Upload folder using huggingface_hub
Browse files- checkpoint-20062/merges.txt +0 -0
- checkpoint-20062/optimizer.pt +3 -0
- checkpoint-20062/pytorch_model.bin +3 -0
- checkpoint-20062/rng_state.pth +3 -0
- checkpoint-20062/scheduler.pt +3 -0
- checkpoint-20062/special_tokens_map.json +51 -0
- checkpoint-20062/tokenizer.json +0 -0
- checkpoint-20062/tokenizer_config.json +58 -0
- checkpoint-20062/trainer_state.json +1434 -0
- checkpoint-20062/training_args.bin +3 -0
- checkpoint-20062/vocab.json +0 -0
- checkpoint-22928/merges.txt +0 -0
- checkpoint-22928/optimizer.pt +3 -0
- checkpoint-22928/pytorch_model.bin +3 -0
- checkpoint-22928/rng_state.pth +3 -0
- checkpoint-22928/scheduler.pt +3 -0
- checkpoint-22928/special_tokens_map.json +51 -0
- checkpoint-22928/tokenizer.json +0 -0
- checkpoint-22928/tokenizer_config.json +58 -0
- checkpoint-22928/trainer_state.json +1637 -0
- checkpoint-22928/training_args.bin +3 -0
- checkpoint-22928/vocab.json +0 -0
- config.json +9 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
- vocab.json +0 -0
checkpoint-20062/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-20062/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d726ad6bf4601cb9407ef171e32a0964a3b5e0a154ef62b913abbc4a669f1de9
|
| 3 |
+
size 1370834379
|
checkpoint-20062/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:684b04c5329e28cce1228973fde1adf3b270ef0a2b6694212581e5df47e433c3
|
| 3 |
+
size 719294071
|
checkpoint-20062/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ca051215e53e8d9df90a81ce1ecdc4cc447bd8dbb701f6e7c0654b659aae834
|
| 3 |
+
size 14645
|
checkpoint-20062/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa818dcc5953bac8c9665228d737ef399710b899749eb25146a8f16d5eef1cac
|
| 3 |
+
size 1465
|
checkpoint-20062/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-20062/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-20062/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 512,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
checkpoint-20062/trainer_state.json
ADDED
|
@@ -0,0 +1,1434 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 7.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 20062,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.034891835310537335,
|
| 14 |
+
"grad_norm": 4.449178218841553,
|
| 15 |
+
"learning_rate": 4.9784106769016056e-05,
|
| 16 |
+
"loss": 7.4361,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.06978367062107467,
|
| 21 |
+
"grad_norm": 4.605655670166016,
|
| 22 |
+
"learning_rate": 4.95660327983252e-05,
|
| 23 |
+
"loss": 5.6934,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.104675505931612,
|
| 28 |
+
"grad_norm": 5.126296520233154,
|
| 29 |
+
"learning_rate": 4.9347958827634335e-05,
|
| 30 |
+
"loss": 5.1849,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.13956734124214934,
|
| 35 |
+
"grad_norm": 5.184763431549072,
|
| 36 |
+
"learning_rate": 4.912988485694348e-05,
|
| 37 |
+
"loss": 4.9327,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.17445917655268667,
|
| 42 |
+
"grad_norm": 4.761885643005371,
|
| 43 |
+
"learning_rate": 4.891181088625262e-05,
|
| 44 |
+
"loss": 4.7416,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.209351011863224,
|
| 49 |
+
"grad_norm": 4.478248596191406,
|
| 50 |
+
"learning_rate": 4.869373691556176e-05,
|
| 51 |
+
"loss": 4.5712,
|
| 52 |
+
"step": 600
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.24424284717376135,
|
| 56 |
+
"grad_norm": 4.7443928718566895,
|
| 57 |
+
"learning_rate": 4.84756629448709e-05,
|
| 58 |
+
"loss": 4.4319,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.2791346824842987,
|
| 63 |
+
"grad_norm": 4.571919918060303,
|
| 64 |
+
"learning_rate": 4.8257588974180044e-05,
|
| 65 |
+
"loss": 4.3216,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.31402651779483604,
|
| 70 |
+
"grad_norm": 4.504453182220459,
|
| 71 |
+
"learning_rate": 4.803951500348919e-05,
|
| 72 |
+
"loss": 4.1818,
|
| 73 |
+
"step": 900
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.34891835310537334,
|
| 77 |
+
"grad_norm": 4.749291896820068,
|
| 78 |
+
"learning_rate": 4.782144103279832e-05,
|
| 79 |
+
"loss": 4.0893,
|
| 80 |
+
"step": 1000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.3838101884159107,
|
| 84 |
+
"grad_norm": 4.697039604187012,
|
| 85 |
+
"learning_rate": 4.7603367062107466e-05,
|
| 86 |
+
"loss": 4.0596,
|
| 87 |
+
"step": 1100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.418702023726448,
|
| 91 |
+
"grad_norm": 4.919949054718018,
|
| 92 |
+
"learning_rate": 4.738529309141661e-05,
|
| 93 |
+
"loss": 4.0145,
|
| 94 |
+
"step": 1200
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.45359385903698535,
|
| 98 |
+
"grad_norm": 4.816226482391357,
|
| 99 |
+
"learning_rate": 4.716721912072575e-05,
|
| 100 |
+
"loss": 3.9097,
|
| 101 |
+
"step": 1300
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.4884856943475227,
|
| 105 |
+
"grad_norm": 4.794589519500732,
|
| 106 |
+
"learning_rate": 4.6949145150034896e-05,
|
| 107 |
+
"loss": 3.8486,
|
| 108 |
+
"step": 1400
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.5233775296580601,
|
| 112 |
+
"grad_norm": 4.941982269287109,
|
| 113 |
+
"learning_rate": 4.673107117934404e-05,
|
| 114 |
+
"loss": 3.8414,
|
| 115 |
+
"step": 1500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.5582693649685974,
|
| 119 |
+
"grad_norm": 4.8971452713012695,
|
| 120 |
+
"learning_rate": 4.6512997208653175e-05,
|
| 121 |
+
"loss": 3.7677,
|
| 122 |
+
"step": 1600
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.5931612002791347,
|
| 126 |
+
"grad_norm": 4.788393974304199,
|
| 127 |
+
"learning_rate": 4.629492323796232e-05,
|
| 128 |
+
"loss": 3.7563,
|
| 129 |
+
"step": 1700
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.6280530355896721,
|
| 133 |
+
"grad_norm": 8.283535957336426,
|
| 134 |
+
"learning_rate": 4.607684926727146e-05,
|
| 135 |
+
"loss": 3.702,
|
| 136 |
+
"step": 1800
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.6629448709002094,
|
| 140 |
+
"grad_norm": 4.443343639373779,
|
| 141 |
+
"learning_rate": 4.5858775296580604e-05,
|
| 142 |
+
"loss": 3.6575,
|
| 143 |
+
"step": 1900
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.6978367062107467,
|
| 147 |
+
"grad_norm": 4.8935956954956055,
|
| 148 |
+
"learning_rate": 4.564070132588975e-05,
|
| 149 |
+
"loss": 3.6542,
|
| 150 |
+
"step": 2000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.732728541521284,
|
| 154 |
+
"grad_norm": 4.706109523773193,
|
| 155 |
+
"learning_rate": 4.542262735519889e-05,
|
| 156 |
+
"loss": 3.588,
|
| 157 |
+
"step": 2100
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.7676203768318214,
|
| 161 |
+
"grad_norm": 5.829479694366455,
|
| 162 |
+
"learning_rate": 4.520455338450803e-05,
|
| 163 |
+
"loss": 3.5628,
|
| 164 |
+
"step": 2200
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.8025122121423587,
|
| 168 |
+
"grad_norm": 5.121861457824707,
|
| 169 |
+
"learning_rate": 4.498647941381717e-05,
|
| 170 |
+
"loss": 3.5284,
|
| 171 |
+
"step": 2300
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.837404047452896,
|
| 175 |
+
"grad_norm": 9.078815460205078,
|
| 176 |
+
"learning_rate": 4.476840544312631e-05,
|
| 177 |
+
"loss": 3.5192,
|
| 178 |
+
"step": 2400
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.8722958827634334,
|
| 182 |
+
"grad_norm": 4.904483318328857,
|
| 183 |
+
"learning_rate": 4.455033147243545e-05,
|
| 184 |
+
"loss": 3.4818,
|
| 185 |
+
"step": 2500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.9071877180739707,
|
| 189 |
+
"grad_norm": 4.965977668762207,
|
| 190 |
+
"learning_rate": 4.433225750174459e-05,
|
| 191 |
+
"loss": 3.4393,
|
| 192 |
+
"step": 2600
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.942079553384508,
|
| 196 |
+
"grad_norm": 4.89396858215332,
|
| 197 |
+
"learning_rate": 4.4114183531053736e-05,
|
| 198 |
+
"loss": 3.4231,
|
| 199 |
+
"step": 2700
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.9769713886950454,
|
| 203 |
+
"grad_norm": 5.0034661293029785,
|
| 204 |
+
"learning_rate": 4.389610956036287e-05,
|
| 205 |
+
"loss": 3.3895,
|
| 206 |
+
"step": 2800
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.0118632240055827,
|
| 210 |
+
"grad_norm": 4.820219039916992,
|
| 211 |
+
"learning_rate": 4.3678035589672015e-05,
|
| 212 |
+
"loss": 3.2998,
|
| 213 |
+
"step": 2900
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.0467550593161201,
|
| 217 |
+
"grad_norm": 4.667869567871094,
|
| 218 |
+
"learning_rate": 4.345996161898116e-05,
|
| 219 |
+
"loss": 3.172,
|
| 220 |
+
"step": 3000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.0816468946266573,
|
| 224 |
+
"grad_norm": 4.847691059112549,
|
| 225 |
+
"learning_rate": 4.32418876482903e-05,
|
| 226 |
+
"loss": 3.1746,
|
| 227 |
+
"step": 3100
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.1165387299371947,
|
| 231 |
+
"grad_norm": 4.929681301116943,
|
| 232 |
+
"learning_rate": 4.3023813677599444e-05,
|
| 233 |
+
"loss": 3.1565,
|
| 234 |
+
"step": 3200
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.1514305652477321,
|
| 238 |
+
"grad_norm": 5.4113359451293945,
|
| 239 |
+
"learning_rate": 4.280573970690859e-05,
|
| 240 |
+
"loss": 3.1381,
|
| 241 |
+
"step": 3300
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.1863224005582693,
|
| 245 |
+
"grad_norm": 5.372176647186279,
|
| 246 |
+
"learning_rate": 4.2587665736217724e-05,
|
| 247 |
+
"loss": 3.1268,
|
| 248 |
+
"step": 3400
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.2212142358688067,
|
| 252 |
+
"grad_norm": 5.134545803070068,
|
| 253 |
+
"learning_rate": 4.236959176552687e-05,
|
| 254 |
+
"loss": 3.1067,
|
| 255 |
+
"step": 3500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.2561060711793441,
|
| 259 |
+
"grad_norm": 5.3275861740112305,
|
| 260 |
+
"learning_rate": 4.215151779483601e-05,
|
| 261 |
+
"loss": 3.0777,
|
| 262 |
+
"step": 3600
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.2909979064898813,
|
| 266 |
+
"grad_norm": 5.151634216308594,
|
| 267 |
+
"learning_rate": 4.193344382414515e-05,
|
| 268 |
+
"loss": 3.067,
|
| 269 |
+
"step": 3700
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.3258897418004187,
|
| 273 |
+
"grad_norm": 5.169743061065674,
|
| 274 |
+
"learning_rate": 4.1715369853454296e-05,
|
| 275 |
+
"loss": 3.0564,
|
| 276 |
+
"step": 3800
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.3607815771109562,
|
| 280 |
+
"grad_norm": 4.969324588775635,
|
| 281 |
+
"learning_rate": 4.149729588276344e-05,
|
| 282 |
+
"loss": 3.0547,
|
| 283 |
+
"step": 3900
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.3956734124214933,
|
| 287 |
+
"grad_norm": 4.806005477905273,
|
| 288 |
+
"learning_rate": 4.1279221912072576e-05,
|
| 289 |
+
"loss": 3.0324,
|
| 290 |
+
"step": 4000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.4305652477320308,
|
| 294 |
+
"grad_norm": 5.4942426681518555,
|
| 295 |
+
"learning_rate": 4.106114794138172e-05,
|
| 296 |
+
"loss": 3.0307,
|
| 297 |
+
"step": 4100
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.4654570830425682,
|
| 301 |
+
"grad_norm": 5.495986461639404,
|
| 302 |
+
"learning_rate": 4.084307397069086e-05,
|
| 303 |
+
"loss": 3.0058,
|
| 304 |
+
"step": 4200
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.5003489183531054,
|
| 308 |
+
"grad_norm": 4.752720355987549,
|
| 309 |
+
"learning_rate": 4.0625000000000005e-05,
|
| 310 |
+
"loss": 2.9856,
|
| 311 |
+
"step": 4300
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.5352407536636425,
|
| 315 |
+
"grad_norm": 4.929941654205322,
|
| 316 |
+
"learning_rate": 4.040692602930914e-05,
|
| 317 |
+
"loss": 2.9931,
|
| 318 |
+
"step": 4400
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.5701325889741802,
|
| 322 |
+
"grad_norm": 4.883072853088379,
|
| 323 |
+
"learning_rate": 4.0188852058618284e-05,
|
| 324 |
+
"loss": 2.9824,
|
| 325 |
+
"step": 4500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.6050244242847174,
|
| 329 |
+
"grad_norm": 5.3392333984375,
|
| 330 |
+
"learning_rate": 3.997077808792743e-05,
|
| 331 |
+
"loss": 2.9538,
|
| 332 |
+
"step": 4600
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.6399162595952546,
|
| 336 |
+
"grad_norm": 5.304770469665527,
|
| 337 |
+
"learning_rate": 3.9752704117236564e-05,
|
| 338 |
+
"loss": 2.9584,
|
| 339 |
+
"step": 4700
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.6748080949057922,
|
| 343 |
+
"grad_norm": 5.055889129638672,
|
| 344 |
+
"learning_rate": 3.953463014654571e-05,
|
| 345 |
+
"loss": 2.9221,
|
| 346 |
+
"step": 4800
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.7096999302163294,
|
| 350 |
+
"grad_norm": 5.006368637084961,
|
| 351 |
+
"learning_rate": 3.931655617585485e-05,
|
| 352 |
+
"loss": 2.9154,
|
| 353 |
+
"step": 4900
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.7445917655268666,
|
| 357 |
+
"grad_norm": 5.258544921875,
|
| 358 |
+
"learning_rate": 3.909848220516399e-05,
|
| 359 |
+
"loss": 2.9123,
|
| 360 |
+
"step": 5000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.7794836008374042,
|
| 364 |
+
"grad_norm": 4.940785884857178,
|
| 365 |
+
"learning_rate": 3.8880408234473136e-05,
|
| 366 |
+
"loss": 2.8721,
|
| 367 |
+
"step": 5100
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.8143754361479414,
|
| 371 |
+
"grad_norm": 5.046368598937988,
|
| 372 |
+
"learning_rate": 3.866233426378228e-05,
|
| 373 |
+
"loss": 2.8598,
|
| 374 |
+
"step": 5200
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.8492672714584786,
|
| 378 |
+
"grad_norm": 5.59748649597168,
|
| 379 |
+
"learning_rate": 3.8444260293091416e-05,
|
| 380 |
+
"loss": 2.8819,
|
| 381 |
+
"step": 5300
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.8841591067690162,
|
| 385 |
+
"grad_norm": 5.261348247528076,
|
| 386 |
+
"learning_rate": 3.822618632240056e-05,
|
| 387 |
+
"loss": 2.8284,
|
| 388 |
+
"step": 5400
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.9190509420795534,
|
| 392 |
+
"grad_norm": 5.169360160827637,
|
| 393 |
+
"learning_rate": 3.80081123517097e-05,
|
| 394 |
+
"loss": 2.8456,
|
| 395 |
+
"step": 5500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.9539427773900906,
|
| 399 |
+
"grad_norm": 5.436888694763184,
|
| 400 |
+
"learning_rate": 3.7790038381018845e-05,
|
| 401 |
+
"loss": 2.8561,
|
| 402 |
+
"step": 5600
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.988834612700628,
|
| 406 |
+
"grad_norm": 5.126554489135742,
|
| 407 |
+
"learning_rate": 3.757196441032799e-05,
|
| 408 |
+
"loss": 2.8151,
|
| 409 |
+
"step": 5700
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 2.0237264480111654,
|
| 413 |
+
"grad_norm": 4.704784870147705,
|
| 414 |
+
"learning_rate": 3.735389043963713e-05,
|
| 415 |
+
"loss": 2.674,
|
| 416 |
+
"step": 5800
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.0586182833217026,
|
| 420 |
+
"grad_norm": 5.37230920791626,
|
| 421 |
+
"learning_rate": 3.713581646894627e-05,
|
| 422 |
+
"loss": 2.608,
|
| 423 |
+
"step": 5900
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.0935101186322402,
|
| 427 |
+
"grad_norm": 4.852290630340576,
|
| 428 |
+
"learning_rate": 3.691774249825541e-05,
|
| 429 |
+
"loss": 2.591,
|
| 430 |
+
"step": 6000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 2.1284019539427774,
|
| 434 |
+
"grad_norm": 5.700033664703369,
|
| 435 |
+
"learning_rate": 3.6699668527564554e-05,
|
| 436 |
+
"loss": 2.5985,
|
| 437 |
+
"step": 6100
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 2.1632937892533146,
|
| 441 |
+
"grad_norm": 5.340079307556152,
|
| 442 |
+
"learning_rate": 3.64815945568737e-05,
|
| 443 |
+
"loss": 2.5871,
|
| 444 |
+
"step": 6200
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.1981856245638522,
|
| 448 |
+
"grad_norm": 5.0922532081604,
|
| 449 |
+
"learning_rate": 3.626352058618284e-05,
|
| 450 |
+
"loss": 2.5762,
|
| 451 |
+
"step": 6300
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 2.2330774598743894,
|
| 455 |
+
"grad_norm": 5.114669322967529,
|
| 456 |
+
"learning_rate": 3.6045446615491976e-05,
|
| 457 |
+
"loss": 2.5665,
|
| 458 |
+
"step": 6400
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.2679692951849266,
|
| 462 |
+
"grad_norm": 5.286740303039551,
|
| 463 |
+
"learning_rate": 3.582737264480112e-05,
|
| 464 |
+
"loss": 2.5635,
|
| 465 |
+
"step": 6500
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.3028611304954643,
|
| 469 |
+
"grad_norm": 5.458755016326904,
|
| 470 |
+
"learning_rate": 3.5609298674110256e-05,
|
| 471 |
+
"loss": 2.5559,
|
| 472 |
+
"step": 6600
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 2.3377529658060014,
|
| 476 |
+
"grad_norm": 5.574306488037109,
|
| 477 |
+
"learning_rate": 3.53912247034194e-05,
|
| 478 |
+
"loss": 2.5386,
|
| 479 |
+
"step": 6700
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 2.3726448011165386,
|
| 483 |
+
"grad_norm": 5.048354148864746,
|
| 484 |
+
"learning_rate": 3.517315073272854e-05,
|
| 485 |
+
"loss": 2.5325,
|
| 486 |
+
"step": 6800
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 2.407536636427076,
|
| 490 |
+
"grad_norm": 5.464790344238281,
|
| 491 |
+
"learning_rate": 3.4955076762037685e-05,
|
| 492 |
+
"loss": 2.5501,
|
| 493 |
+
"step": 6900
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 2.4424284717376135,
|
| 497 |
+
"grad_norm": 5.763171672821045,
|
| 498 |
+
"learning_rate": 3.473700279134683e-05,
|
| 499 |
+
"loss": 2.5496,
|
| 500 |
+
"step": 7000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 2.4773203070481506,
|
| 504 |
+
"grad_norm": 5.179362773895264,
|
| 505 |
+
"learning_rate": 3.4518928820655964e-05,
|
| 506 |
+
"loss": 2.5447,
|
| 507 |
+
"step": 7100
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 2.5122121423586883,
|
| 511 |
+
"grad_norm": 5.075343132019043,
|
| 512 |
+
"learning_rate": 3.430085484996511e-05,
|
| 513 |
+
"loss": 2.5568,
|
| 514 |
+
"step": 7200
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 2.5471039776692255,
|
| 518 |
+
"grad_norm": 5.105709552764893,
|
| 519 |
+
"learning_rate": 3.408278087927425e-05,
|
| 520 |
+
"loss": 2.5631,
|
| 521 |
+
"step": 7300
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.5819958129797627,
|
| 525 |
+
"grad_norm": 5.484874248504639,
|
| 526 |
+
"learning_rate": 3.3864706908583394e-05,
|
| 527 |
+
"loss": 2.5462,
|
| 528 |
+
"step": 7400
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 2.6168876482903,
|
| 532 |
+
"grad_norm": 5.008668422698975,
|
| 533 |
+
"learning_rate": 3.364663293789254e-05,
|
| 534 |
+
"loss": 2.5169,
|
| 535 |
+
"step": 7500
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 2.6517794836008375,
|
| 539 |
+
"grad_norm": 5.086187362670898,
|
| 540 |
+
"learning_rate": 3.342855896720168e-05,
|
| 541 |
+
"loss": 2.5182,
|
| 542 |
+
"step": 7600
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 2.6866713189113747,
|
| 546 |
+
"grad_norm": 5.237493991851807,
|
| 547 |
+
"learning_rate": 3.3210484996510816e-05,
|
| 548 |
+
"loss": 2.5152,
|
| 549 |
+
"step": 7700
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 2.7215631542219123,
|
| 553 |
+
"grad_norm": 4.8399977684021,
|
| 554 |
+
"learning_rate": 3.299241102581996e-05,
|
| 555 |
+
"loss": 2.5159,
|
| 556 |
+
"step": 7800
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 2.7564549895324495,
|
| 560 |
+
"grad_norm": 5.455721378326416,
|
| 561 |
+
"learning_rate": 3.27743370551291e-05,
|
| 562 |
+
"loss": 2.5059,
|
| 563 |
+
"step": 7900
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 2.7913468248429867,
|
| 567 |
+
"grad_norm": 4.843439102172852,
|
| 568 |
+
"learning_rate": 3.2556263084438245e-05,
|
| 569 |
+
"loss": 2.5007,
|
| 570 |
+
"step": 8000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 2.826238660153524,
|
| 574 |
+
"grad_norm": 5.252379417419434,
|
| 575 |
+
"learning_rate": 3.233818911374739e-05,
|
| 576 |
+
"loss": 2.4966,
|
| 577 |
+
"step": 8100
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 2.8611304954640615,
|
| 581 |
+
"grad_norm": 4.738300800323486,
|
| 582 |
+
"learning_rate": 3.212011514305653e-05,
|
| 583 |
+
"loss": 2.5076,
|
| 584 |
+
"step": 8200
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 2.8960223307745987,
|
| 588 |
+
"grad_norm": 4.630394458770752,
|
| 589 |
+
"learning_rate": 3.190204117236567e-05,
|
| 590 |
+
"loss": 2.5125,
|
| 591 |
+
"step": 8300
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 2.9309141660851363,
|
| 595 |
+
"grad_norm": 5.112858772277832,
|
| 596 |
+
"learning_rate": 3.168396720167481e-05,
|
| 597 |
+
"loss": 2.496,
|
| 598 |
+
"step": 8400
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 2.9658060013956735,
|
| 602 |
+
"grad_norm": 4.9403510093688965,
|
| 603 |
+
"learning_rate": 3.146589323098395e-05,
|
| 604 |
+
"loss": 2.4916,
|
| 605 |
+
"step": 8500
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 3.0006978367062107,
|
| 609 |
+
"grad_norm": 4.983951091766357,
|
| 610 |
+
"learning_rate": 3.124781926029309e-05,
|
| 611 |
+
"loss": 2.4925,
|
| 612 |
+
"step": 8600
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 3.035589672016748,
|
| 616 |
+
"grad_norm": 4.399389743804932,
|
| 617 |
+
"learning_rate": 3.1029745289602233e-05,
|
| 618 |
+
"loss": 2.27,
|
| 619 |
+
"step": 8700
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 3.0704815073272855,
|
| 623 |
+
"grad_norm": 5.247836589813232,
|
| 624 |
+
"learning_rate": 3.0811671318911377e-05,
|
| 625 |
+
"loss": 2.283,
|
| 626 |
+
"step": 8800
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 3.1053733426378227,
|
| 630 |
+
"grad_norm": 5.457115173339844,
|
| 631 |
+
"learning_rate": 3.059359734822051e-05,
|
| 632 |
+
"loss": 2.2568,
|
| 633 |
+
"step": 8900
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 3.14026517794836,
|
| 637 |
+
"grad_norm": 4.6203179359436035,
|
| 638 |
+
"learning_rate": 3.037552337752966e-05,
|
| 639 |
+
"loss": 2.2618,
|
| 640 |
+
"step": 9000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 3.1751570132588975,
|
| 644 |
+
"grad_norm": 5.432634353637695,
|
| 645 |
+
"learning_rate": 3.01574494068388e-05,
|
| 646 |
+
"loss": 2.2945,
|
| 647 |
+
"step": 9100
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 3.2100488485694347,
|
| 651 |
+
"grad_norm": 5.295199871063232,
|
| 652 |
+
"learning_rate": 2.9939375436147942e-05,
|
| 653 |
+
"loss": 2.2687,
|
| 654 |
+
"step": 9200
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 3.244940683879972,
|
| 658 |
+
"grad_norm": 5.510141849517822,
|
| 659 |
+
"learning_rate": 2.9721301465457085e-05,
|
| 660 |
+
"loss": 2.2846,
|
| 661 |
+
"step": 9300
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 3.2798325191905096,
|
| 665 |
+
"grad_norm": 5.49964714050293,
|
| 666 |
+
"learning_rate": 2.950322749476623e-05,
|
| 667 |
+
"loss": 2.2727,
|
| 668 |
+
"step": 9400
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 3.3147243545010467,
|
| 672 |
+
"grad_norm": 5.006816864013672,
|
| 673 |
+
"learning_rate": 2.928515352407537e-05,
|
| 674 |
+
"loss": 2.27,
|
| 675 |
+
"step": 9500
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 3.349616189811584,
|
| 679 |
+
"grad_norm": 4.75443172454834,
|
| 680 |
+
"learning_rate": 2.9067079553384508e-05,
|
| 681 |
+
"loss": 2.2896,
|
| 682 |
+
"step": 9600
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 3.3845080251221216,
|
| 686 |
+
"grad_norm": 5.43818473815918,
|
| 687 |
+
"learning_rate": 2.884900558269365e-05,
|
| 688 |
+
"loss": 2.2823,
|
| 689 |
+
"step": 9700
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 3.4193998604326588,
|
| 693 |
+
"grad_norm": 5.078537940979004,
|
| 694 |
+
"learning_rate": 2.8630931612002794e-05,
|
| 695 |
+
"loss": 2.2689,
|
| 696 |
+
"step": 9800
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 3.454291695743196,
|
| 700 |
+
"grad_norm": 5.591304302215576,
|
| 701 |
+
"learning_rate": 2.8412857641311934e-05,
|
| 702 |
+
"loss": 2.2915,
|
| 703 |
+
"step": 9900
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 3.4891835310537336,
|
| 707 |
+
"grad_norm": 5.2217559814453125,
|
| 708 |
+
"learning_rate": 2.8194783670621077e-05,
|
| 709 |
+
"loss": 2.268,
|
| 710 |
+
"step": 10000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 3.5240753663642708,
|
| 714 |
+
"grad_norm": 5.424462795257568,
|
| 715 |
+
"learning_rate": 2.797670969993022e-05,
|
| 716 |
+
"loss": 2.2562,
|
| 717 |
+
"step": 10100
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 3.558967201674808,
|
| 721 |
+
"grad_norm": 5.45490837097168,
|
| 722 |
+
"learning_rate": 2.7758635729239356e-05,
|
| 723 |
+
"loss": 2.2699,
|
| 724 |
+
"step": 10200
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 3.5938590369853456,
|
| 728 |
+
"grad_norm": 5.29006814956665,
|
| 729 |
+
"learning_rate": 2.75405617585485e-05,
|
| 730 |
+
"loss": 2.2875,
|
| 731 |
+
"step": 10300
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 3.628750872295883,
|
| 735 |
+
"grad_norm": 5.640931606292725,
|
| 736 |
+
"learning_rate": 2.7322487787857642e-05,
|
| 737 |
+
"loss": 2.277,
|
| 738 |
+
"step": 10400
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 3.66364270760642,
|
| 742 |
+
"grad_norm": 5.791449069976807,
|
| 743 |
+
"learning_rate": 2.7104413817166786e-05,
|
| 744 |
+
"loss": 2.289,
|
| 745 |
+
"step": 10500
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 3.698534542916957,
|
| 749 |
+
"grad_norm": 5.233780860900879,
|
| 750 |
+
"learning_rate": 2.688633984647593e-05,
|
| 751 |
+
"loss": 2.2559,
|
| 752 |
+
"step": 10600
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 3.733426378227495,
|
| 756 |
+
"grad_norm": 4.809124946594238,
|
| 757 |
+
"learning_rate": 2.6668265875785072e-05,
|
| 758 |
+
"loss": 2.2699,
|
| 759 |
+
"step": 10700
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 3.768318213538032,
|
| 763 |
+
"grad_norm": 5.174726963043213,
|
| 764 |
+
"learning_rate": 2.6450191905094208e-05,
|
| 765 |
+
"loss": 2.2584,
|
| 766 |
+
"step": 10800
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 3.8032100488485696,
|
| 770 |
+
"grad_norm": 5.181713104248047,
|
| 771 |
+
"learning_rate": 2.623211793440335e-05,
|
| 772 |
+
"loss": 2.2426,
|
| 773 |
+
"step": 10900
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 3.838101884159107,
|
| 777 |
+
"grad_norm": 5.212897777557373,
|
| 778 |
+
"learning_rate": 2.601404396371249e-05,
|
| 779 |
+
"loss": 2.2257,
|
| 780 |
+
"step": 11000
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 3.872993719469644,
|
| 784 |
+
"grad_norm": 5.191478252410889,
|
| 785 |
+
"learning_rate": 2.5795969993021634e-05,
|
| 786 |
+
"loss": 2.2468,
|
| 787 |
+
"step": 11100
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 3.907885554780181,
|
| 791 |
+
"grad_norm": 5.237133979797363,
|
| 792 |
+
"learning_rate": 2.5577896022330777e-05,
|
| 793 |
+
"loss": 2.2529,
|
| 794 |
+
"step": 11200
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 3.942777390090719,
|
| 798 |
+
"grad_norm": 5.110697269439697,
|
| 799 |
+
"learning_rate": 2.535982205163992e-05,
|
| 800 |
+
"loss": 2.2403,
|
| 801 |
+
"step": 11300
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 3.977669225401256,
|
| 805 |
+
"grad_norm": 5.379474639892578,
|
| 806 |
+
"learning_rate": 2.5141748080949056e-05,
|
| 807 |
+
"loss": 2.2432,
|
| 808 |
+
"step": 11400
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 4.012561060711794,
|
| 812 |
+
"grad_norm": 5.239147663116455,
|
| 813 |
+
"learning_rate": 2.49236741102582e-05,
|
| 814 |
+
"loss": 2.1658,
|
| 815 |
+
"step": 11500
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 4.047452896022331,
|
| 819 |
+
"grad_norm": 5.401543140411377,
|
| 820 |
+
"learning_rate": 2.4705600139567343e-05,
|
| 821 |
+
"loss": 2.0642,
|
| 822 |
+
"step": 11600
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 4.082344731332868,
|
| 826 |
+
"grad_norm": 5.2488322257995605,
|
| 827 |
+
"learning_rate": 2.4487526168876486e-05,
|
| 828 |
+
"loss": 2.0671,
|
| 829 |
+
"step": 11700
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 4.117236566643405,
|
| 833 |
+
"grad_norm": 5.270359039306641,
|
| 834 |
+
"learning_rate": 2.4269452198185625e-05,
|
| 835 |
+
"loss": 2.0655,
|
| 836 |
+
"step": 11800
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 4.152128401953942,
|
| 840 |
+
"grad_norm": 5.2798614501953125,
|
| 841 |
+
"learning_rate": 2.4051378227494765e-05,
|
| 842 |
+
"loss": 2.0595,
|
| 843 |
+
"step": 11900
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 4.1870202372644805,
|
| 847 |
+
"grad_norm": 5.490713119506836,
|
| 848 |
+
"learning_rate": 2.3833304256803908e-05,
|
| 849 |
+
"loss": 2.076,
|
| 850 |
+
"step": 12000
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 4.221912072575018,
|
| 854 |
+
"grad_norm": 5.069546699523926,
|
| 855 |
+
"learning_rate": 2.361523028611305e-05,
|
| 856 |
+
"loss": 2.0744,
|
| 857 |
+
"step": 12100
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 4.256803907885555,
|
| 861 |
+
"grad_norm": 5.110651016235352,
|
| 862 |
+
"learning_rate": 2.339715631542219e-05,
|
| 863 |
+
"loss": 2.058,
|
| 864 |
+
"step": 12200
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 4.291695743196092,
|
| 868 |
+
"grad_norm": 5.666290760040283,
|
| 869 |
+
"learning_rate": 2.3179082344731334e-05,
|
| 870 |
+
"loss": 2.111,
|
| 871 |
+
"step": 12300
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 4.326587578506629,
|
| 875 |
+
"grad_norm": 5.498898983001709,
|
| 876 |
+
"learning_rate": 2.2961008374040477e-05,
|
| 877 |
+
"loss": 2.0557,
|
| 878 |
+
"step": 12400
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 4.361479413817166,
|
| 882 |
+
"grad_norm": 5.75054407119751,
|
| 883 |
+
"learning_rate": 2.2742934403349617e-05,
|
| 884 |
+
"loss": 2.0703,
|
| 885 |
+
"step": 12500
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 4.3963712491277045,
|
| 889 |
+
"grad_norm": 5.280162811279297,
|
| 890 |
+
"learning_rate": 2.252486043265876e-05,
|
| 891 |
+
"loss": 2.0588,
|
| 892 |
+
"step": 12600
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 4.431263084438242,
|
| 896 |
+
"grad_norm": 5.701440334320068,
|
| 897 |
+
"learning_rate": 2.2306786461967903e-05,
|
| 898 |
+
"loss": 2.0804,
|
| 899 |
+
"step": 12700
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 4.466154919748779,
|
| 903 |
+
"grad_norm": 5.908513069152832,
|
| 904 |
+
"learning_rate": 2.2088712491277043e-05,
|
| 905 |
+
"loss": 2.0645,
|
| 906 |
+
"step": 12800
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 4.501046755059316,
|
| 910 |
+
"grad_norm": 4.762182712554932,
|
| 911 |
+
"learning_rate": 2.1870638520586183e-05,
|
| 912 |
+
"loss": 2.0615,
|
| 913 |
+
"step": 12900
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 4.535938590369853,
|
| 917 |
+
"grad_norm": 5.06411075592041,
|
| 918 |
+
"learning_rate": 2.1652564549895326e-05,
|
| 919 |
+
"loss": 2.0684,
|
| 920 |
+
"step": 13000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 4.57083042568039,
|
| 924 |
+
"grad_norm": 5.691733360290527,
|
| 925 |
+
"learning_rate": 2.1434490579204465e-05,
|
| 926 |
+
"loss": 2.0636,
|
| 927 |
+
"step": 13100
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 4.6057222609909285,
|
| 931 |
+
"grad_norm": 5.261690139770508,
|
| 932 |
+
"learning_rate": 2.121641660851361e-05,
|
| 933 |
+
"loss": 2.0679,
|
| 934 |
+
"step": 13200
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 4.640614096301466,
|
| 938 |
+
"grad_norm": 5.58465051651001,
|
| 939 |
+
"learning_rate": 2.099834263782275e-05,
|
| 940 |
+
"loss": 2.086,
|
| 941 |
+
"step": 13300
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 4.675505931612003,
|
| 945 |
+
"grad_norm": 5.2169952392578125,
|
| 946 |
+
"learning_rate": 2.078026866713189e-05,
|
| 947 |
+
"loss": 2.0703,
|
| 948 |
+
"step": 13400
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 4.71039776692254,
|
| 952 |
+
"grad_norm": 5.576324939727783,
|
| 953 |
+
"learning_rate": 2.0562194696441034e-05,
|
| 954 |
+
"loss": 2.0862,
|
| 955 |
+
"step": 13500
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 4.745289602233077,
|
| 959 |
+
"grad_norm": 5.461946964263916,
|
| 960 |
+
"learning_rate": 2.0344120725750178e-05,
|
| 961 |
+
"loss": 2.0627,
|
| 962 |
+
"step": 13600
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 4.7801814375436145,
|
| 966 |
+
"grad_norm": 5.098294258117676,
|
| 967 |
+
"learning_rate": 2.0126046755059317e-05,
|
| 968 |
+
"loss": 2.0736,
|
| 969 |
+
"step": 13700
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 4.815073272854152,
|
| 973 |
+
"grad_norm": 5.7679853439331055,
|
| 974 |
+
"learning_rate": 1.990797278436846e-05,
|
| 975 |
+
"loss": 2.0635,
|
| 976 |
+
"step": 13800
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 4.84996510816469,
|
| 980 |
+
"grad_norm": 5.441159725189209,
|
| 981 |
+
"learning_rate": 1.96898988136776e-05,
|
| 982 |
+
"loss": 2.1033,
|
| 983 |
+
"step": 13900
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 4.884856943475227,
|
| 987 |
+
"grad_norm": 6.114187717437744,
|
| 988 |
+
"learning_rate": 1.947182484298674e-05,
|
| 989 |
+
"loss": 2.0641,
|
| 990 |
+
"step": 14000
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 4.919748778785764,
|
| 994 |
+
"grad_norm": 5.230809688568115,
|
| 995 |
+
"learning_rate": 1.9253750872295883e-05,
|
| 996 |
+
"loss": 2.0742,
|
| 997 |
+
"step": 14100
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 4.954640614096301,
|
| 1001 |
+
"grad_norm": 5.573941707611084,
|
| 1002 |
+
"learning_rate": 1.9035676901605026e-05,
|
| 1003 |
+
"loss": 2.0967,
|
| 1004 |
+
"step": 14200
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 4.9895324494068385,
|
| 1008 |
+
"grad_norm": 5.449982166290283,
|
| 1009 |
+
"learning_rate": 1.8817602930914166e-05,
|
| 1010 |
+
"loss": 2.0524,
|
| 1011 |
+
"step": 14300
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 5.024424284717377,
|
| 1015 |
+
"grad_norm": 5.071106433868408,
|
| 1016 |
+
"learning_rate": 1.859952896022331e-05,
|
| 1017 |
+
"loss": 1.9743,
|
| 1018 |
+
"step": 14400
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 5.059316120027914,
|
| 1022 |
+
"grad_norm": 5.510537624359131,
|
| 1023 |
+
"learning_rate": 1.8381454989532452e-05,
|
| 1024 |
+
"loss": 1.8963,
|
| 1025 |
+
"step": 14500
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 5.094207955338451,
|
| 1029 |
+
"grad_norm": 5.249537467956543,
|
| 1030 |
+
"learning_rate": 1.816338101884159e-05,
|
| 1031 |
+
"loss": 1.9142,
|
| 1032 |
+
"step": 14600
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 5.129099790648988,
|
| 1036 |
+
"grad_norm": 6.67589807510376,
|
| 1037 |
+
"learning_rate": 1.7945307048150735e-05,
|
| 1038 |
+
"loss": 1.888,
|
| 1039 |
+
"step": 14700
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 5.163991625959525,
|
| 1043 |
+
"grad_norm": 5.381292819976807,
|
| 1044 |
+
"learning_rate": 1.7727233077459874e-05,
|
| 1045 |
+
"loss": 1.9226,
|
| 1046 |
+
"step": 14800
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 5.1988834612700625,
|
| 1050 |
+
"grad_norm": 5.443178653717041,
|
| 1051 |
+
"learning_rate": 1.7509159106769018e-05,
|
| 1052 |
+
"loss": 1.901,
|
| 1053 |
+
"step": 14900
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 5.2337752965806,
|
| 1057 |
+
"grad_norm": 5.7889018058776855,
|
| 1058 |
+
"learning_rate": 1.7291085136078157e-05,
|
| 1059 |
+
"loss": 1.9326,
|
| 1060 |
+
"step": 15000
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 5.268667131891138,
|
| 1064 |
+
"grad_norm": 5.440788745880127,
|
| 1065 |
+
"learning_rate": 1.70730111653873e-05,
|
| 1066 |
+
"loss": 1.9295,
|
| 1067 |
+
"step": 15100
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 5.303558967201675,
|
| 1071 |
+
"grad_norm": 5.275712490081787,
|
| 1072 |
+
"learning_rate": 1.685493719469644e-05,
|
| 1073 |
+
"loss": 1.9146,
|
| 1074 |
+
"step": 15200
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 5.338450802512212,
|
| 1078 |
+
"grad_norm": 5.518808841705322,
|
| 1079 |
+
"learning_rate": 1.6636863224005583e-05,
|
| 1080 |
+
"loss": 1.9308,
|
| 1081 |
+
"step": 15300
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 5.373342637822749,
|
| 1085 |
+
"grad_norm": 5.810028553009033,
|
| 1086 |
+
"learning_rate": 1.6418789253314726e-05,
|
| 1087 |
+
"loss": 1.9393,
|
| 1088 |
+
"step": 15400
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 5.4082344731332865,
|
| 1092 |
+
"grad_norm": 5.17830753326416,
|
| 1093 |
+
"learning_rate": 1.6200715282623866e-05,
|
| 1094 |
+
"loss": 1.9166,
|
| 1095 |
+
"step": 15500
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 5.443126308443825,
|
| 1099 |
+
"grad_norm": 5.424782752990723,
|
| 1100 |
+
"learning_rate": 1.598264131193301e-05,
|
| 1101 |
+
"loss": 1.8713,
|
| 1102 |
+
"step": 15600
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 5.478018143754362,
|
| 1106 |
+
"grad_norm": 5.202701568603516,
|
| 1107 |
+
"learning_rate": 1.5764567341242152e-05,
|
| 1108 |
+
"loss": 1.9279,
|
| 1109 |
+
"step": 15700
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 5.512909979064899,
|
| 1113 |
+
"grad_norm": 5.875789642333984,
|
| 1114 |
+
"learning_rate": 1.5546493370551292e-05,
|
| 1115 |
+
"loss": 1.9216,
|
| 1116 |
+
"step": 15800
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 5.547801814375436,
|
| 1120 |
+
"grad_norm": 5.769129276275635,
|
| 1121 |
+
"learning_rate": 1.532841939986043e-05,
|
| 1122 |
+
"loss": 1.9097,
|
| 1123 |
+
"step": 15900
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 5.582693649685973,
|
| 1127 |
+
"grad_norm": 5.4025421142578125,
|
| 1128 |
+
"learning_rate": 1.5110345429169576e-05,
|
| 1129 |
+
"loss": 1.9151,
|
| 1130 |
+
"step": 16000
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 5.617585484996511,
|
| 1134 |
+
"grad_norm": 4.817849636077881,
|
| 1135 |
+
"learning_rate": 1.4892271458478716e-05,
|
| 1136 |
+
"loss": 1.9122,
|
| 1137 |
+
"step": 16100
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 5.652477320307048,
|
| 1141 |
+
"grad_norm": 5.83222770690918,
|
| 1142 |
+
"learning_rate": 1.4674197487787857e-05,
|
| 1143 |
+
"loss": 1.9219,
|
| 1144 |
+
"step": 16200
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 5.687369155617586,
|
| 1148 |
+
"grad_norm": 5.329492092132568,
|
| 1149 |
+
"learning_rate": 1.4456123517097e-05,
|
| 1150 |
+
"loss": 1.9142,
|
| 1151 |
+
"step": 16300
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 5.722260990928123,
|
| 1155 |
+
"grad_norm": 5.5221686363220215,
|
| 1156 |
+
"learning_rate": 1.423804954640614e-05,
|
| 1157 |
+
"loss": 1.9194,
|
| 1158 |
+
"step": 16400
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 5.75715282623866,
|
| 1162 |
+
"grad_norm": 6.1820197105407715,
|
| 1163 |
+
"learning_rate": 1.4019975575715283e-05,
|
| 1164 |
+
"loss": 1.937,
|
| 1165 |
+
"step": 16500
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 5.792044661549197,
|
| 1169 |
+
"grad_norm": 5.7394232749938965,
|
| 1170 |
+
"learning_rate": 1.3801901605024425e-05,
|
| 1171 |
+
"loss": 1.919,
|
| 1172 |
+
"step": 16600
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 5.826936496859735,
|
| 1176 |
+
"grad_norm": 5.4087042808532715,
|
| 1177 |
+
"learning_rate": 1.3583827634333568e-05,
|
| 1178 |
+
"loss": 1.9118,
|
| 1179 |
+
"step": 16700
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 5.861828332170272,
|
| 1183 |
+
"grad_norm": 5.745779037475586,
|
| 1184 |
+
"learning_rate": 1.3365753663642708e-05,
|
| 1185 |
+
"loss": 1.934,
|
| 1186 |
+
"step": 16800
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 5.89672016748081,
|
| 1190 |
+
"grad_norm": 5.784609794616699,
|
| 1191 |
+
"learning_rate": 1.314767969295185e-05,
|
| 1192 |
+
"loss": 1.9248,
|
| 1193 |
+
"step": 16900
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 5.931612002791347,
|
| 1197 |
+
"grad_norm": 7.318721294403076,
|
| 1198 |
+
"learning_rate": 1.2929605722260992e-05,
|
| 1199 |
+
"loss": 1.9192,
|
| 1200 |
+
"step": 17000
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 5.966503838101884,
|
| 1204 |
+
"grad_norm": 5.4304304122924805,
|
| 1205 |
+
"learning_rate": 1.2711531751570133e-05,
|
| 1206 |
+
"loss": 1.948,
|
| 1207 |
+
"step": 17100
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 6.001395673412421,
|
| 1211 |
+
"grad_norm": 5.5656609535217285,
|
| 1212 |
+
"learning_rate": 1.2493457780879275e-05,
|
| 1213 |
+
"loss": 1.9194,
|
| 1214 |
+
"step": 17200
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 6.036287508722959,
|
| 1218 |
+
"grad_norm": 5.588869094848633,
|
| 1219 |
+
"learning_rate": 1.2275383810188416e-05,
|
| 1220 |
+
"loss": 1.78,
|
| 1221 |
+
"step": 17300
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 6.071179344033496,
|
| 1225 |
+
"grad_norm": 5.662446975708008,
|
| 1226 |
+
"learning_rate": 1.2057309839497558e-05,
|
| 1227 |
+
"loss": 1.7815,
|
| 1228 |
+
"step": 17400
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 6.106071179344034,
|
| 1232 |
+
"grad_norm": 5.681488037109375,
|
| 1233 |
+
"learning_rate": 1.18392358688067e-05,
|
| 1234 |
+
"loss": 1.7902,
|
| 1235 |
+
"step": 17500
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 6.140963014654571,
|
| 1239 |
+
"grad_norm": 5.237543106079102,
|
| 1240 |
+
"learning_rate": 1.162116189811584e-05,
|
| 1241 |
+
"loss": 1.7949,
|
| 1242 |
+
"step": 17600
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 6.175854849965108,
|
| 1246 |
+
"grad_norm": 6.3692474365234375,
|
| 1247 |
+
"learning_rate": 1.1403087927424982e-05,
|
| 1248 |
+
"loss": 1.7712,
|
| 1249 |
+
"step": 17700
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 6.210746685275645,
|
| 1253 |
+
"grad_norm": 5.9078049659729,
|
| 1254 |
+
"learning_rate": 1.1185013956734125e-05,
|
| 1255 |
+
"loss": 1.7964,
|
| 1256 |
+
"step": 17800
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 6.245638520586183,
|
| 1260 |
+
"grad_norm": 5.628890037536621,
|
| 1261 |
+
"learning_rate": 1.0966939986043266e-05,
|
| 1262 |
+
"loss": 1.7937,
|
| 1263 |
+
"step": 17900
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 6.28053035589672,
|
| 1267 |
+
"grad_norm": 5.680924415588379,
|
| 1268 |
+
"learning_rate": 1.074886601535241e-05,
|
| 1269 |
+
"loss": 1.8011,
|
| 1270 |
+
"step": 18000
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 6.315422191207258,
|
| 1274 |
+
"grad_norm": 5.3683857917785645,
|
| 1275 |
+
"learning_rate": 1.053079204466155e-05,
|
| 1276 |
+
"loss": 1.8093,
|
| 1277 |
+
"step": 18100
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 6.350314026517795,
|
| 1281 |
+
"grad_norm": 6.106055736541748,
|
| 1282 |
+
"learning_rate": 1.031271807397069e-05,
|
| 1283 |
+
"loss": 1.8021,
|
| 1284 |
+
"step": 18200
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 6.385205861828332,
|
| 1288 |
+
"grad_norm": 5.841535568237305,
|
| 1289 |
+
"learning_rate": 1.0094644103279834e-05,
|
| 1290 |
+
"loss": 1.8266,
|
| 1291 |
+
"step": 18300
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 6.4200976971388695,
|
| 1295 |
+
"grad_norm": 5.864353179931641,
|
| 1296 |
+
"learning_rate": 9.876570132588975e-06,
|
| 1297 |
+
"loss": 1.8075,
|
| 1298 |
+
"step": 18400
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 6.454989532449407,
|
| 1302 |
+
"grad_norm": 8.195747375488281,
|
| 1303 |
+
"learning_rate": 9.658496161898117e-06,
|
| 1304 |
+
"loss": 1.8123,
|
| 1305 |
+
"step": 18500
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 6.489881367759944,
|
| 1309 |
+
"grad_norm": 6.448851585388184,
|
| 1310 |
+
"learning_rate": 9.440422191207258e-06,
|
| 1311 |
+
"loss": 1.7956,
|
| 1312 |
+
"step": 18600
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 6.524773203070481,
|
| 1316 |
+
"grad_norm": 5.370660305023193,
|
| 1317 |
+
"learning_rate": 9.2223482205164e-06,
|
| 1318 |
+
"loss": 1.7862,
|
| 1319 |
+
"step": 18700
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 6.559665038381019,
|
| 1323 |
+
"grad_norm": 5.711855411529541,
|
| 1324 |
+
"learning_rate": 9.00427424982554e-06,
|
| 1325 |
+
"loss": 1.8082,
|
| 1326 |
+
"step": 18800
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 6.594556873691556,
|
| 1330 |
+
"grad_norm": 5.534999847412109,
|
| 1331 |
+
"learning_rate": 8.786200279134684e-06,
|
| 1332 |
+
"loss": 1.8117,
|
| 1333 |
+
"step": 18900
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 6.6294487090020935,
|
| 1337 |
+
"grad_norm": 5.1350789070129395,
|
| 1338 |
+
"learning_rate": 8.568126308443825e-06,
|
| 1339 |
+
"loss": 1.8072,
|
| 1340 |
+
"step": 19000
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 6.664340544312631,
|
| 1344 |
+
"grad_norm": 5.525078773498535,
|
| 1345 |
+
"learning_rate": 8.350052337752965e-06,
|
| 1346 |
+
"loss": 1.7891,
|
| 1347 |
+
"step": 19100
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 6.699232379623168,
|
| 1351 |
+
"grad_norm": 5.587681293487549,
|
| 1352 |
+
"learning_rate": 8.131978367062108e-06,
|
| 1353 |
+
"loss": 1.786,
|
| 1354 |
+
"step": 19200
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 6.734124214933706,
|
| 1358 |
+
"grad_norm": 5.702240467071533,
|
| 1359 |
+
"learning_rate": 7.91390439637125e-06,
|
| 1360 |
+
"loss": 1.8239,
|
| 1361 |
+
"step": 19300
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 6.769016050244243,
|
| 1365 |
+
"grad_norm": 6.304993152618408,
|
| 1366 |
+
"learning_rate": 7.695830425680391e-06,
|
| 1367 |
+
"loss": 1.8181,
|
| 1368 |
+
"step": 19400
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 6.80390788555478,
|
| 1372 |
+
"grad_norm": 5.786768913269043,
|
| 1373 |
+
"learning_rate": 7.477756454989533e-06,
|
| 1374 |
+
"loss": 1.8127,
|
| 1375 |
+
"step": 19500
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 6.8387997208653175,
|
| 1379 |
+
"grad_norm": 5.68336820602417,
|
| 1380 |
+
"learning_rate": 7.2596824842986745e-06,
|
| 1381 |
+
"loss": 1.7917,
|
| 1382 |
+
"step": 19600
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 6.873691556175855,
|
| 1386 |
+
"grad_norm": 5.827804088592529,
|
| 1387 |
+
"learning_rate": 7.041608513607816e-06,
|
| 1388 |
+
"loss": 1.8309,
|
| 1389 |
+
"step": 19700
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 6.908583391486392,
|
| 1393 |
+
"grad_norm": 5.98842716217041,
|
| 1394 |
+
"learning_rate": 6.823534542916958e-06,
|
| 1395 |
+
"loss": 1.7808,
|
| 1396 |
+
"step": 19800
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 6.943475226796929,
|
| 1400 |
+
"grad_norm": 5.252569198608398,
|
| 1401 |
+
"learning_rate": 6.6054605722261e-06,
|
| 1402 |
+
"loss": 1.8115,
|
| 1403 |
+
"step": 19900
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 6.978367062107467,
|
| 1407 |
+
"grad_norm": 5.1013288497924805,
|
| 1408 |
+
"learning_rate": 6.38738660153524e-06,
|
| 1409 |
+
"loss": 1.7922,
|
| 1410 |
+
"step": 20000
|
| 1411 |
+
}
|
| 1412 |
+
],
|
| 1413 |
+
"logging_steps": 100,
|
| 1414 |
+
"max_steps": 22928,
|
| 1415 |
+
"num_input_tokens_seen": 0,
|
| 1416 |
+
"num_train_epochs": 8,
|
| 1417 |
+
"save_steps": 500,
|
| 1418 |
+
"stateful_callbacks": {
|
| 1419 |
+
"TrainerControl": {
|
| 1420 |
+
"args": {
|
| 1421 |
+
"should_epoch_stop": false,
|
| 1422 |
+
"should_evaluate": false,
|
| 1423 |
+
"should_log": false,
|
| 1424 |
+
"should_save": true,
|
| 1425 |
+
"should_training_stop": false
|
| 1426 |
+
},
|
| 1427 |
+
"attributes": {}
|
| 1428 |
+
}
|
| 1429 |
+
},
|
| 1430 |
+
"total_flos": 0.0,
|
| 1431 |
+
"train_batch_size": 50,
|
| 1432 |
+
"trial_name": null,
|
| 1433 |
+
"trial_params": null
|
| 1434 |
+
}
|
checkpoint-20062/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d04177183f69ff02a9a61d43a95f7d4481d2d791b52a88b41d83152a07032546
|
| 3 |
+
size 5969
|
checkpoint-20062/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-22928/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-22928/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc37573335e7d2903e70b51db18f99235822768d87a9634e4569997dd4a7b3b6
|
| 3 |
+
size 1370834379
|
checkpoint-22928/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc13070ab752c0ca947526b410b802ef731fcc22fe42d3fec939351b1c197a7c
|
| 3 |
+
size 719294071
|
checkpoint-22928/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bde1a47d6647efb19a42ad9ededd889081da6fe43de63b87639a03be4423eded
|
| 3 |
+
size 14645
|
checkpoint-22928/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef0e157453d0aff95371e87af1281bcdd845be4b2de7caed71179743360f35c9
|
| 3 |
+
size 1465
|
checkpoint-22928/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-22928/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-22928/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 512,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
checkpoint-22928/trainer_state.json
ADDED
|
@@ -0,0 +1,1637 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 8.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 22928,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.034891835310537335,
|
| 14 |
+
"grad_norm": 4.449178218841553,
|
| 15 |
+
"learning_rate": 4.9784106769016056e-05,
|
| 16 |
+
"loss": 7.4361,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.06978367062107467,
|
| 21 |
+
"grad_norm": 4.605655670166016,
|
| 22 |
+
"learning_rate": 4.95660327983252e-05,
|
| 23 |
+
"loss": 5.6934,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.104675505931612,
|
| 28 |
+
"grad_norm": 5.126296520233154,
|
| 29 |
+
"learning_rate": 4.9347958827634335e-05,
|
| 30 |
+
"loss": 5.1849,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.13956734124214934,
|
| 35 |
+
"grad_norm": 5.184763431549072,
|
| 36 |
+
"learning_rate": 4.912988485694348e-05,
|
| 37 |
+
"loss": 4.9327,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.17445917655268667,
|
| 42 |
+
"grad_norm": 4.761885643005371,
|
| 43 |
+
"learning_rate": 4.891181088625262e-05,
|
| 44 |
+
"loss": 4.7416,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.209351011863224,
|
| 49 |
+
"grad_norm": 4.478248596191406,
|
| 50 |
+
"learning_rate": 4.869373691556176e-05,
|
| 51 |
+
"loss": 4.5712,
|
| 52 |
+
"step": 600
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.24424284717376135,
|
| 56 |
+
"grad_norm": 4.7443928718566895,
|
| 57 |
+
"learning_rate": 4.84756629448709e-05,
|
| 58 |
+
"loss": 4.4319,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.2791346824842987,
|
| 63 |
+
"grad_norm": 4.571919918060303,
|
| 64 |
+
"learning_rate": 4.8257588974180044e-05,
|
| 65 |
+
"loss": 4.3216,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.31402651779483604,
|
| 70 |
+
"grad_norm": 4.504453182220459,
|
| 71 |
+
"learning_rate": 4.803951500348919e-05,
|
| 72 |
+
"loss": 4.1818,
|
| 73 |
+
"step": 900
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.34891835310537334,
|
| 77 |
+
"grad_norm": 4.749291896820068,
|
| 78 |
+
"learning_rate": 4.782144103279832e-05,
|
| 79 |
+
"loss": 4.0893,
|
| 80 |
+
"step": 1000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.3838101884159107,
|
| 84 |
+
"grad_norm": 4.697039604187012,
|
| 85 |
+
"learning_rate": 4.7603367062107466e-05,
|
| 86 |
+
"loss": 4.0596,
|
| 87 |
+
"step": 1100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.418702023726448,
|
| 91 |
+
"grad_norm": 4.919949054718018,
|
| 92 |
+
"learning_rate": 4.738529309141661e-05,
|
| 93 |
+
"loss": 4.0145,
|
| 94 |
+
"step": 1200
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.45359385903698535,
|
| 98 |
+
"grad_norm": 4.816226482391357,
|
| 99 |
+
"learning_rate": 4.716721912072575e-05,
|
| 100 |
+
"loss": 3.9097,
|
| 101 |
+
"step": 1300
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.4884856943475227,
|
| 105 |
+
"grad_norm": 4.794589519500732,
|
| 106 |
+
"learning_rate": 4.6949145150034896e-05,
|
| 107 |
+
"loss": 3.8486,
|
| 108 |
+
"step": 1400
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.5233775296580601,
|
| 112 |
+
"grad_norm": 4.941982269287109,
|
| 113 |
+
"learning_rate": 4.673107117934404e-05,
|
| 114 |
+
"loss": 3.8414,
|
| 115 |
+
"step": 1500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.5582693649685974,
|
| 119 |
+
"grad_norm": 4.8971452713012695,
|
| 120 |
+
"learning_rate": 4.6512997208653175e-05,
|
| 121 |
+
"loss": 3.7677,
|
| 122 |
+
"step": 1600
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.5931612002791347,
|
| 126 |
+
"grad_norm": 4.788393974304199,
|
| 127 |
+
"learning_rate": 4.629492323796232e-05,
|
| 128 |
+
"loss": 3.7563,
|
| 129 |
+
"step": 1700
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.6280530355896721,
|
| 133 |
+
"grad_norm": 8.283535957336426,
|
| 134 |
+
"learning_rate": 4.607684926727146e-05,
|
| 135 |
+
"loss": 3.702,
|
| 136 |
+
"step": 1800
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.6629448709002094,
|
| 140 |
+
"grad_norm": 4.443343639373779,
|
| 141 |
+
"learning_rate": 4.5858775296580604e-05,
|
| 142 |
+
"loss": 3.6575,
|
| 143 |
+
"step": 1900
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.6978367062107467,
|
| 147 |
+
"grad_norm": 4.8935956954956055,
|
| 148 |
+
"learning_rate": 4.564070132588975e-05,
|
| 149 |
+
"loss": 3.6542,
|
| 150 |
+
"step": 2000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.732728541521284,
|
| 154 |
+
"grad_norm": 4.706109523773193,
|
| 155 |
+
"learning_rate": 4.542262735519889e-05,
|
| 156 |
+
"loss": 3.588,
|
| 157 |
+
"step": 2100
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.7676203768318214,
|
| 161 |
+
"grad_norm": 5.829479694366455,
|
| 162 |
+
"learning_rate": 4.520455338450803e-05,
|
| 163 |
+
"loss": 3.5628,
|
| 164 |
+
"step": 2200
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.8025122121423587,
|
| 168 |
+
"grad_norm": 5.121861457824707,
|
| 169 |
+
"learning_rate": 4.498647941381717e-05,
|
| 170 |
+
"loss": 3.5284,
|
| 171 |
+
"step": 2300
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.837404047452896,
|
| 175 |
+
"grad_norm": 9.078815460205078,
|
| 176 |
+
"learning_rate": 4.476840544312631e-05,
|
| 177 |
+
"loss": 3.5192,
|
| 178 |
+
"step": 2400
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.8722958827634334,
|
| 182 |
+
"grad_norm": 4.904483318328857,
|
| 183 |
+
"learning_rate": 4.455033147243545e-05,
|
| 184 |
+
"loss": 3.4818,
|
| 185 |
+
"step": 2500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.9071877180739707,
|
| 189 |
+
"grad_norm": 4.965977668762207,
|
| 190 |
+
"learning_rate": 4.433225750174459e-05,
|
| 191 |
+
"loss": 3.4393,
|
| 192 |
+
"step": 2600
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.942079553384508,
|
| 196 |
+
"grad_norm": 4.89396858215332,
|
| 197 |
+
"learning_rate": 4.4114183531053736e-05,
|
| 198 |
+
"loss": 3.4231,
|
| 199 |
+
"step": 2700
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.9769713886950454,
|
| 203 |
+
"grad_norm": 5.0034661293029785,
|
| 204 |
+
"learning_rate": 4.389610956036287e-05,
|
| 205 |
+
"loss": 3.3895,
|
| 206 |
+
"step": 2800
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.0118632240055827,
|
| 210 |
+
"grad_norm": 4.820219039916992,
|
| 211 |
+
"learning_rate": 4.3678035589672015e-05,
|
| 212 |
+
"loss": 3.2998,
|
| 213 |
+
"step": 2900
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.0467550593161201,
|
| 217 |
+
"grad_norm": 4.667869567871094,
|
| 218 |
+
"learning_rate": 4.345996161898116e-05,
|
| 219 |
+
"loss": 3.172,
|
| 220 |
+
"step": 3000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.0816468946266573,
|
| 224 |
+
"grad_norm": 4.847691059112549,
|
| 225 |
+
"learning_rate": 4.32418876482903e-05,
|
| 226 |
+
"loss": 3.1746,
|
| 227 |
+
"step": 3100
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.1165387299371947,
|
| 231 |
+
"grad_norm": 4.929681301116943,
|
| 232 |
+
"learning_rate": 4.3023813677599444e-05,
|
| 233 |
+
"loss": 3.1565,
|
| 234 |
+
"step": 3200
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.1514305652477321,
|
| 238 |
+
"grad_norm": 5.4113359451293945,
|
| 239 |
+
"learning_rate": 4.280573970690859e-05,
|
| 240 |
+
"loss": 3.1381,
|
| 241 |
+
"step": 3300
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.1863224005582693,
|
| 245 |
+
"grad_norm": 5.372176647186279,
|
| 246 |
+
"learning_rate": 4.2587665736217724e-05,
|
| 247 |
+
"loss": 3.1268,
|
| 248 |
+
"step": 3400
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.2212142358688067,
|
| 252 |
+
"grad_norm": 5.134545803070068,
|
| 253 |
+
"learning_rate": 4.236959176552687e-05,
|
| 254 |
+
"loss": 3.1067,
|
| 255 |
+
"step": 3500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.2561060711793441,
|
| 259 |
+
"grad_norm": 5.3275861740112305,
|
| 260 |
+
"learning_rate": 4.215151779483601e-05,
|
| 261 |
+
"loss": 3.0777,
|
| 262 |
+
"step": 3600
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.2909979064898813,
|
| 266 |
+
"grad_norm": 5.151634216308594,
|
| 267 |
+
"learning_rate": 4.193344382414515e-05,
|
| 268 |
+
"loss": 3.067,
|
| 269 |
+
"step": 3700
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.3258897418004187,
|
| 273 |
+
"grad_norm": 5.169743061065674,
|
| 274 |
+
"learning_rate": 4.1715369853454296e-05,
|
| 275 |
+
"loss": 3.0564,
|
| 276 |
+
"step": 3800
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.3607815771109562,
|
| 280 |
+
"grad_norm": 4.969324588775635,
|
| 281 |
+
"learning_rate": 4.149729588276344e-05,
|
| 282 |
+
"loss": 3.0547,
|
| 283 |
+
"step": 3900
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.3956734124214933,
|
| 287 |
+
"grad_norm": 4.806005477905273,
|
| 288 |
+
"learning_rate": 4.1279221912072576e-05,
|
| 289 |
+
"loss": 3.0324,
|
| 290 |
+
"step": 4000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.4305652477320308,
|
| 294 |
+
"grad_norm": 5.4942426681518555,
|
| 295 |
+
"learning_rate": 4.106114794138172e-05,
|
| 296 |
+
"loss": 3.0307,
|
| 297 |
+
"step": 4100
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.4654570830425682,
|
| 301 |
+
"grad_norm": 5.495986461639404,
|
| 302 |
+
"learning_rate": 4.084307397069086e-05,
|
| 303 |
+
"loss": 3.0058,
|
| 304 |
+
"step": 4200
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.5003489183531054,
|
| 308 |
+
"grad_norm": 4.752720355987549,
|
| 309 |
+
"learning_rate": 4.0625000000000005e-05,
|
| 310 |
+
"loss": 2.9856,
|
| 311 |
+
"step": 4300
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.5352407536636425,
|
| 315 |
+
"grad_norm": 4.929941654205322,
|
| 316 |
+
"learning_rate": 4.040692602930914e-05,
|
| 317 |
+
"loss": 2.9931,
|
| 318 |
+
"step": 4400
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.5701325889741802,
|
| 322 |
+
"grad_norm": 4.883072853088379,
|
| 323 |
+
"learning_rate": 4.0188852058618284e-05,
|
| 324 |
+
"loss": 2.9824,
|
| 325 |
+
"step": 4500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.6050244242847174,
|
| 329 |
+
"grad_norm": 5.3392333984375,
|
| 330 |
+
"learning_rate": 3.997077808792743e-05,
|
| 331 |
+
"loss": 2.9538,
|
| 332 |
+
"step": 4600
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.6399162595952546,
|
| 336 |
+
"grad_norm": 5.304770469665527,
|
| 337 |
+
"learning_rate": 3.9752704117236564e-05,
|
| 338 |
+
"loss": 2.9584,
|
| 339 |
+
"step": 4700
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.6748080949057922,
|
| 343 |
+
"grad_norm": 5.055889129638672,
|
| 344 |
+
"learning_rate": 3.953463014654571e-05,
|
| 345 |
+
"loss": 2.9221,
|
| 346 |
+
"step": 4800
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.7096999302163294,
|
| 350 |
+
"grad_norm": 5.006368637084961,
|
| 351 |
+
"learning_rate": 3.931655617585485e-05,
|
| 352 |
+
"loss": 2.9154,
|
| 353 |
+
"step": 4900
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.7445917655268666,
|
| 357 |
+
"grad_norm": 5.258544921875,
|
| 358 |
+
"learning_rate": 3.909848220516399e-05,
|
| 359 |
+
"loss": 2.9123,
|
| 360 |
+
"step": 5000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.7794836008374042,
|
| 364 |
+
"grad_norm": 4.940785884857178,
|
| 365 |
+
"learning_rate": 3.8880408234473136e-05,
|
| 366 |
+
"loss": 2.8721,
|
| 367 |
+
"step": 5100
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.8143754361479414,
|
| 371 |
+
"grad_norm": 5.046368598937988,
|
| 372 |
+
"learning_rate": 3.866233426378228e-05,
|
| 373 |
+
"loss": 2.8598,
|
| 374 |
+
"step": 5200
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.8492672714584786,
|
| 378 |
+
"grad_norm": 5.59748649597168,
|
| 379 |
+
"learning_rate": 3.8444260293091416e-05,
|
| 380 |
+
"loss": 2.8819,
|
| 381 |
+
"step": 5300
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.8841591067690162,
|
| 385 |
+
"grad_norm": 5.261348247528076,
|
| 386 |
+
"learning_rate": 3.822618632240056e-05,
|
| 387 |
+
"loss": 2.8284,
|
| 388 |
+
"step": 5400
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.9190509420795534,
|
| 392 |
+
"grad_norm": 5.169360160827637,
|
| 393 |
+
"learning_rate": 3.80081123517097e-05,
|
| 394 |
+
"loss": 2.8456,
|
| 395 |
+
"step": 5500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.9539427773900906,
|
| 399 |
+
"grad_norm": 5.436888694763184,
|
| 400 |
+
"learning_rate": 3.7790038381018845e-05,
|
| 401 |
+
"loss": 2.8561,
|
| 402 |
+
"step": 5600
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.988834612700628,
|
| 406 |
+
"grad_norm": 5.126554489135742,
|
| 407 |
+
"learning_rate": 3.757196441032799e-05,
|
| 408 |
+
"loss": 2.8151,
|
| 409 |
+
"step": 5700
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 2.0237264480111654,
|
| 413 |
+
"grad_norm": 4.704784870147705,
|
| 414 |
+
"learning_rate": 3.735389043963713e-05,
|
| 415 |
+
"loss": 2.674,
|
| 416 |
+
"step": 5800
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.0586182833217026,
|
| 420 |
+
"grad_norm": 5.37230920791626,
|
| 421 |
+
"learning_rate": 3.713581646894627e-05,
|
| 422 |
+
"loss": 2.608,
|
| 423 |
+
"step": 5900
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.0935101186322402,
|
| 427 |
+
"grad_norm": 4.852290630340576,
|
| 428 |
+
"learning_rate": 3.691774249825541e-05,
|
| 429 |
+
"loss": 2.591,
|
| 430 |
+
"step": 6000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 2.1284019539427774,
|
| 434 |
+
"grad_norm": 5.700033664703369,
|
| 435 |
+
"learning_rate": 3.6699668527564554e-05,
|
| 436 |
+
"loss": 2.5985,
|
| 437 |
+
"step": 6100
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 2.1632937892533146,
|
| 441 |
+
"grad_norm": 5.340079307556152,
|
| 442 |
+
"learning_rate": 3.64815945568737e-05,
|
| 443 |
+
"loss": 2.5871,
|
| 444 |
+
"step": 6200
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.1981856245638522,
|
| 448 |
+
"grad_norm": 5.0922532081604,
|
| 449 |
+
"learning_rate": 3.626352058618284e-05,
|
| 450 |
+
"loss": 2.5762,
|
| 451 |
+
"step": 6300
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 2.2330774598743894,
|
| 455 |
+
"grad_norm": 5.114669322967529,
|
| 456 |
+
"learning_rate": 3.6045446615491976e-05,
|
| 457 |
+
"loss": 2.5665,
|
| 458 |
+
"step": 6400
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.2679692951849266,
|
| 462 |
+
"grad_norm": 5.286740303039551,
|
| 463 |
+
"learning_rate": 3.582737264480112e-05,
|
| 464 |
+
"loss": 2.5635,
|
| 465 |
+
"step": 6500
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.3028611304954643,
|
| 469 |
+
"grad_norm": 5.458755016326904,
|
| 470 |
+
"learning_rate": 3.5609298674110256e-05,
|
| 471 |
+
"loss": 2.5559,
|
| 472 |
+
"step": 6600
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 2.3377529658060014,
|
| 476 |
+
"grad_norm": 5.574306488037109,
|
| 477 |
+
"learning_rate": 3.53912247034194e-05,
|
| 478 |
+
"loss": 2.5386,
|
| 479 |
+
"step": 6700
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 2.3726448011165386,
|
| 483 |
+
"grad_norm": 5.048354148864746,
|
| 484 |
+
"learning_rate": 3.517315073272854e-05,
|
| 485 |
+
"loss": 2.5325,
|
| 486 |
+
"step": 6800
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 2.407536636427076,
|
| 490 |
+
"grad_norm": 5.464790344238281,
|
| 491 |
+
"learning_rate": 3.4955076762037685e-05,
|
| 492 |
+
"loss": 2.5501,
|
| 493 |
+
"step": 6900
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 2.4424284717376135,
|
| 497 |
+
"grad_norm": 5.763171672821045,
|
| 498 |
+
"learning_rate": 3.473700279134683e-05,
|
| 499 |
+
"loss": 2.5496,
|
| 500 |
+
"step": 7000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 2.4773203070481506,
|
| 504 |
+
"grad_norm": 5.179362773895264,
|
| 505 |
+
"learning_rate": 3.4518928820655964e-05,
|
| 506 |
+
"loss": 2.5447,
|
| 507 |
+
"step": 7100
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 2.5122121423586883,
|
| 511 |
+
"grad_norm": 5.075343132019043,
|
| 512 |
+
"learning_rate": 3.430085484996511e-05,
|
| 513 |
+
"loss": 2.5568,
|
| 514 |
+
"step": 7200
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 2.5471039776692255,
|
| 518 |
+
"grad_norm": 5.105709552764893,
|
| 519 |
+
"learning_rate": 3.408278087927425e-05,
|
| 520 |
+
"loss": 2.5631,
|
| 521 |
+
"step": 7300
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.5819958129797627,
|
| 525 |
+
"grad_norm": 5.484874248504639,
|
| 526 |
+
"learning_rate": 3.3864706908583394e-05,
|
| 527 |
+
"loss": 2.5462,
|
| 528 |
+
"step": 7400
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 2.6168876482903,
|
| 532 |
+
"grad_norm": 5.008668422698975,
|
| 533 |
+
"learning_rate": 3.364663293789254e-05,
|
| 534 |
+
"loss": 2.5169,
|
| 535 |
+
"step": 7500
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 2.6517794836008375,
|
| 539 |
+
"grad_norm": 5.086187362670898,
|
| 540 |
+
"learning_rate": 3.342855896720168e-05,
|
| 541 |
+
"loss": 2.5182,
|
| 542 |
+
"step": 7600
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 2.6866713189113747,
|
| 546 |
+
"grad_norm": 5.237493991851807,
|
| 547 |
+
"learning_rate": 3.3210484996510816e-05,
|
| 548 |
+
"loss": 2.5152,
|
| 549 |
+
"step": 7700
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 2.7215631542219123,
|
| 553 |
+
"grad_norm": 4.8399977684021,
|
| 554 |
+
"learning_rate": 3.299241102581996e-05,
|
| 555 |
+
"loss": 2.5159,
|
| 556 |
+
"step": 7800
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 2.7564549895324495,
|
| 560 |
+
"grad_norm": 5.455721378326416,
|
| 561 |
+
"learning_rate": 3.27743370551291e-05,
|
| 562 |
+
"loss": 2.5059,
|
| 563 |
+
"step": 7900
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 2.7913468248429867,
|
| 567 |
+
"grad_norm": 4.843439102172852,
|
| 568 |
+
"learning_rate": 3.2556263084438245e-05,
|
| 569 |
+
"loss": 2.5007,
|
| 570 |
+
"step": 8000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 2.826238660153524,
|
| 574 |
+
"grad_norm": 5.252379417419434,
|
| 575 |
+
"learning_rate": 3.233818911374739e-05,
|
| 576 |
+
"loss": 2.4966,
|
| 577 |
+
"step": 8100
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 2.8611304954640615,
|
| 581 |
+
"grad_norm": 4.738300800323486,
|
| 582 |
+
"learning_rate": 3.212011514305653e-05,
|
| 583 |
+
"loss": 2.5076,
|
| 584 |
+
"step": 8200
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 2.8960223307745987,
|
| 588 |
+
"grad_norm": 4.630394458770752,
|
| 589 |
+
"learning_rate": 3.190204117236567e-05,
|
| 590 |
+
"loss": 2.5125,
|
| 591 |
+
"step": 8300
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 2.9309141660851363,
|
| 595 |
+
"grad_norm": 5.112858772277832,
|
| 596 |
+
"learning_rate": 3.168396720167481e-05,
|
| 597 |
+
"loss": 2.496,
|
| 598 |
+
"step": 8400
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 2.9658060013956735,
|
| 602 |
+
"grad_norm": 4.9403510093688965,
|
| 603 |
+
"learning_rate": 3.146589323098395e-05,
|
| 604 |
+
"loss": 2.4916,
|
| 605 |
+
"step": 8500
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 3.0006978367062107,
|
| 609 |
+
"grad_norm": 4.983951091766357,
|
| 610 |
+
"learning_rate": 3.124781926029309e-05,
|
| 611 |
+
"loss": 2.4925,
|
| 612 |
+
"step": 8600
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 3.035589672016748,
|
| 616 |
+
"grad_norm": 4.399389743804932,
|
| 617 |
+
"learning_rate": 3.1029745289602233e-05,
|
| 618 |
+
"loss": 2.27,
|
| 619 |
+
"step": 8700
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 3.0704815073272855,
|
| 623 |
+
"grad_norm": 5.247836589813232,
|
| 624 |
+
"learning_rate": 3.0811671318911377e-05,
|
| 625 |
+
"loss": 2.283,
|
| 626 |
+
"step": 8800
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 3.1053733426378227,
|
| 630 |
+
"grad_norm": 5.457115173339844,
|
| 631 |
+
"learning_rate": 3.059359734822051e-05,
|
| 632 |
+
"loss": 2.2568,
|
| 633 |
+
"step": 8900
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 3.14026517794836,
|
| 637 |
+
"grad_norm": 4.6203179359436035,
|
| 638 |
+
"learning_rate": 3.037552337752966e-05,
|
| 639 |
+
"loss": 2.2618,
|
| 640 |
+
"step": 9000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 3.1751570132588975,
|
| 644 |
+
"grad_norm": 5.432634353637695,
|
| 645 |
+
"learning_rate": 3.01574494068388e-05,
|
| 646 |
+
"loss": 2.2945,
|
| 647 |
+
"step": 9100
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 3.2100488485694347,
|
| 651 |
+
"grad_norm": 5.295199871063232,
|
| 652 |
+
"learning_rate": 2.9939375436147942e-05,
|
| 653 |
+
"loss": 2.2687,
|
| 654 |
+
"step": 9200
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 3.244940683879972,
|
| 658 |
+
"grad_norm": 5.510141849517822,
|
| 659 |
+
"learning_rate": 2.9721301465457085e-05,
|
| 660 |
+
"loss": 2.2846,
|
| 661 |
+
"step": 9300
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 3.2798325191905096,
|
| 665 |
+
"grad_norm": 5.49964714050293,
|
| 666 |
+
"learning_rate": 2.950322749476623e-05,
|
| 667 |
+
"loss": 2.2727,
|
| 668 |
+
"step": 9400
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 3.3147243545010467,
|
| 672 |
+
"grad_norm": 5.006816864013672,
|
| 673 |
+
"learning_rate": 2.928515352407537e-05,
|
| 674 |
+
"loss": 2.27,
|
| 675 |
+
"step": 9500
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 3.349616189811584,
|
| 679 |
+
"grad_norm": 4.75443172454834,
|
| 680 |
+
"learning_rate": 2.9067079553384508e-05,
|
| 681 |
+
"loss": 2.2896,
|
| 682 |
+
"step": 9600
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 3.3845080251221216,
|
| 686 |
+
"grad_norm": 5.43818473815918,
|
| 687 |
+
"learning_rate": 2.884900558269365e-05,
|
| 688 |
+
"loss": 2.2823,
|
| 689 |
+
"step": 9700
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 3.4193998604326588,
|
| 693 |
+
"grad_norm": 5.078537940979004,
|
| 694 |
+
"learning_rate": 2.8630931612002794e-05,
|
| 695 |
+
"loss": 2.2689,
|
| 696 |
+
"step": 9800
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 3.454291695743196,
|
| 700 |
+
"grad_norm": 5.591304302215576,
|
| 701 |
+
"learning_rate": 2.8412857641311934e-05,
|
| 702 |
+
"loss": 2.2915,
|
| 703 |
+
"step": 9900
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 3.4891835310537336,
|
| 707 |
+
"grad_norm": 5.2217559814453125,
|
| 708 |
+
"learning_rate": 2.8194783670621077e-05,
|
| 709 |
+
"loss": 2.268,
|
| 710 |
+
"step": 10000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 3.5240753663642708,
|
| 714 |
+
"grad_norm": 5.424462795257568,
|
| 715 |
+
"learning_rate": 2.797670969993022e-05,
|
| 716 |
+
"loss": 2.2562,
|
| 717 |
+
"step": 10100
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 3.558967201674808,
|
| 721 |
+
"grad_norm": 5.45490837097168,
|
| 722 |
+
"learning_rate": 2.7758635729239356e-05,
|
| 723 |
+
"loss": 2.2699,
|
| 724 |
+
"step": 10200
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 3.5938590369853456,
|
| 728 |
+
"grad_norm": 5.29006814956665,
|
| 729 |
+
"learning_rate": 2.75405617585485e-05,
|
| 730 |
+
"loss": 2.2875,
|
| 731 |
+
"step": 10300
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 3.628750872295883,
|
| 735 |
+
"grad_norm": 5.640931606292725,
|
| 736 |
+
"learning_rate": 2.7322487787857642e-05,
|
| 737 |
+
"loss": 2.277,
|
| 738 |
+
"step": 10400
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 3.66364270760642,
|
| 742 |
+
"grad_norm": 5.791449069976807,
|
| 743 |
+
"learning_rate": 2.7104413817166786e-05,
|
| 744 |
+
"loss": 2.289,
|
| 745 |
+
"step": 10500
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 3.698534542916957,
|
| 749 |
+
"grad_norm": 5.233780860900879,
|
| 750 |
+
"learning_rate": 2.688633984647593e-05,
|
| 751 |
+
"loss": 2.2559,
|
| 752 |
+
"step": 10600
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 3.733426378227495,
|
| 756 |
+
"grad_norm": 4.809124946594238,
|
| 757 |
+
"learning_rate": 2.6668265875785072e-05,
|
| 758 |
+
"loss": 2.2699,
|
| 759 |
+
"step": 10700
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 3.768318213538032,
|
| 763 |
+
"grad_norm": 5.174726963043213,
|
| 764 |
+
"learning_rate": 2.6450191905094208e-05,
|
| 765 |
+
"loss": 2.2584,
|
| 766 |
+
"step": 10800
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 3.8032100488485696,
|
| 770 |
+
"grad_norm": 5.181713104248047,
|
| 771 |
+
"learning_rate": 2.623211793440335e-05,
|
| 772 |
+
"loss": 2.2426,
|
| 773 |
+
"step": 10900
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 3.838101884159107,
|
| 777 |
+
"grad_norm": 5.212897777557373,
|
| 778 |
+
"learning_rate": 2.601404396371249e-05,
|
| 779 |
+
"loss": 2.2257,
|
| 780 |
+
"step": 11000
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 3.872993719469644,
|
| 784 |
+
"grad_norm": 5.191478252410889,
|
| 785 |
+
"learning_rate": 2.5795969993021634e-05,
|
| 786 |
+
"loss": 2.2468,
|
| 787 |
+
"step": 11100
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 3.907885554780181,
|
| 791 |
+
"grad_norm": 5.237133979797363,
|
| 792 |
+
"learning_rate": 2.5577896022330777e-05,
|
| 793 |
+
"loss": 2.2529,
|
| 794 |
+
"step": 11200
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 3.942777390090719,
|
| 798 |
+
"grad_norm": 5.110697269439697,
|
| 799 |
+
"learning_rate": 2.535982205163992e-05,
|
| 800 |
+
"loss": 2.2403,
|
| 801 |
+
"step": 11300
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 3.977669225401256,
|
| 805 |
+
"grad_norm": 5.379474639892578,
|
| 806 |
+
"learning_rate": 2.5141748080949056e-05,
|
| 807 |
+
"loss": 2.2432,
|
| 808 |
+
"step": 11400
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 4.012561060711794,
|
| 812 |
+
"grad_norm": 5.239147663116455,
|
| 813 |
+
"learning_rate": 2.49236741102582e-05,
|
| 814 |
+
"loss": 2.1658,
|
| 815 |
+
"step": 11500
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 4.047452896022331,
|
| 819 |
+
"grad_norm": 5.401543140411377,
|
| 820 |
+
"learning_rate": 2.4705600139567343e-05,
|
| 821 |
+
"loss": 2.0642,
|
| 822 |
+
"step": 11600
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 4.082344731332868,
|
| 826 |
+
"grad_norm": 5.2488322257995605,
|
| 827 |
+
"learning_rate": 2.4487526168876486e-05,
|
| 828 |
+
"loss": 2.0671,
|
| 829 |
+
"step": 11700
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 4.117236566643405,
|
| 833 |
+
"grad_norm": 5.270359039306641,
|
| 834 |
+
"learning_rate": 2.4269452198185625e-05,
|
| 835 |
+
"loss": 2.0655,
|
| 836 |
+
"step": 11800
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 4.152128401953942,
|
| 840 |
+
"grad_norm": 5.2798614501953125,
|
| 841 |
+
"learning_rate": 2.4051378227494765e-05,
|
| 842 |
+
"loss": 2.0595,
|
| 843 |
+
"step": 11900
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 4.1870202372644805,
|
| 847 |
+
"grad_norm": 5.490713119506836,
|
| 848 |
+
"learning_rate": 2.3833304256803908e-05,
|
| 849 |
+
"loss": 2.076,
|
| 850 |
+
"step": 12000
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 4.221912072575018,
|
| 854 |
+
"grad_norm": 5.069546699523926,
|
| 855 |
+
"learning_rate": 2.361523028611305e-05,
|
| 856 |
+
"loss": 2.0744,
|
| 857 |
+
"step": 12100
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 4.256803907885555,
|
| 861 |
+
"grad_norm": 5.110651016235352,
|
| 862 |
+
"learning_rate": 2.339715631542219e-05,
|
| 863 |
+
"loss": 2.058,
|
| 864 |
+
"step": 12200
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 4.291695743196092,
|
| 868 |
+
"grad_norm": 5.666290760040283,
|
| 869 |
+
"learning_rate": 2.3179082344731334e-05,
|
| 870 |
+
"loss": 2.111,
|
| 871 |
+
"step": 12300
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 4.326587578506629,
|
| 875 |
+
"grad_norm": 5.498898983001709,
|
| 876 |
+
"learning_rate": 2.2961008374040477e-05,
|
| 877 |
+
"loss": 2.0557,
|
| 878 |
+
"step": 12400
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 4.361479413817166,
|
| 882 |
+
"grad_norm": 5.75054407119751,
|
| 883 |
+
"learning_rate": 2.2742934403349617e-05,
|
| 884 |
+
"loss": 2.0703,
|
| 885 |
+
"step": 12500
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 4.3963712491277045,
|
| 889 |
+
"grad_norm": 5.280162811279297,
|
| 890 |
+
"learning_rate": 2.252486043265876e-05,
|
| 891 |
+
"loss": 2.0588,
|
| 892 |
+
"step": 12600
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 4.431263084438242,
|
| 896 |
+
"grad_norm": 5.701440334320068,
|
| 897 |
+
"learning_rate": 2.2306786461967903e-05,
|
| 898 |
+
"loss": 2.0804,
|
| 899 |
+
"step": 12700
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 4.466154919748779,
|
| 903 |
+
"grad_norm": 5.908513069152832,
|
| 904 |
+
"learning_rate": 2.2088712491277043e-05,
|
| 905 |
+
"loss": 2.0645,
|
| 906 |
+
"step": 12800
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 4.501046755059316,
|
| 910 |
+
"grad_norm": 4.762182712554932,
|
| 911 |
+
"learning_rate": 2.1870638520586183e-05,
|
| 912 |
+
"loss": 2.0615,
|
| 913 |
+
"step": 12900
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 4.535938590369853,
|
| 917 |
+
"grad_norm": 5.06411075592041,
|
| 918 |
+
"learning_rate": 2.1652564549895326e-05,
|
| 919 |
+
"loss": 2.0684,
|
| 920 |
+
"step": 13000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 4.57083042568039,
|
| 924 |
+
"grad_norm": 5.691733360290527,
|
| 925 |
+
"learning_rate": 2.1434490579204465e-05,
|
| 926 |
+
"loss": 2.0636,
|
| 927 |
+
"step": 13100
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 4.6057222609909285,
|
| 931 |
+
"grad_norm": 5.261690139770508,
|
| 932 |
+
"learning_rate": 2.121641660851361e-05,
|
| 933 |
+
"loss": 2.0679,
|
| 934 |
+
"step": 13200
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 4.640614096301466,
|
| 938 |
+
"grad_norm": 5.58465051651001,
|
| 939 |
+
"learning_rate": 2.099834263782275e-05,
|
| 940 |
+
"loss": 2.086,
|
| 941 |
+
"step": 13300
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 4.675505931612003,
|
| 945 |
+
"grad_norm": 5.2169952392578125,
|
| 946 |
+
"learning_rate": 2.078026866713189e-05,
|
| 947 |
+
"loss": 2.0703,
|
| 948 |
+
"step": 13400
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 4.71039776692254,
|
| 952 |
+
"grad_norm": 5.576324939727783,
|
| 953 |
+
"learning_rate": 2.0562194696441034e-05,
|
| 954 |
+
"loss": 2.0862,
|
| 955 |
+
"step": 13500
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 4.745289602233077,
|
| 959 |
+
"grad_norm": 5.461946964263916,
|
| 960 |
+
"learning_rate": 2.0344120725750178e-05,
|
| 961 |
+
"loss": 2.0627,
|
| 962 |
+
"step": 13600
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 4.7801814375436145,
|
| 966 |
+
"grad_norm": 5.098294258117676,
|
| 967 |
+
"learning_rate": 2.0126046755059317e-05,
|
| 968 |
+
"loss": 2.0736,
|
| 969 |
+
"step": 13700
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 4.815073272854152,
|
| 973 |
+
"grad_norm": 5.7679853439331055,
|
| 974 |
+
"learning_rate": 1.990797278436846e-05,
|
| 975 |
+
"loss": 2.0635,
|
| 976 |
+
"step": 13800
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 4.84996510816469,
|
| 980 |
+
"grad_norm": 5.441159725189209,
|
| 981 |
+
"learning_rate": 1.96898988136776e-05,
|
| 982 |
+
"loss": 2.1033,
|
| 983 |
+
"step": 13900
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 4.884856943475227,
|
| 987 |
+
"grad_norm": 6.114187717437744,
|
| 988 |
+
"learning_rate": 1.947182484298674e-05,
|
| 989 |
+
"loss": 2.0641,
|
| 990 |
+
"step": 14000
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 4.919748778785764,
|
| 994 |
+
"grad_norm": 5.230809688568115,
|
| 995 |
+
"learning_rate": 1.9253750872295883e-05,
|
| 996 |
+
"loss": 2.0742,
|
| 997 |
+
"step": 14100
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 4.954640614096301,
|
| 1001 |
+
"grad_norm": 5.573941707611084,
|
| 1002 |
+
"learning_rate": 1.9035676901605026e-05,
|
| 1003 |
+
"loss": 2.0967,
|
| 1004 |
+
"step": 14200
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 4.9895324494068385,
|
| 1008 |
+
"grad_norm": 5.449982166290283,
|
| 1009 |
+
"learning_rate": 1.8817602930914166e-05,
|
| 1010 |
+
"loss": 2.0524,
|
| 1011 |
+
"step": 14300
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 5.024424284717377,
|
| 1015 |
+
"grad_norm": 5.071106433868408,
|
| 1016 |
+
"learning_rate": 1.859952896022331e-05,
|
| 1017 |
+
"loss": 1.9743,
|
| 1018 |
+
"step": 14400
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 5.059316120027914,
|
| 1022 |
+
"grad_norm": 5.510537624359131,
|
| 1023 |
+
"learning_rate": 1.8381454989532452e-05,
|
| 1024 |
+
"loss": 1.8963,
|
| 1025 |
+
"step": 14500
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 5.094207955338451,
|
| 1029 |
+
"grad_norm": 5.249537467956543,
|
| 1030 |
+
"learning_rate": 1.816338101884159e-05,
|
| 1031 |
+
"loss": 1.9142,
|
| 1032 |
+
"step": 14600
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 5.129099790648988,
|
| 1036 |
+
"grad_norm": 6.67589807510376,
|
| 1037 |
+
"learning_rate": 1.7945307048150735e-05,
|
| 1038 |
+
"loss": 1.888,
|
| 1039 |
+
"step": 14700
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 5.163991625959525,
|
| 1043 |
+
"grad_norm": 5.381292819976807,
|
| 1044 |
+
"learning_rate": 1.7727233077459874e-05,
|
| 1045 |
+
"loss": 1.9226,
|
| 1046 |
+
"step": 14800
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 5.1988834612700625,
|
| 1050 |
+
"grad_norm": 5.443178653717041,
|
| 1051 |
+
"learning_rate": 1.7509159106769018e-05,
|
| 1052 |
+
"loss": 1.901,
|
| 1053 |
+
"step": 14900
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 5.2337752965806,
|
| 1057 |
+
"grad_norm": 5.7889018058776855,
|
| 1058 |
+
"learning_rate": 1.7291085136078157e-05,
|
| 1059 |
+
"loss": 1.9326,
|
| 1060 |
+
"step": 15000
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 5.268667131891138,
|
| 1064 |
+
"grad_norm": 5.440788745880127,
|
| 1065 |
+
"learning_rate": 1.70730111653873e-05,
|
| 1066 |
+
"loss": 1.9295,
|
| 1067 |
+
"step": 15100
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 5.303558967201675,
|
| 1071 |
+
"grad_norm": 5.275712490081787,
|
| 1072 |
+
"learning_rate": 1.685493719469644e-05,
|
| 1073 |
+
"loss": 1.9146,
|
| 1074 |
+
"step": 15200
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 5.338450802512212,
|
| 1078 |
+
"grad_norm": 5.518808841705322,
|
| 1079 |
+
"learning_rate": 1.6636863224005583e-05,
|
| 1080 |
+
"loss": 1.9308,
|
| 1081 |
+
"step": 15300
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 5.373342637822749,
|
| 1085 |
+
"grad_norm": 5.810028553009033,
|
| 1086 |
+
"learning_rate": 1.6418789253314726e-05,
|
| 1087 |
+
"loss": 1.9393,
|
| 1088 |
+
"step": 15400
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 5.4082344731332865,
|
| 1092 |
+
"grad_norm": 5.17830753326416,
|
| 1093 |
+
"learning_rate": 1.6200715282623866e-05,
|
| 1094 |
+
"loss": 1.9166,
|
| 1095 |
+
"step": 15500
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 5.443126308443825,
|
| 1099 |
+
"grad_norm": 5.424782752990723,
|
| 1100 |
+
"learning_rate": 1.598264131193301e-05,
|
| 1101 |
+
"loss": 1.8713,
|
| 1102 |
+
"step": 15600
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 5.478018143754362,
|
| 1106 |
+
"grad_norm": 5.202701568603516,
|
| 1107 |
+
"learning_rate": 1.5764567341242152e-05,
|
| 1108 |
+
"loss": 1.9279,
|
| 1109 |
+
"step": 15700
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 5.512909979064899,
|
| 1113 |
+
"grad_norm": 5.875789642333984,
|
| 1114 |
+
"learning_rate": 1.5546493370551292e-05,
|
| 1115 |
+
"loss": 1.9216,
|
| 1116 |
+
"step": 15800
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 5.547801814375436,
|
| 1120 |
+
"grad_norm": 5.769129276275635,
|
| 1121 |
+
"learning_rate": 1.532841939986043e-05,
|
| 1122 |
+
"loss": 1.9097,
|
| 1123 |
+
"step": 15900
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 5.582693649685973,
|
| 1127 |
+
"grad_norm": 5.4025421142578125,
|
| 1128 |
+
"learning_rate": 1.5110345429169576e-05,
|
| 1129 |
+
"loss": 1.9151,
|
| 1130 |
+
"step": 16000
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 5.617585484996511,
|
| 1134 |
+
"grad_norm": 4.817849636077881,
|
| 1135 |
+
"learning_rate": 1.4892271458478716e-05,
|
| 1136 |
+
"loss": 1.9122,
|
| 1137 |
+
"step": 16100
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 5.652477320307048,
|
| 1141 |
+
"grad_norm": 5.83222770690918,
|
| 1142 |
+
"learning_rate": 1.4674197487787857e-05,
|
| 1143 |
+
"loss": 1.9219,
|
| 1144 |
+
"step": 16200
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 5.687369155617586,
|
| 1148 |
+
"grad_norm": 5.329492092132568,
|
| 1149 |
+
"learning_rate": 1.4456123517097e-05,
|
| 1150 |
+
"loss": 1.9142,
|
| 1151 |
+
"step": 16300
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 5.722260990928123,
|
| 1155 |
+
"grad_norm": 5.5221686363220215,
|
| 1156 |
+
"learning_rate": 1.423804954640614e-05,
|
| 1157 |
+
"loss": 1.9194,
|
| 1158 |
+
"step": 16400
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 5.75715282623866,
|
| 1162 |
+
"grad_norm": 6.1820197105407715,
|
| 1163 |
+
"learning_rate": 1.4019975575715283e-05,
|
| 1164 |
+
"loss": 1.937,
|
| 1165 |
+
"step": 16500
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 5.792044661549197,
|
| 1169 |
+
"grad_norm": 5.7394232749938965,
|
| 1170 |
+
"learning_rate": 1.3801901605024425e-05,
|
| 1171 |
+
"loss": 1.919,
|
| 1172 |
+
"step": 16600
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 5.826936496859735,
|
| 1176 |
+
"grad_norm": 5.4087042808532715,
|
| 1177 |
+
"learning_rate": 1.3583827634333568e-05,
|
| 1178 |
+
"loss": 1.9118,
|
| 1179 |
+
"step": 16700
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 5.861828332170272,
|
| 1183 |
+
"grad_norm": 5.745779037475586,
|
| 1184 |
+
"learning_rate": 1.3365753663642708e-05,
|
| 1185 |
+
"loss": 1.934,
|
| 1186 |
+
"step": 16800
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 5.89672016748081,
|
| 1190 |
+
"grad_norm": 5.784609794616699,
|
| 1191 |
+
"learning_rate": 1.314767969295185e-05,
|
| 1192 |
+
"loss": 1.9248,
|
| 1193 |
+
"step": 16900
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 5.931612002791347,
|
| 1197 |
+
"grad_norm": 7.318721294403076,
|
| 1198 |
+
"learning_rate": 1.2929605722260992e-05,
|
| 1199 |
+
"loss": 1.9192,
|
| 1200 |
+
"step": 17000
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 5.966503838101884,
|
| 1204 |
+
"grad_norm": 5.4304304122924805,
|
| 1205 |
+
"learning_rate": 1.2711531751570133e-05,
|
| 1206 |
+
"loss": 1.948,
|
| 1207 |
+
"step": 17100
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 6.001395673412421,
|
| 1211 |
+
"grad_norm": 5.5656609535217285,
|
| 1212 |
+
"learning_rate": 1.2493457780879275e-05,
|
| 1213 |
+
"loss": 1.9194,
|
| 1214 |
+
"step": 17200
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 6.036287508722959,
|
| 1218 |
+
"grad_norm": 5.588869094848633,
|
| 1219 |
+
"learning_rate": 1.2275383810188416e-05,
|
| 1220 |
+
"loss": 1.78,
|
| 1221 |
+
"step": 17300
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 6.071179344033496,
|
| 1225 |
+
"grad_norm": 5.662446975708008,
|
| 1226 |
+
"learning_rate": 1.2057309839497558e-05,
|
| 1227 |
+
"loss": 1.7815,
|
| 1228 |
+
"step": 17400
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 6.106071179344034,
|
| 1232 |
+
"grad_norm": 5.681488037109375,
|
| 1233 |
+
"learning_rate": 1.18392358688067e-05,
|
| 1234 |
+
"loss": 1.7902,
|
| 1235 |
+
"step": 17500
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 6.140963014654571,
|
| 1239 |
+
"grad_norm": 5.237543106079102,
|
| 1240 |
+
"learning_rate": 1.162116189811584e-05,
|
| 1241 |
+
"loss": 1.7949,
|
| 1242 |
+
"step": 17600
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 6.175854849965108,
|
| 1246 |
+
"grad_norm": 6.3692474365234375,
|
| 1247 |
+
"learning_rate": 1.1403087927424982e-05,
|
| 1248 |
+
"loss": 1.7712,
|
| 1249 |
+
"step": 17700
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 6.210746685275645,
|
| 1253 |
+
"grad_norm": 5.9078049659729,
|
| 1254 |
+
"learning_rate": 1.1185013956734125e-05,
|
| 1255 |
+
"loss": 1.7964,
|
| 1256 |
+
"step": 17800
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 6.245638520586183,
|
| 1260 |
+
"grad_norm": 5.628890037536621,
|
| 1261 |
+
"learning_rate": 1.0966939986043266e-05,
|
| 1262 |
+
"loss": 1.7937,
|
| 1263 |
+
"step": 17900
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 6.28053035589672,
|
| 1267 |
+
"grad_norm": 5.680924415588379,
|
| 1268 |
+
"learning_rate": 1.074886601535241e-05,
|
| 1269 |
+
"loss": 1.8011,
|
| 1270 |
+
"step": 18000
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 6.315422191207258,
|
| 1274 |
+
"grad_norm": 5.3683857917785645,
|
| 1275 |
+
"learning_rate": 1.053079204466155e-05,
|
| 1276 |
+
"loss": 1.8093,
|
| 1277 |
+
"step": 18100
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 6.350314026517795,
|
| 1281 |
+
"grad_norm": 6.106055736541748,
|
| 1282 |
+
"learning_rate": 1.031271807397069e-05,
|
| 1283 |
+
"loss": 1.8021,
|
| 1284 |
+
"step": 18200
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 6.385205861828332,
|
| 1288 |
+
"grad_norm": 5.841535568237305,
|
| 1289 |
+
"learning_rate": 1.0094644103279834e-05,
|
| 1290 |
+
"loss": 1.8266,
|
| 1291 |
+
"step": 18300
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 6.4200976971388695,
|
| 1295 |
+
"grad_norm": 5.864353179931641,
|
| 1296 |
+
"learning_rate": 9.876570132588975e-06,
|
| 1297 |
+
"loss": 1.8075,
|
| 1298 |
+
"step": 18400
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 6.454989532449407,
|
| 1302 |
+
"grad_norm": 8.195747375488281,
|
| 1303 |
+
"learning_rate": 9.658496161898117e-06,
|
| 1304 |
+
"loss": 1.8123,
|
| 1305 |
+
"step": 18500
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 6.489881367759944,
|
| 1309 |
+
"grad_norm": 6.448851585388184,
|
| 1310 |
+
"learning_rate": 9.440422191207258e-06,
|
| 1311 |
+
"loss": 1.7956,
|
| 1312 |
+
"step": 18600
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 6.524773203070481,
|
| 1316 |
+
"grad_norm": 5.370660305023193,
|
| 1317 |
+
"learning_rate": 9.2223482205164e-06,
|
| 1318 |
+
"loss": 1.7862,
|
| 1319 |
+
"step": 18700
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 6.559665038381019,
|
| 1323 |
+
"grad_norm": 5.711855411529541,
|
| 1324 |
+
"learning_rate": 9.00427424982554e-06,
|
| 1325 |
+
"loss": 1.8082,
|
| 1326 |
+
"step": 18800
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 6.594556873691556,
|
| 1330 |
+
"grad_norm": 5.534999847412109,
|
| 1331 |
+
"learning_rate": 8.786200279134684e-06,
|
| 1332 |
+
"loss": 1.8117,
|
| 1333 |
+
"step": 18900
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 6.6294487090020935,
|
| 1337 |
+
"grad_norm": 5.1350789070129395,
|
| 1338 |
+
"learning_rate": 8.568126308443825e-06,
|
| 1339 |
+
"loss": 1.8072,
|
| 1340 |
+
"step": 19000
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 6.664340544312631,
|
| 1344 |
+
"grad_norm": 5.525078773498535,
|
| 1345 |
+
"learning_rate": 8.350052337752965e-06,
|
| 1346 |
+
"loss": 1.7891,
|
| 1347 |
+
"step": 19100
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 6.699232379623168,
|
| 1351 |
+
"grad_norm": 5.587681293487549,
|
| 1352 |
+
"learning_rate": 8.131978367062108e-06,
|
| 1353 |
+
"loss": 1.786,
|
| 1354 |
+
"step": 19200
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 6.734124214933706,
|
| 1358 |
+
"grad_norm": 5.702240467071533,
|
| 1359 |
+
"learning_rate": 7.91390439637125e-06,
|
| 1360 |
+
"loss": 1.8239,
|
| 1361 |
+
"step": 19300
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 6.769016050244243,
|
| 1365 |
+
"grad_norm": 6.304993152618408,
|
| 1366 |
+
"learning_rate": 7.695830425680391e-06,
|
| 1367 |
+
"loss": 1.8181,
|
| 1368 |
+
"step": 19400
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 6.80390788555478,
|
| 1372 |
+
"grad_norm": 5.786768913269043,
|
| 1373 |
+
"learning_rate": 7.477756454989533e-06,
|
| 1374 |
+
"loss": 1.8127,
|
| 1375 |
+
"step": 19500
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 6.8387997208653175,
|
| 1379 |
+
"grad_norm": 5.68336820602417,
|
| 1380 |
+
"learning_rate": 7.2596824842986745e-06,
|
| 1381 |
+
"loss": 1.7917,
|
| 1382 |
+
"step": 19600
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 6.873691556175855,
|
| 1386 |
+
"grad_norm": 5.827804088592529,
|
| 1387 |
+
"learning_rate": 7.041608513607816e-06,
|
| 1388 |
+
"loss": 1.8309,
|
| 1389 |
+
"step": 19700
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 6.908583391486392,
|
| 1393 |
+
"grad_norm": 5.98842716217041,
|
| 1394 |
+
"learning_rate": 6.823534542916958e-06,
|
| 1395 |
+
"loss": 1.7808,
|
| 1396 |
+
"step": 19800
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 6.943475226796929,
|
| 1400 |
+
"grad_norm": 5.252569198608398,
|
| 1401 |
+
"learning_rate": 6.6054605722261e-06,
|
| 1402 |
+
"loss": 1.8115,
|
| 1403 |
+
"step": 19900
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 6.978367062107467,
|
| 1407 |
+
"grad_norm": 5.1013288497924805,
|
| 1408 |
+
"learning_rate": 6.38738660153524e-06,
|
| 1409 |
+
"loss": 1.7922,
|
| 1410 |
+
"step": 20000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 7.013258897418004,
|
| 1414 |
+
"grad_norm": 5.664073467254639,
|
| 1415 |
+
"learning_rate": 6.169312630844383e-06,
|
| 1416 |
+
"loss": 1.7694,
|
| 1417 |
+
"step": 20100
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 7.0481507327285415,
|
| 1421 |
+
"grad_norm": 5.690623760223389,
|
| 1422 |
+
"learning_rate": 5.951238660153524e-06,
|
| 1423 |
+
"loss": 1.7241,
|
| 1424 |
+
"step": 20200
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 7.083042568039079,
|
| 1428 |
+
"grad_norm": 5.286320209503174,
|
| 1429 |
+
"learning_rate": 5.733164689462666e-06,
|
| 1430 |
+
"loss": 1.7105,
|
| 1431 |
+
"step": 20300
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 7.117934403349616,
|
| 1435 |
+
"grad_norm": 5.791104793548584,
|
| 1436 |
+
"learning_rate": 5.515090718771808e-06,
|
| 1437 |
+
"loss": 1.7085,
|
| 1438 |
+
"step": 20400
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 7.152826238660153,
|
| 1442 |
+
"grad_norm": 5.083521366119385,
|
| 1443 |
+
"learning_rate": 5.297016748080949e-06,
|
| 1444 |
+
"loss": 1.7011,
|
| 1445 |
+
"step": 20500
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 7.187718073970691,
|
| 1449 |
+
"grad_norm": 5.443909645080566,
|
| 1450 |
+
"learning_rate": 5.078942777390091e-06,
|
| 1451 |
+
"loss": 1.7239,
|
| 1452 |
+
"step": 20600
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 7.222609909281228,
|
| 1456 |
+
"grad_norm": 6.203304767608643,
|
| 1457 |
+
"learning_rate": 4.8608688066992325e-06,
|
| 1458 |
+
"loss": 1.7177,
|
| 1459 |
+
"step": 20700
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 7.257501744591766,
|
| 1463 |
+
"grad_norm": 6.1620564460754395,
|
| 1464 |
+
"learning_rate": 4.642794836008374e-06,
|
| 1465 |
+
"loss": 1.6979,
|
| 1466 |
+
"step": 20800
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 7.292393579902303,
|
| 1470 |
+
"grad_norm": 6.96720027923584,
|
| 1471 |
+
"learning_rate": 4.424720865317516e-06,
|
| 1472 |
+
"loss": 1.7266,
|
| 1473 |
+
"step": 20900
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 7.32728541521284,
|
| 1477 |
+
"grad_norm": 6.198672771453857,
|
| 1478 |
+
"learning_rate": 4.206646894626658e-06,
|
| 1479 |
+
"loss": 1.7106,
|
| 1480 |
+
"step": 21000
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 7.362177250523377,
|
| 1484 |
+
"grad_norm": 5.367521286010742,
|
| 1485 |
+
"learning_rate": 3.9885729239358e-06,
|
| 1486 |
+
"loss": 1.7188,
|
| 1487 |
+
"step": 21100
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 7.397069085833915,
|
| 1491 |
+
"grad_norm": 5.912238597869873,
|
| 1492 |
+
"learning_rate": 3.770498953244941e-06,
|
| 1493 |
+
"loss": 1.7194,
|
| 1494 |
+
"step": 21200
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 7.431960921144452,
|
| 1498 |
+
"grad_norm": 5.624551296234131,
|
| 1499 |
+
"learning_rate": 3.5524249825540826e-06,
|
| 1500 |
+
"loss": 1.7169,
|
| 1501 |
+
"step": 21300
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 7.46685275645499,
|
| 1505 |
+
"grad_norm": 5.592011451721191,
|
| 1506 |
+
"learning_rate": 3.3343510118632245e-06,
|
| 1507 |
+
"loss": 1.7247,
|
| 1508 |
+
"step": 21400
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 7.501744591765527,
|
| 1512 |
+
"grad_norm": 5.727781295776367,
|
| 1513 |
+
"learning_rate": 3.116277041172366e-06,
|
| 1514 |
+
"loss": 1.7231,
|
| 1515 |
+
"step": 21500
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 7.536636427076064,
|
| 1519 |
+
"grad_norm": 5.530336856842041,
|
| 1520 |
+
"learning_rate": 2.8982030704815073e-06,
|
| 1521 |
+
"loss": 1.7057,
|
| 1522 |
+
"step": 21600
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 7.571528262386601,
|
| 1526 |
+
"grad_norm": 6.076034069061279,
|
| 1527 |
+
"learning_rate": 2.680129099790649e-06,
|
| 1528 |
+
"loss": 1.7196,
|
| 1529 |
+
"step": 21700
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 7.606420097697139,
|
| 1533 |
+
"grad_norm": 5.994781017303467,
|
| 1534 |
+
"learning_rate": 2.462055129099791e-06,
|
| 1535 |
+
"loss": 1.7241,
|
| 1536 |
+
"step": 21800
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 7.641311933007676,
|
| 1540 |
+
"grad_norm": 5.7654948234558105,
|
| 1541 |
+
"learning_rate": 2.2439811584089323e-06,
|
| 1542 |
+
"loss": 1.7211,
|
| 1543 |
+
"step": 21900
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 7.676203768318214,
|
| 1547 |
+
"grad_norm": 5.507397174835205,
|
| 1548 |
+
"learning_rate": 2.025907187718074e-06,
|
| 1549 |
+
"loss": 1.7044,
|
| 1550 |
+
"step": 22000
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 7.711095603628751,
|
| 1554 |
+
"grad_norm": 5.571853160858154,
|
| 1555 |
+
"learning_rate": 1.8078332170272158e-06,
|
| 1556 |
+
"loss": 1.7384,
|
| 1557 |
+
"step": 22100
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 7.745987438939288,
|
| 1561 |
+
"grad_norm": 5.2521867752075195,
|
| 1562 |
+
"learning_rate": 1.5897592463363572e-06,
|
| 1563 |
+
"loss": 1.7174,
|
| 1564 |
+
"step": 22200
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 7.780879274249825,
|
| 1568 |
+
"grad_norm": 26.5225887298584,
|
| 1569 |
+
"learning_rate": 1.371685275645499e-06,
|
| 1570 |
+
"loss": 1.7183,
|
| 1571 |
+
"step": 22300
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 7.815771109560363,
|
| 1575 |
+
"grad_norm": 6.7133307456970215,
|
| 1576 |
+
"learning_rate": 1.1536113049546406e-06,
|
| 1577 |
+
"loss": 1.7281,
|
| 1578 |
+
"step": 22400
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 7.8506629448709,
|
| 1582 |
+
"grad_norm": 5.532526016235352,
|
| 1583 |
+
"learning_rate": 9.355373342637824e-07,
|
| 1584 |
+
"loss": 1.7132,
|
| 1585 |
+
"step": 22500
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 7.885554780181438,
|
| 1589 |
+
"grad_norm": 5.792304992675781,
|
| 1590 |
+
"learning_rate": 7.17463363572924e-07,
|
| 1591 |
+
"loss": 1.6923,
|
| 1592 |
+
"step": 22600
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 7.920446615491975,
|
| 1596 |
+
"grad_norm": 6.1261210441589355,
|
| 1597 |
+
"learning_rate": 4.993893928820656e-07,
|
| 1598 |
+
"loss": 1.7188,
|
| 1599 |
+
"step": 22700
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 7.955338450802512,
|
| 1603 |
+
"grad_norm": 5.306552410125732,
|
| 1604 |
+
"learning_rate": 2.8131542219120726e-07,
|
| 1605 |
+
"loss": 1.7141,
|
| 1606 |
+
"step": 22800
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 7.990230286113049,
|
| 1610 |
+
"grad_norm": 5.88728141784668,
|
| 1611 |
+
"learning_rate": 6.324145150034892e-08,
|
| 1612 |
+
"loss": 1.7307,
|
| 1613 |
+
"step": 22900
|
| 1614 |
+
}
|
| 1615 |
+
],
|
| 1616 |
+
"logging_steps": 100,
|
| 1617 |
+
"max_steps": 22928,
|
| 1618 |
+
"num_input_tokens_seen": 0,
|
| 1619 |
+
"num_train_epochs": 8,
|
| 1620 |
+
"save_steps": 500,
|
| 1621 |
+
"stateful_callbacks": {
|
| 1622 |
+
"TrainerControl": {
|
| 1623 |
+
"args": {
|
| 1624 |
+
"should_epoch_stop": false,
|
| 1625 |
+
"should_evaluate": false,
|
| 1626 |
+
"should_log": false,
|
| 1627 |
+
"should_save": true,
|
| 1628 |
+
"should_training_stop": true
|
| 1629 |
+
},
|
| 1630 |
+
"attributes": {}
|
| 1631 |
+
}
|
| 1632 |
+
},
|
| 1633 |
+
"total_flos": 0.0,
|
| 1634 |
+
"train_batch_size": 50,
|
| 1635 |
+
"trial_name": null,
|
| 1636 |
+
"trial_params": null
|
| 1637 |
+
}
|
checkpoint-22928/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d04177183f69ff02a9a61d43a95f7d4481d2d791b52a88b41d83152a07032546
|
| 3 |
+
size 5969
|
checkpoint-22928/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_name_or_path": "microsoft/codebert-base",
|
| 3 |
+
"max_length": 64,
|
| 4 |
+
"hidden_size": 768,
|
| 5 |
+
"vocab_size": 50265,
|
| 6 |
+
"sos_id": 0,
|
| 7 |
+
"eos_id": 2,
|
| 8 |
+
"pad_id": 1
|
| 9 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc13070ab752c0ca947526b410b802ef731fcc22fe42d3fec939351b1c197a7c
|
| 3 |
+
size 719294071
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 512,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d04177183f69ff02a9a61d43a95f7d4481d2d791b52a88b41d83152a07032546
|
| 3 |
+
size 5969
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|