Upload 10 files
Browse files- added_tokens.json +3 -0
- model.safetensors +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +15 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- trainer_state.json +2411 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04d9e380df5a6c650fb8521f83186469cbde877cac71a87a1916cd5aee12622b
|
| 3 |
+
size 1736227920
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb982c58b2f0572860a9dde3bdfec0e47a801d0b364ca5d2927d2f01aef3523b
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5e17d5f5062da6a162358e5dbb55621489c2aa0306f2d5f7d0c9809a3476cc4
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": {
|
| 9 |
+
"content": "[UNK]",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": true,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
}
|
| 15 |
+
}
|
spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
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 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[UNK]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128000": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "[CLS]",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"eos_token": "[SEP]",
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"sp_model_kwargs": {},
|
| 54 |
+
"split_by_punct": false,
|
| 55 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 56 |
+
"unk_token": "[UNK]",
|
| 57 |
+
"vocab_type": "spm"
|
| 58 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2411 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9049823782519661,
|
| 3 |
+
"best_model_checkpoint": "./results/checkpoint-3145",
|
| 4 |
+
"epoch": 8.998569384835479,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 3145,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02861230329041488,
|
| 13 |
+
"grad_norm": 6.876509666442871,
|
| 14 |
+
"learning_rate": 5.730659025787966e-07,
|
| 15 |
+
"loss": 2.4197,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.05722460658082976,
|
| 20 |
+
"grad_norm": 7.476705074310303,
|
| 21 |
+
"learning_rate": 1.1461318051575932e-06,
|
| 22 |
+
"loss": 2.4492,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.08583690987124463,
|
| 27 |
+
"grad_norm": 7.696058750152588,
|
| 28 |
+
"learning_rate": 1.7191977077363897e-06,
|
| 29 |
+
"loss": 2.4148,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.11444921316165951,
|
| 34 |
+
"grad_norm": 7.015161514282227,
|
| 35 |
+
"learning_rate": 2.2922636103151864e-06,
|
| 36 |
+
"loss": 2.3494,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.1430615164520744,
|
| 41 |
+
"grad_norm": 12.62998104095459,
|
| 42 |
+
"learning_rate": 2.865329512893983e-06,
|
| 43 |
+
"loss": 2.2623,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.17167381974248927,
|
| 48 |
+
"grad_norm": 14.117810249328613,
|
| 49 |
+
"learning_rate": 3.3810888252149e-06,
|
| 50 |
+
"loss": 2.098,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.20028612303290416,
|
| 55 |
+
"grad_norm": 9.416646957397461,
|
| 56 |
+
"learning_rate": 3.954154727793696e-06,
|
| 57 |
+
"loss": 1.9519,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.22889842632331903,
|
| 62 |
+
"grad_norm": 8.700328826904297,
|
| 63 |
+
"learning_rate": 4.527220630372493e-06,
|
| 64 |
+
"loss": 1.7806,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.2575107296137339,
|
| 69 |
+
"grad_norm": 10.860468864440918,
|
| 70 |
+
"learning_rate": 5.10028653295129e-06,
|
| 71 |
+
"loss": 1.8199,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.2861230329041488,
|
| 76 |
+
"grad_norm": 9.035737037658691,
|
| 77 |
+
"learning_rate": 5.673352435530086e-06,
|
| 78 |
+
"loss": 1.7734,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.3147353361945637,
|
| 83 |
+
"grad_norm": 8.161845207214355,
|
| 84 |
+
"learning_rate": 6.246418338108883e-06,
|
| 85 |
+
"loss": 1.7332,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.34334763948497854,
|
| 90 |
+
"grad_norm": 9.786896705627441,
|
| 91 |
+
"learning_rate": 6.819484240687679e-06,
|
| 92 |
+
"loss": 1.6379,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.3719599427753934,
|
| 97 |
+
"grad_norm": 8.398969650268555,
|
| 98 |
+
"learning_rate": 7.392550143266476e-06,
|
| 99 |
+
"loss": 1.5716,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.4005722460658083,
|
| 104 |
+
"grad_norm": 10.114533424377441,
|
| 105 |
+
"learning_rate": 7.965616045845273e-06,
|
| 106 |
+
"loss": 1.6692,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.4291845493562232,
|
| 111 |
+
"grad_norm": 9.715279579162598,
|
| 112 |
+
"learning_rate": 8.53868194842407e-06,
|
| 113 |
+
"loss": 1.562,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.45779685264663805,
|
| 118 |
+
"grad_norm": 9.378506660461426,
|
| 119 |
+
"learning_rate": 9.111747851002865e-06,
|
| 120 |
+
"loss": 1.495,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.4864091559370529,
|
| 125 |
+
"grad_norm": 10.23122787475586,
|
| 126 |
+
"learning_rate": 9.684813753581662e-06,
|
| 127 |
+
"loss": 1.5594,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.5150214592274678,
|
| 132 |
+
"grad_norm": 9.27610969543457,
|
| 133 |
+
"learning_rate": 1.0257879656160459e-05,
|
| 134 |
+
"loss": 1.3837,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.5436337625178826,
|
| 139 |
+
"grad_norm": 7.880237579345703,
|
| 140 |
+
"learning_rate": 1.0830945558739256e-05,
|
| 141 |
+
"loss": 1.5223,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.5722460658082976,
|
| 146 |
+
"grad_norm": 9.665934562683105,
|
| 147 |
+
"learning_rate": 1.1404011461318051e-05,
|
| 148 |
+
"loss": 1.5726,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.6008583690987125,
|
| 153 |
+
"grad_norm": 10.41831111907959,
|
| 154 |
+
"learning_rate": 1.197707736389685e-05,
|
| 155 |
+
"loss": 1.3886,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.6294706723891274,
|
| 160 |
+
"grad_norm": 10.866052627563477,
|
| 161 |
+
"learning_rate": 1.2550143266475645e-05,
|
| 162 |
+
"loss": 1.2832,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.6580829756795422,
|
| 167 |
+
"grad_norm": 8.700434684753418,
|
| 168 |
+
"learning_rate": 1.3123209169054444e-05,
|
| 169 |
+
"loss": 1.3478,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.6866952789699571,
|
| 174 |
+
"grad_norm": 9.831547737121582,
|
| 175 |
+
"learning_rate": 1.3696275071633239e-05,
|
| 176 |
+
"loss": 1.3709,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.7153075822603719,
|
| 181 |
+
"grad_norm": 8.401679992675781,
|
| 182 |
+
"learning_rate": 1.4269340974212036e-05,
|
| 183 |
+
"loss": 1.1379,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.7439198855507868,
|
| 188 |
+
"grad_norm": 8.623452186584473,
|
| 189 |
+
"learning_rate": 1.4842406876790831e-05,
|
| 190 |
+
"loss": 1.1539,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.7725321888412017,
|
| 195 |
+
"grad_norm": 8.327902793884277,
|
| 196 |
+
"learning_rate": 1.541547277936963e-05,
|
| 197 |
+
"loss": 1.2316,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.8011444921316166,
|
| 202 |
+
"grad_norm": 7.682071208953857,
|
| 203 |
+
"learning_rate": 1.5988538681948423e-05,
|
| 204 |
+
"loss": 1.0331,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.8297567954220315,
|
| 209 |
+
"grad_norm": 11.49991512298584,
|
| 210 |
+
"learning_rate": 1.6561604584527223e-05,
|
| 211 |
+
"loss": 1.0284,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.8583690987124464,
|
| 216 |
+
"grad_norm": 12.24896240234375,
|
| 217 |
+
"learning_rate": 1.7134670487106017e-05,
|
| 218 |
+
"loss": 0.9963,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.8869814020028612,
|
| 223 |
+
"grad_norm": 11.292716979980469,
|
| 224 |
+
"learning_rate": 1.7707736389684814e-05,
|
| 225 |
+
"loss": 1.0393,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.9155937052932761,
|
| 230 |
+
"grad_norm": 12.811381340026855,
|
| 231 |
+
"learning_rate": 1.828080229226361e-05,
|
| 232 |
+
"loss": 0.9775,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.944206008583691,
|
| 237 |
+
"grad_norm": 10.303635597229004,
|
| 238 |
+
"learning_rate": 1.8853868194842408e-05,
|
| 239 |
+
"loss": 0.9981,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.9728183118741058,
|
| 244 |
+
"grad_norm": 8.658745765686035,
|
| 245 |
+
"learning_rate": 1.9426934097421205e-05,
|
| 246 |
+
"loss": 0.8987,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.9985693848354793,
|
| 251 |
+
"eval_avg_f1": 0.628490484052183,
|
| 252 |
+
"eval_avg_macro_f1": 0.42788465867275915,
|
| 253 |
+
"eval_hazard_accuracy": 0.825589706933524,
|
| 254 |
+
"eval_hazard_f1": 0.8033759184058155,
|
| 255 |
+
"eval_hazard_macro_f1": 0.5331731123201242,
|
| 256 |
+
"eval_hazard_precision": 0.8219654012602551,
|
| 257 |
+
"eval_hazard_recall": 0.825589706933524,
|
| 258 |
+
"eval_loss": 0.8228468298912048,
|
| 259 |
+
"eval_product_accuracy": 0.5160829163688349,
|
| 260 |
+
"eval_product_f1": 0.4536050496985506,
|
| 261 |
+
"eval_product_macro_f1": 0.3225962050253941,
|
| 262 |
+
"eval_product_precision": 0.5171642919697715,
|
| 263 |
+
"eval_product_recall": 0.5160829163688349,
|
| 264 |
+
"eval_runtime": 129.8116,
|
| 265 |
+
"eval_samples_per_second": 10.777,
|
| 266 |
+
"eval_steps_per_second": 5.392,
|
| 267 |
+
"step": 349
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.0014306151645207,
|
| 271 |
+
"grad_norm": 18.984487533569336,
|
| 272 |
+
"learning_rate": 2e-05,
|
| 273 |
+
"loss": 0.8162,
|
| 274 |
+
"step": 350
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.0300429184549356,
|
| 278 |
+
"grad_norm": 11.077680587768555,
|
| 279 |
+
"learning_rate": 1.993632601082458e-05,
|
| 280 |
+
"loss": 0.8289,
|
| 281 |
+
"step": 360
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.0586552217453504,
|
| 285 |
+
"grad_norm": 8.779168128967285,
|
| 286 |
+
"learning_rate": 1.9872652021649158e-05,
|
| 287 |
+
"loss": 0.7518,
|
| 288 |
+
"step": 370
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.0872675250357653,
|
| 292 |
+
"grad_norm": 11.665291786193848,
|
| 293 |
+
"learning_rate": 1.9808978032473735e-05,
|
| 294 |
+
"loss": 0.8352,
|
| 295 |
+
"step": 380
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.1158798283261802,
|
| 299 |
+
"grad_norm": 10.888090133666992,
|
| 300 |
+
"learning_rate": 1.9745304043298315e-05,
|
| 301 |
+
"loss": 0.7818,
|
| 302 |
+
"step": 390
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.144492131616595,
|
| 306 |
+
"grad_norm": 7.827507495880127,
|
| 307 |
+
"learning_rate": 1.9681630054122895e-05,
|
| 308 |
+
"loss": 0.7133,
|
| 309 |
+
"step": 400
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.17310443490701,
|
| 313 |
+
"grad_norm": 9.694169044494629,
|
| 314 |
+
"learning_rate": 1.961795606494747e-05,
|
| 315 |
+
"loss": 0.7354,
|
| 316 |
+
"step": 410
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.201716738197425,
|
| 320 |
+
"grad_norm": 9.30434513092041,
|
| 321 |
+
"learning_rate": 1.9554282075772048e-05,
|
| 322 |
+
"loss": 0.7404,
|
| 323 |
+
"step": 420
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 1.2303290414878398,
|
| 327 |
+
"grad_norm": 9.60873031616211,
|
| 328 |
+
"learning_rate": 1.9490608086596628e-05,
|
| 329 |
+
"loss": 0.6384,
|
| 330 |
+
"step": 430
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 1.2589413447782547,
|
| 334 |
+
"grad_norm": 8.565361022949219,
|
| 335 |
+
"learning_rate": 1.9426934097421205e-05,
|
| 336 |
+
"loss": 0.5877,
|
| 337 |
+
"step": 440
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 1.2875536480686696,
|
| 341 |
+
"grad_norm": 6.860024452209473,
|
| 342 |
+
"learning_rate": 1.936326010824578e-05,
|
| 343 |
+
"loss": 0.5608,
|
| 344 |
+
"step": 450
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.3161659513590844,
|
| 348 |
+
"grad_norm": 10.23735523223877,
|
| 349 |
+
"learning_rate": 1.929958611907036e-05,
|
| 350 |
+
"loss": 0.5611,
|
| 351 |
+
"step": 460
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.3447782546494993,
|
| 355 |
+
"grad_norm": 9.30553913116455,
|
| 356 |
+
"learning_rate": 1.923591212989494e-05,
|
| 357 |
+
"loss": 0.6389,
|
| 358 |
+
"step": 470
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 1.3733905579399142,
|
| 362 |
+
"grad_norm": 10.408185005187988,
|
| 363 |
+
"learning_rate": 1.9172238140719518e-05,
|
| 364 |
+
"loss": 0.5982,
|
| 365 |
+
"step": 480
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.402002861230329,
|
| 369 |
+
"grad_norm": 7.272457122802734,
|
| 370 |
+
"learning_rate": 1.9114931550461637e-05,
|
| 371 |
+
"loss": 0.6152,
|
| 372 |
+
"step": 490
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.4306151645207439,
|
| 376 |
+
"grad_norm": 14.093036651611328,
|
| 377 |
+
"learning_rate": 1.9051257561286217e-05,
|
| 378 |
+
"loss": 0.5622,
|
| 379 |
+
"step": 500
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 1.4592274678111588,
|
| 383 |
+
"grad_norm": 9.175661087036133,
|
| 384 |
+
"learning_rate": 1.8987583572110794e-05,
|
| 385 |
+
"loss": 0.5649,
|
| 386 |
+
"step": 510
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 1.4878397711015736,
|
| 390 |
+
"grad_norm": 9.00843620300293,
|
| 391 |
+
"learning_rate": 1.892390958293537e-05,
|
| 392 |
+
"loss": 0.497,
|
| 393 |
+
"step": 520
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 1.5164520743919887,
|
| 397 |
+
"grad_norm": 12.909320831298828,
|
| 398 |
+
"learning_rate": 1.886023559375995e-05,
|
| 399 |
+
"loss": 0.5668,
|
| 400 |
+
"step": 530
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 1.5450643776824036,
|
| 404 |
+
"grad_norm": 8.075855255126953,
|
| 405 |
+
"learning_rate": 1.879656160458453e-05,
|
| 406 |
+
"loss": 0.4738,
|
| 407 |
+
"step": 540
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 1.5736766809728184,
|
| 411 |
+
"grad_norm": 8.01660442352295,
|
| 412 |
+
"learning_rate": 1.8732887615409107e-05,
|
| 413 |
+
"loss": 0.5215,
|
| 414 |
+
"step": 550
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.6022889842632333,
|
| 418 |
+
"grad_norm": 8.67613697052002,
|
| 419 |
+
"learning_rate": 1.8669213626233684e-05,
|
| 420 |
+
"loss": 0.402,
|
| 421 |
+
"step": 560
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 1.6309012875536482,
|
| 425 |
+
"grad_norm": 12.167224884033203,
|
| 426 |
+
"learning_rate": 1.8605539637058264e-05,
|
| 427 |
+
"loss": 0.5239,
|
| 428 |
+
"step": 570
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.659513590844063,
|
| 432 |
+
"grad_norm": 8.326301574707031,
|
| 433 |
+
"learning_rate": 1.854186564788284e-05,
|
| 434 |
+
"loss": 0.4593,
|
| 435 |
+
"step": 580
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 1.688125894134478,
|
| 439 |
+
"grad_norm": 8.792169570922852,
|
| 440 |
+
"learning_rate": 1.847819165870742e-05,
|
| 441 |
+
"loss": 0.4246,
|
| 442 |
+
"step": 590
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 1.7167381974248928,
|
| 446 |
+
"grad_norm": 5.764039993286133,
|
| 447 |
+
"learning_rate": 1.8414517669531997e-05,
|
| 448 |
+
"loss": 0.4653,
|
| 449 |
+
"step": 600
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.7453505007153076,
|
| 453 |
+
"grad_norm": 9.632957458496094,
|
| 454 |
+
"learning_rate": 1.8350843680356577e-05,
|
| 455 |
+
"loss": 0.4983,
|
| 456 |
+
"step": 610
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 1.7739628040057225,
|
| 460 |
+
"grad_norm": 5.234284400939941,
|
| 461 |
+
"learning_rate": 1.8287169691181154e-05,
|
| 462 |
+
"loss": 0.437,
|
| 463 |
+
"step": 620
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 1.8025751072961373,
|
| 467 |
+
"grad_norm": 9.065439224243164,
|
| 468 |
+
"learning_rate": 1.822349570200573e-05,
|
| 469 |
+
"loss": 0.4994,
|
| 470 |
+
"step": 630
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 1.8311874105865522,
|
| 474 |
+
"grad_norm": 8.478631019592285,
|
| 475 |
+
"learning_rate": 1.815982171283031e-05,
|
| 476 |
+
"loss": 0.4488,
|
| 477 |
+
"step": 640
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 1.859799713876967,
|
| 481 |
+
"grad_norm": 9.906896591186523,
|
| 482 |
+
"learning_rate": 1.809614772365489e-05,
|
| 483 |
+
"loss": 0.4591,
|
| 484 |
+
"step": 650
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 1.888412017167382,
|
| 488 |
+
"grad_norm": 8.688902854919434,
|
| 489 |
+
"learning_rate": 1.8032473734479467e-05,
|
| 490 |
+
"loss": 0.3987,
|
| 491 |
+
"step": 660
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 1.9170243204577968,
|
| 495 |
+
"grad_norm": 8.751792907714844,
|
| 496 |
+
"learning_rate": 1.7968799745304043e-05,
|
| 497 |
+
"loss": 0.3636,
|
| 498 |
+
"step": 670
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 1.9456366237482117,
|
| 502 |
+
"grad_norm": 8.234392166137695,
|
| 503 |
+
"learning_rate": 1.7905125756128623e-05,
|
| 504 |
+
"loss": 0.38,
|
| 505 |
+
"step": 680
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 1.9742489270386265,
|
| 509 |
+
"grad_norm": 11.33198070526123,
|
| 510 |
+
"learning_rate": 1.7841451766953203e-05,
|
| 511 |
+
"loss": 0.4105,
|
| 512 |
+
"step": 690
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 2.0,
|
| 516 |
+
"eval_avg_f1": 0.8280098465171617,
|
| 517 |
+
"eval_avg_macro_f1": 0.74927766614807,
|
| 518 |
+
"eval_hazard_accuracy": 0.8956397426733381,
|
| 519 |
+
"eval_hazard_f1": 0.8909842147196562,
|
| 520 |
+
"eval_hazard_macro_f1": 0.7504887189330472,
|
| 521 |
+
"eval_hazard_precision": 0.8943267421662421,
|
| 522 |
+
"eval_hazard_recall": 0.8956397426733381,
|
| 523 |
+
"eval_loss": 0.4124191701412201,
|
| 524 |
+
"eval_product_accuracy": 0.7684060042887777,
|
| 525 |
+
"eval_product_f1": 0.7650354783146672,
|
| 526 |
+
"eval_product_macro_f1": 0.7480666133630927,
|
| 527 |
+
"eval_product_precision": 0.7938898073346229,
|
| 528 |
+
"eval_product_recall": 0.7684060042887777,
|
| 529 |
+
"eval_runtime": 129.9333,
|
| 530 |
+
"eval_samples_per_second": 10.767,
|
| 531 |
+
"eval_steps_per_second": 5.387,
|
| 532 |
+
"step": 699
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 2.0028612303290414,
|
| 536 |
+
"grad_norm": 8.635429382324219,
|
| 537 |
+
"learning_rate": 1.7777777777777777e-05,
|
| 538 |
+
"loss": 0.4702,
|
| 539 |
+
"step": 700
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 2.0314735336194563,
|
| 543 |
+
"grad_norm": 8.250715255737305,
|
| 544 |
+
"learning_rate": 1.7714103788602357e-05,
|
| 545 |
+
"loss": 0.3381,
|
| 546 |
+
"step": 710
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 2.060085836909871,
|
| 550 |
+
"grad_norm": 9.375146865844727,
|
| 551 |
+
"learning_rate": 1.7650429799426937e-05,
|
| 552 |
+
"loss": 0.25,
|
| 553 |
+
"step": 720
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 2.088698140200286,
|
| 557 |
+
"grad_norm": 8.349605560302734,
|
| 558 |
+
"learning_rate": 1.7586755810251513e-05,
|
| 559 |
+
"loss": 0.2904,
|
| 560 |
+
"step": 730
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 2.117310443490701,
|
| 564 |
+
"grad_norm": 5.922322750091553,
|
| 565 |
+
"learning_rate": 1.752308182107609e-05,
|
| 566 |
+
"loss": 0.2953,
|
| 567 |
+
"step": 740
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 2.1459227467811157,
|
| 571 |
+
"grad_norm": 9.073394775390625,
|
| 572 |
+
"learning_rate": 1.745940783190067e-05,
|
| 573 |
+
"loss": 0.4012,
|
| 574 |
+
"step": 750
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 2.1745350500715306,
|
| 578 |
+
"grad_norm": 5.899810791015625,
|
| 579 |
+
"learning_rate": 1.739573384272525e-05,
|
| 580 |
+
"loss": 0.2627,
|
| 581 |
+
"step": 760
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 2.2031473533619454,
|
| 585 |
+
"grad_norm": 8.413034439086914,
|
| 586 |
+
"learning_rate": 1.7332059853549826e-05,
|
| 587 |
+
"loss": 0.2664,
|
| 588 |
+
"step": 770
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 2.2317596566523603,
|
| 592 |
+
"grad_norm": 5.280710697174072,
|
| 593 |
+
"learning_rate": 1.7268385864374403e-05,
|
| 594 |
+
"loss": 0.2687,
|
| 595 |
+
"step": 780
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 2.260371959942775,
|
| 599 |
+
"grad_norm": 4.636008262634277,
|
| 600 |
+
"learning_rate": 1.7204711875198983e-05,
|
| 601 |
+
"loss": 0.3354,
|
| 602 |
+
"step": 790
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 2.28898426323319,
|
| 606 |
+
"grad_norm": 7.188244819641113,
|
| 607 |
+
"learning_rate": 1.7141037886023563e-05,
|
| 608 |
+
"loss": 0.3449,
|
| 609 |
+
"step": 800
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 2.317596566523605,
|
| 613 |
+
"grad_norm": 8.121512413024902,
|
| 614 |
+
"learning_rate": 1.707736389684814e-05,
|
| 615 |
+
"loss": 0.3,
|
| 616 |
+
"step": 810
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 2.34620886981402,
|
| 620 |
+
"grad_norm": 8.199843406677246,
|
| 621 |
+
"learning_rate": 1.7013689907672716e-05,
|
| 622 |
+
"loss": 0.2975,
|
| 623 |
+
"step": 820
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 2.374821173104435,
|
| 627 |
+
"grad_norm": 4.355212211608887,
|
| 628 |
+
"learning_rate": 1.6950015918497296e-05,
|
| 629 |
+
"loss": 0.3658,
|
| 630 |
+
"step": 830
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 2.40343347639485,
|
| 634 |
+
"grad_norm": 4.755102634429932,
|
| 635 |
+
"learning_rate": 1.6886341929321873e-05,
|
| 636 |
+
"loss": 0.2632,
|
| 637 |
+
"step": 840
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 2.432045779685265,
|
| 641 |
+
"grad_norm": 7.069221496582031,
|
| 642 |
+
"learning_rate": 1.682266794014645e-05,
|
| 643 |
+
"loss": 0.2625,
|
| 644 |
+
"step": 850
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 2.4606580829756797,
|
| 648 |
+
"grad_norm": 5.802147388458252,
|
| 649 |
+
"learning_rate": 1.675899395097103e-05,
|
| 650 |
+
"loss": 0.2629,
|
| 651 |
+
"step": 860
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 2.4892703862660945,
|
| 655 |
+
"grad_norm": 9.528565406799316,
|
| 656 |
+
"learning_rate": 1.669531996179561e-05,
|
| 657 |
+
"loss": 0.3839,
|
| 658 |
+
"step": 870
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 2.5178826895565094,
|
| 662 |
+
"grad_norm": 5.615097999572754,
|
| 663 |
+
"learning_rate": 1.6631645972620186e-05,
|
| 664 |
+
"loss": 0.2388,
|
| 665 |
+
"step": 880
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 2.5464949928469243,
|
| 669 |
+
"grad_norm": 6.9182209968566895,
|
| 670 |
+
"learning_rate": 1.6567971983444763e-05,
|
| 671 |
+
"loss": 0.2958,
|
| 672 |
+
"step": 890
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 2.575107296137339,
|
| 676 |
+
"grad_norm": 12.66451644897461,
|
| 677 |
+
"learning_rate": 1.6504297994269343e-05,
|
| 678 |
+
"loss": 0.2204,
|
| 679 |
+
"step": 900
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 2.603719599427754,
|
| 683 |
+
"grad_norm": 6.674743175506592,
|
| 684 |
+
"learning_rate": 1.6440624005093923e-05,
|
| 685 |
+
"loss": 0.2877,
|
| 686 |
+
"step": 910
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 2.632331902718169,
|
| 690 |
+
"grad_norm": 5.2552289962768555,
|
| 691 |
+
"learning_rate": 1.63769500159185e-05,
|
| 692 |
+
"loss": 0.2812,
|
| 693 |
+
"step": 920
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 2.6609442060085837,
|
| 697 |
+
"grad_norm": 7.143093585968018,
|
| 698 |
+
"learning_rate": 1.6313276026743076e-05,
|
| 699 |
+
"loss": 0.232,
|
| 700 |
+
"step": 930
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 2.6895565092989986,
|
| 704 |
+
"grad_norm": 6.480932235717773,
|
| 705 |
+
"learning_rate": 1.6249602037567656e-05,
|
| 706 |
+
"loss": 0.2833,
|
| 707 |
+
"step": 940
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 2.7181688125894135,
|
| 711 |
+
"grad_norm": 4.548788547515869,
|
| 712 |
+
"learning_rate": 1.6185928048392233e-05,
|
| 713 |
+
"loss": 0.303,
|
| 714 |
+
"step": 950
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 2.7467811158798283,
|
| 718 |
+
"grad_norm": 6.597518444061279,
|
| 719 |
+
"learning_rate": 1.612225405921681e-05,
|
| 720 |
+
"loss": 0.226,
|
| 721 |
+
"step": 960
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 2.775393419170243,
|
| 725 |
+
"grad_norm": 5.480116844177246,
|
| 726 |
+
"learning_rate": 1.605858007004139e-05,
|
| 727 |
+
"loss": 0.2969,
|
| 728 |
+
"step": 970
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 2.804005722460658,
|
| 732 |
+
"grad_norm": 7.167335510253906,
|
| 733 |
+
"learning_rate": 1.599490608086597e-05,
|
| 734 |
+
"loss": 0.291,
|
| 735 |
+
"step": 980
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 2.832618025751073,
|
| 739 |
+
"grad_norm": 7.781642436981201,
|
| 740 |
+
"learning_rate": 1.5931232091690546e-05,
|
| 741 |
+
"loss": 0.3327,
|
| 742 |
+
"step": 990
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 2.8612303290414878,
|
| 746 |
+
"grad_norm": 6.379146575927734,
|
| 747 |
+
"learning_rate": 1.5867558102515122e-05,
|
| 748 |
+
"loss": 0.2287,
|
| 749 |
+
"step": 1000
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 2.8898426323319026,
|
| 753 |
+
"grad_norm": 4.854823589324951,
|
| 754 |
+
"learning_rate": 1.5803884113339702e-05,
|
| 755 |
+
"loss": 0.2949,
|
| 756 |
+
"step": 1010
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 2.9184549356223175,
|
| 760 |
+
"grad_norm": 8.530597686767578,
|
| 761 |
+
"learning_rate": 1.574021012416428e-05,
|
| 762 |
+
"loss": 0.2513,
|
| 763 |
+
"step": 1020
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 2.9470672389127324,
|
| 767 |
+
"grad_norm": 3.9975430965423584,
|
| 768 |
+
"learning_rate": 1.567653613498886e-05,
|
| 769 |
+
"loss": 0.241,
|
| 770 |
+
"step": 1030
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 2.9756795422031472,
|
| 774 |
+
"grad_norm": 7.5502495765686035,
|
| 775 |
+
"learning_rate": 1.5612862145813436e-05,
|
| 776 |
+
"loss": 0.2415,
|
| 777 |
+
"step": 1040
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 2.9985693848354793,
|
| 781 |
+
"eval_avg_f1": 0.8646060311796574,
|
| 782 |
+
"eval_avg_macro_f1": 0.8202031937507945,
|
| 783 |
+
"eval_hazard_accuracy": 0.9242315939957112,
|
| 784 |
+
"eval_hazard_f1": 0.9209214047945541,
|
| 785 |
+
"eval_hazard_macro_f1": 0.8335196381848966,
|
| 786 |
+
"eval_hazard_precision": 0.922656067429271,
|
| 787 |
+
"eval_hazard_recall": 0.9242315939957112,
|
| 788 |
+
"eval_loss": 0.31081312894821167,
|
| 789 |
+
"eval_product_accuracy": 0.8091493924231594,
|
| 790 |
+
"eval_product_f1": 0.8082906575647607,
|
| 791 |
+
"eval_product_macro_f1": 0.8068867493166926,
|
| 792 |
+
"eval_product_precision": 0.821048045009564,
|
| 793 |
+
"eval_product_recall": 0.8091493924231594,
|
| 794 |
+
"eval_runtime": 129.7873,
|
| 795 |
+
"eval_samples_per_second": 10.779,
|
| 796 |
+
"eval_steps_per_second": 5.393,
|
| 797 |
+
"step": 1048
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 3.004291845493562,
|
| 801 |
+
"grad_norm": 7.4025726318359375,
|
| 802 |
+
"learning_rate": 1.5549188156638016e-05,
|
| 803 |
+
"loss": 0.2662,
|
| 804 |
+
"step": 1050
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 3.032904148783977,
|
| 808 |
+
"grad_norm": 3.517706871032715,
|
| 809 |
+
"learning_rate": 1.5485514167462592e-05,
|
| 810 |
+
"loss": 0.1339,
|
| 811 |
+
"step": 1060
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 3.061516452074392,
|
| 815 |
+
"grad_norm": 7.23236083984375,
|
| 816 |
+
"learning_rate": 1.5421840178287172e-05,
|
| 817 |
+
"loss": 0.1601,
|
| 818 |
+
"step": 1070
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 3.0901287553648067,
|
| 822 |
+
"grad_norm": 8.8353853225708,
|
| 823 |
+
"learning_rate": 1.535816618911175e-05,
|
| 824 |
+
"loss": 0.1327,
|
| 825 |
+
"step": 1080
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 3.1187410586552216,
|
| 829 |
+
"grad_norm": 7.725401878356934,
|
| 830 |
+
"learning_rate": 1.529449219993633e-05,
|
| 831 |
+
"loss": 0.1812,
|
| 832 |
+
"step": 1090
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 3.1473533619456364,
|
| 836 |
+
"grad_norm": 7.550207138061523,
|
| 837 |
+
"learning_rate": 1.5230818210760905e-05,
|
| 838 |
+
"loss": 0.1994,
|
| 839 |
+
"step": 1100
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 3.1759656652360517,
|
| 843 |
+
"grad_norm": 9.055293083190918,
|
| 844 |
+
"learning_rate": 1.5167144221585484e-05,
|
| 845 |
+
"loss": 0.1645,
|
| 846 |
+
"step": 1110
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 3.2045779685264666,
|
| 850 |
+
"grad_norm": 3.738288640975952,
|
| 851 |
+
"learning_rate": 1.5103470232410062e-05,
|
| 852 |
+
"loss": 0.167,
|
| 853 |
+
"step": 1120
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 3.2331902718168815,
|
| 857 |
+
"grad_norm": 4.433919906616211,
|
| 858 |
+
"learning_rate": 1.5039796243234639e-05,
|
| 859 |
+
"loss": 0.2408,
|
| 860 |
+
"step": 1130
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 3.2618025751072963,
|
| 864 |
+
"grad_norm": 7.696563243865967,
|
| 865 |
+
"learning_rate": 1.4976122254059217e-05,
|
| 866 |
+
"loss": 0.1636,
|
| 867 |
+
"step": 1140
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 3.290414878397711,
|
| 871 |
+
"grad_norm": 3.678316354751587,
|
| 872 |
+
"learning_rate": 1.4912448264883797e-05,
|
| 873 |
+
"loss": 0.1288,
|
| 874 |
+
"step": 1150
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 3.319027181688126,
|
| 878 |
+
"grad_norm": 5.206940174102783,
|
| 879 |
+
"learning_rate": 1.4848774275708375e-05,
|
| 880 |
+
"loss": 0.1615,
|
| 881 |
+
"step": 1160
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 3.347639484978541,
|
| 885 |
+
"grad_norm": 6.231516361236572,
|
| 886 |
+
"learning_rate": 1.4785100286532952e-05,
|
| 887 |
+
"loss": 0.203,
|
| 888 |
+
"step": 1170
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 3.376251788268956,
|
| 892 |
+
"grad_norm": 6.873571395874023,
|
| 893 |
+
"learning_rate": 1.472142629735753e-05,
|
| 894 |
+
"loss": 0.145,
|
| 895 |
+
"step": 1180
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 3.4048640915593706,
|
| 899 |
+
"grad_norm": 8.790820121765137,
|
| 900 |
+
"learning_rate": 1.4657752308182109e-05,
|
| 901 |
+
"loss": 0.1287,
|
| 902 |
+
"step": 1190
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 3.4334763948497855,
|
| 906 |
+
"grad_norm": 3.0134575366973877,
|
| 907 |
+
"learning_rate": 1.4594078319006685e-05,
|
| 908 |
+
"loss": 0.1526,
|
| 909 |
+
"step": 1200
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 3.4620886981402004,
|
| 913 |
+
"grad_norm": 3.7933926582336426,
|
| 914 |
+
"learning_rate": 1.4530404329831265e-05,
|
| 915 |
+
"loss": 0.1477,
|
| 916 |
+
"step": 1210
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 3.4907010014306152,
|
| 920 |
+
"grad_norm": 5.385199546813965,
|
| 921 |
+
"learning_rate": 1.4466730340655843e-05,
|
| 922 |
+
"loss": 0.1924,
|
| 923 |
+
"step": 1220
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 3.51931330472103,
|
| 927 |
+
"grad_norm": 4.563629627227783,
|
| 928 |
+
"learning_rate": 1.4403056351480422e-05,
|
| 929 |
+
"loss": 0.1599,
|
| 930 |
+
"step": 1230
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 3.547925608011445,
|
| 934 |
+
"grad_norm": 4.976149559020996,
|
| 935 |
+
"learning_rate": 1.4339382362304998e-05,
|
| 936 |
+
"loss": 0.1056,
|
| 937 |
+
"step": 1240
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 3.57653791130186,
|
| 941 |
+
"grad_norm": 7.8397369384765625,
|
| 942 |
+
"learning_rate": 1.4275708373129578e-05,
|
| 943 |
+
"loss": 0.1606,
|
| 944 |
+
"step": 1250
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 3.6051502145922747,
|
| 948 |
+
"grad_norm": 4.005160808563232,
|
| 949 |
+
"learning_rate": 1.4212034383954157e-05,
|
| 950 |
+
"loss": 0.1435,
|
| 951 |
+
"step": 1260
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 3.6337625178826896,
|
| 955 |
+
"grad_norm": 4.652032375335693,
|
| 956 |
+
"learning_rate": 1.4148360394778735e-05,
|
| 957 |
+
"loss": 0.1331,
|
| 958 |
+
"step": 1270
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 3.6623748211731044,
|
| 962 |
+
"grad_norm": 5.29043436050415,
|
| 963 |
+
"learning_rate": 1.4084686405603312e-05,
|
| 964 |
+
"loss": 0.2153,
|
| 965 |
+
"step": 1280
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 3.6909871244635193,
|
| 969 |
+
"grad_norm": 3.634098529815674,
|
| 970 |
+
"learning_rate": 1.402101241642789e-05,
|
| 971 |
+
"loss": 0.1544,
|
| 972 |
+
"step": 1290
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 3.719599427753934,
|
| 976 |
+
"grad_norm": 8.322735786437988,
|
| 977 |
+
"learning_rate": 1.395733842725247e-05,
|
| 978 |
+
"loss": 0.1972,
|
| 979 |
+
"step": 1300
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 3.748211731044349,
|
| 983 |
+
"grad_norm": 7.596883773803711,
|
| 984 |
+
"learning_rate": 1.3893664438077047e-05,
|
| 985 |
+
"loss": 0.0944,
|
| 986 |
+
"step": 1310
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 3.776824034334764,
|
| 990 |
+
"grad_norm": 7.210901737213135,
|
| 991 |
+
"learning_rate": 1.3829990448901625e-05,
|
| 992 |
+
"loss": 0.2145,
|
| 993 |
+
"step": 1320
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 3.8054363376251787,
|
| 997 |
+
"grad_norm": 2.7890021800994873,
|
| 998 |
+
"learning_rate": 1.3766316459726203e-05,
|
| 999 |
+
"loss": 0.1598,
|
| 1000 |
+
"step": 1330
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 3.8340486409155936,
|
| 1004 |
+
"grad_norm": 5.991145133972168,
|
| 1005 |
+
"learning_rate": 1.3702642470550781e-05,
|
| 1006 |
+
"loss": 0.1237,
|
| 1007 |
+
"step": 1340
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 3.8626609442060085,
|
| 1011 |
+
"grad_norm": 9.527064323425293,
|
| 1012 |
+
"learning_rate": 1.3638968481375358e-05,
|
| 1013 |
+
"loss": 0.2123,
|
| 1014 |
+
"step": 1350
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 3.8912732474964233,
|
| 1018 |
+
"grad_norm": 7.581963062286377,
|
| 1019 |
+
"learning_rate": 1.3575294492199938e-05,
|
| 1020 |
+
"loss": 0.1112,
|
| 1021 |
+
"step": 1360
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 3.919885550786838,
|
| 1025 |
+
"grad_norm": 3.083259344100952,
|
| 1026 |
+
"learning_rate": 1.3511620503024516e-05,
|
| 1027 |
+
"loss": 0.1645,
|
| 1028 |
+
"step": 1370
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 3.948497854077253,
|
| 1032 |
+
"grad_norm": 5.185080051422119,
|
| 1033 |
+
"learning_rate": 1.3447946513849093e-05,
|
| 1034 |
+
"loss": 0.1617,
|
| 1035 |
+
"step": 1380
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 3.977110157367668,
|
| 1039 |
+
"grad_norm": 3.8500514030456543,
|
| 1040 |
+
"learning_rate": 1.3384272524673671e-05,
|
| 1041 |
+
"loss": 0.1992,
|
| 1042 |
+
"step": 1390
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 4.0,
|
| 1046 |
+
"eval_avg_f1": 0.8851622412902382,
|
| 1047 |
+
"eval_avg_macro_f1": 0.8655477884160602,
|
| 1048 |
+
"eval_hazard_accuracy": 0.9306647605432452,
|
| 1049 |
+
"eval_hazard_f1": 0.9291664035270353,
|
| 1050 |
+
"eval_hazard_macro_f1": 0.8679930988825365,
|
| 1051 |
+
"eval_hazard_precision": 0.9299572534743619,
|
| 1052 |
+
"eval_hazard_recall": 0.9306647605432452,
|
| 1053 |
+
"eval_loss": 0.27699437737464905,
|
| 1054 |
+
"eval_product_accuracy": 0.8391708363116511,
|
| 1055 |
+
"eval_product_f1": 0.8411580790534411,
|
| 1056 |
+
"eval_product_macro_f1": 0.8631024779495838,
|
| 1057 |
+
"eval_product_precision": 0.8488249750983786,
|
| 1058 |
+
"eval_product_recall": 0.8391708363116511,
|
| 1059 |
+
"eval_runtime": 130.3572,
|
| 1060 |
+
"eval_samples_per_second": 10.732,
|
| 1061 |
+
"eval_steps_per_second": 5.37,
|
| 1062 |
+
"step": 1398
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 4.005722460658083,
|
| 1066 |
+
"grad_norm": 0.853125274181366,
|
| 1067 |
+
"learning_rate": 1.332059853549825e-05,
|
| 1068 |
+
"loss": 0.1052,
|
| 1069 |
+
"step": 1400
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 4.034334763948498,
|
| 1073 |
+
"grad_norm": 4.933560371398926,
|
| 1074 |
+
"learning_rate": 1.325692454632283e-05,
|
| 1075 |
+
"loss": 0.0654,
|
| 1076 |
+
"step": 1410
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 4.0629470672389125,
|
| 1080 |
+
"grad_norm": 3.6680829524993896,
|
| 1081 |
+
"learning_rate": 1.3193250557147406e-05,
|
| 1082 |
+
"loss": 0.1259,
|
| 1083 |
+
"step": 1420
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 4.091559370529327,
|
| 1087 |
+
"grad_norm": 6.895246982574463,
|
| 1088 |
+
"learning_rate": 1.3129576567971985e-05,
|
| 1089 |
+
"loss": 0.1075,
|
| 1090 |
+
"step": 1430
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 4.120171673819742,
|
| 1094 |
+
"grad_norm": 1.8694907426834106,
|
| 1095 |
+
"learning_rate": 1.3065902578796563e-05,
|
| 1096 |
+
"loss": 0.0468,
|
| 1097 |
+
"step": 1440
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 4.148783977110157,
|
| 1101 |
+
"grad_norm": 3.379357099533081,
|
| 1102 |
+
"learning_rate": 1.300222858962114e-05,
|
| 1103 |
+
"loss": 0.1315,
|
| 1104 |
+
"step": 1450
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 4.177396280400572,
|
| 1108 |
+
"grad_norm": 7.892834186553955,
|
| 1109 |
+
"learning_rate": 1.2938554600445718e-05,
|
| 1110 |
+
"loss": 0.1094,
|
| 1111 |
+
"step": 1460
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 4.206008583690987,
|
| 1115 |
+
"grad_norm": 1.6634479761123657,
|
| 1116 |
+
"learning_rate": 1.2874880611270298e-05,
|
| 1117 |
+
"loss": 0.0958,
|
| 1118 |
+
"step": 1470
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 4.234620886981402,
|
| 1122 |
+
"grad_norm": 3.4273829460144043,
|
| 1123 |
+
"learning_rate": 1.2811206622094876e-05,
|
| 1124 |
+
"loss": 0.0919,
|
| 1125 |
+
"step": 1480
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 4.263233190271817,
|
| 1129 |
+
"grad_norm": 3.1847472190856934,
|
| 1130 |
+
"learning_rate": 1.2747532632919453e-05,
|
| 1131 |
+
"loss": 0.119,
|
| 1132 |
+
"step": 1490
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 4.291845493562231,
|
| 1136 |
+
"grad_norm": 6.2553815841674805,
|
| 1137 |
+
"learning_rate": 1.2683858643744031e-05,
|
| 1138 |
+
"loss": 0.0607,
|
| 1139 |
+
"step": 1500
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 4.320457796852646,
|
| 1143 |
+
"grad_norm": 4.419532775878906,
|
| 1144 |
+
"learning_rate": 1.2620184654568611e-05,
|
| 1145 |
+
"loss": 0.0674,
|
| 1146 |
+
"step": 1510
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 4.349070100143061,
|
| 1150 |
+
"grad_norm": 0.7810031771659851,
|
| 1151 |
+
"learning_rate": 1.255651066539319e-05,
|
| 1152 |
+
"loss": 0.0714,
|
| 1153 |
+
"step": 1520
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 4.377682403433476,
|
| 1157 |
+
"grad_norm": 5.215312480926514,
|
| 1158 |
+
"learning_rate": 1.2492836676217766e-05,
|
| 1159 |
+
"loss": 0.1047,
|
| 1160 |
+
"step": 1530
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 4.406294706723891,
|
| 1164 |
+
"grad_norm": 3.8974525928497314,
|
| 1165 |
+
"learning_rate": 1.2429162687042344e-05,
|
| 1166 |
+
"loss": 0.1382,
|
| 1167 |
+
"step": 1540
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 4.434907010014306,
|
| 1171 |
+
"grad_norm": 2.479971408843994,
|
| 1172 |
+
"learning_rate": 1.2365488697866923e-05,
|
| 1173 |
+
"loss": 0.1178,
|
| 1174 |
+
"step": 1550
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 4.463519313304721,
|
| 1178 |
+
"grad_norm": 6.309189319610596,
|
| 1179 |
+
"learning_rate": 1.23018147086915e-05,
|
| 1180 |
+
"loss": 0.1058,
|
| 1181 |
+
"step": 1560
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 4.492131616595136,
|
| 1185 |
+
"grad_norm": 5.032012462615967,
|
| 1186 |
+
"learning_rate": 1.223814071951608e-05,
|
| 1187 |
+
"loss": 0.1014,
|
| 1188 |
+
"step": 1570
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 4.52074391988555,
|
| 1192 |
+
"grad_norm": 3.660862684249878,
|
| 1193 |
+
"learning_rate": 1.2174466730340657e-05,
|
| 1194 |
+
"loss": 0.1059,
|
| 1195 |
+
"step": 1580
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 4.549356223175966,
|
| 1199 |
+
"grad_norm": 4.471796035766602,
|
| 1200 |
+
"learning_rate": 1.2110792741165236e-05,
|
| 1201 |
+
"loss": 0.1342,
|
| 1202 |
+
"step": 1590
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 4.57796852646638,
|
| 1206 |
+
"grad_norm": 1.652951717376709,
|
| 1207 |
+
"learning_rate": 1.2047118751989812e-05,
|
| 1208 |
+
"loss": 0.0819,
|
| 1209 |
+
"step": 1600
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 4.606580829756796,
|
| 1213 |
+
"grad_norm": 10.334088325500488,
|
| 1214 |
+
"learning_rate": 1.198344476281439e-05,
|
| 1215 |
+
"loss": 0.126,
|
| 1216 |
+
"step": 1610
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 4.63519313304721,
|
| 1220 |
+
"grad_norm": 2.5108392238616943,
|
| 1221 |
+
"learning_rate": 1.191977077363897e-05,
|
| 1222 |
+
"loss": 0.06,
|
| 1223 |
+
"step": 1620
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 4.663805436337626,
|
| 1227 |
+
"grad_norm": 1.85515558719635,
|
| 1228 |
+
"learning_rate": 1.1856096784463547e-05,
|
| 1229 |
+
"loss": 0.1013,
|
| 1230 |
+
"step": 1630
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 4.69241773962804,
|
| 1234 |
+
"grad_norm": 3.7234935760498047,
|
| 1235 |
+
"learning_rate": 1.1792422795288126e-05,
|
| 1236 |
+
"loss": 0.118,
|
| 1237 |
+
"step": 1640
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 4.721030042918455,
|
| 1241 |
+
"grad_norm": 1.4880505800247192,
|
| 1242 |
+
"learning_rate": 1.1728748806112704e-05,
|
| 1243 |
+
"loss": 0.1033,
|
| 1244 |
+
"step": 1650
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 4.74964234620887,
|
| 1248 |
+
"grad_norm": 0.767953097820282,
|
| 1249 |
+
"learning_rate": 1.1665074816937282e-05,
|
| 1250 |
+
"loss": 0.0686,
|
| 1251 |
+
"step": 1660
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 4.778254649499285,
|
| 1255 |
+
"grad_norm": 6.8715643882751465,
|
| 1256 |
+
"learning_rate": 1.1601400827761859e-05,
|
| 1257 |
+
"loss": 0.1569,
|
| 1258 |
+
"step": 1670
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 4.8068669527897,
|
| 1262 |
+
"grad_norm": 4.068518161773682,
|
| 1263 |
+
"learning_rate": 1.1537726838586439e-05,
|
| 1264 |
+
"loss": 0.1418,
|
| 1265 |
+
"step": 1680
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 4.835479256080115,
|
| 1269 |
+
"grad_norm": 4.682926654815674,
|
| 1270 |
+
"learning_rate": 1.1474052849411017e-05,
|
| 1271 |
+
"loss": 0.0648,
|
| 1272 |
+
"step": 1690
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 4.86409155937053,
|
| 1276 |
+
"grad_norm": 7.655228614807129,
|
| 1277 |
+
"learning_rate": 1.1410378860235594e-05,
|
| 1278 |
+
"loss": 0.0663,
|
| 1279 |
+
"step": 1700
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 4.8927038626609445,
|
| 1283 |
+
"grad_norm": 3.970196485519409,
|
| 1284 |
+
"learning_rate": 1.1346704871060172e-05,
|
| 1285 |
+
"loss": 0.0987,
|
| 1286 |
+
"step": 1710
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 4.921316165951359,
|
| 1290 |
+
"grad_norm": 5.761990070343018,
|
| 1291 |
+
"learning_rate": 1.128303088188475e-05,
|
| 1292 |
+
"loss": 0.1427,
|
| 1293 |
+
"step": 1720
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 4.949928469241774,
|
| 1297 |
+
"grad_norm": 4.295167922973633,
|
| 1298 |
+
"learning_rate": 1.121935689270933e-05,
|
| 1299 |
+
"loss": 0.0823,
|
| 1300 |
+
"step": 1730
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 4.978540772532189,
|
| 1304 |
+
"grad_norm": 4.116291046142578,
|
| 1305 |
+
"learning_rate": 1.1155682903533907e-05,
|
| 1306 |
+
"loss": 0.1385,
|
| 1307 |
+
"step": 1740
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 4.998569384835479,
|
| 1311 |
+
"eval_avg_f1": 0.8941948349225115,
|
| 1312 |
+
"eval_avg_macro_f1": 0.8878550329309804,
|
| 1313 |
+
"eval_hazard_accuracy": 0.9435310936383131,
|
| 1314 |
+
"eval_hazard_f1": 0.9425641782349181,
|
| 1315 |
+
"eval_hazard_macro_f1": 0.9097795857611878,
|
| 1316 |
+
"eval_hazard_precision": 0.9426745513555169,
|
| 1317 |
+
"eval_hazard_recall": 0.9435310936383131,
|
| 1318 |
+
"eval_loss": 0.28357216715812683,
|
| 1319 |
+
"eval_product_accuracy": 0.8456040028591851,
|
| 1320 |
+
"eval_product_f1": 0.8458254916101048,
|
| 1321 |
+
"eval_product_macro_f1": 0.8659304801007732,
|
| 1322 |
+
"eval_product_precision": 0.8482459261870001,
|
| 1323 |
+
"eval_product_recall": 0.8456040028591851,
|
| 1324 |
+
"eval_runtime": 130.0777,
|
| 1325 |
+
"eval_samples_per_second": 10.755,
|
| 1326 |
+
"eval_steps_per_second": 5.381,
|
| 1327 |
+
"step": 1747
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 5.007153075822604,
|
| 1331 |
+
"grad_norm": 0.7914103269577026,
|
| 1332 |
+
"learning_rate": 1.1092008914358485e-05,
|
| 1333 |
+
"loss": 0.103,
|
| 1334 |
+
"step": 1750
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 5.035765379113019,
|
| 1338 |
+
"grad_norm": 1.690512776374817,
|
| 1339 |
+
"learning_rate": 1.1028334925183064e-05,
|
| 1340 |
+
"loss": 0.0496,
|
| 1341 |
+
"step": 1760
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 5.064377682403434,
|
| 1345 |
+
"grad_norm": 2.9918479919433594,
|
| 1346 |
+
"learning_rate": 1.0964660936007644e-05,
|
| 1347 |
+
"loss": 0.0575,
|
| 1348 |
+
"step": 1770
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 5.0929899856938485,
|
| 1352 |
+
"grad_norm": 4.817768573760986,
|
| 1353 |
+
"learning_rate": 1.0900986946832219e-05,
|
| 1354 |
+
"loss": 0.0352,
|
| 1355 |
+
"step": 1780
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 5.121602288984263,
|
| 1359 |
+
"grad_norm": 4.413773059844971,
|
| 1360 |
+
"learning_rate": 1.0837312957656799e-05,
|
| 1361 |
+
"loss": 0.0619,
|
| 1362 |
+
"step": 1790
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 5.150214592274678,
|
| 1366 |
+
"grad_norm": 5.848459243774414,
|
| 1367 |
+
"learning_rate": 1.0773638968481377e-05,
|
| 1368 |
+
"loss": 0.0832,
|
| 1369 |
+
"step": 1800
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 5.178826895565093,
|
| 1373 |
+
"grad_norm": 1.7106515169143677,
|
| 1374 |
+
"learning_rate": 1.0709964979305953e-05,
|
| 1375 |
+
"loss": 0.0364,
|
| 1376 |
+
"step": 1810
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 5.207439198855508,
|
| 1380 |
+
"grad_norm": 0.5961392521858215,
|
| 1381 |
+
"learning_rate": 1.0646290990130532e-05,
|
| 1382 |
+
"loss": 0.059,
|
| 1383 |
+
"step": 1820
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 5.236051502145923,
|
| 1387 |
+
"grad_norm": 6.867336750030518,
|
| 1388 |
+
"learning_rate": 1.0582617000955112e-05,
|
| 1389 |
+
"loss": 0.1284,
|
| 1390 |
+
"step": 1830
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 5.264663805436338,
|
| 1394 |
+
"grad_norm": 2.6260428428649902,
|
| 1395 |
+
"learning_rate": 1.051894301177969e-05,
|
| 1396 |
+
"loss": 0.0571,
|
| 1397 |
+
"step": 1840
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 5.293276108726753,
|
| 1401 |
+
"grad_norm": 4.524204730987549,
|
| 1402 |
+
"learning_rate": 1.0455269022604267e-05,
|
| 1403 |
+
"loss": 0.0271,
|
| 1404 |
+
"step": 1850
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 5.3218884120171674,
|
| 1408 |
+
"grad_norm": 0.2257910519838333,
|
| 1409 |
+
"learning_rate": 1.0391595033428845e-05,
|
| 1410 |
+
"loss": 0.0412,
|
| 1411 |
+
"step": 1860
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 5.350500715307582,
|
| 1415 |
+
"grad_norm": 2.122143268585205,
|
| 1416 |
+
"learning_rate": 1.0327921044253423e-05,
|
| 1417 |
+
"loss": 0.0523,
|
| 1418 |
+
"step": 1870
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 5.379113018597997,
|
| 1422 |
+
"grad_norm": 3.099912643432617,
|
| 1423 |
+
"learning_rate": 1.0264247055078e-05,
|
| 1424 |
+
"loss": 0.0956,
|
| 1425 |
+
"step": 1880
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 5.407725321888412,
|
| 1429 |
+
"grad_norm": 1.7758303880691528,
|
| 1430 |
+
"learning_rate": 1.020057306590258e-05,
|
| 1431 |
+
"loss": 0.0505,
|
| 1432 |
+
"step": 1890
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 5.436337625178827,
|
| 1436 |
+
"grad_norm": 0.38635560870170593,
|
| 1437 |
+
"learning_rate": 1.0136899076727158e-05,
|
| 1438 |
+
"loss": 0.0337,
|
| 1439 |
+
"step": 1900
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 5.464949928469242,
|
| 1443 |
+
"grad_norm": 1.2298860549926758,
|
| 1444 |
+
"learning_rate": 1.0073225087551737e-05,
|
| 1445 |
+
"loss": 0.0366,
|
| 1446 |
+
"step": 1910
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 5.493562231759657,
|
| 1450 |
+
"grad_norm": 3.3369784355163574,
|
| 1451 |
+
"learning_rate": 1.0009551098376313e-05,
|
| 1452 |
+
"loss": 0.077,
|
| 1453 |
+
"step": 1920
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 5.5221745350500715,
|
| 1457 |
+
"grad_norm": 3.413776397705078,
|
| 1458 |
+
"learning_rate": 9.945877109200891e-06,
|
| 1459 |
+
"loss": 0.064,
|
| 1460 |
+
"step": 1930
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 5.550786838340486,
|
| 1464 |
+
"grad_norm": 8.428875923156738,
|
| 1465 |
+
"learning_rate": 9.882203120025471e-06,
|
| 1466 |
+
"loss": 0.0546,
|
| 1467 |
+
"step": 1940
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 5.579399141630901,
|
| 1471 |
+
"grad_norm": 3.4294254779815674,
|
| 1472 |
+
"learning_rate": 9.818529130850048e-06,
|
| 1473 |
+
"loss": 0.0712,
|
| 1474 |
+
"step": 1950
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 5.608011444921316,
|
| 1478 |
+
"grad_norm": 6.573678970336914,
|
| 1479 |
+
"learning_rate": 9.754855141674626e-06,
|
| 1480 |
+
"loss": 0.0693,
|
| 1481 |
+
"step": 1960
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 5.636623748211731,
|
| 1485 |
+
"grad_norm": 2.1921682357788086,
|
| 1486 |
+
"learning_rate": 9.691181152499205e-06,
|
| 1487 |
+
"loss": 0.0433,
|
| 1488 |
+
"step": 1970
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 5.665236051502146,
|
| 1492 |
+
"grad_norm": 4.298460006713867,
|
| 1493 |
+
"learning_rate": 9.627507163323783e-06,
|
| 1494 |
+
"loss": 0.0624,
|
| 1495 |
+
"step": 1980
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 5.693848354792561,
|
| 1499 |
+
"grad_norm": 0.3570319712162018,
|
| 1500 |
+
"learning_rate": 9.563833174148361e-06,
|
| 1501 |
+
"loss": 0.0354,
|
| 1502 |
+
"step": 1990
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 5.7224606580829755,
|
| 1506 |
+
"grad_norm": 0.37695419788360596,
|
| 1507 |
+
"learning_rate": 9.50015918497294e-06,
|
| 1508 |
+
"loss": 0.0354,
|
| 1509 |
+
"step": 2000
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 5.75107296137339,
|
| 1513 |
+
"grad_norm": 3.561854362487793,
|
| 1514 |
+
"learning_rate": 9.436485195797518e-06,
|
| 1515 |
+
"loss": 0.0616,
|
| 1516 |
+
"step": 2010
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 5.779685264663805,
|
| 1520 |
+
"grad_norm": 4.1541900634765625,
|
| 1521 |
+
"learning_rate": 9.372811206622096e-06,
|
| 1522 |
+
"loss": 0.0536,
|
| 1523 |
+
"step": 2020
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 5.80829756795422,
|
| 1527 |
+
"grad_norm": 1.080567717552185,
|
| 1528 |
+
"learning_rate": 9.309137217446675e-06,
|
| 1529 |
+
"loss": 0.0245,
|
| 1530 |
+
"step": 2030
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 5.836909871244635,
|
| 1534 |
+
"grad_norm": 6.586161136627197,
|
| 1535 |
+
"learning_rate": 9.245463228271251e-06,
|
| 1536 |
+
"loss": 0.0332,
|
| 1537 |
+
"step": 2040
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 5.86552217453505,
|
| 1541 |
+
"grad_norm": 3.8174326419830322,
|
| 1542 |
+
"learning_rate": 9.18178923909583e-06,
|
| 1543 |
+
"loss": 0.0959,
|
| 1544 |
+
"step": 2050
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 5.894134477825465,
|
| 1548 |
+
"grad_norm": 1.1422789096832275,
|
| 1549 |
+
"learning_rate": 9.118115249920408e-06,
|
| 1550 |
+
"loss": 0.0333,
|
| 1551 |
+
"step": 2060
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 5.92274678111588,
|
| 1555 |
+
"grad_norm": 2.6852996349334717,
|
| 1556 |
+
"learning_rate": 9.054441260744986e-06,
|
| 1557 |
+
"loss": 0.0747,
|
| 1558 |
+
"step": 2070
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 5.9513590844062945,
|
| 1562 |
+
"grad_norm": 2.938167095184326,
|
| 1563 |
+
"learning_rate": 8.990767271569564e-06,
|
| 1564 |
+
"loss": 0.0546,
|
| 1565 |
+
"step": 2080
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 5.979971387696709,
|
| 1569 |
+
"grad_norm": 4.585486888885498,
|
| 1570 |
+
"learning_rate": 8.927093282394143e-06,
|
| 1571 |
+
"loss": 0.0743,
|
| 1572 |
+
"step": 2090
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 6.0,
|
| 1576 |
+
"eval_avg_f1": 0.899039326351045,
|
| 1577 |
+
"eval_avg_macro_f1": 0.8991573960541488,
|
| 1578 |
+
"eval_hazard_accuracy": 0.9485346676197284,
|
| 1579 |
+
"eval_hazard_f1": 0.9484425225873391,
|
| 1580 |
+
"eval_hazard_macro_f1": 0.9204644489900575,
|
| 1581 |
+
"eval_hazard_precision": 0.9486631245033109,
|
| 1582 |
+
"eval_hazard_recall": 0.9485346676197284,
|
| 1583 |
+
"eval_loss": 0.3084051012992859,
|
| 1584 |
+
"eval_product_accuracy": 0.8470335954253038,
|
| 1585 |
+
"eval_product_f1": 0.849636130114751,
|
| 1586 |
+
"eval_product_macro_f1": 0.8778503431182402,
|
| 1587 |
+
"eval_product_precision": 0.8553543990148441,
|
| 1588 |
+
"eval_product_recall": 0.8470335954253038,
|
| 1589 |
+
"eval_runtime": 130.815,
|
| 1590 |
+
"eval_samples_per_second": 10.694,
|
| 1591 |
+
"eval_steps_per_second": 5.351,
|
| 1592 |
+
"step": 2097
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 6.008583690987124,
|
| 1596 |
+
"grad_norm": 2.7679495811462402,
|
| 1597 |
+
"learning_rate": 8.863419293218721e-06,
|
| 1598 |
+
"loss": 0.0518,
|
| 1599 |
+
"step": 2100
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 6.037195994277539,
|
| 1603 |
+
"grad_norm": 3.5409038066864014,
|
| 1604 |
+
"learning_rate": 8.7997453040433e-06,
|
| 1605 |
+
"loss": 0.0344,
|
| 1606 |
+
"step": 2110
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 6.065808297567954,
|
| 1610 |
+
"grad_norm": 0.5573897957801819,
|
| 1611 |
+
"learning_rate": 8.736071314867878e-06,
|
| 1612 |
+
"loss": 0.0116,
|
| 1613 |
+
"step": 2120
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 6.094420600858369,
|
| 1617 |
+
"grad_norm": 3.2066051959991455,
|
| 1618 |
+
"learning_rate": 8.672397325692456e-06,
|
| 1619 |
+
"loss": 0.0145,
|
| 1620 |
+
"step": 2130
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 6.123032904148784,
|
| 1624 |
+
"grad_norm": 2.6980865001678467,
|
| 1625 |
+
"learning_rate": 8.608723336517033e-06,
|
| 1626 |
+
"loss": 0.0319,
|
| 1627 |
+
"step": 2140
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 6.1516452074391985,
|
| 1631 |
+
"grad_norm": 3.0440590381622314,
|
| 1632 |
+
"learning_rate": 8.545049347341613e-06,
|
| 1633 |
+
"loss": 0.0327,
|
| 1634 |
+
"step": 2150
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 6.180257510729613,
|
| 1638 |
+
"grad_norm": 0.7029679417610168,
|
| 1639 |
+
"learning_rate": 8.481375358166189e-06,
|
| 1640 |
+
"loss": 0.0361,
|
| 1641 |
+
"step": 2160
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 6.208869814020028,
|
| 1645 |
+
"grad_norm": 1.076248288154602,
|
| 1646 |
+
"learning_rate": 8.417701368990769e-06,
|
| 1647 |
+
"loss": 0.0219,
|
| 1648 |
+
"step": 2170
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 6.237482117310443,
|
| 1652 |
+
"grad_norm": 0.21603639423847198,
|
| 1653 |
+
"learning_rate": 8.354027379815346e-06,
|
| 1654 |
+
"loss": 0.0254,
|
| 1655 |
+
"step": 2180
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 6.266094420600858,
|
| 1659 |
+
"grad_norm": 1.9013558626174927,
|
| 1660 |
+
"learning_rate": 8.290353390639924e-06,
|
| 1661 |
+
"loss": 0.0463,
|
| 1662 |
+
"step": 2190
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 6.294706723891273,
|
| 1666 |
+
"grad_norm": 5.441349983215332,
|
| 1667 |
+
"learning_rate": 8.226679401464502e-06,
|
| 1668 |
+
"loss": 0.024,
|
| 1669 |
+
"step": 2200
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 6.323319027181688,
|
| 1673 |
+
"grad_norm": 5.063304901123047,
|
| 1674 |
+
"learning_rate": 8.16300541228908e-06,
|
| 1675 |
+
"loss": 0.0637,
|
| 1676 |
+
"step": 2210
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 6.3519313304721035,
|
| 1680 |
+
"grad_norm": 1.4071033000946045,
|
| 1681 |
+
"learning_rate": 8.099331423113659e-06,
|
| 1682 |
+
"loss": 0.0517,
|
| 1683 |
+
"step": 2220
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 6.380543633762517,
|
| 1687 |
+
"grad_norm": 1.1152009963989258,
|
| 1688 |
+
"learning_rate": 8.035657433938237e-06,
|
| 1689 |
+
"loss": 0.0389,
|
| 1690 |
+
"step": 2230
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 6.409155937052933,
|
| 1694 |
+
"grad_norm": 0.7116595506668091,
|
| 1695 |
+
"learning_rate": 7.971983444762816e-06,
|
| 1696 |
+
"loss": 0.0189,
|
| 1697 |
+
"step": 2240
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 6.437768240343348,
|
| 1701 |
+
"grad_norm": 0.37217339873313904,
|
| 1702 |
+
"learning_rate": 7.908309455587392e-06,
|
| 1703 |
+
"loss": 0.0474,
|
| 1704 |
+
"step": 2250
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 6.466380543633763,
|
| 1708 |
+
"grad_norm": 4.032446384429932,
|
| 1709 |
+
"learning_rate": 7.844635466411972e-06,
|
| 1710 |
+
"loss": 0.0192,
|
| 1711 |
+
"step": 2260
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 6.494992846924178,
|
| 1715 |
+
"grad_norm": 1.627589464187622,
|
| 1716 |
+
"learning_rate": 7.780961477236549e-06,
|
| 1717 |
+
"loss": 0.0287,
|
| 1718 |
+
"step": 2270
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 6.523605150214593,
|
| 1722 |
+
"grad_norm": 4.680599689483643,
|
| 1723 |
+
"learning_rate": 7.717287488061129e-06,
|
| 1724 |
+
"loss": 0.0266,
|
| 1725 |
+
"step": 2280
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 6.5522174535050075,
|
| 1729 |
+
"grad_norm": 2.4412145614624023,
|
| 1730 |
+
"learning_rate": 7.653613498885705e-06,
|
| 1731 |
+
"loss": 0.0359,
|
| 1732 |
+
"step": 2290
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 6.580829756795422,
|
| 1736 |
+
"grad_norm": 7.0371994972229,
|
| 1737 |
+
"learning_rate": 7.589939509710284e-06,
|
| 1738 |
+
"loss": 0.0444,
|
| 1739 |
+
"step": 2300
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 6.609442060085837,
|
| 1743 |
+
"grad_norm": 1.9186558723449707,
|
| 1744 |
+
"learning_rate": 7.526265520534862e-06,
|
| 1745 |
+
"loss": 0.0464,
|
| 1746 |
+
"step": 2310
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 6.638054363376252,
|
| 1750 |
+
"grad_norm": 5.816532135009766,
|
| 1751 |
+
"learning_rate": 7.4625915313594395e-06,
|
| 1752 |
+
"loss": 0.0326,
|
| 1753 |
+
"step": 2320
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 6.666666666666667,
|
| 1757 |
+
"grad_norm": 0.9704585075378418,
|
| 1758 |
+
"learning_rate": 7.398917542184019e-06,
|
| 1759 |
+
"loss": 0.0509,
|
| 1760 |
+
"step": 2330
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 6.695278969957082,
|
| 1764 |
+
"grad_norm": 0.7912341356277466,
|
| 1765 |
+
"learning_rate": 7.335243553008596e-06,
|
| 1766 |
+
"loss": 0.0271,
|
| 1767 |
+
"step": 2340
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 6.723891273247497,
|
| 1771 |
+
"grad_norm": 1.4395134449005127,
|
| 1772 |
+
"learning_rate": 7.271569563833175e-06,
|
| 1773 |
+
"loss": 0.0116,
|
| 1774 |
+
"step": 2350
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 6.752503576537912,
|
| 1778 |
+
"grad_norm": 1.1446588039398193,
|
| 1779 |
+
"learning_rate": 7.207895574657753e-06,
|
| 1780 |
+
"loss": 0.0144,
|
| 1781 |
+
"step": 2360
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 6.781115879828326,
|
| 1785 |
+
"grad_norm": 9.389579772949219,
|
| 1786 |
+
"learning_rate": 7.144221585482332e-06,
|
| 1787 |
+
"loss": 0.0501,
|
| 1788 |
+
"step": 2370
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 6.809728183118741,
|
| 1792 |
+
"grad_norm": 0.7342149615287781,
|
| 1793 |
+
"learning_rate": 7.080547596306909e-06,
|
| 1794 |
+
"loss": 0.0423,
|
| 1795 |
+
"step": 2380
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 6.838340486409156,
|
| 1799 |
+
"grad_norm": 0.45319071412086487,
|
| 1800 |
+
"learning_rate": 7.016873607131487e-06,
|
| 1801 |
+
"loss": 0.0166,
|
| 1802 |
+
"step": 2390
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 6.866952789699571,
|
| 1806 |
+
"grad_norm": 1.0449373722076416,
|
| 1807 |
+
"learning_rate": 6.953199617956066e-06,
|
| 1808 |
+
"loss": 0.0334,
|
| 1809 |
+
"step": 2400
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 6.895565092989986,
|
| 1813 |
+
"grad_norm": 2.302659034729004,
|
| 1814 |
+
"learning_rate": 6.889525628780643e-06,
|
| 1815 |
+
"loss": 0.0245,
|
| 1816 |
+
"step": 2410
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 6.924177396280401,
|
| 1820 |
+
"grad_norm": 4.263031005859375,
|
| 1821 |
+
"learning_rate": 6.825851639605222e-06,
|
| 1822 |
+
"loss": 0.0471,
|
| 1823 |
+
"step": 2420
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 6.952789699570816,
|
| 1827 |
+
"grad_norm": 1.7275855541229248,
|
| 1828 |
+
"learning_rate": 6.7621776504298e-06,
|
| 1829 |
+
"loss": 0.0398,
|
| 1830 |
+
"step": 2430
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 6.9814020028612305,
|
| 1834 |
+
"grad_norm": 7.692391872406006,
|
| 1835 |
+
"learning_rate": 6.698503661254378e-06,
|
| 1836 |
+
"loss": 0.0518,
|
| 1837 |
+
"step": 2440
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 6.998569384835479,
|
| 1841 |
+
"eval_avg_f1": 0.898106190665952,
|
| 1842 |
+
"eval_avg_macro_f1": 0.8971876250415056,
|
| 1843 |
+
"eval_hazard_accuracy": 0.9449606862044317,
|
| 1844 |
+
"eval_hazard_f1": 0.9433007151966496,
|
| 1845 |
+
"eval_hazard_macro_f1": 0.9137195353650875,
|
| 1846 |
+
"eval_hazard_precision": 0.9454855478200699,
|
| 1847 |
+
"eval_hazard_recall": 0.9449606862044317,
|
| 1848 |
+
"eval_loss": 0.316262811422348,
|
| 1849 |
+
"eval_product_accuracy": 0.8491779842744818,
|
| 1850 |
+
"eval_product_f1": 0.8529116661352544,
|
| 1851 |
+
"eval_product_macro_f1": 0.8806557147179237,
|
| 1852 |
+
"eval_product_precision": 0.8601471328543786,
|
| 1853 |
+
"eval_product_recall": 0.8491779842744818,
|
| 1854 |
+
"eval_runtime": 130.6421,
|
| 1855 |
+
"eval_samples_per_second": 10.709,
|
| 1856 |
+
"eval_steps_per_second": 5.358,
|
| 1857 |
+
"step": 2446
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 7.010014306151645,
|
| 1861 |
+
"grad_norm": 0.39778342843055725,
|
| 1862 |
+
"learning_rate": 6.634829672078957e-06,
|
| 1863 |
+
"loss": 0.0237,
|
| 1864 |
+
"step": 2450
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 7.03862660944206,
|
| 1868 |
+
"grad_norm": 0.2173616886138916,
|
| 1869 |
+
"learning_rate": 6.571155682903534e-06,
|
| 1870 |
+
"loss": 0.0126,
|
| 1871 |
+
"step": 2460
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 7.067238912732475,
|
| 1875 |
+
"grad_norm": 0.37986260652542114,
|
| 1876 |
+
"learning_rate": 6.507481693728112e-06,
|
| 1877 |
+
"loss": 0.0175,
|
| 1878 |
+
"step": 2470
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 7.09585121602289,
|
| 1882 |
+
"grad_norm": 0.17169423401355743,
|
| 1883 |
+
"learning_rate": 6.443807704552691e-06,
|
| 1884 |
+
"loss": 0.0084,
|
| 1885 |
+
"step": 2480
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 7.124463519313305,
|
| 1889 |
+
"grad_norm": 0.15883368253707886,
|
| 1890 |
+
"learning_rate": 6.380133715377269e-06,
|
| 1891 |
+
"loss": 0.0113,
|
| 1892 |
+
"step": 2490
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 7.15307582260372,
|
| 1896 |
+
"grad_norm": 0.38070613145828247,
|
| 1897 |
+
"learning_rate": 6.3164597262018465e-06,
|
| 1898 |
+
"loss": 0.0158,
|
| 1899 |
+
"step": 2500
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 7.1816881258941345,
|
| 1903 |
+
"grad_norm": 1.6812623739242554,
|
| 1904 |
+
"learning_rate": 6.252785737026426e-06,
|
| 1905 |
+
"loss": 0.0058,
|
| 1906 |
+
"step": 2510
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 7.210300429184549,
|
| 1910 |
+
"grad_norm": 0.9641416668891907,
|
| 1911 |
+
"learning_rate": 6.189111747851003e-06,
|
| 1912 |
+
"loss": 0.0164,
|
| 1913 |
+
"step": 2520
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 7.238912732474964,
|
| 1917 |
+
"grad_norm": 0.4583294689655304,
|
| 1918 |
+
"learning_rate": 6.125437758675582e-06,
|
| 1919 |
+
"loss": 0.0276,
|
| 1920 |
+
"step": 2530
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 7.267525035765379,
|
| 1924 |
+
"grad_norm": 0.13083776831626892,
|
| 1925 |
+
"learning_rate": 6.06176376950016e-06,
|
| 1926 |
+
"loss": 0.0218,
|
| 1927 |
+
"step": 2540
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 7.296137339055794,
|
| 1931 |
+
"grad_norm": 1.4103626012802124,
|
| 1932 |
+
"learning_rate": 5.998089780324737e-06,
|
| 1933 |
+
"loss": 0.0125,
|
| 1934 |
+
"step": 2550
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 7.324749642346209,
|
| 1938 |
+
"grad_norm": 0.144416943192482,
|
| 1939 |
+
"learning_rate": 5.934415791149316e-06,
|
| 1940 |
+
"loss": 0.0107,
|
| 1941 |
+
"step": 2560
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 7.353361945636624,
|
| 1945 |
+
"grad_norm": 0.27716395258903503,
|
| 1946 |
+
"learning_rate": 5.870741801973894e-06,
|
| 1947 |
+
"loss": 0.0134,
|
| 1948 |
+
"step": 2570
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 7.381974248927039,
|
| 1952 |
+
"grad_norm": 1.8152793645858765,
|
| 1953 |
+
"learning_rate": 5.807067812798473e-06,
|
| 1954 |
+
"loss": 0.0082,
|
| 1955 |
+
"step": 2580
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 7.410586552217453,
|
| 1959 |
+
"grad_norm": 0.464851438999176,
|
| 1960 |
+
"learning_rate": 5.74339382362305e-06,
|
| 1961 |
+
"loss": 0.0205,
|
| 1962 |
+
"step": 2590
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 7.439198855507868,
|
| 1966 |
+
"grad_norm": 0.06875355541706085,
|
| 1967 |
+
"learning_rate": 5.679719834447629e-06,
|
| 1968 |
+
"loss": 0.0139,
|
| 1969 |
+
"step": 2600
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 7.467811158798283,
|
| 1973 |
+
"grad_norm": 3.882838487625122,
|
| 1974 |
+
"learning_rate": 5.616045845272207e-06,
|
| 1975 |
+
"loss": 0.0231,
|
| 1976 |
+
"step": 2610
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 7.496423462088698,
|
| 1980 |
+
"grad_norm": 1.3986179828643799,
|
| 1981 |
+
"learning_rate": 5.552371856096785e-06,
|
| 1982 |
+
"loss": 0.0107,
|
| 1983 |
+
"step": 2620
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 7.525035765379113,
|
| 1987 |
+
"grad_norm": 0.6413142085075378,
|
| 1988 |
+
"learning_rate": 5.488697866921363e-06,
|
| 1989 |
+
"loss": 0.0209,
|
| 1990 |
+
"step": 2630
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 7.553648068669528,
|
| 1994 |
+
"grad_norm": 0.40927574038505554,
|
| 1995 |
+
"learning_rate": 5.425023877745941e-06,
|
| 1996 |
+
"loss": 0.0069,
|
| 1997 |
+
"step": 2640
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 7.582260371959943,
|
| 2001 |
+
"grad_norm": 0.2263065129518509,
|
| 2002 |
+
"learning_rate": 5.361349888570519e-06,
|
| 2003 |
+
"loss": 0.0178,
|
| 2004 |
+
"step": 2650
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 7.6108726752503575,
|
| 2008 |
+
"grad_norm": 0.36000296473503113,
|
| 2009 |
+
"learning_rate": 5.30404329831264e-06,
|
| 2010 |
+
"loss": 0.0169,
|
| 2011 |
+
"step": 2660
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 7.639484978540772,
|
| 2015 |
+
"grad_norm": 4.618471622467041,
|
| 2016 |
+
"learning_rate": 5.240369309137218e-06,
|
| 2017 |
+
"loss": 0.031,
|
| 2018 |
+
"step": 2670
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 7.668097281831187,
|
| 2022 |
+
"grad_norm": 0.1742757260799408,
|
| 2023 |
+
"learning_rate": 5.176695319961796e-06,
|
| 2024 |
+
"loss": 0.0067,
|
| 2025 |
+
"step": 2680
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 7.696709585121602,
|
| 2029 |
+
"grad_norm": 4.546988487243652,
|
| 2030 |
+
"learning_rate": 5.1130213307863745e-06,
|
| 2031 |
+
"loss": 0.0262,
|
| 2032 |
+
"step": 2690
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 7.725321888412017,
|
| 2036 |
+
"grad_norm": 0.41645824909210205,
|
| 2037 |
+
"learning_rate": 5.049347341610953e-06,
|
| 2038 |
+
"loss": 0.0171,
|
| 2039 |
+
"step": 2700
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 7.753934191702432,
|
| 2043 |
+
"grad_norm": 1.6162680387496948,
|
| 2044 |
+
"learning_rate": 4.98567335243553e-06,
|
| 2045 |
+
"loss": 0.0366,
|
| 2046 |
+
"step": 2710
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 7.782546494992847,
|
| 2050 |
+
"grad_norm": 0.5289233922958374,
|
| 2051 |
+
"learning_rate": 4.9219993632601085e-06,
|
| 2052 |
+
"loss": 0.0229,
|
| 2053 |
+
"step": 2720
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 7.8111587982832615,
|
| 2057 |
+
"grad_norm": 1.002968430519104,
|
| 2058 |
+
"learning_rate": 4.858325374084687e-06,
|
| 2059 |
+
"loss": 0.0148,
|
| 2060 |
+
"step": 2730
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 7.839771101573676,
|
| 2064 |
+
"grad_norm": 0.32215040922164917,
|
| 2065 |
+
"learning_rate": 4.794651384909265e-06,
|
| 2066 |
+
"loss": 0.0438,
|
| 2067 |
+
"step": 2740
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 7.868383404864091,
|
| 2071 |
+
"grad_norm": 0.2097528576850891,
|
| 2072 |
+
"learning_rate": 4.730977395733843e-06,
|
| 2073 |
+
"loss": 0.0234,
|
| 2074 |
+
"step": 2750
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 7.896995708154506,
|
| 2078 |
+
"grad_norm": 0.3217938542366028,
|
| 2079 |
+
"learning_rate": 4.667303406558421e-06,
|
| 2080 |
+
"loss": 0.0256,
|
| 2081 |
+
"step": 2760
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 7.925608011444921,
|
| 2085 |
+
"grad_norm": 0.6360646486282349,
|
| 2086 |
+
"learning_rate": 4.603629417382999e-06,
|
| 2087 |
+
"loss": 0.0417,
|
| 2088 |
+
"step": 2770
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 7.954220314735336,
|
| 2092 |
+
"grad_norm": 2.2907752990722656,
|
| 2093 |
+
"learning_rate": 4.5399554282075775e-06,
|
| 2094 |
+
"loss": 0.0146,
|
| 2095 |
+
"step": 2780
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 7.982832618025751,
|
| 2099 |
+
"grad_norm": 0.6704244613647461,
|
| 2100 |
+
"learning_rate": 4.476281439032156e-06,
|
| 2101 |
+
"loss": 0.0203,
|
| 2102 |
+
"step": 2790
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 8.0,
|
| 2106 |
+
"eval_avg_f1": 0.9009805609498489,
|
| 2107 |
+
"eval_avg_macro_f1": 0.8958663202550365,
|
| 2108 |
+
"eval_hazard_accuracy": 0.9449606862044317,
|
| 2109 |
+
"eval_hazard_f1": 0.9442059444799251,
|
| 2110 |
+
"eval_hazard_macro_f1": 0.90671634348049,
|
| 2111 |
+
"eval_hazard_precision": 0.9452464738608288,
|
| 2112 |
+
"eval_hazard_recall": 0.9449606862044317,
|
| 2113 |
+
"eval_loss": 0.31793642044067383,
|
| 2114 |
+
"eval_product_accuracy": 0.8556111508220158,
|
| 2115 |
+
"eval_product_f1": 0.8577551774197726,
|
| 2116 |
+
"eval_product_macro_f1": 0.885016297029583,
|
| 2117 |
+
"eval_product_precision": 0.8628350198223755,
|
| 2118 |
+
"eval_product_recall": 0.8556111508220158,
|
| 2119 |
+
"eval_runtime": 130.7407,
|
| 2120 |
+
"eval_samples_per_second": 10.701,
|
| 2121 |
+
"eval_steps_per_second": 5.354,
|
| 2122 |
+
"step": 2796
|
| 2123 |
+
},
|
| 2124 |
+
{
|
| 2125 |
+
"epoch": 8.011444921316166,
|
| 2126 |
+
"grad_norm": 0.2047724425792694,
|
| 2127 |
+
"learning_rate": 4.412607449856734e-06,
|
| 2128 |
+
"loss": 0.0064,
|
| 2129 |
+
"step": 2800
|
| 2130 |
+
},
|
| 2131 |
+
{
|
| 2132 |
+
"epoch": 8.040057224606581,
|
| 2133 |
+
"grad_norm": 0.07871759682893753,
|
| 2134 |
+
"learning_rate": 4.3489334606813125e-06,
|
| 2135 |
+
"loss": 0.0138,
|
| 2136 |
+
"step": 2810
|
| 2137 |
+
},
|
| 2138 |
+
{
|
| 2139 |
+
"epoch": 8.068669527896995,
|
| 2140 |
+
"grad_norm": 1.8063669204711914,
|
| 2141 |
+
"learning_rate": 4.285259471505891e-06,
|
| 2142 |
+
"loss": 0.0043,
|
| 2143 |
+
"step": 2820
|
| 2144 |
+
},
|
| 2145 |
+
{
|
| 2146 |
+
"epoch": 8.097281831187411,
|
| 2147 |
+
"grad_norm": 0.4856473505496979,
|
| 2148 |
+
"learning_rate": 4.221585482330468e-06,
|
| 2149 |
+
"loss": 0.0062,
|
| 2150 |
+
"step": 2830
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"epoch": 8.125894134477825,
|
| 2154 |
+
"grad_norm": 0.5017396807670593,
|
| 2155 |
+
"learning_rate": 4.1579114931550465e-06,
|
| 2156 |
+
"loss": 0.0263,
|
| 2157 |
+
"step": 2840
|
| 2158 |
+
},
|
| 2159 |
+
{
|
| 2160 |
+
"epoch": 8.15450643776824,
|
| 2161 |
+
"grad_norm": 2.501828193664551,
|
| 2162 |
+
"learning_rate": 4.094237503979625e-06,
|
| 2163 |
+
"loss": 0.0295,
|
| 2164 |
+
"step": 2850
|
| 2165 |
+
},
|
| 2166 |
+
{
|
| 2167 |
+
"epoch": 8.183118741058655,
|
| 2168 |
+
"grad_norm": 0.36499956250190735,
|
| 2169 |
+
"learning_rate": 4.030563514804202e-06,
|
| 2170 |
+
"loss": 0.0218,
|
| 2171 |
+
"step": 2860
|
| 2172 |
+
},
|
| 2173 |
+
{
|
| 2174 |
+
"epoch": 8.21173104434907,
|
| 2175 |
+
"grad_norm": 1.9966788291931152,
|
| 2176 |
+
"learning_rate": 3.966889525628781e-06,
|
| 2177 |
+
"loss": 0.0108,
|
| 2178 |
+
"step": 2870
|
| 2179 |
+
},
|
| 2180 |
+
{
|
| 2181 |
+
"epoch": 8.240343347639485,
|
| 2182 |
+
"grad_norm": 2.827831983566284,
|
| 2183 |
+
"learning_rate": 3.903215536453359e-06,
|
| 2184 |
+
"loss": 0.0123,
|
| 2185 |
+
"step": 2880
|
| 2186 |
+
},
|
| 2187 |
+
{
|
| 2188 |
+
"epoch": 8.2689556509299,
|
| 2189 |
+
"grad_norm": 0.40095698833465576,
|
| 2190 |
+
"learning_rate": 3.839541547277937e-06,
|
| 2191 |
+
"loss": 0.0014,
|
| 2192 |
+
"step": 2890
|
| 2193 |
+
},
|
| 2194 |
+
{
|
| 2195 |
+
"epoch": 8.297567954220314,
|
| 2196 |
+
"grad_norm": 0.21733756363391876,
|
| 2197 |
+
"learning_rate": 3.7758675581025155e-06,
|
| 2198 |
+
"loss": 0.0231,
|
| 2199 |
+
"step": 2900
|
| 2200 |
+
},
|
| 2201 |
+
{
|
| 2202 |
+
"epoch": 8.32618025751073,
|
| 2203 |
+
"grad_norm": 0.2822847366333008,
|
| 2204 |
+
"learning_rate": 3.712193568927094e-06,
|
| 2205 |
+
"loss": 0.0027,
|
| 2206 |
+
"step": 2910
|
| 2207 |
+
},
|
| 2208 |
+
{
|
| 2209 |
+
"epoch": 8.354792560801144,
|
| 2210 |
+
"grad_norm": 0.19272436201572418,
|
| 2211 |
+
"learning_rate": 3.6485195797516713e-06,
|
| 2212 |
+
"loss": 0.0015,
|
| 2213 |
+
"step": 2920
|
| 2214 |
+
},
|
| 2215 |
+
{
|
| 2216 |
+
"epoch": 8.38340486409156,
|
| 2217 |
+
"grad_norm": 0.49634698033332825,
|
| 2218 |
+
"learning_rate": 3.5848455905762496e-06,
|
| 2219 |
+
"loss": 0.0074,
|
| 2220 |
+
"step": 2930
|
| 2221 |
+
},
|
| 2222 |
+
{
|
| 2223 |
+
"epoch": 8.412017167381974,
|
| 2224 |
+
"grad_norm": 0.06298165023326874,
|
| 2225 |
+
"learning_rate": 3.521171601400828e-06,
|
| 2226 |
+
"loss": 0.0218,
|
| 2227 |
+
"step": 2940
|
| 2228 |
+
},
|
| 2229 |
+
{
|
| 2230 |
+
"epoch": 8.44062947067239,
|
| 2231 |
+
"grad_norm": 0.0625123679637909,
|
| 2232 |
+
"learning_rate": 3.4574976122254062e-06,
|
| 2233 |
+
"loss": 0.0051,
|
| 2234 |
+
"step": 2950
|
| 2235 |
+
},
|
| 2236 |
+
{
|
| 2237 |
+
"epoch": 8.469241773962803,
|
| 2238 |
+
"grad_norm": 0.0806524008512497,
|
| 2239 |
+
"learning_rate": 3.3938236230499845e-06,
|
| 2240 |
+
"loss": 0.003,
|
| 2241 |
+
"step": 2960
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"epoch": 8.49785407725322,
|
| 2245 |
+
"grad_norm": 0.1726488322019577,
|
| 2246 |
+
"learning_rate": 3.3301496338745624e-06,
|
| 2247 |
+
"loss": 0.0038,
|
| 2248 |
+
"step": 2970
|
| 2249 |
+
},
|
| 2250 |
+
{
|
| 2251 |
+
"epoch": 8.526466380543633,
|
| 2252 |
+
"grad_norm": 2.4908065795898438,
|
| 2253 |
+
"learning_rate": 3.2664756446991407e-06,
|
| 2254 |
+
"loss": 0.0124,
|
| 2255 |
+
"step": 2980
|
| 2256 |
+
},
|
| 2257 |
+
{
|
| 2258 |
+
"epoch": 8.555078683834049,
|
| 2259 |
+
"grad_norm": 0.015561264008283615,
|
| 2260 |
+
"learning_rate": 3.202801655523719e-06,
|
| 2261 |
+
"loss": 0.0132,
|
| 2262 |
+
"step": 2990
|
| 2263 |
+
},
|
| 2264 |
+
{
|
| 2265 |
+
"epoch": 8.583690987124463,
|
| 2266 |
+
"grad_norm": 0.09347698092460632,
|
| 2267 |
+
"learning_rate": 3.1391276663482973e-06,
|
| 2268 |
+
"loss": 0.0094,
|
| 2269 |
+
"step": 3000
|
| 2270 |
+
},
|
| 2271 |
+
{
|
| 2272 |
+
"epoch": 8.612303290414879,
|
| 2273 |
+
"grad_norm": 0.6292846202850342,
|
| 2274 |
+
"learning_rate": 3.075453677172875e-06,
|
| 2275 |
+
"loss": 0.0047,
|
| 2276 |
+
"step": 3010
|
| 2277 |
+
},
|
| 2278 |
+
{
|
| 2279 |
+
"epoch": 8.640915593705293,
|
| 2280 |
+
"grad_norm": 0.0815897285938263,
|
| 2281 |
+
"learning_rate": 3.011779687997453e-06,
|
| 2282 |
+
"loss": 0.0028,
|
| 2283 |
+
"step": 3020
|
| 2284 |
+
},
|
| 2285 |
+
{
|
| 2286 |
+
"epoch": 8.669527896995708,
|
| 2287 |
+
"grad_norm": 0.4412260055541992,
|
| 2288 |
+
"learning_rate": 2.9481056988220314e-06,
|
| 2289 |
+
"loss": 0.0066,
|
| 2290 |
+
"step": 3030
|
| 2291 |
+
},
|
| 2292 |
+
{
|
| 2293 |
+
"epoch": 8.698140200286122,
|
| 2294 |
+
"grad_norm": 6.015453815460205,
|
| 2295 |
+
"learning_rate": 2.8844317096466097e-06,
|
| 2296 |
+
"loss": 0.0351,
|
| 2297 |
+
"step": 3040
|
| 2298 |
+
},
|
| 2299 |
+
{
|
| 2300 |
+
"epoch": 8.726752503576538,
|
| 2301 |
+
"grad_norm": 3.0399041175842285,
|
| 2302 |
+
"learning_rate": 2.8207577204711876e-06,
|
| 2303 |
+
"loss": 0.0049,
|
| 2304 |
+
"step": 3050
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"epoch": 8.755364806866952,
|
| 2308 |
+
"grad_norm": 0.5966952443122864,
|
| 2309 |
+
"learning_rate": 2.757083731295766e-06,
|
| 2310 |
+
"loss": 0.0153,
|
| 2311 |
+
"step": 3060
|
| 2312 |
+
},
|
| 2313 |
+
{
|
| 2314 |
+
"epoch": 8.783977110157368,
|
| 2315 |
+
"grad_norm": 0.6676664352416992,
|
| 2316 |
+
"learning_rate": 2.693409742120344e-06,
|
| 2317 |
+
"loss": 0.0079,
|
| 2318 |
+
"step": 3070
|
| 2319 |
+
},
|
| 2320 |
+
{
|
| 2321 |
+
"epoch": 8.812589413447782,
|
| 2322 |
+
"grad_norm": 1.2754206657409668,
|
| 2323 |
+
"learning_rate": 2.6297357529449225e-06,
|
| 2324 |
+
"loss": 0.0028,
|
| 2325 |
+
"step": 3080
|
| 2326 |
+
},
|
| 2327 |
+
{
|
| 2328 |
+
"epoch": 8.841201716738198,
|
| 2329 |
+
"grad_norm": 0.17587369680404663,
|
| 2330 |
+
"learning_rate": 2.5660617637695e-06,
|
| 2331 |
+
"loss": 0.0148,
|
| 2332 |
+
"step": 3090
|
| 2333 |
+
},
|
| 2334 |
+
{
|
| 2335 |
+
"epoch": 8.869814020028612,
|
| 2336 |
+
"grad_norm": 1.2772883176803589,
|
| 2337 |
+
"learning_rate": 2.5023877745940783e-06,
|
| 2338 |
+
"loss": 0.005,
|
| 2339 |
+
"step": 3100
|
| 2340 |
+
},
|
| 2341 |
+
{
|
| 2342 |
+
"epoch": 8.898426323319027,
|
| 2343 |
+
"grad_norm": 1.0710519552230835,
|
| 2344 |
+
"learning_rate": 2.4387137854186566e-06,
|
| 2345 |
+
"loss": 0.0109,
|
| 2346 |
+
"step": 3110
|
| 2347 |
+
},
|
| 2348 |
+
{
|
| 2349 |
+
"epoch": 8.927038626609441,
|
| 2350 |
+
"grad_norm": 0.30399370193481445,
|
| 2351 |
+
"learning_rate": 2.375039796243235e-06,
|
| 2352 |
+
"loss": 0.0029,
|
| 2353 |
+
"step": 3120
|
| 2354 |
+
},
|
| 2355 |
+
{
|
| 2356 |
+
"epoch": 8.955650929899857,
|
| 2357 |
+
"grad_norm": 0.3177274167537689,
|
| 2358 |
+
"learning_rate": 2.3113658070678128e-06,
|
| 2359 |
+
"loss": 0.0057,
|
| 2360 |
+
"step": 3130
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"epoch": 8.984263233190273,
|
| 2364 |
+
"grad_norm": 0.523124635219574,
|
| 2365 |
+
"learning_rate": 2.247691817892391e-06,
|
| 2366 |
+
"loss": 0.0058,
|
| 2367 |
+
"step": 3140
|
| 2368 |
+
},
|
| 2369 |
+
{
|
| 2370 |
+
"epoch": 8.998569384835479,
|
| 2371 |
+
"eval_avg_f1": 0.9074990725453154,
|
| 2372 |
+
"eval_avg_macro_f1": 0.9049823782519661,
|
| 2373 |
+
"eval_hazard_accuracy": 0.949964260185847,
|
| 2374 |
+
"eval_hazard_f1": 0.9494646211249262,
|
| 2375 |
+
"eval_hazard_macro_f1": 0.9187490461241665,
|
| 2376 |
+
"eval_hazard_precision": 0.9503361146795187,
|
| 2377 |
+
"eval_hazard_recall": 0.949964260185847,
|
| 2378 |
+
"eval_loss": 0.32502511143684387,
|
| 2379 |
+
"eval_product_accuracy": 0.8649035025017869,
|
| 2380 |
+
"eval_product_f1": 0.8655335239657044,
|
| 2381 |
+
"eval_product_macro_f1": 0.8912157103797657,
|
| 2382 |
+
"eval_product_precision": 0.8676022686098708,
|
| 2383 |
+
"eval_product_recall": 0.8649035025017869,
|
| 2384 |
+
"eval_runtime": 130.924,
|
| 2385 |
+
"eval_samples_per_second": 10.686,
|
| 2386 |
+
"eval_steps_per_second": 5.347,
|
| 2387 |
+
"step": 3145
|
| 2388 |
+
}
|
| 2389 |
+
],
|
| 2390 |
+
"logging_steps": 10,
|
| 2391 |
+
"max_steps": 3490,
|
| 2392 |
+
"num_input_tokens_seen": 0,
|
| 2393 |
+
"num_train_epochs": 10,
|
| 2394 |
+
"save_steps": 500,
|
| 2395 |
+
"stateful_callbacks": {
|
| 2396 |
+
"TrainerControl": {
|
| 2397 |
+
"args": {
|
| 2398 |
+
"should_epoch_stop": false,
|
| 2399 |
+
"should_evaluate": false,
|
| 2400 |
+
"should_log": false,
|
| 2401 |
+
"should_save": true,
|
| 2402 |
+
"should_training_stop": false
|
| 2403 |
+
},
|
| 2404 |
+
"attributes": {}
|
| 2405 |
+
}
|
| 2406 |
+
},
|
| 2407 |
+
"total_flos": 0.0,
|
| 2408 |
+
"train_batch_size": 4,
|
| 2409 |
+
"trial_name": null,
|
| 2410 |
+
"trial_params": null
|
| 2411 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98a060bf6b8d15c86839a56b6fd991015acc22276326356ae6ac5634f2dcb7bf
|
| 3 |
+
size 5176
|