 819 |
+
"50354": {
|
| 820 |
+
"content": "[unused69]",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": true,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": false
|
| 826 |
+
},
|
| 827 |
+
"50355": {
|
| 828 |
+
"content": "[unused70]",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": true,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": false
|
| 834 |
+
},
|
| 835 |
+
"50356": {
|
| 836 |
+
"content": "[unused71]",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": true,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": false
|
| 842 |
+
},
|
| 843 |
+
"50357": {
|
| 844 |
+
"content": "[unused72]",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": true,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": false
|
| 850 |
+
},
|
| 851 |
+
"50358": {
|
| 852 |
+
"content": "[unused73]",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": true,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": false
|
| 858 |
+
},
|
| 859 |
+
"50359": {
|
| 860 |
+
"content": "[unused74]",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": true,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": false
|
| 866 |
+
},
|
| 867 |
+
"50360": {
|
| 868 |
+
"content": "[unused75]",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": true,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": false
|
| 874 |
+
},
|
| 875 |
+
"50361": {
|
| 876 |
+
"content": "[unused76]",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": true,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": false
|
| 882 |
+
},
|
| 883 |
+
"50362": {
|
| 884 |
+
"content": "[unused77]",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": true,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": false
|
| 890 |
+
},
|
| 891 |
+
"50363": {
|
| 892 |
+
"content": "[unused78]",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": true,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": false
|
| 898 |
+
},
|
| 899 |
+
"50364": {
|
| 900 |
+
"content": "[unused79]",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": true,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": false
|
| 906 |
+
},
|
| 907 |
+
"50365": {
|
| 908 |
+
"content": "[unused80]",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": true,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": false
|
| 914 |
+
},
|
| 915 |
+
"50366": {
|
| 916 |
+
"content": "[unused81]",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": true,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": false
|
| 922 |
+
},
|
| 923 |
+
"50367": {
|
| 924 |
+
"content": "[unused82]",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": true,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": false
|
| 930 |
+
}
|
| 931 |
+
},
|
| 932 |
+
"clean_up_tokenization_spaces": true,
|
| 933 |
+
"cls_token": "[CLS]",
|
| 934 |
+
"extra_special_tokens": {},
|
| 935 |
+
"mask_token": "[MASK]",
|
| 936 |
+
"model_input_names": [
|
| 937 |
+
"input_ids",
|
| 938 |
+
"attention_mask"
|
| 939 |
+
],
|
| 940 |
+
"model_max_length": 8192,
|
| 941 |
+
"pad_token": "[PAD]",
|
| 942 |
+
"sep_token": "[SEP]",
|
| 943 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 944 |
+
"unk_token": "[UNK]"
|
| 945 |
+
}
|
checkpoint-10255/trainer_state.json
ADDED
|
@@ -0,0 +1,1148 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 4.997563352826511,
|
| 6 |
+
"eval_steps": 205,
|
| 7 |
+
"global_step": 10255,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.04873294346978557,
|
| 14 |
+
"grad_norm": 0.26171875,
|
| 15 |
+
"learning_rate": 4.95e-06,
|
| 16 |
+
"loss": 0.1116,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.09746588693957114,
|
| 21 |
+
"grad_norm": 0.09375,
|
| 22 |
+
"learning_rate": 4.987909135319981e-06,
|
| 23 |
+
"loss": 0.0355,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.09990253411306042,
|
| 28 |
+
"eval_loss": 0.019339486956596375,
|
| 29 |
+
"eval_runtime": 95.318,
|
| 30 |
+
"eval_samples_per_second": 37.821,
|
| 31 |
+
"eval_steps_per_second": 2.371,
|
| 32 |
+
"step": 205
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.14619883040935672,
|
| 36 |
+
"grad_norm": 0.0703125,
|
| 37 |
+
"learning_rate": 4.9756961406936984e-06,
|
| 38 |
+
"loss": 0.0281,
|
| 39 |
+
"step": 300
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.1949317738791423,
|
| 43 |
+
"grad_norm": 0.06982421875,
|
| 44 |
+
"learning_rate": 4.963483146067416e-06,
|
| 45 |
+
"loss": 0.0272,
|
| 46 |
+
"step": 400
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.19980506822612085,
|
| 50 |
+
"eval_loss": 0.015745563432574272,
|
| 51 |
+
"eval_runtime": 81.1163,
|
| 52 |
+
"eval_samples_per_second": 44.442,
|
| 53 |
+
"eval_steps_per_second": 2.786,
|
| 54 |
+
"step": 410
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.24366471734892786,
|
| 58 |
+
"grad_norm": 0.048828125,
|
| 59 |
+
"learning_rate": 4.951270151441134e-06,
|
| 60 |
+
"loss": 0.0258,
|
| 61 |
+
"step": 500
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.29239766081871343,
|
| 65 |
+
"grad_norm": 0.0400390625,
|
| 66 |
+
"learning_rate": 4.9390571568148515e-06,
|
| 67 |
+
"loss": 0.025,
|
| 68 |
+
"step": 600
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.2997076023391813,
|
| 72 |
+
"eval_loss": 0.013976933434605598,
|
| 73 |
+
"eval_runtime": 81.0948,
|
| 74 |
+
"eval_samples_per_second": 44.454,
|
| 75 |
+
"eval_steps_per_second": 2.787,
|
| 76 |
+
"step": 615
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.341130604288499,
|
| 80 |
+
"grad_norm": 0.052001953125,
|
| 81 |
+
"learning_rate": 4.926844162188569e-06,
|
| 82 |
+
"loss": 0.0246,
|
| 83 |
+
"step": 700
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.3898635477582846,
|
| 87 |
+
"grad_norm": 0.033935546875,
|
| 88 |
+
"learning_rate": 4.914631167562286e-06,
|
| 89 |
+
"loss": 0.0242,
|
| 90 |
+
"step": 800
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.3996101364522417,
|
| 94 |
+
"eval_loss": 0.013302326202392578,
|
| 95 |
+
"eval_runtime": 81.138,
|
| 96 |
+
"eval_samples_per_second": 44.43,
|
| 97 |
+
"eval_steps_per_second": 2.785,
|
| 98 |
+
"step": 820
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.43859649122807015,
|
| 102 |
+
"grad_norm": 0.041015625,
|
| 103 |
+
"learning_rate": 4.9024181729360046e-06,
|
| 104 |
+
"loss": 0.0239,
|
| 105 |
+
"step": 900
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.4873294346978557,
|
| 109 |
+
"grad_norm": 0.051513671875,
|
| 110 |
+
"learning_rate": 4.890205178309722e-06,
|
| 111 |
+
"loss": 0.0238,
|
| 112 |
+
"step": 1000
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.49951267056530213,
|
| 116 |
+
"eval_loss": 0.01298708189278841,
|
| 117 |
+
"eval_runtime": 81.1054,
|
| 118 |
+
"eval_samples_per_second": 44.448,
|
| 119 |
+
"eval_steps_per_second": 2.786,
|
| 120 |
+
"step": 1025
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.5360623781676414,
|
| 124 |
+
"grad_norm": 0.0556640625,
|
| 125 |
+
"learning_rate": 4.87799218368344e-06,
|
| 126 |
+
"loss": 0.0237,
|
| 127 |
+
"step": 1100
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.5847953216374269,
|
| 131 |
+
"grad_norm": 0.04248046875,
|
| 132 |
+
"learning_rate": 4.865779189057157e-06,
|
| 133 |
+
"loss": 0.0237,
|
| 134 |
+
"step": 1200
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.5994152046783626,
|
| 138 |
+
"eval_loss": 0.012813900597393513,
|
| 139 |
+
"eval_runtime": 81.1253,
|
| 140 |
+
"eval_samples_per_second": 44.437,
|
| 141 |
+
"eval_steps_per_second": 2.786,
|
| 142 |
+
"step": 1230
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.6335282651072125,
|
| 146 |
+
"grad_norm": 0.03662109375,
|
| 147 |
+
"learning_rate": 4.853566194430875e-06,
|
| 148 |
+
"loss": 0.0235,
|
| 149 |
+
"step": 1300
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.682261208576998,
|
| 153 |
+
"grad_norm": 0.04150390625,
|
| 154 |
+
"learning_rate": 4.8413531998045925e-06,
|
| 155 |
+
"loss": 0.0234,
|
| 156 |
+
"step": 1400
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.699317738791423,
|
| 160 |
+
"eval_loss": 0.012716173194348812,
|
| 161 |
+
"eval_runtime": 81.0419,
|
| 162 |
+
"eval_samples_per_second": 44.483,
|
| 163 |
+
"eval_steps_per_second": 2.789,
|
| 164 |
+
"step": 1435
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.7309941520467836,
|
| 168 |
+
"grad_norm": 0.03125,
|
| 169 |
+
"learning_rate": 4.829140205178311e-06,
|
| 170 |
+
"loss": 0.0235,
|
| 171 |
+
"step": 1500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.7797270955165692,
|
| 175 |
+
"grad_norm": 0.061767578125,
|
| 176 |
+
"learning_rate": 4.816927210552027e-06,
|
| 177 |
+
"loss": 0.0233,
|
| 178 |
+
"step": 1600
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.7992202729044834,
|
| 182 |
+
"eval_loss": 0.012624112889170647,
|
| 183 |
+
"eval_runtime": 81.1166,
|
| 184 |
+
"eval_samples_per_second": 44.442,
|
| 185 |
+
"eval_steps_per_second": 2.786,
|
| 186 |
+
"step": 1640
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.8284600389863548,
|
| 190 |
+
"grad_norm": 0.037109375,
|
| 191 |
+
"learning_rate": 4.8047142159257455e-06,
|
| 192 |
+
"loss": 0.0234,
|
| 193 |
+
"step": 1700
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.8771929824561403,
|
| 197 |
+
"grad_norm": 0.04833984375,
|
| 198 |
+
"learning_rate": 4.792501221299463e-06,
|
| 199 |
+
"loss": 0.0235,
|
| 200 |
+
"step": 1800
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.8991228070175439,
|
| 204 |
+
"eval_loss": 0.01258858386427164,
|
| 205 |
+
"eval_runtime": 81.2202,
|
| 206 |
+
"eval_samples_per_second": 44.386,
|
| 207 |
+
"eval_steps_per_second": 2.783,
|
| 208 |
+
"step": 1845
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.9259259259259259,
|
| 212 |
+
"grad_norm": 0.03125,
|
| 213 |
+
"learning_rate": 4.780288226673181e-06,
|
| 214 |
+
"loss": 0.0232,
|
| 215 |
+
"step": 1900
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.9746588693957114,
|
| 219 |
+
"grad_norm": 0.050048828125,
|
| 220 |
+
"learning_rate": 4.768075232046898e-06,
|
| 221 |
+
"loss": 0.0234,
|
| 222 |
+
"step": 2000
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.9990253411306043,
|
| 226 |
+
"eval_loss": 0.012545167468488216,
|
| 227 |
+
"eval_runtime": 81.0849,
|
| 228 |
+
"eval_samples_per_second": 44.46,
|
| 229 |
+
"eval_steps_per_second": 2.787,
|
| 230 |
+
"step": 2050
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.023391812865497,
|
| 234 |
+
"grad_norm": 0.037109375,
|
| 235 |
+
"learning_rate": 4.755862237420616e-06,
|
| 236 |
+
"loss": 0.0231,
|
| 237 |
+
"step": 2100
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.0721247563352827,
|
| 241 |
+
"grad_norm": 0.0341796875,
|
| 242 |
+
"learning_rate": 4.743649242794333e-06,
|
| 243 |
+
"loss": 0.0232,
|
| 244 |
+
"step": 2200
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.0989278752436646,
|
| 248 |
+
"eval_loss": 0.012512513436377048,
|
| 249 |
+
"eval_runtime": 81.1634,
|
| 250 |
+
"eval_samples_per_second": 44.417,
|
| 251 |
+
"eval_steps_per_second": 2.785,
|
| 252 |
+
"step": 2255
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.120857699805068,
|
| 256 |
+
"grad_norm": 0.041259765625,
|
| 257 |
+
"learning_rate": 4.731436248168051e-06,
|
| 258 |
+
"loss": 0.0233,
|
| 259 |
+
"step": 2300
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 1.1695906432748537,
|
| 263 |
+
"grad_norm": 0.037841796875,
|
| 264 |
+
"learning_rate": 4.719223253541769e-06,
|
| 265 |
+
"loss": 0.0233,
|
| 266 |
+
"step": 2400
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.198830409356725,
|
| 270 |
+
"eval_loss": 0.012475969269871712,
|
| 271 |
+
"eval_runtime": 81.1416,
|
| 272 |
+
"eval_samples_per_second": 44.429,
|
| 273 |
+
"eval_steps_per_second": 2.785,
|
| 274 |
+
"step": 2460
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.2183235867446394,
|
| 278 |
+
"grad_norm": 0.036376953125,
|
| 279 |
+
"learning_rate": 4.7070102589154865e-06,
|
| 280 |
+
"loss": 0.0232,
|
| 281 |
+
"step": 2500
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.267056530214425,
|
| 285 |
+
"grad_norm": 0.0400390625,
|
| 286 |
+
"learning_rate": 4.694797264289204e-06,
|
| 287 |
+
"loss": 0.0232,
|
| 288 |
+
"step": 2600
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.2987329434697856,
|
| 292 |
+
"eval_loss": 0.012460815720260143,
|
| 293 |
+
"eval_runtime": 81.1639,
|
| 294 |
+
"eval_samples_per_second": 44.416,
|
| 295 |
+
"eval_steps_per_second": 2.784,
|
| 296 |
+
"step": 2665
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.3157894736842106,
|
| 300 |
+
"grad_norm": 0.03466796875,
|
| 301 |
+
"learning_rate": 4.682584269662921e-06,
|
| 302 |
+
"loss": 0.0231,
|
| 303 |
+
"step": 2700
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.364522417153996,
|
| 307 |
+
"grad_norm": 0.031494140625,
|
| 308 |
+
"learning_rate": 4.6703712750366396e-06,
|
| 309 |
+
"loss": 0.0231,
|
| 310 |
+
"step": 2800
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.398635477582846,
|
| 314 |
+
"eval_loss": 0.01243742648512125,
|
| 315 |
+
"eval_runtime": 81.1291,
|
| 316 |
+
"eval_samples_per_second": 44.435,
|
| 317 |
+
"eval_steps_per_second": 2.786,
|
| 318 |
+
"step": 2870
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.4132553606237817,
|
| 322 |
+
"grad_norm": 0.0284423828125,
|
| 323 |
+
"learning_rate": 4.658158280410357e-06,
|
| 324 |
+
"loss": 0.0234,
|
| 325 |
+
"step": 2900
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.4619883040935673,
|
| 329 |
+
"grad_norm": 0.055419921875,
|
| 330 |
+
"learning_rate": 4.645945285784074e-06,
|
| 331 |
+
"loss": 0.0233,
|
| 332 |
+
"step": 3000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.4985380116959064,
|
| 336 |
+
"eval_loss": 0.012422734871506691,
|
| 337 |
+
"eval_runtime": 81.155,
|
| 338 |
+
"eval_samples_per_second": 44.421,
|
| 339 |
+
"eval_steps_per_second": 2.785,
|
| 340 |
+
"step": 3075
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 1.5107212475633527,
|
| 344 |
+
"grad_norm": 0.03515625,
|
| 345 |
+
"learning_rate": 4.633732291157792e-06,
|
| 346 |
+
"loss": 0.0233,
|
| 347 |
+
"step": 3100
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 1.5594541910331383,
|
| 351 |
+
"grad_norm": 0.044189453125,
|
| 352 |
+
"learning_rate": 4.62151929653151e-06,
|
| 353 |
+
"loss": 0.0232,
|
| 354 |
+
"step": 3200
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.598440545808967,
|
| 358 |
+
"eval_loss": 0.01240704208612442,
|
| 359 |
+
"eval_runtime": 81.1397,
|
| 360 |
+
"eval_samples_per_second": 44.43,
|
| 361 |
+
"eval_steps_per_second": 2.785,
|
| 362 |
+
"step": 3280
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 1.608187134502924,
|
| 366 |
+
"grad_norm": 0.035400390625,
|
| 367 |
+
"learning_rate": 4.6093063019052274e-06,
|
| 368 |
+
"loss": 0.0232,
|
| 369 |
+
"step": 3300
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.6569200779727096,
|
| 373 |
+
"grad_norm": 0.02685546875,
|
| 374 |
+
"learning_rate": 4.597093307278946e-06,
|
| 375 |
+
"loss": 0.0231,
|
| 376 |
+
"step": 3400
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 1.6983430799220272,
|
| 380 |
+
"eval_loss": 0.012407787144184113,
|
| 381 |
+
"eval_runtime": 81.0879,
|
| 382 |
+
"eval_samples_per_second": 44.458,
|
| 383 |
+
"eval_steps_per_second": 2.787,
|
| 384 |
+
"step": 3485
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.7056530214424952,
|
| 388 |
+
"grad_norm": 0.034912109375,
|
| 389 |
+
"learning_rate": 4.584880312652662e-06,
|
| 390 |
+
"loss": 0.023,
|
| 391 |
+
"step": 3500
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.7543859649122808,
|
| 395 |
+
"grad_norm": 0.0390625,
|
| 396 |
+
"learning_rate": 4.5726673180263805e-06,
|
| 397 |
+
"loss": 0.0233,
|
| 398 |
+
"step": 3600
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.7982456140350878,
|
| 402 |
+
"eval_loss": 0.012400415726006031,
|
| 403 |
+
"eval_runtime": 81.1229,
|
| 404 |
+
"eval_samples_per_second": 44.439,
|
| 405 |
+
"eval_steps_per_second": 2.786,
|
| 406 |
+
"step": 3690
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.8031189083820662,
|
| 410 |
+
"grad_norm": 0.03466796875,
|
| 411 |
+
"learning_rate": 4.560454323400098e-06,
|
| 412 |
+
"loss": 0.0232,
|
| 413 |
+
"step": 3700
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.8518518518518519,
|
| 417 |
+
"grad_norm": 0.035400390625,
|
| 418 |
+
"learning_rate": 4.548241328773816e-06,
|
| 419 |
+
"loss": 0.0233,
|
| 420 |
+
"step": 3800
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.8981481481481481,
|
| 424 |
+
"eval_loss": 0.01238940004259348,
|
| 425 |
+
"eval_runtime": 81.1598,
|
| 426 |
+
"eval_samples_per_second": 44.419,
|
| 427 |
+
"eval_steps_per_second": 2.785,
|
| 428 |
+
"step": 3895
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.9005847953216373,
|
| 432 |
+
"grad_norm": 0.041015625,
|
| 433 |
+
"learning_rate": 4.536028334147533e-06,
|
| 434 |
+
"loss": 0.0232,
|
| 435 |
+
"step": 3900
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 1.949317738791423,
|
| 439 |
+
"grad_norm": 0.0341796875,
|
| 440 |
+
"learning_rate": 4.523815339521251e-06,
|
| 441 |
+
"loss": 0.0231,
|
| 442 |
+
"step": 4000
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 1.9980506822612085,
|
| 446 |
+
"grad_norm": 0.048828125,
|
| 447 |
+
"learning_rate": 4.511602344894968e-06,
|
| 448 |
+
"loss": 0.0232,
|
| 449 |
+
"step": 4100
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.9980506822612085,
|
| 453 |
+
"eval_loss": 0.012369532138109207,
|
| 454 |
+
"eval_runtime": 81.1104,
|
| 455 |
+
"eval_samples_per_second": 44.446,
|
| 456 |
+
"eval_steps_per_second": 2.786,
|
| 457 |
+
"step": 4100
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 2.046783625730994,
|
| 461 |
+
"grad_norm": 0.0303955078125,
|
| 462 |
+
"learning_rate": 4.499389350268687e-06,
|
| 463 |
+
"loss": 0.0234,
|
| 464 |
+
"step": 4200
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.0955165692007798,
|
| 468 |
+
"grad_norm": 0.03759765625,
|
| 469 |
+
"learning_rate": 4.487176355642403e-06,
|
| 470 |
+
"loss": 0.0231,
|
| 471 |
+
"step": 4300
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.097953216374269,
|
| 475 |
+
"eval_loss": 0.012380041182041168,
|
| 476 |
+
"eval_runtime": 81.2893,
|
| 477 |
+
"eval_samples_per_second": 44.348,
|
| 478 |
+
"eval_steps_per_second": 2.78,
|
| 479 |
+
"step": 4305
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 2.1442495126705654,
|
| 483 |
+
"grad_norm": 0.033447265625,
|
| 484 |
+
"learning_rate": 4.4749633610161215e-06,
|
| 485 |
+
"loss": 0.0232,
|
| 486 |
+
"step": 4400
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 2.192982456140351,
|
| 490 |
+
"grad_norm": 0.03955078125,
|
| 491 |
+
"learning_rate": 4.462750366389839e-06,
|
| 492 |
+
"loss": 0.0231,
|
| 493 |
+
"step": 4500
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 2.1978557504873293,
|
| 497 |
+
"eval_loss": 0.012386424466967583,
|
| 498 |
+
"eval_runtime": 81.158,
|
| 499 |
+
"eval_samples_per_second": 44.42,
|
| 500 |
+
"eval_steps_per_second": 2.785,
|
| 501 |
+
"step": 4510
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.241715399610136,
|
| 505 |
+
"grad_norm": 0.044677734375,
|
| 506 |
+
"learning_rate": 4.450537371763557e-06,
|
| 507 |
+
"loss": 0.0231,
|
| 508 |
+
"step": 4600
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 2.290448343079922,
|
| 512 |
+
"grad_norm": 0.03466796875,
|
| 513 |
+
"learning_rate": 4.4383243771372746e-06,
|
| 514 |
+
"loss": 0.023,
|
| 515 |
+
"step": 4700
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 2.29775828460039,
|
| 519 |
+
"eval_loss": 0.01237535197287798,
|
| 520 |
+
"eval_runtime": 81.1146,
|
| 521 |
+
"eval_samples_per_second": 44.443,
|
| 522 |
+
"eval_steps_per_second": 2.786,
|
| 523 |
+
"step": 4715
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 2.3391812865497075,
|
| 527 |
+
"grad_norm": 0.043701171875,
|
| 528 |
+
"learning_rate": 4.426111382510992e-06,
|
| 529 |
+
"loss": 0.0231,
|
| 530 |
+
"step": 4800
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 2.387914230019493,
|
| 534 |
+
"grad_norm": 0.031982421875,
|
| 535 |
+
"learning_rate": 4.413898387884709e-06,
|
| 536 |
+
"loss": 0.0231,
|
| 537 |
+
"step": 4900
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 2.39766081871345,
|
| 541 |
+
"eval_loss": 0.012380600906908512,
|
| 542 |
+
"eval_runtime": 81.1686,
|
| 543 |
+
"eval_samples_per_second": 44.414,
|
| 544 |
+
"eval_steps_per_second": 2.784,
|
| 545 |
+
"step": 4920
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 2.4366471734892787,
|
| 549 |
+
"grad_norm": 0.0286865234375,
|
| 550 |
+
"learning_rate": 4.401685393258428e-06,
|
| 551 |
+
"loss": 0.0233,
|
| 552 |
+
"step": 5000
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 2.4853801169590644,
|
| 556 |
+
"grad_norm": 0.034423828125,
|
| 557 |
+
"learning_rate": 4.389472398632145e-06,
|
| 558 |
+
"loss": 0.0232,
|
| 559 |
+
"step": 5100
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 2.4975633528265107,
|
| 563 |
+
"eval_loss": 0.012365665286779404,
|
| 564 |
+
"eval_runtime": 81.0999,
|
| 565 |
+
"eval_samples_per_second": 44.451,
|
| 566 |
+
"eval_steps_per_second": 2.787,
|
| 567 |
+
"step": 5125
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 2.53411306042885,
|
| 571 |
+
"grad_norm": 0.0267333984375,
|
| 572 |
+
"learning_rate": 4.3772594040058624e-06,
|
| 573 |
+
"loss": 0.0232,
|
| 574 |
+
"step": 5200
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 2.5828460038986356,
|
| 578 |
+
"grad_norm": 0.043212890625,
|
| 579 |
+
"learning_rate": 4.36504640937958e-06,
|
| 580 |
+
"loss": 0.0231,
|
| 581 |
+
"step": 5300
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 2.5974658869395713,
|
| 585 |
+
"eval_loss": 0.01237800344824791,
|
| 586 |
+
"eval_runtime": 81.5556,
|
| 587 |
+
"eval_samples_per_second": 44.203,
|
| 588 |
+
"eval_steps_per_second": 2.771,
|
| 589 |
+
"step": 5330
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 2.6315789473684212,
|
| 593 |
+
"grad_norm": 0.043701171875,
|
| 594 |
+
"learning_rate": 4.352833414753298e-06,
|
| 595 |
+
"loss": 0.0232,
|
| 596 |
+
"step": 5400
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 2.6803118908382064,
|
| 600 |
+
"grad_norm": 0.033447265625,
|
| 601 |
+
"learning_rate": 4.3406204201270155e-06,
|
| 602 |
+
"loss": 0.0235,
|
| 603 |
+
"step": 5500
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 2.6973684210526314,
|
| 607 |
+
"eval_loss": 0.012383415363729,
|
| 608 |
+
"eval_runtime": 81.1943,
|
| 609 |
+
"eval_samples_per_second": 44.4,
|
| 610 |
+
"eval_steps_per_second": 2.783,
|
| 611 |
+
"step": 5535
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 2.729044834307992,
|
| 615 |
+
"grad_norm": 0.028076171875,
|
| 616 |
+
"learning_rate": 4.328407425500733e-06,
|
| 617 |
+
"loss": 0.0231,
|
| 618 |
+
"step": 5600
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 2.7777777777777777,
|
| 622 |
+
"grad_norm": 0.03271484375,
|
| 623 |
+
"learning_rate": 4.316194430874451e-06,
|
| 624 |
+
"loss": 0.0233,
|
| 625 |
+
"step": 5700
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 2.797270955165692,
|
| 629 |
+
"eval_loss": 0.012366292998194695,
|
| 630 |
+
"eval_runtime": 81.124,
|
| 631 |
+
"eval_samples_per_second": 44.438,
|
| 632 |
+
"eval_steps_per_second": 2.786,
|
| 633 |
+
"step": 5740
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 2.8265107212475633,
|
| 637 |
+
"grad_norm": 0.0380859375,
|
| 638 |
+
"learning_rate": 4.303981436248169e-06,
|
| 639 |
+
"loss": 0.0232,
|
| 640 |
+
"step": 5800
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 2.875243664717349,
|
| 644 |
+
"grad_norm": 0.0478515625,
|
| 645 |
+
"learning_rate": 4.291768441621886e-06,
|
| 646 |
+
"loss": 0.0232,
|
| 647 |
+
"step": 5900
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 2.897173489278752,
|
| 651 |
+
"eval_loss": 0.012359858490526676,
|
| 652 |
+
"eval_runtime": 81.2294,
|
| 653 |
+
"eval_samples_per_second": 44.381,
|
| 654 |
+
"eval_steps_per_second": 2.782,
|
| 655 |
+
"step": 5945
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.9239766081871346,
|
| 659 |
+
"grad_norm": 0.0279541015625,
|
| 660 |
+
"learning_rate": 4.279555446995603e-06,
|
| 661 |
+
"loss": 0.0232,
|
| 662 |
+
"step": 6000
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.97270955165692,
|
| 666 |
+
"grad_norm": 0.028076171875,
|
| 667 |
+
"learning_rate": 4.267342452369322e-06,
|
| 668 |
+
"loss": 0.0232,
|
| 669 |
+
"step": 6100
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.997076023391813,
|
| 673 |
+
"eval_loss": 0.012368520721793175,
|
| 674 |
+
"eval_runtime": 81.2163,
|
| 675 |
+
"eval_samples_per_second": 44.388,
|
| 676 |
+
"eval_steps_per_second": 2.783,
|
| 677 |
+
"step": 6150
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 3.021442495126706,
|
| 681 |
+
"grad_norm": 0.035400390625,
|
| 682 |
+
"learning_rate": 4.255129457743039e-06,
|
| 683 |
+
"loss": 0.0232,
|
| 684 |
+
"step": 6200
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 3.0701754385964914,
|
| 688 |
+
"grad_norm": 0.028076171875,
|
| 689 |
+
"learning_rate": 4.2429164631167565e-06,
|
| 690 |
+
"loss": 0.0232,
|
| 691 |
+
"step": 6300
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 3.0969785575048734,
|
| 695 |
+
"eval_loss": 0.012371581047773361,
|
| 696 |
+
"eval_runtime": 81.6571,
|
| 697 |
+
"eval_samples_per_second": 44.148,
|
| 698 |
+
"eval_steps_per_second": 2.768,
|
| 699 |
+
"step": 6355
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 3.1189083820662766,
|
| 703 |
+
"grad_norm": 0.0322265625,
|
| 704 |
+
"learning_rate": 4.230703468490474e-06,
|
| 705 |
+
"loss": 0.0231,
|
| 706 |
+
"step": 6400
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 3.1676413255360623,
|
| 710 |
+
"grad_norm": 0.043701171875,
|
| 711 |
+
"learning_rate": 4.218490473864192e-06,
|
| 712 |
+
"loss": 0.0231,
|
| 713 |
+
"step": 6500
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 3.1968810916179335,
|
| 717 |
+
"eval_loss": 0.012365739792585373,
|
| 718 |
+
"eval_runtime": 81.8373,
|
| 719 |
+
"eval_samples_per_second": 44.051,
|
| 720 |
+
"eval_steps_per_second": 2.762,
|
| 721 |
+
"step": 6560
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 3.216374269005848,
|
| 725 |
+
"grad_norm": 0.028564453125,
|
| 726 |
+
"learning_rate": 4.2062774792379095e-06,
|
| 727 |
+
"loss": 0.0233,
|
| 728 |
+
"step": 6600
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 3.2651072124756335,
|
| 732 |
+
"grad_norm": 0.036376953125,
|
| 733 |
+
"learning_rate": 4.194064484611627e-06,
|
| 734 |
+
"loss": 0.0233,
|
| 735 |
+
"step": 6700
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 3.296783625730994,
|
| 739 |
+
"eval_loss": 0.012359827756881714,
|
| 740 |
+
"eval_runtime": 81.746,
|
| 741 |
+
"eval_samples_per_second": 44.1,
|
| 742 |
+
"eval_steps_per_second": 2.765,
|
| 743 |
+
"step": 6765
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 3.313840155945419,
|
| 747 |
+
"grad_norm": 0.0299072265625,
|
| 748 |
+
"learning_rate": 4.181851489985344e-06,
|
| 749 |
+
"loss": 0.0231,
|
| 750 |
+
"step": 6800
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 3.3625730994152048,
|
| 754 |
+
"grad_norm": 0.036376953125,
|
| 755 |
+
"learning_rate": 4.169638495359063e-06,
|
| 756 |
+
"loss": 0.0231,
|
| 757 |
+
"step": 6900
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 3.3966861598440548,
|
| 761 |
+
"eval_loss": 0.012360342778265476,
|
| 762 |
+
"eval_runtime": 81.0488,
|
| 763 |
+
"eval_samples_per_second": 44.479,
|
| 764 |
+
"eval_steps_per_second": 2.788,
|
| 765 |
+
"step": 6970
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 3.4113060428849904,
|
| 769 |
+
"grad_norm": 0.0400390625,
|
| 770 |
+
"learning_rate": 4.15742550073278e-06,
|
| 771 |
+
"loss": 0.0232,
|
| 772 |
+
"step": 7000
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 3.4600389863547756,
|
| 776 |
+
"grad_norm": 0.0400390625,
|
| 777 |
+
"learning_rate": 4.1452125061064974e-06,
|
| 778 |
+
"loss": 0.0231,
|
| 779 |
+
"step": 7100
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 3.496588693957115,
|
| 783 |
+
"eval_loss": 0.012353786267340183,
|
| 784 |
+
"eval_runtime": 81.1493,
|
| 785 |
+
"eval_samples_per_second": 44.424,
|
| 786 |
+
"eval_steps_per_second": 2.785,
|
| 787 |
+
"step": 7175
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 3.5087719298245617,
|
| 791 |
+
"grad_norm": 0.02978515625,
|
| 792 |
+
"learning_rate": 4.132999511480215e-06,
|
| 793 |
+
"loss": 0.0232,
|
| 794 |
+
"step": 7200
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 3.557504873294347,
|
| 798 |
+
"grad_norm": 0.041015625,
|
| 799 |
+
"learning_rate": 4.120786516853933e-06,
|
| 800 |
+
"loss": 0.0231,
|
| 801 |
+
"step": 7300
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 3.5964912280701755,
|
| 805 |
+
"eval_loss": 0.012348741292953491,
|
| 806 |
+
"eval_runtime": 81.3012,
|
| 807 |
+
"eval_samples_per_second": 44.341,
|
| 808 |
+
"eval_steps_per_second": 2.78,
|
| 809 |
+
"step": 7380
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 3.6062378167641325,
|
| 813 |
+
"grad_norm": 0.0341796875,
|
| 814 |
+
"learning_rate": 4.1085735222276505e-06,
|
| 815 |
+
"loss": 0.0232,
|
| 816 |
+
"step": 7400
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 3.654970760233918,
|
| 820 |
+
"grad_norm": 0.03076171875,
|
| 821 |
+
"learning_rate": 4.096360527601368e-06,
|
| 822 |
+
"loss": 0.0232,
|
| 823 |
+
"step": 7500
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 3.696393762183236,
|
| 827 |
+
"eval_loss": 0.01235182024538517,
|
| 828 |
+
"eval_runtime": 81.1456,
|
| 829 |
+
"eval_samples_per_second": 44.426,
|
| 830 |
+
"eval_steps_per_second": 2.785,
|
| 831 |
+
"step": 7585
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 3.7037037037037037,
|
| 835 |
+
"grad_norm": 0.035400390625,
|
| 836 |
+
"learning_rate": 4.084147532975085e-06,
|
| 837 |
+
"loss": 0.023,
|
| 838 |
+
"step": 7600
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 3.7524366471734893,
|
| 842 |
+
"grad_norm": 0.03271484375,
|
| 843 |
+
"learning_rate": 4.0719345383488036e-06,
|
| 844 |
+
"loss": 0.0231,
|
| 845 |
+
"step": 7700
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 3.7962962962962963,
|
| 849 |
+
"eval_loss": 0.012360481545329094,
|
| 850 |
+
"eval_runtime": 81.1205,
|
| 851 |
+
"eval_samples_per_second": 44.44,
|
| 852 |
+
"eval_steps_per_second": 2.786,
|
| 853 |
+
"step": 7790
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 3.801169590643275,
|
| 857 |
+
"grad_norm": 0.027099609375,
|
| 858 |
+
"learning_rate": 4.059721543722521e-06,
|
| 859 |
+
"loss": 0.0232,
|
| 860 |
+
"step": 7800
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 3.8499025341130606,
|
| 864 |
+
"grad_norm": 0.04736328125,
|
| 865 |
+
"learning_rate": 4.047508549096238e-06,
|
| 866 |
+
"loss": 0.0232,
|
| 867 |
+
"step": 7900
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 3.896198830409357,
|
| 871 |
+
"eval_loss": 0.01235805545002222,
|
| 872 |
+
"eval_runtime": 81.1366,
|
| 873 |
+
"eval_samples_per_second": 44.431,
|
| 874 |
+
"eval_steps_per_second": 2.785,
|
| 875 |
+
"step": 7995
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 3.898635477582846,
|
| 879 |
+
"grad_norm": 0.04443359375,
|
| 880 |
+
"learning_rate": 4.035295554469957e-06,
|
| 881 |
+
"loss": 0.0232,
|
| 882 |
+
"step": 8000
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 3.9473684210526314,
|
| 886 |
+
"grad_norm": 0.0306396484375,
|
| 887 |
+
"learning_rate": 4.023082559843674e-06,
|
| 888 |
+
"loss": 0.023,
|
| 889 |
+
"step": 8100
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 3.996101364522417,
|
| 893 |
+
"grad_norm": 0.0322265625,
|
| 894 |
+
"learning_rate": 4.0108695652173915e-06,
|
| 895 |
+
"loss": 0.0232,
|
| 896 |
+
"step": 8200
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 3.996101364522417,
|
| 900 |
+
"eval_loss": 0.012353403493762016,
|
| 901 |
+
"eval_runtime": 81.0778,
|
| 902 |
+
"eval_samples_per_second": 44.463,
|
| 903 |
+
"eval_steps_per_second": 2.787,
|
| 904 |
+
"step": 8200
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 4.044834307992203,
|
| 908 |
+
"grad_norm": 0.0250244140625,
|
| 909 |
+
"learning_rate": 3.998656570591109e-06,
|
| 910 |
+
"loss": 0.0231,
|
| 911 |
+
"step": 8300
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 4.093567251461988,
|
| 915 |
+
"grad_norm": 0.0625,
|
| 916 |
+
"learning_rate": 3.986443575964827e-06,
|
| 917 |
+
"loss": 0.0232,
|
| 918 |
+
"step": 8400
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 4.096003898635478,
|
| 922 |
+
"eval_loss": 0.012346148490905762,
|
| 923 |
+
"eval_runtime": 81.0994,
|
| 924 |
+
"eval_samples_per_second": 44.452,
|
| 925 |
+
"eval_steps_per_second": 2.787,
|
| 926 |
+
"step": 8405
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 4.1423001949317735,
|
| 930 |
+
"grad_norm": 0.05078125,
|
| 931 |
+
"learning_rate": 3.9742305813385445e-06,
|
| 932 |
+
"loss": 0.023,
|
| 933 |
+
"step": 8500
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 4.1910331384015596,
|
| 937 |
+
"grad_norm": 0.039306640625,
|
| 938 |
+
"learning_rate": 3.962017586712262e-06,
|
| 939 |
+
"loss": 0.023,
|
| 940 |
+
"step": 8600
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 4.195906432748538,
|
| 944 |
+
"eval_loss": 0.012355214916169643,
|
| 945 |
+
"eval_runtime": 81.0333,
|
| 946 |
+
"eval_samples_per_second": 44.488,
|
| 947 |
+
"eval_steps_per_second": 2.789,
|
| 948 |
+
"step": 8610
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 4.239766081871345,
|
| 952 |
+
"grad_norm": 0.02587890625,
|
| 953 |
+
"learning_rate": 3.949804592085979e-06,
|
| 954 |
+
"loss": 0.0232,
|
| 955 |
+
"step": 8700
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 4.288499025341131,
|
| 959 |
+
"grad_norm": 0.0255126953125,
|
| 960 |
+
"learning_rate": 3.937591597459698e-06,
|
| 961 |
+
"loss": 0.023,
|
| 962 |
+
"step": 8800
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 4.295808966861599,
|
| 966 |
+
"eval_loss": 0.012366610579192638,
|
| 967 |
+
"eval_runtime": 81.0656,
|
| 968 |
+
"eval_samples_per_second": 44.47,
|
| 969 |
+
"eval_steps_per_second": 2.788,
|
| 970 |
+
"step": 8815
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 4.337231968810916,
|
| 974 |
+
"grad_norm": 0.031982421875,
|
| 975 |
+
"learning_rate": 3.925378602833415e-06,
|
| 976 |
+
"loss": 0.0232,
|
| 977 |
+
"step": 8900
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 4.385964912280702,
|
| 981 |
+
"grad_norm": 0.03076171875,
|
| 982 |
+
"learning_rate": 3.913165608207133e-06,
|
| 983 |
+
"loss": 0.0232,
|
| 984 |
+
"step": 9000
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 4.395711500974659,
|
| 988 |
+
"eval_loss": 0.01235954463481903,
|
| 989 |
+
"eval_runtime": 81.1074,
|
| 990 |
+
"eval_samples_per_second": 44.447,
|
| 991 |
+
"eval_steps_per_second": 2.786,
|
| 992 |
+
"step": 9020
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 4.434697855750487,
|
| 996 |
+
"grad_norm": 0.053955078125,
|
| 997 |
+
"learning_rate": 3.90095261358085e-06,
|
| 998 |
+
"loss": 0.0232,
|
| 999 |
+
"step": 9100
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 4.483430799220272,
|
| 1003 |
+
"grad_norm": 0.046142578125,
|
| 1004 |
+
"learning_rate": 3.888739618954568e-06,
|
| 1005 |
+
"loss": 0.0233,
|
| 1006 |
+
"step": 9200
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 4.495614035087719,
|
| 1010 |
+
"eval_loss": 0.012365696020424366,
|
| 1011 |
+
"eval_runtime": 81.1262,
|
| 1012 |
+
"eval_samples_per_second": 44.437,
|
| 1013 |
+
"eval_steps_per_second": 2.786,
|
| 1014 |
+
"step": 9225
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 4.5321637426900585,
|
| 1018 |
+
"grad_norm": 0.025390625,
|
| 1019 |
+
"learning_rate": 3.8765266243282855e-06,
|
| 1020 |
+
"loss": 0.0232,
|
| 1021 |
+
"step": 9300
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 4.580896686159844,
|
| 1025 |
+
"grad_norm": 0.04833984375,
|
| 1026 |
+
"learning_rate": 3.864313629702004e-06,
|
| 1027 |
+
"loss": 0.0232,
|
| 1028 |
+
"step": 9400
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 4.59551656920078,
|
| 1032 |
+
"eval_loss": 0.012365074828267097,
|
| 1033 |
+
"eval_runtime": 81.0995,
|
| 1034 |
+
"eval_samples_per_second": 44.452,
|
| 1035 |
+
"eval_steps_per_second": 2.787,
|
| 1036 |
+
"step": 9430
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 4.62962962962963,
|
| 1040 |
+
"grad_norm": 0.025634765625,
|
| 1041 |
+
"learning_rate": 3.85210063507572e-06,
|
| 1042 |
+
"loss": 0.0233,
|
| 1043 |
+
"step": 9500
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 4.678362573099415,
|
| 1047 |
+
"grad_norm": 0.040283203125,
|
| 1048 |
+
"learning_rate": 3.8398876404494386e-06,
|
| 1049 |
+
"loss": 0.0231,
|
| 1050 |
+
"step": 9600
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 4.69541910331384,
|
| 1054 |
+
"eval_loss": 0.01237095519900322,
|
| 1055 |
+
"eval_runtime": 81.06,
|
| 1056 |
+
"eval_samples_per_second": 44.473,
|
| 1057 |
+
"eval_steps_per_second": 2.788,
|
| 1058 |
+
"step": 9635
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 4.727095516569201,
|
| 1062 |
+
"grad_norm": 0.042724609375,
|
| 1063 |
+
"learning_rate": 3.827674645823156e-06,
|
| 1064 |
+
"loss": 0.0231,
|
| 1065 |
+
"step": 9700
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 4.775828460038986,
|
| 1069 |
+
"grad_norm": 0.027587890625,
|
| 1070 |
+
"learning_rate": 3.815461651196874e-06,
|
| 1071 |
+
"loss": 0.0231,
|
| 1072 |
+
"step": 9800
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 4.7953216374269,
|
| 1076 |
+
"eval_loss": 0.012356248684227467,
|
| 1077 |
+
"eval_runtime": 81.1368,
|
| 1078 |
+
"eval_samples_per_second": 44.431,
|
| 1079 |
+
"eval_steps_per_second": 2.785,
|
| 1080 |
+
"step": 9840
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 4.824561403508772,
|
| 1084 |
+
"grad_norm": 0.031982421875,
|
| 1085 |
+
"learning_rate": 3.8032486565705912e-06,
|
| 1086 |
+
"loss": 0.0231,
|
| 1087 |
+
"step": 9900
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 4.8732943469785575,
|
| 1091 |
+
"grad_norm": 0.026123046875,
|
| 1092 |
+
"learning_rate": 3.791035661944309e-06,
|
| 1093 |
+
"loss": 0.0232,
|
| 1094 |
+
"step": 10000
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 4.895224171539961,
|
| 1098 |
+
"eval_loss": 0.012366380542516708,
|
| 1099 |
+
"eval_runtime": 81.1395,
|
| 1100 |
+
"eval_samples_per_second": 44.43,
|
| 1101 |
+
"eval_steps_per_second": 2.785,
|
| 1102 |
+
"step": 10045
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 4.922027290448343,
|
| 1106 |
+
"grad_norm": 0.04052734375,
|
| 1107 |
+
"learning_rate": 3.778822667318027e-06,
|
| 1108 |
+
"loss": 0.0233,
|
| 1109 |
+
"step": 10100
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 4.970760233918129,
|
| 1113 |
+
"grad_norm": 0.0419921875,
|
| 1114 |
+
"learning_rate": 3.7666096726917443e-06,
|
| 1115 |
+
"loss": 0.0233,
|
| 1116 |
+
"step": 10200
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 4.995126705653021,
|
| 1120 |
+
"eval_loss": 0.012368387542665005,
|
| 1121 |
+
"eval_runtime": 81.1592,
|
| 1122 |
+
"eval_samples_per_second": 44.419,
|
| 1123 |
+
"eval_steps_per_second": 2.785,
|
| 1124 |
+
"step": 10250
|
| 1125 |
+
}
|
| 1126 |
+
],
|
| 1127 |
+
"logging_steps": 100,
|
| 1128 |
+
"max_steps": 41040,
|
| 1129 |
+
"num_input_tokens_seen": 0,
|
| 1130 |
+
"num_train_epochs": 20,
|
| 1131 |
+
"save_steps": 2051,
|
| 1132 |
+
"stateful_callbacks": {
|
| 1133 |
+
"TrainerControl": {
|
| 1134 |
+
"args": {
|
| 1135 |
+
"should_epoch_stop": false,
|
| 1136 |
+
"should_evaluate": false,
|
| 1137 |
+
"should_log": false,
|
| 1138 |
+
"should_save": true,
|
| 1139 |
+
"should_training_stop": false
|
| 1140 |
+
},
|
| 1141 |
+
"attributes": {}
|
| 1142 |
+
}
|
| 1143 |
+
},
|
| 1144 |
+
"total_flos": 0.0,
|
| 1145 |
+
"train_batch_size": 2,
|
| 1146 |
+
"trial_name": null,
|
| 1147 |
+
"trial_params": null
|
| 1148 |
+
}
|
checkpoint-10255/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0838b83ef4e41e98ddc47dd3d383c5b7247db50a5d0ef4a531694e5e97147f9
|
| 3 |
+
size 5905
|