Training in progress, step 1500, checkpoint
Browse files- last-checkpoint/model.safetensors +3 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/special_tokens_map.json +37 -0
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/tokenizer_config.json +945 -0
- last-checkpoint/trainer_state.json +1323 -0
- last-checkpoint/training_args.bin +3 -0
last-checkpoint/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c4b3264d8426687f4b50168cdca6241441dfbc285a4c51940c82f0dd3b7d88c
|
| 3 |
+
size 735217848
|
last-checkpoint/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45522e2d95b727a7794c89784a8dbeb658a6e8d547dd1f60be95776967ef24f6
|
| 3 |
+
size 1470521978
|
last-checkpoint/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5672d4a2bab2f5ec1b202aa86f336deecf9ade33ecc3e9f1ae101d08c2403c85
|
| 3 |
+
size 14244
|
last-checkpoint/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dea0aba72f700814d776f8926ad184d76b3c510f754b334a94c0cd38ed47ebbb
|
| 3 |
+
size 1000
|
last-checkpoint/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 |
+
}
|
last-checkpoint/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last-checkpoint/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 |
+
"95580": {
|
| 268 |
+
"content": "[unused0]",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": true,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": false
|
| 274 |
+
},
|
| 275 |
+
"95581": {
|
| 276 |
+
"content": "[unused1]",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": true,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": false
|
| 282 |
+
},
|
| 283 |
+
"95582": {
|
| 284 |
+
"content": "[unused2]",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": true,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": false
|
| 290 |
+
},
|
| 291 |
+
"95583": {
|
| 292 |
+
"content": "[unused3]",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": true,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": false
|
| 298 |
+
},
|
| 299 |
+
"95584": {
|
| 300 |
+
"content": "[unused4]",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": true,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": false
|
| 306 |
+
},
|
| 307 |
+
"95585": {
|
| 308 |
+
"content": "[unused5]",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": true,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": false
|
| 314 |
+
},
|
| 315 |
+
"95586": {
|
| 316 |
+
"content": "[unused6]",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": true,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": false
|
| 322 |
+
},
|
| 323 |
+
"95587": {
|
| 324 |
+
"content": "[unused7]",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": true,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": false
|
| 330 |
+
},
|
| 331 |
+
"95588": {
|
| 332 |
+
"content": "[unused8]",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": true,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": false
|
| 338 |
+
},
|
| 339 |
+
"95589": {
|
| 340 |
+
"content": "[unused9]",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": true,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": false
|
| 346 |
+
},
|
| 347 |
+
"95590": {
|
| 348 |
+
"content": "[unused10]",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": true,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": false
|
| 354 |
+
},
|
| 355 |
+
"95591": {
|
| 356 |
+
"content": "[unused11]",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": true,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": false
|
| 362 |
+
},
|
| 363 |
+
"95592": {
|
| 364 |
+
"content": "[unused12]",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": true,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": false
|
| 370 |
+
},
|
| 371 |
+
"95593": {
|
| 372 |
+
"content": "[unused13]",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": true,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": false
|
| 378 |
+
},
|
| 379 |
+
"95594": {
|
| 380 |
+
"content": "[unused14]",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": true,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": false
|
| 386 |
+
},
|
| 387 |
+
"95595": {
|
| 388 |
+
"content": "[unused15]",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": true,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": false
|
| 394 |
+
},
|
| 395 |
+
"95596": {
|
| 396 |
+
"content": "[unused16]",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": true,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": false
|
| 402 |
+
},
|
| 403 |
+
"95597": {
|
| 404 |
+
"content": "[unused17]",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": true,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": false
|
| 410 |
+
},
|
| 411 |
+
"95598": {
|
| 412 |
+
"content": "[unused18]",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": true,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": false
|
| 418 |
+
},
|
| 419 |
+
"95599": {
|
| 420 |
+
"content": "[unused19]",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": true,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": false
|
| 426 |
+
},
|
| 427 |
+
"95600": {
|
| 428 |
+
"content": "[unused20]",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": true,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": false
|
| 434 |
+
},
|
| 435 |
+
"95601": {
|
| 436 |
+
"content": "[unused21]",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": true,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": false
|
| 442 |
+
},
|
| 443 |
+
"95602": {
|
| 444 |
+
"content": "[unused22]",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": true,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": false
|
| 450 |
+
},
|
| 451 |
+
"95603": {
|
| 452 |
+
"content": "[unused23]",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": true,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": false
|
| 458 |
+
},
|
| 459 |
+
"95604": {
|
| 460 |
+
"content": "[unused24]",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": true,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": false
|
| 466 |
+
},
|
| 467 |
+
"95605": {
|
| 468 |
+
"content": "[unused25]",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": true,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": false
|
| 474 |
+
},
|
| 475 |
+
"95606": {
|
| 476 |
+
"content": "[unused26]",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": true,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": false
|
| 482 |
+
},
|
| 483 |
+
"95607": {
|
| 484 |
+
"content": "[unused27]",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": true,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": false
|
| 490 |
+
},
|
| 491 |
+
"95608": {
|
| 492 |
+
"content": "[unused28]",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": true,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": false
|
| 498 |
+
},
|
| 499 |
+
"95609": {
|
| 500 |
+
"content": "[unused29]",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": true,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": false
|
| 506 |
+
},
|
| 507 |
+
"95610": {
|
| 508 |
+
"content": "[unused30]",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": true,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": false
|
| 514 |
+
},
|
| 515 |
+
"95611": {
|
| 516 |
+
"content": "[unused31]",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": true,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": false
|
| 522 |
+
},
|
| 523 |
+
"95612": {
|
| 524 |
+
"content": "[unused32]",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": true,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": false
|
| 530 |
+
},
|
| 531 |
+
"95613": {
|
| 532 |
+
"content": "[unused33]",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": true,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": false
|
| 538 |
+
},
|
| 539 |
+
"95614": {
|
| 540 |
+
"content": "[unused34]",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": true,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": false
|
| 546 |
+
},
|
| 547 |
+
"95615": {
|
| 548 |
+
"content": "[unused35]",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": true,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": false
|
| 554 |
+
},
|
| 555 |
+
"95616": {
|
| 556 |
+
"content": "[unused36]",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": true,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": false
|
| 562 |
+
},
|
| 563 |
+
"95617": {
|
| 564 |
+
"content": "[unused37]",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": true,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": false
|
| 570 |
+
},
|
| 571 |
+
"95618": {
|
| 572 |
+
"content": "[unused38]",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": true,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": false
|
| 578 |
+
},
|
| 579 |
+
"95619": {
|
| 580 |
+
"content": "[unused39]",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": true,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": false
|
| 586 |
+
},
|
| 587 |
+
"95620": {
|
| 588 |
+
"content": "[unused40]",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": true,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": false
|
| 594 |
+
},
|
| 595 |
+
"95621": {
|
| 596 |
+
"content": "[unused41]",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": true,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": false
|
| 602 |
+
},
|
| 603 |
+
"95622": {
|
| 604 |
+
"content": "[unused42]",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": true,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": false
|
| 610 |
+
},
|
| 611 |
+
"95623": {
|
| 612 |
+
"content": "[unused43]",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": true,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": false
|
| 618 |
+
},
|
| 619 |
+
"95624": {
|
| 620 |
+
"content": "[unused44]",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": true,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": false
|
| 626 |
+
},
|
| 627 |
+
"95625": {
|
| 628 |
+
"content": "[unused45]",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": true,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": false
|
| 634 |
+
},
|
| 635 |
+
"95626": {
|
| 636 |
+
"content": "[unused46]",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": true,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": false
|
| 642 |
+
},
|
| 643 |
+
"95627": {
|
| 644 |
+
"content": "[unused47]",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": true,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": false
|
| 650 |
+
},
|
| 651 |
+
"95628": {
|
| 652 |
+
"content": "[unused48]",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": true,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": false
|
| 658 |
+
},
|
| 659 |
+
"95629": {
|
| 660 |
+
"content": "[unused49]",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": true,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": false
|
| 666 |
+
},
|
| 667 |
+
"95630": {
|
| 668 |
+
"content": "[unused50]",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": true,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": false
|
| 674 |
+
},
|
| 675 |
+
"95631": {
|
| 676 |
+
"content": "[unused51]",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": true,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": false
|
| 682 |
+
},
|
| 683 |
+
"95632": {
|
| 684 |
+
"content": "[unused52]",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": true,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": false
|
| 690 |
+
},
|
| 691 |
+
"95633": {
|
| 692 |
+
"content": "[unused53]",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": true,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": false
|
| 698 |
+
},
|
| 699 |
+
"95634": {
|
| 700 |
+
"content": "[unused54]",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": true,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": false
|
| 706 |
+
},
|
| 707 |
+
"95635": {
|
| 708 |
+
"content": "[unused55]",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": true,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": false
|
| 714 |
+
},
|
| 715 |
+
"95636": {
|
| 716 |
+
"content": "[unused56]",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": true,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": false
|
| 722 |
+
},
|
| 723 |
+
"95637": {
|
| 724 |
+
"content": "[unused57]",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": true,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": false
|
| 730 |
+
},
|
| 731 |
+
"95638": {
|
| 732 |
+
"content": "[unused58]",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": true,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": false
|
| 738 |
+
},
|
| 739 |
+
"95639": {
|
| 740 |
+
"content": "[unused59]",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": true,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": false
|
| 746 |
+
},
|
| 747 |
+
"95640": {
|
| 748 |
+
"content": "[unused60]",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": true,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": false
|
| 754 |
+
},
|
| 755 |
+
"95641": {
|
| 756 |
+
"content": "[unused61]",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": true,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": false
|
| 762 |
+
},
|
| 763 |
+
"95642": {
|
| 764 |
+
"content": "[unused62]",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": true,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": false
|
| 770 |
+
},
|
| 771 |
+
"95643": {
|
| 772 |
+
"content": "[unused63]",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": true,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": false
|
| 778 |
+
},
|
| 779 |
+
"95644": {
|
| 780 |
+
"content": "[unused64]",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": true,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": false
|
| 786 |
+
},
|
| 787 |
+
"95645": {
|
| 788 |
+
"content": "[unused65]",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": true,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": false
|
| 794 |
+
},
|
| 795 |
+
"95646": {
|
| 796 |
+
"content": "[unused66]",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": true,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": false
|
| 802 |
+
},
|
| 803 |
+
"95647": {
|
| 804 |
+
"content": "[unused67]",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": true,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": false
|
| 810 |
+
},
|
| 811 |
+
"95648": {
|
| 812 |
+
"content": "[unused68]",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": true,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": false
|
| 818 |
+
},
|
| 819 |
+
"95649": {
|
| 820 |
+
"content": "[unused69]",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": true,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": false
|
| 826 |
+
},
|
| 827 |
+
"95650": {
|
| 828 |
+
"content": "[unused70]",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": true,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": false
|
| 834 |
+
},
|
| 835 |
+
"95651": {
|
| 836 |
+
"content": "[unused71]",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": true,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": false
|
| 842 |
+
},
|
| 843 |
+
"95652": {
|
| 844 |
+
"content": "[unused72]",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": true,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": false
|
| 850 |
+
},
|
| 851 |
+
"95653": {
|
| 852 |
+
"content": "[unused73]",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": true,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": false
|
| 858 |
+
},
|
| 859 |
+
"95654": {
|
| 860 |
+
"content": "[unused74]",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": true,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": false
|
| 866 |
+
},
|
| 867 |
+
"95655": {
|
| 868 |
+
"content": "[unused75]",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": true,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": false
|
| 874 |
+
},
|
| 875 |
+
"95656": {
|
| 876 |
+
"content": "[unused76]",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": true,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": false
|
| 882 |
+
},
|
| 883 |
+
"95657": {
|
| 884 |
+
"content": "[unused77]",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": true,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": false
|
| 890 |
+
},
|
| 891 |
+
"95658": {
|
| 892 |
+
"content": "[unused78]",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": true,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": false
|
| 898 |
+
},
|
| 899 |
+
"95659": {
|
| 900 |
+
"content": "[unused79]",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": true,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": false
|
| 906 |
+
},
|
| 907 |
+
"95660": {
|
| 908 |
+
"content": "[unused80]",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": true,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": false
|
| 914 |
+
},
|
| 915 |
+
"95661": {
|
| 916 |
+
"content": "[unused81]",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": true,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": false
|
| 922 |
+
},
|
| 923 |
+
"95662": {
|
| 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": 1000000000000000019884624838656,
|
| 941 |
+
"pad_token": "[PAD]",
|
| 942 |
+
"sep_token": "[SEP]",
|
| 943 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 944 |
+
"unk_token": "[UNK]"
|
| 945 |
+
}
|
last-checkpoint/trainer_state.json
ADDED
|
@@ -0,0 +1,1323 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.7029053420805998,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 1500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.004686035613870665,
|
| 13 |
+
"grad_norm": 30.10508155822754,
|
| 14 |
+
"learning_rate": 9.994142455482662e-05,
|
| 15 |
+
"loss": 3.8567,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.00937207122774133,
|
| 20 |
+
"grad_norm": 8.754369735717773,
|
| 21 |
+
"learning_rate": 9.988284910965324e-05,
|
| 22 |
+
"loss": 1.8518,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.014058106841611996,
|
| 27 |
+
"grad_norm": 6.94720458984375,
|
| 28 |
+
"learning_rate": 9.982427366447986e-05,
|
| 29 |
+
"loss": 1.0621,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.01874414245548266,
|
| 34 |
+
"grad_norm": 7.401930809020996,
|
| 35 |
+
"learning_rate": 9.976569821930647e-05,
|
| 36 |
+
"loss": 0.8079,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.023430178069353328,
|
| 41 |
+
"grad_norm": 4.625001430511475,
|
| 42 |
+
"learning_rate": 9.970712277413309e-05,
|
| 43 |
+
"loss": 0.7732,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.028116213683223992,
|
| 48 |
+
"grad_norm": 5.161655426025391,
|
| 49 |
+
"learning_rate": 9.964854732895971e-05,
|
| 50 |
+
"loss": 0.6538,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03280224929709466,
|
| 55 |
+
"grad_norm": 4.755752086639404,
|
| 56 |
+
"learning_rate": 9.958997188378632e-05,
|
| 57 |
+
"loss": 0.5888,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.03748828491096532,
|
| 62 |
+
"grad_norm": 5.150806903839111,
|
| 63 |
+
"learning_rate": 9.953139643861293e-05,
|
| 64 |
+
"loss": 0.6152,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.04217432052483599,
|
| 69 |
+
"grad_norm": 4.075490951538086,
|
| 70 |
+
"learning_rate": 9.947282099343956e-05,
|
| 71 |
+
"loss": 0.5545,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.046860356138706656,
|
| 76 |
+
"grad_norm": 4.118444442749023,
|
| 77 |
+
"learning_rate": 9.941424554826618e-05,
|
| 78 |
+
"loss": 0.6139,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.046860356138706656,
|
| 83 |
+
"eval_loss": 0.08172167092561722,
|
| 84 |
+
"eval_pearson_cosine": 0.7774916057538377,
|
| 85 |
+
"eval_pearson_dot": 0.7673975678531928,
|
| 86 |
+
"eval_pearson_euclidean": 0.7739600680365157,
|
| 87 |
+
"eval_pearson_manhattan": 0.7732699847297653,
|
| 88 |
+
"eval_runtime": 4.6785,
|
| 89 |
+
"eval_samples_per_second": 320.614,
|
| 90 |
+
"eval_spearman_cosine": 0.7788712392049503,
|
| 91 |
+
"eval_spearman_dot": 0.7662758145209008,
|
| 92 |
+
"eval_spearman_euclidean": 0.779851450790825,
|
| 93 |
+
"eval_spearman_manhattan": 0.7790465578192005,
|
| 94 |
+
"eval_steps_per_second": 20.092,
|
| 95 |
+
"step": 100
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.05154639175257732,
|
| 99 |
+
"grad_norm": 4.516867160797119,
|
| 100 |
+
"learning_rate": 9.935567010309279e-05,
|
| 101 |
+
"loss": 0.5911,
|
| 102 |
+
"step": 110
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.056232427366447985,
|
| 106 |
+
"grad_norm": 3.0860955715179443,
|
| 107 |
+
"learning_rate": 9.929709465791941e-05,
|
| 108 |
+
"loss": 0.5118,
|
| 109 |
+
"step": 120
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.06091846298031865,
|
| 113 |
+
"grad_norm": 4.2761616706848145,
|
| 114 |
+
"learning_rate": 9.923851921274601e-05,
|
| 115 |
+
"loss": 0.5347,
|
| 116 |
+
"step": 130
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.06560449859418932,
|
| 120 |
+
"grad_norm": 3.3774375915527344,
|
| 121 |
+
"learning_rate": 9.917994376757263e-05,
|
| 122 |
+
"loss": 0.516,
|
| 123 |
+
"step": 140
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.07029053420805999,
|
| 127 |
+
"grad_norm": 3.043034315109253,
|
| 128 |
+
"learning_rate": 9.912136832239926e-05,
|
| 129 |
+
"loss": 0.5583,
|
| 130 |
+
"step": 150
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.07497656982193064,
|
| 134 |
+
"grad_norm": 3.3026859760284424,
|
| 135 |
+
"learning_rate": 9.906279287722588e-05,
|
| 136 |
+
"loss": 0.5691,
|
| 137 |
+
"step": 160
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.07966260543580131,
|
| 141 |
+
"grad_norm": 3.694498062133789,
|
| 142 |
+
"learning_rate": 9.90042174320525e-05,
|
| 143 |
+
"loss": 0.5126,
|
| 144 |
+
"step": 170
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.08434864104967198,
|
| 148 |
+
"grad_norm": 2.7696762084960938,
|
| 149 |
+
"learning_rate": 9.89456419868791e-05,
|
| 150 |
+
"loss": 0.4945,
|
| 151 |
+
"step": 180
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.08903467666354264,
|
| 155 |
+
"grad_norm": 2.7977497577667236,
|
| 156 |
+
"learning_rate": 9.888706654170572e-05,
|
| 157 |
+
"loss": 0.5133,
|
| 158 |
+
"step": 190
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.09372071227741331,
|
| 162 |
+
"grad_norm": 4.13506555557251,
|
| 163 |
+
"learning_rate": 9.882849109653233e-05,
|
| 164 |
+
"loss": 0.4496,
|
| 165 |
+
"step": 200
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.09372071227741331,
|
| 169 |
+
"eval_loss": 0.06149223446846008,
|
| 170 |
+
"eval_pearson_cosine": 0.7878806911951841,
|
| 171 |
+
"eval_pearson_dot": 0.7892236854270749,
|
| 172 |
+
"eval_pearson_euclidean": 0.7815123592368103,
|
| 173 |
+
"eval_pearson_manhattan": 0.7802018326188076,
|
| 174 |
+
"eval_runtime": 4.629,
|
| 175 |
+
"eval_samples_per_second": 324.041,
|
| 176 |
+
"eval_spearman_cosine": 0.7881602244285756,
|
| 177 |
+
"eval_spearman_dot": 0.7890157817002775,
|
| 178 |
+
"eval_spearman_euclidean": 0.7853020907543472,
|
| 179 |
+
"eval_spearman_manhattan": 0.7841560791576906,
|
| 180 |
+
"eval_steps_per_second": 20.307,
|
| 181 |
+
"step": 200
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.09840674789128398,
|
| 185 |
+
"grad_norm": 3.0135467052459717,
|
| 186 |
+
"learning_rate": 9.876991565135896e-05,
|
| 187 |
+
"loss": 0.5474,
|
| 188 |
+
"step": 210
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.10309278350515463,
|
| 192 |
+
"grad_norm": 2.703244924545288,
|
| 193 |
+
"learning_rate": 9.871134020618558e-05,
|
| 194 |
+
"loss": 0.4499,
|
| 195 |
+
"step": 220
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.1077788191190253,
|
| 199 |
+
"grad_norm": 3.320786714553833,
|
| 200 |
+
"learning_rate": 9.865276476101218e-05,
|
| 201 |
+
"loss": 0.5042,
|
| 202 |
+
"step": 230
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.11246485473289597,
|
| 206 |
+
"grad_norm": 3.642885684967041,
|
| 207 |
+
"learning_rate": 9.85941893158388e-05,
|
| 208 |
+
"loss": 0.4496,
|
| 209 |
+
"step": 240
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.11715089034676664,
|
| 213 |
+
"grad_norm": 2.59848952293396,
|
| 214 |
+
"learning_rate": 9.853561387066542e-05,
|
| 215 |
+
"loss": 0.467,
|
| 216 |
+
"step": 250
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.1218369259606373,
|
| 220 |
+
"grad_norm": 2.8087403774261475,
|
| 221 |
+
"learning_rate": 9.847703842549204e-05,
|
| 222 |
+
"loss": 0.4818,
|
| 223 |
+
"step": 260
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.12652296157450796,
|
| 227 |
+
"grad_norm": 3.655815362930298,
|
| 228 |
+
"learning_rate": 9.841846298031867e-05,
|
| 229 |
+
"loss": 0.4195,
|
| 230 |
+
"step": 270
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.13120899718837864,
|
| 234 |
+
"grad_norm": 2.4474446773529053,
|
| 235 |
+
"learning_rate": 9.835988753514527e-05,
|
| 236 |
+
"loss": 0.4295,
|
| 237 |
+
"step": 280
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.1358950328022493,
|
| 241 |
+
"grad_norm": 4.437081336975098,
|
| 242 |
+
"learning_rate": 9.830131208997189e-05,
|
| 243 |
+
"loss": 0.4783,
|
| 244 |
+
"step": 290
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.14058106841611998,
|
| 248 |
+
"grad_norm": 2.853497266769409,
|
| 249 |
+
"learning_rate": 9.82427366447985e-05,
|
| 250 |
+
"loss": 0.445,
|
| 251 |
+
"step": 300
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.14058106841611998,
|
| 255 |
+
"eval_loss": 0.06087055429816246,
|
| 256 |
+
"eval_pearson_cosine": 0.8085847462809284,
|
| 257 |
+
"eval_pearson_dot": 0.8099837052074292,
|
| 258 |
+
"eval_pearson_euclidean": 0.797235616826157,
|
| 259 |
+
"eval_pearson_manhattan": 0.796084644837677,
|
| 260 |
+
"eval_runtime": 4.8442,
|
| 261 |
+
"eval_samples_per_second": 309.65,
|
| 262 |
+
"eval_spearman_cosine": 0.8087098487869666,
|
| 263 |
+
"eval_spearman_dot": 0.8088350013000529,
|
| 264 |
+
"eval_spearman_euclidean": 0.8038077082663364,
|
| 265 |
+
"eval_spearman_manhattan": 0.8027157437095755,
|
| 266 |
+
"eval_steps_per_second": 19.405,
|
| 267 |
+
"step": 300
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.14526710402999063,
|
| 271 |
+
"grad_norm": 3.850320339202881,
|
| 272 |
+
"learning_rate": 9.818416119962512e-05,
|
| 273 |
+
"loss": 0.4192,
|
| 274 |
+
"step": 310
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.14995313964386128,
|
| 278 |
+
"grad_norm": 3.8749234676361084,
|
| 279 |
+
"learning_rate": 9.812558575445174e-05,
|
| 280 |
+
"loss": 0.4282,
|
| 281 |
+
"step": 320
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.15463917525773196,
|
| 285 |
+
"grad_norm": 2.7373576164245605,
|
| 286 |
+
"learning_rate": 9.806701030927836e-05,
|
| 287 |
+
"loss": 0.5132,
|
| 288 |
+
"step": 330
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.15932521087160262,
|
| 292 |
+
"grad_norm": 2.587904691696167,
|
| 293 |
+
"learning_rate": 9.800843486410497e-05,
|
| 294 |
+
"loss": 0.4452,
|
| 295 |
+
"step": 340
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.1640112464854733,
|
| 299 |
+
"grad_norm": 2.770646333694458,
|
| 300 |
+
"learning_rate": 9.794985941893159e-05,
|
| 301 |
+
"loss": 0.5072,
|
| 302 |
+
"step": 350
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.16869728209934395,
|
| 306 |
+
"grad_norm": 3.2103078365325928,
|
| 307 |
+
"learning_rate": 9.78912839737582e-05,
|
| 308 |
+
"loss": 0.4488,
|
| 309 |
+
"step": 360
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.1733833177132146,
|
| 313 |
+
"grad_norm": 2.8420042991638184,
|
| 314 |
+
"learning_rate": 9.783270852858482e-05,
|
| 315 |
+
"loss": 0.4132,
|
| 316 |
+
"step": 370
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.1780693533270853,
|
| 320 |
+
"grad_norm": 2.8594541549682617,
|
| 321 |
+
"learning_rate": 9.777413308341144e-05,
|
| 322 |
+
"loss": 0.4217,
|
| 323 |
+
"step": 380
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 0.18275538894095594,
|
| 327 |
+
"grad_norm": 2.6843366622924805,
|
| 328 |
+
"learning_rate": 9.771555763823806e-05,
|
| 329 |
+
"loss": 0.423,
|
| 330 |
+
"step": 390
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.18744142455482662,
|
| 334 |
+
"grad_norm": 2.808396339416504,
|
| 335 |
+
"learning_rate": 9.765698219306467e-05,
|
| 336 |
+
"loss": 0.4398,
|
| 337 |
+
"step": 400
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.18744142455482662,
|
| 341 |
+
"eval_loss": 0.06297692656517029,
|
| 342 |
+
"eval_pearson_cosine": 0.7991067883059557,
|
| 343 |
+
"eval_pearson_dot": 0.8028010593184547,
|
| 344 |
+
"eval_pearson_euclidean": 0.7880801281434806,
|
| 345 |
+
"eval_pearson_manhattan": 0.7862328250693538,
|
| 346 |
+
"eval_runtime": 5.1278,
|
| 347 |
+
"eval_samples_per_second": 292.522,
|
| 348 |
+
"eval_spearman_cosine": 0.8008051119507676,
|
| 349 |
+
"eval_spearman_dot": 0.8028962103300248,
|
| 350 |
+
"eval_spearman_euclidean": 0.7941679469832046,
|
| 351 |
+
"eval_spearman_manhattan": 0.7922002625333209,
|
| 352 |
+
"eval_steps_per_second": 18.331,
|
| 353 |
+
"step": 400
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.19212746016869728,
|
| 357 |
+
"grad_norm": 3.4171650409698486,
|
| 358 |
+
"learning_rate": 9.759840674789129e-05,
|
| 359 |
+
"loss": 0.472,
|
| 360 |
+
"step": 410
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.19681349578256796,
|
| 364 |
+
"grad_norm": 2.304884433746338,
|
| 365 |
+
"learning_rate": 9.753983130271791e-05,
|
| 366 |
+
"loss": 0.4269,
|
| 367 |
+
"step": 420
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.2014995313964386,
|
| 371 |
+
"grad_norm": 3.582045793533325,
|
| 372 |
+
"learning_rate": 9.748125585754451e-05,
|
| 373 |
+
"loss": 0.4709,
|
| 374 |
+
"step": 430
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.20618556701030927,
|
| 378 |
+
"grad_norm": 2.555410623550415,
|
| 379 |
+
"learning_rate": 9.742268041237114e-05,
|
| 380 |
+
"loss": 0.428,
|
| 381 |
+
"step": 440
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.21087160262417995,
|
| 385 |
+
"grad_norm": 3.291259288787842,
|
| 386 |
+
"learning_rate": 9.736410496719776e-05,
|
| 387 |
+
"loss": 0.3884,
|
| 388 |
+
"step": 450
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.2155576382380506,
|
| 392 |
+
"grad_norm": 2.4803812503814697,
|
| 393 |
+
"learning_rate": 9.730552952202438e-05,
|
| 394 |
+
"loss": 0.4434,
|
| 395 |
+
"step": 460
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.22024367385192128,
|
| 399 |
+
"grad_norm": 2.9194233417510986,
|
| 400 |
+
"learning_rate": 9.7246954076851e-05,
|
| 401 |
+
"loss": 0.3969,
|
| 402 |
+
"step": 470
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.22492970946579194,
|
| 406 |
+
"grad_norm": 2.5176608562469482,
|
| 407 |
+
"learning_rate": 9.71883786316776e-05,
|
| 408 |
+
"loss": 0.3668,
|
| 409 |
+
"step": 480
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.2296157450796626,
|
| 413 |
+
"grad_norm": 3.111013412475586,
|
| 414 |
+
"learning_rate": 9.712980318650421e-05,
|
| 415 |
+
"loss": 0.4047,
|
| 416 |
+
"step": 490
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.23430178069353327,
|
| 420 |
+
"grad_norm": 2.3099541664123535,
|
| 421 |
+
"learning_rate": 9.707122774133085e-05,
|
| 422 |
+
"loss": 0.4509,
|
| 423 |
+
"step": 500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.23430178069353327,
|
| 427 |
+
"eval_loss": 0.06479576230049133,
|
| 428 |
+
"eval_pearson_cosine": 0.7937691374860236,
|
| 429 |
+
"eval_pearson_dot": 0.8037986869849263,
|
| 430 |
+
"eval_pearson_euclidean": 0.7796252574393066,
|
| 431 |
+
"eval_pearson_manhattan": 0.7788957424132832,
|
| 432 |
+
"eval_runtime": 5.1806,
|
| 433 |
+
"eval_samples_per_second": 289.541,
|
| 434 |
+
"eval_spearman_cosine": 0.7968672368227576,
|
| 435 |
+
"eval_spearman_dot": 0.8062882580483537,
|
| 436 |
+
"eval_spearman_euclidean": 0.785478492768414,
|
| 437 |
+
"eval_spearman_manhattan": 0.7846800638460941,
|
| 438 |
+
"eval_steps_per_second": 18.145,
|
| 439 |
+
"step": 500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.23898781630740393,
|
| 443 |
+
"grad_norm": 2.587941884994507,
|
| 444 |
+
"learning_rate": 9.701265229615746e-05,
|
| 445 |
+
"loss": 0.4402,
|
| 446 |
+
"step": 510
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.2436738519212746,
|
| 450 |
+
"grad_norm": 2.8946237564086914,
|
| 451 |
+
"learning_rate": 9.695407685098408e-05,
|
| 452 |
+
"loss": 0.4303,
|
| 453 |
+
"step": 520
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.24835988753514526,
|
| 457 |
+
"grad_norm": 2.144695997238159,
|
| 458 |
+
"learning_rate": 9.689550140581068e-05,
|
| 459 |
+
"loss": 0.3955,
|
| 460 |
+
"step": 530
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.2530459231490159,
|
| 464 |
+
"grad_norm": 2.310426712036133,
|
| 465 |
+
"learning_rate": 9.68369259606373e-05,
|
| 466 |
+
"loss": 0.4027,
|
| 467 |
+
"step": 540
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.25773195876288657,
|
| 471 |
+
"grad_norm": 1.9948300123214722,
|
| 472 |
+
"learning_rate": 9.677835051546392e-05,
|
| 473 |
+
"loss": 0.3806,
|
| 474 |
+
"step": 550
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.2624179943767573,
|
| 478 |
+
"grad_norm": 2.4448132514953613,
|
| 479 |
+
"learning_rate": 9.671977507029055e-05,
|
| 480 |
+
"loss": 0.3917,
|
| 481 |
+
"step": 560
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.26710402999062793,
|
| 485 |
+
"grad_norm": 2.1171720027923584,
|
| 486 |
+
"learning_rate": 9.666119962511717e-05,
|
| 487 |
+
"loss": 0.4086,
|
| 488 |
+
"step": 570
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.2717900656044986,
|
| 492 |
+
"grad_norm": 3.1124324798583984,
|
| 493 |
+
"learning_rate": 9.660262417994377e-05,
|
| 494 |
+
"loss": 0.3754,
|
| 495 |
+
"step": 580
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.27647610121836924,
|
| 499 |
+
"grad_norm": 2.3518879413604736,
|
| 500 |
+
"learning_rate": 9.654404873477039e-05,
|
| 501 |
+
"loss": 0.4155,
|
| 502 |
+
"step": 590
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.28116213683223995,
|
| 506 |
+
"grad_norm": 2.3229143619537354,
|
| 507 |
+
"learning_rate": 9.6485473289597e-05,
|
| 508 |
+
"loss": 0.3899,
|
| 509 |
+
"step": 600
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.28116213683223995,
|
| 513 |
+
"eval_loss": 0.05898291990160942,
|
| 514 |
+
"eval_pearson_cosine": 0.8002203582671399,
|
| 515 |
+
"eval_pearson_dot": 0.8059872147596572,
|
| 516 |
+
"eval_pearson_euclidean": 0.7924462958823995,
|
| 517 |
+
"eval_pearson_manhattan": 0.7914827034937701,
|
| 518 |
+
"eval_runtime": 4.8482,
|
| 519 |
+
"eval_samples_per_second": 309.39,
|
| 520 |
+
"eval_spearman_cosine": 0.8056451862347204,
|
| 521 |
+
"eval_spearman_dot": 0.8090541661182976,
|
| 522 |
+
"eval_spearman_euclidean": 0.797456379085547,
|
| 523 |
+
"eval_spearman_manhattan": 0.796591059583954,
|
| 524 |
+
"eval_steps_per_second": 19.388,
|
| 525 |
+
"step": 600
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.2858481724461106,
|
| 529 |
+
"grad_norm": 2.2351458072662354,
|
| 530 |
+
"learning_rate": 9.642689784442362e-05,
|
| 531 |
+
"loss": 0.4096,
|
| 532 |
+
"step": 610
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.29053420805998126,
|
| 536 |
+
"grad_norm": 2.529383420944214,
|
| 537 |
+
"learning_rate": 9.636832239925024e-05,
|
| 538 |
+
"loss": 0.4094,
|
| 539 |
+
"step": 620
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.2952202436738519,
|
| 543 |
+
"grad_norm": 2.727684736251831,
|
| 544 |
+
"learning_rate": 9.630974695407685e-05,
|
| 545 |
+
"loss": 0.4017,
|
| 546 |
+
"step": 630
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.29990627928772257,
|
| 550 |
+
"grad_norm": 2.1631858348846436,
|
| 551 |
+
"learning_rate": 9.625117150890347e-05,
|
| 552 |
+
"loss": 0.3829,
|
| 553 |
+
"step": 640
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.3045923149015933,
|
| 557 |
+
"grad_norm": 2.08465838432312,
|
| 558 |
+
"learning_rate": 9.619259606373009e-05,
|
| 559 |
+
"loss": 0.3593,
|
| 560 |
+
"step": 650
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.30927835051546393,
|
| 564 |
+
"grad_norm": 2.7151734828948975,
|
| 565 |
+
"learning_rate": 9.61340206185567e-05,
|
| 566 |
+
"loss": 0.3575,
|
| 567 |
+
"step": 660
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.3139643861293346,
|
| 571 |
+
"grad_norm": 2.9916470050811768,
|
| 572 |
+
"learning_rate": 9.607544517338332e-05,
|
| 573 |
+
"loss": 0.4043,
|
| 574 |
+
"step": 670
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 0.31865042174320524,
|
| 578 |
+
"grad_norm": 2.2090351581573486,
|
| 579 |
+
"learning_rate": 9.601686972820994e-05,
|
| 580 |
+
"loss": 0.3969,
|
| 581 |
+
"step": 680
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 0.3233364573570759,
|
| 585 |
+
"grad_norm": 2.5505614280700684,
|
| 586 |
+
"learning_rate": 9.595829428303656e-05,
|
| 587 |
+
"loss": 0.4162,
|
| 588 |
+
"step": 690
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 0.3280224929709466,
|
| 592 |
+
"grad_norm": 1.9354357719421387,
|
| 593 |
+
"learning_rate": 9.589971883786317e-05,
|
| 594 |
+
"loss": 0.3944,
|
| 595 |
+
"step": 700
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 0.3280224929709466,
|
| 599 |
+
"eval_loss": 0.06544993817806244,
|
| 600 |
+
"eval_pearson_cosine": 0.7849690888771903,
|
| 601 |
+
"eval_pearson_dot": 0.7906563077972777,
|
| 602 |
+
"eval_pearson_euclidean": 0.7744169020961635,
|
| 603 |
+
"eval_pearson_manhattan": 0.773555246133725,
|
| 604 |
+
"eval_runtime": 4.7217,
|
| 605 |
+
"eval_samples_per_second": 317.682,
|
| 606 |
+
"eval_spearman_cosine": 0.7912145091954246,
|
| 607 |
+
"eval_spearman_dot": 0.795880260533099,
|
| 608 |
+
"eval_spearman_euclidean": 0.7788547557160983,
|
| 609 |
+
"eval_spearman_manhattan": 0.7778138343707646,
|
| 610 |
+
"eval_steps_per_second": 19.908,
|
| 611 |
+
"step": 700
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.33270852858481725,
|
| 615 |
+
"grad_norm": 2.754939317703247,
|
| 616 |
+
"learning_rate": 9.584114339268979e-05,
|
| 617 |
+
"loss": 0.3421,
|
| 618 |
+
"step": 710
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.3373945641986879,
|
| 622 |
+
"grad_norm": 2.395989418029785,
|
| 623 |
+
"learning_rate": 9.578256794751641e-05,
|
| 624 |
+
"loss": 0.4181,
|
| 625 |
+
"step": 720
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.34208059981255856,
|
| 629 |
+
"grad_norm": 1.9646469354629517,
|
| 630 |
+
"learning_rate": 9.572399250234303e-05,
|
| 631 |
+
"loss": 0.3604,
|
| 632 |
+
"step": 730
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.3467666354264292,
|
| 636 |
+
"grad_norm": 1.77524995803833,
|
| 637 |
+
"learning_rate": 9.566541705716964e-05,
|
| 638 |
+
"loss": 0.4152,
|
| 639 |
+
"step": 740
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.3514526710402999,
|
| 643 |
+
"grad_norm": 2.225848913192749,
|
| 644 |
+
"learning_rate": 9.560684161199626e-05,
|
| 645 |
+
"loss": 0.3582,
|
| 646 |
+
"step": 750
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.3561387066541706,
|
| 650 |
+
"grad_norm": 2.9699714183807373,
|
| 651 |
+
"learning_rate": 9.554826616682288e-05,
|
| 652 |
+
"loss": 0.3498,
|
| 653 |
+
"step": 760
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.36082474226804123,
|
| 657 |
+
"grad_norm": 2.2419025897979736,
|
| 658 |
+
"learning_rate": 9.54896907216495e-05,
|
| 659 |
+
"loss": 0.4014,
|
| 660 |
+
"step": 770
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.3655107778819119,
|
| 664 |
+
"grad_norm": 2.090801954269409,
|
| 665 |
+
"learning_rate": 9.54311152764761e-05,
|
| 666 |
+
"loss": 0.3788,
|
| 667 |
+
"step": 780
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.3701968134957826,
|
| 671 |
+
"grad_norm": 2.0521080493927,
|
| 672 |
+
"learning_rate": 9.537253983130271e-05,
|
| 673 |
+
"loss": 0.3381,
|
| 674 |
+
"step": 790
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.37488284910965325,
|
| 678 |
+
"grad_norm": 2.189819574356079,
|
| 679 |
+
"learning_rate": 9.531396438612934e-05,
|
| 680 |
+
"loss": 0.3866,
|
| 681 |
+
"step": 800
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.37488284910965325,
|
| 685 |
+
"eval_loss": 0.057871297001838684,
|
| 686 |
+
"eval_pearson_cosine": 0.8000694370275774,
|
| 687 |
+
"eval_pearson_dot": 0.808069225934787,
|
| 688 |
+
"eval_pearson_euclidean": 0.7859619382036129,
|
| 689 |
+
"eval_pearson_manhattan": 0.7850475265092101,
|
| 690 |
+
"eval_runtime": 4.9109,
|
| 691 |
+
"eval_samples_per_second": 305.445,
|
| 692 |
+
"eval_spearman_cosine": 0.802358950496682,
|
| 693 |
+
"eval_spearman_dot": 0.8096070418813107,
|
| 694 |
+
"eval_spearman_euclidean": 0.7916939807330186,
|
| 695 |
+
"eval_spearman_manhattan": 0.7908012039061529,
|
| 696 |
+
"eval_steps_per_second": 19.141,
|
| 697 |
+
"step": 800
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.3795688847235239,
|
| 701 |
+
"grad_norm": 2.161396026611328,
|
| 702 |
+
"learning_rate": 9.525538894095596e-05,
|
| 703 |
+
"loss": 0.411,
|
| 704 |
+
"step": 810
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.38425492033739456,
|
| 708 |
+
"grad_norm": 2.709839344024658,
|
| 709 |
+
"learning_rate": 9.519681349578258e-05,
|
| 710 |
+
"loss": 0.379,
|
| 711 |
+
"step": 820
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.3889409559512652,
|
| 715 |
+
"grad_norm": 2.1237142086029053,
|
| 716 |
+
"learning_rate": 9.513823805060918e-05,
|
| 717 |
+
"loss": 0.3333,
|
| 718 |
+
"step": 830
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.3936269915651359,
|
| 722 |
+
"grad_norm": 2.088275194168091,
|
| 723 |
+
"learning_rate": 9.50796626054358e-05,
|
| 724 |
+
"loss": 0.4006,
|
| 725 |
+
"step": 840
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.3983130271790066,
|
| 729 |
+
"grad_norm": 2.1435964107513428,
|
| 730 |
+
"learning_rate": 9.502108716026242e-05,
|
| 731 |
+
"loss": 0.3328,
|
| 732 |
+
"step": 850
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.4029990627928772,
|
| 736 |
+
"grad_norm": 2.671003580093384,
|
| 737 |
+
"learning_rate": 9.496251171508905e-05,
|
| 738 |
+
"loss": 0.3751,
|
| 739 |
+
"step": 860
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 0.4076850984067479,
|
| 743 |
+
"grad_norm": 2.3052737712860107,
|
| 744 |
+
"learning_rate": 9.490393626991566e-05,
|
| 745 |
+
"loss": 0.3988,
|
| 746 |
+
"step": 870
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.41237113402061853,
|
| 750 |
+
"grad_norm": 1.9277461767196655,
|
| 751 |
+
"learning_rate": 9.484536082474227e-05,
|
| 752 |
+
"loss": 0.3717,
|
| 753 |
+
"step": 880
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.41705716963448924,
|
| 757 |
+
"grad_norm": 2.213792324066162,
|
| 758 |
+
"learning_rate": 9.478678537956888e-05,
|
| 759 |
+
"loss": 0.3521,
|
| 760 |
+
"step": 890
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.4217432052483599,
|
| 764 |
+
"grad_norm": 2.0909924507141113,
|
| 765 |
+
"learning_rate": 9.47282099343955e-05,
|
| 766 |
+
"loss": 0.3292,
|
| 767 |
+
"step": 900
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.4217432052483599,
|
| 771 |
+
"eval_loss": 0.05752936750650406,
|
| 772 |
+
"eval_pearson_cosine": 0.7969533250152949,
|
| 773 |
+
"eval_pearson_dot": 0.8037643743757386,
|
| 774 |
+
"eval_pearson_euclidean": 0.7823638645148634,
|
| 775 |
+
"eval_pearson_manhattan": 0.7813551521507094,
|
| 776 |
+
"eval_runtime": 4.8299,
|
| 777 |
+
"eval_samples_per_second": 310.563,
|
| 778 |
+
"eval_spearman_cosine": 0.7992619351747234,
|
| 779 |
+
"eval_spearman_dot": 0.8055866654381859,
|
| 780 |
+
"eval_spearman_euclidean": 0.7873785407587978,
|
| 781 |
+
"eval_spearman_manhattan": 0.7866152504590422,
|
| 782 |
+
"eval_steps_per_second": 19.462,
|
| 783 |
+
"step": 900
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.42642924086223055,
|
| 787 |
+
"grad_norm": 2.122093915939331,
|
| 788 |
+
"learning_rate": 9.466963448922212e-05,
|
| 789 |
+
"loss": 0.3008,
|
| 790 |
+
"step": 910
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.4311152764761012,
|
| 794 |
+
"grad_norm": 2.1320900917053223,
|
| 795 |
+
"learning_rate": 9.461105904404875e-05,
|
| 796 |
+
"loss": 0.3691,
|
| 797 |
+
"step": 920
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.43580131208997186,
|
| 801 |
+
"grad_norm": 2.6174728870391846,
|
| 802 |
+
"learning_rate": 9.455248359887535e-05,
|
| 803 |
+
"loss": 0.3433,
|
| 804 |
+
"step": 930
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.44048734770384257,
|
| 808 |
+
"grad_norm": 1.940846562385559,
|
| 809 |
+
"learning_rate": 9.449390815370197e-05,
|
| 810 |
+
"loss": 0.3517,
|
| 811 |
+
"step": 940
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.4451733833177132,
|
| 815 |
+
"grad_norm": 2.081587791442871,
|
| 816 |
+
"learning_rate": 9.443533270852859e-05,
|
| 817 |
+
"loss": 0.3455,
|
| 818 |
+
"step": 950
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.4498594189315839,
|
| 822 |
+
"grad_norm": 2.1150238513946533,
|
| 823 |
+
"learning_rate": 9.43767572633552e-05,
|
| 824 |
+
"loss": 0.3791,
|
| 825 |
+
"step": 960
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.45454545454545453,
|
| 829 |
+
"grad_norm": 2.286648750305176,
|
| 830 |
+
"learning_rate": 9.431818181818182e-05,
|
| 831 |
+
"loss": 0.363,
|
| 832 |
+
"step": 970
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 0.4592314901593252,
|
| 836 |
+
"grad_norm": 2.0841028690338135,
|
| 837 |
+
"learning_rate": 9.425960637300844e-05,
|
| 838 |
+
"loss": 0.3541,
|
| 839 |
+
"step": 980
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 0.4639175257731959,
|
| 843 |
+
"grad_norm": 2.329029083251953,
|
| 844 |
+
"learning_rate": 9.420103092783506e-05,
|
| 845 |
+
"loss": 0.3635,
|
| 846 |
+
"step": 990
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 0.46860356138706655,
|
| 850 |
+
"grad_norm": 1.905613660812378,
|
| 851 |
+
"learning_rate": 9.414245548266167e-05,
|
| 852 |
+
"loss": 0.3714,
|
| 853 |
+
"step": 1000
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 0.46860356138706655,
|
| 857 |
+
"eval_loss": 0.05644960328936577,
|
| 858 |
+
"eval_pearson_cosine": 0.803875799789175,
|
| 859 |
+
"eval_pearson_dot": 0.8110916308252172,
|
| 860 |
+
"eval_pearson_euclidean": 0.7894191369326222,
|
| 861 |
+
"eval_pearson_manhattan": 0.7890558407124857,
|
| 862 |
+
"eval_runtime": 4.8648,
|
| 863 |
+
"eval_samples_per_second": 308.335,
|
| 864 |
+
"eval_spearman_cosine": 0.8060476875796366,
|
| 865 |
+
"eval_spearman_dot": 0.8116367057743546,
|
| 866 |
+
"eval_spearman_euclidean": 0.7952310888165739,
|
| 867 |
+
"eval_spearman_manhattan": 0.7948288092961023,
|
| 868 |
+
"eval_steps_per_second": 19.322,
|
| 869 |
+
"step": 1000
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 0.4732895970009372,
|
| 873 |
+
"grad_norm": 2.0706255435943604,
|
| 874 |
+
"learning_rate": 9.408388003748829e-05,
|
| 875 |
+
"loss": 0.3365,
|
| 876 |
+
"step": 1010
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 0.47797563261480785,
|
| 880 |
+
"grad_norm": 1.9742926359176636,
|
| 881 |
+
"learning_rate": 9.402530459231491e-05,
|
| 882 |
+
"loss": 0.3723,
|
| 883 |
+
"step": 1020
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 0.48266166822867856,
|
| 887 |
+
"grad_norm": 2.0600244998931885,
|
| 888 |
+
"learning_rate": 9.396672914714152e-05,
|
| 889 |
+
"loss": 0.3605,
|
| 890 |
+
"step": 1030
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 0.4873477038425492,
|
| 894 |
+
"grad_norm": 1.6684983968734741,
|
| 895 |
+
"learning_rate": 9.390815370196814e-05,
|
| 896 |
+
"loss": 0.346,
|
| 897 |
+
"step": 1040
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.49203373945641987,
|
| 901 |
+
"grad_norm": 2.3354814052581787,
|
| 902 |
+
"learning_rate": 9.384957825679476e-05,
|
| 903 |
+
"loss": 0.3657,
|
| 904 |
+
"step": 1050
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 0.4967197750702905,
|
| 908 |
+
"grad_norm": 1.809728980064392,
|
| 909 |
+
"learning_rate": 9.379100281162138e-05,
|
| 910 |
+
"loss": 0.3579,
|
| 911 |
+
"step": 1060
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 0.5014058106841612,
|
| 915 |
+
"grad_norm": 2.339686155319214,
|
| 916 |
+
"learning_rate": 9.373242736644799e-05,
|
| 917 |
+
"loss": 0.382,
|
| 918 |
+
"step": 1070
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 0.5060918462980318,
|
| 922 |
+
"grad_norm": 2.170480966567993,
|
| 923 |
+
"learning_rate": 9.36738519212746e-05,
|
| 924 |
+
"loss": 0.3636,
|
| 925 |
+
"step": 1080
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 0.5107778819119025,
|
| 929 |
+
"grad_norm": 2.4314892292022705,
|
| 930 |
+
"learning_rate": 9.361527647610123e-05,
|
| 931 |
+
"loss": 0.3638,
|
| 932 |
+
"step": 1090
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 0.5154639175257731,
|
| 936 |
+
"grad_norm": 2.1810007095336914,
|
| 937 |
+
"learning_rate": 9.355670103092784e-05,
|
| 938 |
+
"loss": 0.3583,
|
| 939 |
+
"step": 1100
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.5154639175257731,
|
| 943 |
+
"eval_loss": 0.057510774582624435,
|
| 944 |
+
"eval_pearson_cosine": 0.7969929903339477,
|
| 945 |
+
"eval_pearson_dot": 0.8054373741957335,
|
| 946 |
+
"eval_pearson_euclidean": 0.7808607374061509,
|
| 947 |
+
"eval_pearson_manhattan": 0.7798589297759975,
|
| 948 |
+
"eval_runtime": 4.7384,
|
| 949 |
+
"eval_samples_per_second": 316.564,
|
| 950 |
+
"eval_spearman_cosine": 0.7973557927542151,
|
| 951 |
+
"eval_spearman_dot": 0.8047121394369887,
|
| 952 |
+
"eval_spearman_euclidean": 0.7843951879137491,
|
| 953 |
+
"eval_spearman_manhattan": 0.783835500667981,
|
| 954 |
+
"eval_steps_per_second": 19.838,
|
| 955 |
+
"step": 1100
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.5201499531396439,
|
| 959 |
+
"grad_norm": 2.1650052070617676,
|
| 960 |
+
"learning_rate": 9.349812558575446e-05,
|
| 961 |
+
"loss": 0.3565,
|
| 962 |
+
"step": 1110
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.5248359887535146,
|
| 966 |
+
"grad_norm": 1.9347268342971802,
|
| 967 |
+
"learning_rate": 9.343955014058108e-05,
|
| 968 |
+
"loss": 0.3732,
|
| 969 |
+
"step": 1120
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.5295220243673852,
|
| 973 |
+
"grad_norm": 2.7452573776245117,
|
| 974 |
+
"learning_rate": 9.338097469540768e-05,
|
| 975 |
+
"loss": 0.4022,
|
| 976 |
+
"step": 1130
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.5342080599812559,
|
| 980 |
+
"grad_norm": 2.7319650650024414,
|
| 981 |
+
"learning_rate": 9.33223992502343e-05,
|
| 982 |
+
"loss": 0.4039,
|
| 983 |
+
"step": 1140
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.5388940955951266,
|
| 987 |
+
"grad_norm": 1.8111310005187988,
|
| 988 |
+
"learning_rate": 9.326382380506093e-05,
|
| 989 |
+
"loss": 0.3445,
|
| 990 |
+
"step": 1150
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.5435801312089972,
|
| 994 |
+
"grad_norm": 2.470259189605713,
|
| 995 |
+
"learning_rate": 9.320524835988755e-05,
|
| 996 |
+
"loss": 0.329,
|
| 997 |
+
"step": 1160
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.5482661668228679,
|
| 1001 |
+
"grad_norm": 2.465682029724121,
|
| 1002 |
+
"learning_rate": 9.314667291471416e-05,
|
| 1003 |
+
"loss": 0.3621,
|
| 1004 |
+
"step": 1170
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.5529522024367385,
|
| 1008 |
+
"grad_norm": 1.7908481359481812,
|
| 1009 |
+
"learning_rate": 9.308809746954077e-05,
|
| 1010 |
+
"loss": 0.3657,
|
| 1011 |
+
"step": 1180
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.5576382380506092,
|
| 1015 |
+
"grad_norm": 2.1389901638031006,
|
| 1016 |
+
"learning_rate": 9.302952202436738e-05,
|
| 1017 |
+
"loss": 0.3388,
|
| 1018 |
+
"step": 1190
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.5623242736644799,
|
| 1022 |
+
"grad_norm": 2.2106475830078125,
|
| 1023 |
+
"learning_rate": 9.2970946579194e-05,
|
| 1024 |
+
"loss": 0.3913,
|
| 1025 |
+
"step": 1200
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.5623242736644799,
|
| 1029 |
+
"eval_loss": 0.06687228381633759,
|
| 1030 |
+
"eval_pearson_cosine": 0.7966150240375356,
|
| 1031 |
+
"eval_pearson_dot": 0.8042618343582149,
|
| 1032 |
+
"eval_pearson_euclidean": 0.7828267973995509,
|
| 1033 |
+
"eval_pearson_manhattan": 0.7833213095644886,
|
| 1034 |
+
"eval_runtime": 4.9951,
|
| 1035 |
+
"eval_samples_per_second": 300.291,
|
| 1036 |
+
"eval_spearman_cosine": 0.8000396168871208,
|
| 1037 |
+
"eval_spearman_dot": 0.8048980184574105,
|
| 1038 |
+
"eval_spearman_euclidean": 0.7859538030557693,
|
| 1039 |
+
"eval_spearman_manhattan": 0.7864758987006061,
|
| 1040 |
+
"eval_steps_per_second": 18.818,
|
| 1041 |
+
"step": 1200
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.5670103092783505,
|
| 1045 |
+
"grad_norm": 1.9803818464279175,
|
| 1046 |
+
"learning_rate": 9.291237113402063e-05,
|
| 1047 |
+
"loss": 0.3435,
|
| 1048 |
+
"step": 1210
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.5716963448922212,
|
| 1052 |
+
"grad_norm": 1.7664510011672974,
|
| 1053 |
+
"learning_rate": 9.285379568884725e-05,
|
| 1054 |
+
"loss": 0.3798,
|
| 1055 |
+
"step": 1220
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.5763823805060918,
|
| 1059 |
+
"grad_norm": 1.8455970287322998,
|
| 1060 |
+
"learning_rate": 9.279522024367385e-05,
|
| 1061 |
+
"loss": 0.3612,
|
| 1062 |
+
"step": 1230
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.5810684161199625,
|
| 1066 |
+
"grad_norm": 1.92662513256073,
|
| 1067 |
+
"learning_rate": 9.273664479850047e-05,
|
| 1068 |
+
"loss": 0.3214,
|
| 1069 |
+
"step": 1240
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.5857544517338332,
|
| 1073 |
+
"grad_norm": 1.968152403831482,
|
| 1074 |
+
"learning_rate": 9.267806935332709e-05,
|
| 1075 |
+
"loss": 0.3362,
|
| 1076 |
+
"step": 1250
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.5904404873477038,
|
| 1080 |
+
"grad_norm": 2.589308261871338,
|
| 1081 |
+
"learning_rate": 9.26194939081537e-05,
|
| 1082 |
+
"loss": 0.3742,
|
| 1083 |
+
"step": 1260
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.5951265229615745,
|
| 1087 |
+
"grad_norm": 1.9938191175460815,
|
| 1088 |
+
"learning_rate": 9.256091846298033e-05,
|
| 1089 |
+
"loss": 0.3507,
|
| 1090 |
+
"step": 1270
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 0.5998125585754451,
|
| 1094 |
+
"grad_norm": 2.208752155303955,
|
| 1095 |
+
"learning_rate": 9.250234301780694e-05,
|
| 1096 |
+
"loss": 0.3396,
|
| 1097 |
+
"step": 1280
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 0.6044985941893158,
|
| 1101 |
+
"grad_norm": 1.8320244550704956,
|
| 1102 |
+
"learning_rate": 9.244376757263355e-05,
|
| 1103 |
+
"loss": 0.3242,
|
| 1104 |
+
"step": 1290
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.6091846298031866,
|
| 1108 |
+
"grad_norm": 2.33010196685791,
|
| 1109 |
+
"learning_rate": 9.238519212746017e-05,
|
| 1110 |
+
"loss": 0.3208,
|
| 1111 |
+
"step": 1300
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 0.6091846298031866,
|
| 1115 |
+
"eval_loss": 0.045637644827365875,
|
| 1116 |
+
"eval_pearson_cosine": 0.8113760130294838,
|
| 1117 |
+
"eval_pearson_dot": 0.8168668534470953,
|
| 1118 |
+
"eval_pearson_euclidean": 0.7946685783976477,
|
| 1119 |
+
"eval_pearson_manhattan": 0.7948391219509574,
|
| 1120 |
+
"eval_runtime": 4.6512,
|
| 1121 |
+
"eval_samples_per_second": 322.5,
|
| 1122 |
+
"eval_spearman_cosine": 0.8117070589902026,
|
| 1123 |
+
"eval_spearman_dot": 0.8166875703437103,
|
| 1124 |
+
"eval_spearman_euclidean": 0.8003786649119463,
|
| 1125 |
+
"eval_spearman_manhattan": 0.8005194055765069,
|
| 1126 |
+
"eval_steps_per_second": 20.21,
|
| 1127 |
+
"step": 1300
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 0.6138706654170571,
|
| 1131 |
+
"grad_norm": 1.4652146100997925,
|
| 1132 |
+
"learning_rate": 9.232661668228679e-05,
|
| 1133 |
+
"loss": 0.3707,
|
| 1134 |
+
"step": 1310
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 0.6185567010309279,
|
| 1138 |
+
"grad_norm": 2.13409161567688,
|
| 1139 |
+
"learning_rate": 9.22680412371134e-05,
|
| 1140 |
+
"loss": 0.3617,
|
| 1141 |
+
"step": 1320
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 0.6232427366447985,
|
| 1145 |
+
"grad_norm": 1.738176941871643,
|
| 1146 |
+
"learning_rate": 9.220946579194002e-05,
|
| 1147 |
+
"loss": 0.3376,
|
| 1148 |
+
"step": 1330
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 0.6279287722586692,
|
| 1152 |
+
"grad_norm": 1.750163197517395,
|
| 1153 |
+
"learning_rate": 9.215089034676664e-05,
|
| 1154 |
+
"loss": 0.3404,
|
| 1155 |
+
"step": 1340
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 0.6326148078725399,
|
| 1159 |
+
"grad_norm": 2.1063754558563232,
|
| 1160 |
+
"learning_rate": 9.209231490159326e-05,
|
| 1161 |
+
"loss": 0.3752,
|
| 1162 |
+
"step": 1350
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 0.6373008434864105,
|
| 1166 |
+
"grad_norm": 1.4449872970581055,
|
| 1167 |
+
"learning_rate": 9.203373945641987e-05,
|
| 1168 |
+
"loss": 0.2979,
|
| 1169 |
+
"step": 1360
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 0.6419868791002812,
|
| 1173 |
+
"grad_norm": 2.006011724472046,
|
| 1174 |
+
"learning_rate": 9.197516401124649e-05,
|
| 1175 |
+
"loss": 0.3501,
|
| 1176 |
+
"step": 1370
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 0.6466729147141518,
|
| 1180 |
+
"grad_norm": 2.036403179168701,
|
| 1181 |
+
"learning_rate": 9.191658856607311e-05,
|
| 1182 |
+
"loss": 0.3557,
|
| 1183 |
+
"step": 1380
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 0.6513589503280225,
|
| 1187 |
+
"grad_norm": 2.405442237854004,
|
| 1188 |
+
"learning_rate": 9.185801312089973e-05,
|
| 1189 |
+
"loss": 0.3584,
|
| 1190 |
+
"step": 1390
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 0.6560449859418932,
|
| 1194 |
+
"grad_norm": 1.8007841110229492,
|
| 1195 |
+
"learning_rate": 9.179943767572634e-05,
|
| 1196 |
+
"loss": 0.3247,
|
| 1197 |
+
"step": 1400
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 0.6560449859418932,
|
| 1201 |
+
"eval_loss": 0.053980741649866104,
|
| 1202 |
+
"eval_pearson_cosine": 0.8086150300067487,
|
| 1203 |
+
"eval_pearson_dot": 0.8174400112152469,
|
| 1204 |
+
"eval_pearson_euclidean": 0.7907082515140829,
|
| 1205 |
+
"eval_pearson_manhattan": 0.7906201840168094,
|
| 1206 |
+
"eval_runtime": 4.7766,
|
| 1207 |
+
"eval_samples_per_second": 314.029,
|
| 1208 |
+
"eval_spearman_cosine": 0.8111256668964958,
|
| 1209 |
+
"eval_spearman_dot": 0.8195298336175879,
|
| 1210 |
+
"eval_spearman_euclidean": 0.7970481482249502,
|
| 1211 |
+
"eval_spearman_manhattan": 0.7967056753253113,
|
| 1212 |
+
"eval_steps_per_second": 19.679,
|
| 1213 |
+
"step": 1400
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.6607310215557638,
|
| 1217 |
+
"grad_norm": 1.750858187675476,
|
| 1218 |
+
"learning_rate": 9.174086223055296e-05,
|
| 1219 |
+
"loss": 0.3304,
|
| 1220 |
+
"step": 1410
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.6654170571696345,
|
| 1224 |
+
"grad_norm": 1.7640630006790161,
|
| 1225 |
+
"learning_rate": 9.168228678537958e-05,
|
| 1226 |
+
"loss": 0.3282,
|
| 1227 |
+
"step": 1420
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.6701030927835051,
|
| 1231 |
+
"grad_norm": 1.7033814191818237,
|
| 1232 |
+
"learning_rate": 9.162371134020618e-05,
|
| 1233 |
+
"loss": 0.3544,
|
| 1234 |
+
"step": 1430
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.6747891283973758,
|
| 1238 |
+
"grad_norm": 2.1169116497039795,
|
| 1239 |
+
"learning_rate": 9.156513589503281e-05,
|
| 1240 |
+
"loss": 0.3599,
|
| 1241 |
+
"step": 1440
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.6794751640112465,
|
| 1245 |
+
"grad_norm": 1.8890944719314575,
|
| 1246 |
+
"learning_rate": 9.150656044985943e-05,
|
| 1247 |
+
"loss": 0.3097,
|
| 1248 |
+
"step": 1450
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.6841611996251171,
|
| 1252 |
+
"grad_norm": 1.9908314943313599,
|
| 1253 |
+
"learning_rate": 9.144798500468605e-05,
|
| 1254 |
+
"loss": 0.3187,
|
| 1255 |
+
"step": 1460
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.6888472352389878,
|
| 1259 |
+
"grad_norm": 2.442484140396118,
|
| 1260 |
+
"learning_rate": 9.138940955951266e-05,
|
| 1261 |
+
"loss": 0.3184,
|
| 1262 |
+
"step": 1470
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.6935332708528584,
|
| 1266 |
+
"grad_norm": 2.19154953956604,
|
| 1267 |
+
"learning_rate": 9.133083411433927e-05,
|
| 1268 |
+
"loss": 0.3585,
|
| 1269 |
+
"step": 1480
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.6982193064667291,
|
| 1273 |
+
"grad_norm": 1.869988203048706,
|
| 1274 |
+
"learning_rate": 9.127225866916588e-05,
|
| 1275 |
+
"loss": 0.3149,
|
| 1276 |
+
"step": 1490
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.7029053420805998,
|
| 1280 |
+
"grad_norm": 2.1679623126983643,
|
| 1281 |
+
"learning_rate": 9.121368322399251e-05,
|
| 1282 |
+
"loss": 0.3269,
|
| 1283 |
+
"step": 1500
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.7029053420805998,
|
| 1287 |
+
"eval_loss": 0.04739663749933243,
|
| 1288 |
+
"eval_pearson_cosine": 0.8141597203524853,
|
| 1289 |
+
"eval_pearson_dot": 0.8207163609193167,
|
| 1290 |
+
"eval_pearson_euclidean": 0.796674853711913,
|
| 1291 |
+
"eval_pearson_manhattan": 0.7960896801887358,
|
| 1292 |
+
"eval_runtime": 4.6642,
|
| 1293 |
+
"eval_samples_per_second": 321.601,
|
| 1294 |
+
"eval_spearman_cosine": 0.8154525852016754,
|
| 1295 |
+
"eval_spearman_dot": 0.8205176794102382,
|
| 1296 |
+
"eval_spearman_euclidean": 0.8031080794349076,
|
| 1297 |
+
"eval_spearman_manhattan": 0.8025975518083548,
|
| 1298 |
+
"eval_steps_per_second": 20.154,
|
| 1299 |
+
"step": 1500
|
| 1300 |
+
}
|
| 1301 |
+
],
|
| 1302 |
+
"logging_steps": 10,
|
| 1303 |
+
"max_steps": 2134,
|
| 1304 |
+
"num_input_tokens_seen": 0,
|
| 1305 |
+
"num_train_epochs": 1,
|
| 1306 |
+
"save_steps": 500,
|
| 1307 |
+
"stateful_callbacks": {
|
| 1308 |
+
"TrainerControl": {
|
| 1309 |
+
"args": {
|
| 1310 |
+
"should_epoch_stop": false,
|
| 1311 |
+
"should_evaluate": false,
|
| 1312 |
+
"should_log": false,
|
| 1313 |
+
"should_save": true,
|
| 1314 |
+
"should_training_stop": false
|
| 1315 |
+
},
|
| 1316 |
+
"attributes": {}
|
| 1317 |
+
}
|
| 1318 |
+
},
|
| 1319 |
+
"total_flos": 0.0,
|
| 1320 |
+
"train_batch_size": 16,
|
| 1321 |
+
"trial_name": null,
|
| 1322 |
+
"trial_params": null
|
| 1323 |
+
}
|
last-checkpoint/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8245ad8d07ebb1dbf31b5bb701c7b6a12ad4c1449de419861b6ec4b0360c92b
|
| 3 |
+
size 5368
|