Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- added_tokens.json +3 -0
- config.json +82 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +51 -0
- spm.model +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +859 -0
- trainer_state.json +1781 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 250101
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "iiiorg/piiranha-v1-detect-personal-information",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DebertaV2ForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "I-ACCOUNTNUM",
|
| 12 |
+
"1": "I-BUILDINGNUM",
|
| 13 |
+
"2": "I-CITY",
|
| 14 |
+
"3": "I-CREDITCARDNUMBER",
|
| 15 |
+
"4": "I-DATEOFBIRTH",
|
| 16 |
+
"5": "I-DRIVERLICENSENUM",
|
| 17 |
+
"6": "I-EMAIL",
|
| 18 |
+
"7": "I-GIVENNAME",
|
| 19 |
+
"8": "I-IDCARDNUM",
|
| 20 |
+
"9": "I-PASSWORD",
|
| 21 |
+
"10": "I-SOCIALNUM",
|
| 22 |
+
"11": "I-STREET",
|
| 23 |
+
"12": "I-SURNAME",
|
| 24 |
+
"13": "I-TAXNUM",
|
| 25 |
+
"14": "I-TELEPHONENUM",
|
| 26 |
+
"15": "I-USERNAME",
|
| 27 |
+
"16": "I-ZIPCODE",
|
| 28 |
+
"17": "O",
|
| 29 |
+
"18": "I-REL",
|
| 30 |
+
"19": "I-ETHN",
|
| 31 |
+
"20": "I-SOR"
|
| 32 |
+
},
|
| 33 |
+
"initializer_range": 0.02,
|
| 34 |
+
"intermediate_size": 3072,
|
| 35 |
+
"label2id": {
|
| 36 |
+
"I-ACCOUNTNUM": 0,
|
| 37 |
+
"I-BUILDINGNUM": 1,
|
| 38 |
+
"I-CITY": 2,
|
| 39 |
+
"I-CREDITCARDNUMBER": 3,
|
| 40 |
+
"I-DATEOFBIRTH": 4,
|
| 41 |
+
"I-DRIVERLICENSENUM": 5,
|
| 42 |
+
"I-EMAIL": 6,
|
| 43 |
+
"I-ETHN": 19,
|
| 44 |
+
"I-GIVENNAME": 7,
|
| 45 |
+
"I-IDCARDNUM": 8,
|
| 46 |
+
"I-PASSWORD": 9,
|
| 47 |
+
"I-REL": 18,
|
| 48 |
+
"I-SOCIALNUM": 10,
|
| 49 |
+
"I-SOR": 20,
|
| 50 |
+
"I-STREET": 11,
|
| 51 |
+
"I-SURNAME": 12,
|
| 52 |
+
"I-TAXNUM": 13,
|
| 53 |
+
"I-TELEPHONENUM": 14,
|
| 54 |
+
"I-USERNAME": 15,
|
| 55 |
+
"I-ZIPCODE": 16,
|
| 56 |
+
"O": 17
|
| 57 |
+
},
|
| 58 |
+
"layer_norm_eps": 1e-07,
|
| 59 |
+
"legacy": true,
|
| 60 |
+
"max_position_embeddings": 512,
|
| 61 |
+
"max_relative_positions": -1,
|
| 62 |
+
"model_type": "deberta-v2",
|
| 63 |
+
"norm_rel_ebd": "layer_norm",
|
| 64 |
+
"num_attention_heads": 12,
|
| 65 |
+
"num_hidden_layers": 12,
|
| 66 |
+
"pad_token_id": 0,
|
| 67 |
+
"pooler_dropout": 0,
|
| 68 |
+
"pooler_hidden_act": "gelu",
|
| 69 |
+
"pooler_hidden_size": 768,
|
| 70 |
+
"pos_att_type": [
|
| 71 |
+
"p2c",
|
| 72 |
+
"c2p"
|
| 73 |
+
],
|
| 74 |
+
"position_biased_input": false,
|
| 75 |
+
"position_buckets": 256,
|
| 76 |
+
"relative_attention": true,
|
| 77 |
+
"share_att_key": true,
|
| 78 |
+
"torch_dtype": "float32",
|
| 79 |
+
"transformers_version": "4.48.2",
|
| 80 |
+
"type_vocab_size": 0,
|
| 81 |
+
"vocab_size": 251000
|
| 82 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6323a06707545f474df9e908d3f5a7596675cc021a89be59aecc637635278cf1
|
| 3 |
+
size 2226040890
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32d32051101ec51c2b04c4ee6a6d2c7f40562e56836cbb02d6e6e3126490484d
|
| 3 |
+
size 13990
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cba1b63e4703eb54d9f84dd05ec2e932a3abd1aaa6e6432b2a5a0a8fa76aeebe
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "[CLS]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "[SEP]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "[MASK]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "[PAD]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "[SEP]",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "[UNK]",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13c8d666d62a7bc4ac8f040aab68e942c861f93303156cc28f5c7e885d86d6e3
|
| 3 |
+
size 4305025
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66dd68f27278061fc1702ba512fb2ec7c41c24eebf27dc5a9cc95d998166f0c7
|
| 3 |
+
size 16335781
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,859 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"250001": {
|
| 36 |
+
"content": "▁<extra_id_99>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": false
|
| 42 |
+
},
|
| 43 |
+
"250002": {
|
| 44 |
+
"content": "▁<extra_id_98>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": false
|
| 50 |
+
},
|
| 51 |
+
"250003": {
|
| 52 |
+
"content": "▁<extra_id_97>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": false
|
| 58 |
+
},
|
| 59 |
+
"250004": {
|
| 60 |
+
"content": "▁<extra_id_96>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": false
|
| 66 |
+
},
|
| 67 |
+
"250005": {
|
| 68 |
+
"content": "▁<extra_id_95>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": false
|
| 74 |
+
},
|
| 75 |
+
"250006": {
|
| 76 |
+
"content": "▁<extra_id_94>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": false
|
| 82 |
+
},
|
| 83 |
+
"250007": {
|
| 84 |
+
"content": "▁<extra_id_93>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": false
|
| 90 |
+
},
|
| 91 |
+
"250008": {
|
| 92 |
+
"content": "▁<extra_id_92>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": false
|
| 98 |
+
},
|
| 99 |
+
"250009": {
|
| 100 |
+
"content": "▁<extra_id_91>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": false
|
| 106 |
+
},
|
| 107 |
+
"250010": {
|
| 108 |
+
"content": "▁<extra_id_90>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": false
|
| 114 |
+
},
|
| 115 |
+
"250011": {
|
| 116 |
+
"content": "▁<extra_id_89>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": false
|
| 122 |
+
},
|
| 123 |
+
"250012": {
|
| 124 |
+
"content": "▁<extra_id_88>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": false
|
| 130 |
+
},
|
| 131 |
+
"250013": {
|
| 132 |
+
"content": "▁<extra_id_87>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": false
|
| 138 |
+
},
|
| 139 |
+
"250014": {
|
| 140 |
+
"content": "▁<extra_id_86>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": false
|
| 146 |
+
},
|
| 147 |
+
"250015": {
|
| 148 |
+
"content": "▁<extra_id_85>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": false
|
| 154 |
+
},
|
| 155 |
+
"250016": {
|
| 156 |
+
"content": "▁<extra_id_84>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": false
|
| 162 |
+
},
|
| 163 |
+
"250017": {
|
| 164 |
+
"content": "▁<extra_id_83>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": false
|
| 170 |
+
},
|
| 171 |
+
"250018": {
|
| 172 |
+
"content": "▁<extra_id_82>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": false
|
| 178 |
+
},
|
| 179 |
+
"250019": {
|
| 180 |
+
"content": "▁<extra_id_81>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": false
|
| 186 |
+
},
|
| 187 |
+
"250020": {
|
| 188 |
+
"content": "▁<extra_id_80>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": false
|
| 194 |
+
},
|
| 195 |
+
"250021": {
|
| 196 |
+
"content": "▁<extra_id_79>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": false
|
| 202 |
+
},
|
| 203 |
+
"250022": {
|
| 204 |
+
"content": "▁<extra_id_78>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": false
|
| 210 |
+
},
|
| 211 |
+
"250023": {
|
| 212 |
+
"content": "▁<extra_id_77>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": false
|
| 218 |
+
},
|
| 219 |
+
"250024": {
|
| 220 |
+
"content": "▁<extra_id_76>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": false
|
| 226 |
+
},
|
| 227 |
+
"250025": {
|
| 228 |
+
"content": "▁<extra_id_75>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": false
|
| 234 |
+
},
|
| 235 |
+
"250026": {
|
| 236 |
+
"content": "▁<extra_id_74>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": false
|
| 242 |
+
},
|
| 243 |
+
"250027": {
|
| 244 |
+
"content": "▁<extra_id_73>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": false
|
| 250 |
+
},
|
| 251 |
+
"250028": {
|
| 252 |
+
"content": "▁<extra_id_72>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": false
|
| 258 |
+
},
|
| 259 |
+
"250029": {
|
| 260 |
+
"content": "▁<extra_id_71>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": false
|
| 266 |
+
},
|
| 267 |
+
"250030": {
|
| 268 |
+
"content": "▁<extra_id_70>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": false
|
| 274 |
+
},
|
| 275 |
+
"250031": {
|
| 276 |
+
"content": "▁<extra_id_69>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": false
|
| 282 |
+
},
|
| 283 |
+
"250032": {
|
| 284 |
+
"content": "▁<extra_id_68>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": false
|
| 290 |
+
},
|
| 291 |
+
"250033": {
|
| 292 |
+
"content": "▁<extra_id_67>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": false
|
| 298 |
+
},
|
| 299 |
+
"250034": {
|
| 300 |
+
"content": "▁<extra_id_66>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": false
|
| 306 |
+
},
|
| 307 |
+
"250035": {
|
| 308 |
+
"content": "▁<extra_id_65>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": false
|
| 314 |
+
},
|
| 315 |
+
"250036": {
|
| 316 |
+
"content": "▁<extra_id_64>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": false
|
| 322 |
+
},
|
| 323 |
+
"250037": {
|
| 324 |
+
"content": "▁<extra_id_63>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": false
|
| 330 |
+
},
|
| 331 |
+
"250038": {
|
| 332 |
+
"content": "▁<extra_id_62>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": false
|
| 338 |
+
},
|
| 339 |
+
"250039": {
|
| 340 |
+
"content": "▁<extra_id_61>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": false
|
| 346 |
+
},
|
| 347 |
+
"250040": {
|
| 348 |
+
"content": "▁<extra_id_60>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": false
|
| 354 |
+
},
|
| 355 |
+
"250041": {
|
| 356 |
+
"content": "▁<extra_id_59>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": false
|
| 362 |
+
},
|
| 363 |
+
"250042": {
|
| 364 |
+
"content": "▁<extra_id_58>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": false
|
| 370 |
+
},
|
| 371 |
+
"250043": {
|
| 372 |
+
"content": "▁<extra_id_57>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": false
|
| 378 |
+
},
|
| 379 |
+
"250044": {
|
| 380 |
+
"content": "▁<extra_id_56>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": false
|
| 386 |
+
},
|
| 387 |
+
"250045": {
|
| 388 |
+
"content": "▁<extra_id_55>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": false
|
| 394 |
+
},
|
| 395 |
+
"250046": {
|
| 396 |
+
"content": "▁<extra_id_54>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": false
|
| 402 |
+
},
|
| 403 |
+
"250047": {
|
| 404 |
+
"content": "▁<extra_id_53>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": false
|
| 410 |
+
},
|
| 411 |
+
"250048": {
|
| 412 |
+
"content": "▁<extra_id_52>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": false
|
| 418 |
+
},
|
| 419 |
+
"250049": {
|
| 420 |
+
"content": "▁<extra_id_51>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": false
|
| 426 |
+
},
|
| 427 |
+
"250050": {
|
| 428 |
+
"content": "▁<extra_id_50>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": false
|
| 434 |
+
},
|
| 435 |
+
"250051": {
|
| 436 |
+
"content": "▁<extra_id_49>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": false
|
| 442 |
+
},
|
| 443 |
+
"250052": {
|
| 444 |
+
"content": "▁<extra_id_48>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": false
|
| 450 |
+
},
|
| 451 |
+
"250053": {
|
| 452 |
+
"content": "▁<extra_id_47>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": false
|
| 458 |
+
},
|
| 459 |
+
"250054": {
|
| 460 |
+
"content": "▁<extra_id_46>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": false
|
| 466 |
+
},
|
| 467 |
+
"250055": {
|
| 468 |
+
"content": "▁<extra_id_45>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": false
|
| 474 |
+
},
|
| 475 |
+
"250056": {
|
| 476 |
+
"content": "▁<extra_id_44>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": false
|
| 482 |
+
},
|
| 483 |
+
"250057": {
|
| 484 |
+
"content": "▁<extra_id_43>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": false
|
| 490 |
+
},
|
| 491 |
+
"250058": {
|
| 492 |
+
"content": "▁<extra_id_42>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": false
|
| 498 |
+
},
|
| 499 |
+
"250059": {
|
| 500 |
+
"content": "▁<extra_id_41>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": false
|
| 506 |
+
},
|
| 507 |
+
"250060": {
|
| 508 |
+
"content": "▁<extra_id_40>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": false
|
| 514 |
+
},
|
| 515 |
+
"250061": {
|
| 516 |
+
"content": "▁<extra_id_39>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": false
|
| 522 |
+
},
|
| 523 |
+
"250062": {
|
| 524 |
+
"content": "▁<extra_id_38>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": false
|
| 530 |
+
},
|
| 531 |
+
"250063": {
|
| 532 |
+
"content": "▁<extra_id_37>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": false
|
| 538 |
+
},
|
| 539 |
+
"250064": {
|
| 540 |
+
"content": "▁<extra_id_36>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": false
|
| 546 |
+
},
|
| 547 |
+
"250065": {
|
| 548 |
+
"content": "▁<extra_id_35>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": false
|
| 554 |
+
},
|
| 555 |
+
"250066": {
|
| 556 |
+
"content": "▁<extra_id_34>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": false
|
| 562 |
+
},
|
| 563 |
+
"250067": {
|
| 564 |
+
"content": "▁<extra_id_33>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": false
|
| 570 |
+
},
|
| 571 |
+
"250068": {
|
| 572 |
+
"content": "▁<extra_id_32>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": false
|
| 578 |
+
},
|
| 579 |
+
"250069": {
|
| 580 |
+
"content": "▁<extra_id_31>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": false
|
| 586 |
+
},
|
| 587 |
+
"250070": {
|
| 588 |
+
"content": "▁<extra_id_30>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": false
|
| 594 |
+
},
|
| 595 |
+
"250071": {
|
| 596 |
+
"content": "▁<extra_id_29>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": false
|
| 602 |
+
},
|
| 603 |
+
"250072": {
|
| 604 |
+
"content": "▁<extra_id_28>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": false
|
| 610 |
+
},
|
| 611 |
+
"250073": {
|
| 612 |
+
"content": "▁<extra_id_27>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": false
|
| 618 |
+
},
|
| 619 |
+
"250074": {
|
| 620 |
+
"content": "▁<extra_id_26>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": false
|
| 626 |
+
},
|
| 627 |
+
"250075": {
|
| 628 |
+
"content": "▁<extra_id_25>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": false
|
| 634 |
+
},
|
| 635 |
+
"250076": {
|
| 636 |
+
"content": "▁<extra_id_24>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": false
|
| 642 |
+
},
|
| 643 |
+
"250077": {
|
| 644 |
+
"content": "▁<extra_id_23>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": false
|
| 650 |
+
},
|
| 651 |
+
"250078": {
|
| 652 |
+
"content": "▁<extra_id_22>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": false
|
| 658 |
+
},
|
| 659 |
+
"250079": {
|
| 660 |
+
"content": "▁<extra_id_21>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": false
|
| 666 |
+
},
|
| 667 |
+
"250080": {
|
| 668 |
+
"content": "▁<extra_id_20>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": false
|
| 674 |
+
},
|
| 675 |
+
"250081": {
|
| 676 |
+
"content": "▁<extra_id_19>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": false
|
| 682 |
+
},
|
| 683 |
+
"250082": {
|
| 684 |
+
"content": "▁<extra_id_18>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": false
|
| 690 |
+
},
|
| 691 |
+
"250083": {
|
| 692 |
+
"content": "▁<extra_id_17>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": false
|
| 698 |
+
},
|
| 699 |
+
"250084": {
|
| 700 |
+
"content": "▁<extra_id_16>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": false
|
| 706 |
+
},
|
| 707 |
+
"250085": {
|
| 708 |
+
"content": "▁<extra_id_15>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": false
|
| 714 |
+
},
|
| 715 |
+
"250086": {
|
| 716 |
+
"content": "▁<extra_id_14>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": false
|
| 722 |
+
},
|
| 723 |
+
"250087": {
|
| 724 |
+
"content": "▁<extra_id_13>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": false
|
| 730 |
+
},
|
| 731 |
+
"250088": {
|
| 732 |
+
"content": "▁<extra_id_12>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": false
|
| 738 |
+
},
|
| 739 |
+
"250089": {
|
| 740 |
+
"content": "▁<extra_id_11>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": false
|
| 746 |
+
},
|
| 747 |
+
"250090": {
|
| 748 |
+
"content": "▁<extra_id_10>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": false
|
| 754 |
+
},
|
| 755 |
+
"250091": {
|
| 756 |
+
"content": "▁<extra_id_9>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": false
|
| 762 |
+
},
|
| 763 |
+
"250092": {
|
| 764 |
+
"content": "▁<extra_id_8>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": false
|
| 770 |
+
},
|
| 771 |
+
"250093": {
|
| 772 |
+
"content": "▁<extra_id_7>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": false
|
| 778 |
+
},
|
| 779 |
+
"250094": {
|
| 780 |
+
"content": "▁<extra_id_6>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": false
|
| 786 |
+
},
|
| 787 |
+
"250095": {
|
| 788 |
+
"content": "▁<extra_id_5>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": false
|
| 794 |
+
},
|
| 795 |
+
"250096": {
|
| 796 |
+
"content": "▁<extra_id_4>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": false
|
| 802 |
+
},
|
| 803 |
+
"250097": {
|
| 804 |
+
"content": "▁<extra_id_3>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": false
|
| 810 |
+
},
|
| 811 |
+
"250098": {
|
| 812 |
+
"content": "▁<extra_id_2>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": false
|
| 818 |
+
},
|
| 819 |
+
"250099": {
|
| 820 |
+
"content": "▁<extra_id_1>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": false
|
| 826 |
+
},
|
| 827 |
+
"250100": {
|
| 828 |
+
"content": "▁<extra_id_0>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": false
|
| 834 |
+
},
|
| 835 |
+
"250101": {
|
| 836 |
+
"content": "[MASK]",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
}
|
| 843 |
+
},
|
| 844 |
+
"bos_token": "[CLS]",
|
| 845 |
+
"clean_up_tokenization_spaces": true,
|
| 846 |
+
"cls_token": "[CLS]",
|
| 847 |
+
"do_lower_case": false,
|
| 848 |
+
"eos_token": "[SEP]",
|
| 849 |
+
"extra_special_tokens": {},
|
| 850 |
+
"mask_token": "[MASK]",
|
| 851 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 852 |
+
"pad_token": "[PAD]",
|
| 853 |
+
"sep_token": "[SEP]",
|
| 854 |
+
"sp_model_kwargs": {},
|
| 855 |
+
"split_by_punct": false,
|
| 856 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 857 |
+
"unk_token": "[UNK]",
|
| 858 |
+
"vocab_type": "spm"
|
| 859 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1781 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 24564,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.012212994626282364,
|
| 13 |
+
"grad_norm": 2.7971887588500977,
|
| 14 |
+
"learning_rate": 4.9796450089561964e-05,
|
| 15 |
+
"loss": 0.3257,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.024425989252564728,
|
| 20 |
+
"grad_norm": 2.295069456100464,
|
| 21 |
+
"learning_rate": 4.9592900179123925e-05,
|
| 22 |
+
"loss": 0.1159,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03663898387884709,
|
| 27 |
+
"grad_norm": 1.1914141178131104,
|
| 28 |
+
"learning_rate": 4.9389350268685886e-05,
|
| 29 |
+
"loss": 0.1073,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.048851978505129456,
|
| 34 |
+
"grad_norm": 0.8838738203048706,
|
| 35 |
+
"learning_rate": 4.918580035824785e-05,
|
| 36 |
+
"loss": 0.1076,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.06106497313141182,
|
| 41 |
+
"grad_norm": 1.8016488552093506,
|
| 42 |
+
"learning_rate": 4.898225044780981e-05,
|
| 43 |
+
"loss": 0.0851,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.07327796775769418,
|
| 48 |
+
"grad_norm": 2.5403218269348145,
|
| 49 |
+
"learning_rate": 4.8778700537371764e-05,
|
| 50 |
+
"loss": 0.1119,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.08549096238397655,
|
| 55 |
+
"grad_norm": 1.6208165884017944,
|
| 56 |
+
"learning_rate": 4.8575150626933725e-05,
|
| 57 |
+
"loss": 0.0968,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.09770395701025891,
|
| 62 |
+
"grad_norm": 1.7685565948486328,
|
| 63 |
+
"learning_rate": 4.8371600716495686e-05,
|
| 64 |
+
"loss": 0.0848,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.10991695163654128,
|
| 69 |
+
"grad_norm": 5.9024882316589355,
|
| 70 |
+
"learning_rate": 4.816805080605765e-05,
|
| 71 |
+
"loss": 0.0816,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.12212994626282364,
|
| 76 |
+
"grad_norm": 1.4809324741363525,
|
| 77 |
+
"learning_rate": 4.796450089561961e-05,
|
| 78 |
+
"loss": 0.0815,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.134342940889106,
|
| 83 |
+
"grad_norm": 1.8953092098236084,
|
| 84 |
+
"learning_rate": 4.776095098518157e-05,
|
| 85 |
+
"loss": 0.0835,
|
| 86 |
+
"step": 1100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.14655593551538837,
|
| 90 |
+
"grad_norm": 0.2310028374195099,
|
| 91 |
+
"learning_rate": 4.755740107474353e-05,
|
| 92 |
+
"loss": 0.0768,
|
| 93 |
+
"step": 1200
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.15876893014167073,
|
| 97 |
+
"grad_norm": 4.047482013702393,
|
| 98 |
+
"learning_rate": 4.735385116430549e-05,
|
| 99 |
+
"loss": 0.0785,
|
| 100 |
+
"step": 1300
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.1709819247679531,
|
| 104 |
+
"grad_norm": 5.049030303955078,
|
| 105 |
+
"learning_rate": 4.7150301253867454e-05,
|
| 106 |
+
"loss": 0.0609,
|
| 107 |
+
"step": 1400
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.18319491939423546,
|
| 111 |
+
"grad_norm": 4.447434902191162,
|
| 112 |
+
"learning_rate": 4.6946751343429415e-05,
|
| 113 |
+
"loss": 0.0625,
|
| 114 |
+
"step": 1500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.19540791402051783,
|
| 118 |
+
"grad_norm": 0.3569432199001312,
|
| 119 |
+
"learning_rate": 4.674320143299138e-05,
|
| 120 |
+
"loss": 0.0612,
|
| 121 |
+
"step": 1600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.2076209086468002,
|
| 125 |
+
"grad_norm": 0.6527674794197083,
|
| 126 |
+
"learning_rate": 4.653965152255334e-05,
|
| 127 |
+
"loss": 0.07,
|
| 128 |
+
"step": 1700
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.21983390327308255,
|
| 132 |
+
"grad_norm": 5.448887825012207,
|
| 133 |
+
"learning_rate": 4.633610161211529e-05,
|
| 134 |
+
"loss": 0.0669,
|
| 135 |
+
"step": 1800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.23204689789936492,
|
| 139 |
+
"grad_norm": 1.804388165473938,
|
| 140 |
+
"learning_rate": 4.6132551701677254e-05,
|
| 141 |
+
"loss": 0.0636,
|
| 142 |
+
"step": 1900
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.24425989252564728,
|
| 146 |
+
"grad_norm": 1.574012279510498,
|
| 147 |
+
"learning_rate": 4.5929001791239215e-05,
|
| 148 |
+
"loss": 0.0798,
|
| 149 |
+
"step": 2000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.2564728871519297,
|
| 153 |
+
"grad_norm": 0.8235198259353638,
|
| 154 |
+
"learning_rate": 4.5725451880801177e-05,
|
| 155 |
+
"loss": 0.054,
|
| 156 |
+
"step": 2100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.268685881778212,
|
| 160 |
+
"grad_norm": 0.6802400350570679,
|
| 161 |
+
"learning_rate": 4.552190197036313e-05,
|
| 162 |
+
"loss": 0.0613,
|
| 163 |
+
"step": 2200
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.2808988764044944,
|
| 167 |
+
"grad_norm": 0.5732834935188293,
|
| 168 |
+
"learning_rate": 4.531835205992509e-05,
|
| 169 |
+
"loss": 0.0544,
|
| 170 |
+
"step": 2300
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.29311187103077674,
|
| 174 |
+
"grad_norm": 0.9544196128845215,
|
| 175 |
+
"learning_rate": 4.5114802149487054e-05,
|
| 176 |
+
"loss": 0.0735,
|
| 177 |
+
"step": 2400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.30532486565705913,
|
| 181 |
+
"grad_norm": 0.8141427040100098,
|
| 182 |
+
"learning_rate": 4.4911252239049015e-05,
|
| 183 |
+
"loss": 0.0586,
|
| 184 |
+
"step": 2500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.31753786028334147,
|
| 188 |
+
"grad_norm": 3.740103006362915,
|
| 189 |
+
"learning_rate": 4.4707702328610976e-05,
|
| 190 |
+
"loss": 0.0498,
|
| 191 |
+
"step": 2600
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.32975085490962386,
|
| 195 |
+
"grad_norm": 0.24550916254520416,
|
| 196 |
+
"learning_rate": 4.450415241817294e-05,
|
| 197 |
+
"loss": 0.056,
|
| 198 |
+
"step": 2700
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.3419638495359062,
|
| 202 |
+
"grad_norm": 0.7254294157028198,
|
| 203 |
+
"learning_rate": 4.43006025077349e-05,
|
| 204 |
+
"loss": 0.053,
|
| 205 |
+
"step": 2800
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.3541768441621886,
|
| 209 |
+
"grad_norm": 0.5358878970146179,
|
| 210 |
+
"learning_rate": 4.409705259729686e-05,
|
| 211 |
+
"loss": 0.0561,
|
| 212 |
+
"step": 2900
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.3663898387884709,
|
| 216 |
+
"grad_norm": 0.3604901432991028,
|
| 217 |
+
"learning_rate": 4.3893502686858815e-05,
|
| 218 |
+
"loss": 0.059,
|
| 219 |
+
"step": 3000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.3786028334147533,
|
| 223 |
+
"grad_norm": 0.19227269291877747,
|
| 224 |
+
"learning_rate": 4.3689952776420776e-05,
|
| 225 |
+
"loss": 0.0548,
|
| 226 |
+
"step": 3100
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.39081582804103565,
|
| 230 |
+
"grad_norm": 0.3620028495788574,
|
| 231 |
+
"learning_rate": 4.348640286598274e-05,
|
| 232 |
+
"loss": 0.0535,
|
| 233 |
+
"step": 3200
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.40302882266731804,
|
| 237 |
+
"grad_norm": 4.794760704040527,
|
| 238 |
+
"learning_rate": 4.32828529555447e-05,
|
| 239 |
+
"loss": 0.0549,
|
| 240 |
+
"step": 3300
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.4152418172936004,
|
| 244 |
+
"grad_norm": 0.5320255160331726,
|
| 245 |
+
"learning_rate": 4.307930304510666e-05,
|
| 246 |
+
"loss": 0.051,
|
| 247 |
+
"step": 3400
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.42745481191988277,
|
| 251 |
+
"grad_norm": 2.048164129257202,
|
| 252 |
+
"learning_rate": 4.287575313466862e-05,
|
| 253 |
+
"loss": 0.067,
|
| 254 |
+
"step": 3500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.4396678065461651,
|
| 258 |
+
"grad_norm": 3.6915972232818604,
|
| 259 |
+
"learning_rate": 4.267220322423058e-05,
|
| 260 |
+
"loss": 0.0494,
|
| 261 |
+
"step": 3600
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.4518808011724475,
|
| 265 |
+
"grad_norm": 0.7861614227294922,
|
| 266 |
+
"learning_rate": 4.2468653313792544e-05,
|
| 267 |
+
"loss": 0.0652,
|
| 268 |
+
"step": 3700
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.46409379579872984,
|
| 272 |
+
"grad_norm": 1.9440407752990723,
|
| 273 |
+
"learning_rate": 4.2265103403354505e-05,
|
| 274 |
+
"loss": 0.0699,
|
| 275 |
+
"step": 3800
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.4763067904250122,
|
| 279 |
+
"grad_norm": 0.15847598016262054,
|
| 280 |
+
"learning_rate": 4.206155349291647e-05,
|
| 281 |
+
"loss": 0.0575,
|
| 282 |
+
"step": 3900
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.48851978505129456,
|
| 286 |
+
"grad_norm": 0.2988128960132599,
|
| 287 |
+
"learning_rate": 4.185800358247843e-05,
|
| 288 |
+
"loss": 0.0468,
|
| 289 |
+
"step": 4000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.5007327796775769,
|
| 293 |
+
"grad_norm": 1.6092756986618042,
|
| 294 |
+
"learning_rate": 4.165445367204039e-05,
|
| 295 |
+
"loss": 0.0555,
|
| 296 |
+
"step": 4100
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.5129457743038593,
|
| 300 |
+
"grad_norm": 13.008635520935059,
|
| 301 |
+
"learning_rate": 4.1450903761602344e-05,
|
| 302 |
+
"loss": 0.0604,
|
| 303 |
+
"step": 4200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.5251587689301417,
|
| 307 |
+
"grad_norm": 2.7357659339904785,
|
| 308 |
+
"learning_rate": 4.1247353851164305e-05,
|
| 309 |
+
"loss": 0.0478,
|
| 310 |
+
"step": 4300
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.537371763556424,
|
| 314 |
+
"grad_norm": 0.4085894823074341,
|
| 315 |
+
"learning_rate": 4.104380394072627e-05,
|
| 316 |
+
"loss": 0.0478,
|
| 317 |
+
"step": 4400
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.5495847581827064,
|
| 321 |
+
"grad_norm": 1.5472468137741089,
|
| 322 |
+
"learning_rate": 4.084025403028823e-05,
|
| 323 |
+
"loss": 0.0559,
|
| 324 |
+
"step": 4500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.5617977528089888,
|
| 328 |
+
"grad_norm": 2.616894006729126,
|
| 329 |
+
"learning_rate": 4.063670411985019e-05,
|
| 330 |
+
"loss": 0.0444,
|
| 331 |
+
"step": 4600
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.5740107474352711,
|
| 335 |
+
"grad_norm": 0.7861430644989014,
|
| 336 |
+
"learning_rate": 4.043315420941215e-05,
|
| 337 |
+
"loss": 0.0431,
|
| 338 |
+
"step": 4700
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.5862237420615535,
|
| 342 |
+
"grad_norm": 1.3745653629302979,
|
| 343 |
+
"learning_rate": 4.022960429897411e-05,
|
| 344 |
+
"loss": 0.0422,
|
| 345 |
+
"step": 4800
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.5984367366878358,
|
| 349 |
+
"grad_norm": 1.471048355102539,
|
| 350 |
+
"learning_rate": 4.002605438853607e-05,
|
| 351 |
+
"loss": 0.052,
|
| 352 |
+
"step": 4900
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.6106497313141183,
|
| 356 |
+
"grad_norm": 0.3034818470478058,
|
| 357 |
+
"learning_rate": 3.9822504478098035e-05,
|
| 358 |
+
"loss": 0.0481,
|
| 359 |
+
"step": 5000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.6228627259404006,
|
| 363 |
+
"grad_norm": 0.5265262722969055,
|
| 364 |
+
"learning_rate": 3.9618954567659996e-05,
|
| 365 |
+
"loss": 0.0592,
|
| 366 |
+
"step": 5100
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.6350757205666829,
|
| 370 |
+
"grad_norm": 1.226517915725708,
|
| 371 |
+
"learning_rate": 3.941540465722196e-05,
|
| 372 |
+
"loss": 0.0554,
|
| 373 |
+
"step": 5200
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.6472887151929653,
|
| 377 |
+
"grad_norm": 0.365315705537796,
|
| 378 |
+
"learning_rate": 3.921185474678392e-05,
|
| 379 |
+
"loss": 0.0466,
|
| 380 |
+
"step": 5300
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.6595017098192477,
|
| 384 |
+
"grad_norm": 0.4508240818977356,
|
| 385 |
+
"learning_rate": 3.900830483634587e-05,
|
| 386 |
+
"loss": 0.0468,
|
| 387 |
+
"step": 5400
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.67171470444553,
|
| 391 |
+
"grad_norm": 0.51467365026474,
|
| 392 |
+
"learning_rate": 3.8804754925907834e-05,
|
| 393 |
+
"loss": 0.054,
|
| 394 |
+
"step": 5500
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.6839276990718124,
|
| 398 |
+
"grad_norm": 0.6186398267745972,
|
| 399 |
+
"learning_rate": 3.8601205015469796e-05,
|
| 400 |
+
"loss": 0.0554,
|
| 401 |
+
"step": 5600
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.6961406936980947,
|
| 405 |
+
"grad_norm": 0.6723864674568176,
|
| 406 |
+
"learning_rate": 3.839765510503176e-05,
|
| 407 |
+
"loss": 0.0556,
|
| 408 |
+
"step": 5700
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.7083536883243772,
|
| 412 |
+
"grad_norm": 3.6368353366851807,
|
| 413 |
+
"learning_rate": 3.819410519459372e-05,
|
| 414 |
+
"loss": 0.0512,
|
| 415 |
+
"step": 5800
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.7205666829506595,
|
| 419 |
+
"grad_norm": 3.5719096660614014,
|
| 420 |
+
"learning_rate": 3.799055528415568e-05,
|
| 421 |
+
"loss": 0.0545,
|
| 422 |
+
"step": 5900
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.7327796775769418,
|
| 426 |
+
"grad_norm": 1.1756514310836792,
|
| 427 |
+
"learning_rate": 3.778700537371764e-05,
|
| 428 |
+
"loss": 0.0465,
|
| 429 |
+
"step": 6000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.7449926722032242,
|
| 433 |
+
"grad_norm": 1.2159337997436523,
|
| 434 |
+
"learning_rate": 3.7583455463279596e-05,
|
| 435 |
+
"loss": 0.0463,
|
| 436 |
+
"step": 6100
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.7572056668295066,
|
| 440 |
+
"grad_norm": 1.0632232427597046,
|
| 441 |
+
"learning_rate": 3.737990555284156e-05,
|
| 442 |
+
"loss": 0.0444,
|
| 443 |
+
"step": 6200
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.769418661455789,
|
| 447 |
+
"grad_norm": 0.669765293598175,
|
| 448 |
+
"learning_rate": 3.717635564240352e-05,
|
| 449 |
+
"loss": 0.0433,
|
| 450 |
+
"step": 6300
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.7816316560820713,
|
| 454 |
+
"grad_norm": 0.13478492200374603,
|
| 455 |
+
"learning_rate": 3.697280573196548e-05,
|
| 456 |
+
"loss": 0.0469,
|
| 457 |
+
"step": 6400
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.7938446507083536,
|
| 461 |
+
"grad_norm": 0.5963812470436096,
|
| 462 |
+
"learning_rate": 3.676925582152744e-05,
|
| 463 |
+
"loss": 0.0504,
|
| 464 |
+
"step": 6500
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.8060576453346361,
|
| 468 |
+
"grad_norm": 0.5829123258590698,
|
| 469 |
+
"learning_rate": 3.6565705911089395e-05,
|
| 470 |
+
"loss": 0.0483,
|
| 471 |
+
"step": 6600
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.8182706399609184,
|
| 475 |
+
"grad_norm": 2.3114776611328125,
|
| 476 |
+
"learning_rate": 3.636215600065136e-05,
|
| 477 |
+
"loss": 0.0601,
|
| 478 |
+
"step": 6700
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.8304836345872008,
|
| 482 |
+
"grad_norm": 0.27553310990333557,
|
| 483 |
+
"learning_rate": 3.615860609021332e-05,
|
| 484 |
+
"loss": 0.0527,
|
| 485 |
+
"step": 6800
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.8426966292134831,
|
| 489 |
+
"grad_norm": 0.3668135106563568,
|
| 490 |
+
"learning_rate": 3.595505617977528e-05,
|
| 491 |
+
"loss": 0.0541,
|
| 492 |
+
"step": 6900
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.8549096238397655,
|
| 496 |
+
"grad_norm": 3.1305336952209473,
|
| 497 |
+
"learning_rate": 3.575150626933724e-05,
|
| 498 |
+
"loss": 0.0534,
|
| 499 |
+
"step": 7000
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.8671226184660479,
|
| 503 |
+
"grad_norm": 0.08432205021381378,
|
| 504 |
+
"learning_rate": 3.55479563588992e-05,
|
| 505 |
+
"loss": 0.0523,
|
| 506 |
+
"step": 7100
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.8793356130923302,
|
| 510 |
+
"grad_norm": 1.3692104816436768,
|
| 511 |
+
"learning_rate": 3.534440644846116e-05,
|
| 512 |
+
"loss": 0.0428,
|
| 513 |
+
"step": 7200
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.8915486077186126,
|
| 517 |
+
"grad_norm": 1.1145917177200317,
|
| 518 |
+
"learning_rate": 3.5140856538023125e-05,
|
| 519 |
+
"loss": 0.0528,
|
| 520 |
+
"step": 7300
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.903761602344895,
|
| 524 |
+
"grad_norm": 0.07234195619821548,
|
| 525 |
+
"learning_rate": 3.4937306627585086e-05,
|
| 526 |
+
"loss": 0.0449,
|
| 527 |
+
"step": 7400
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.9159745969711773,
|
| 531 |
+
"grad_norm": 0.12755821645259857,
|
| 532 |
+
"learning_rate": 3.473375671714705e-05,
|
| 533 |
+
"loss": 0.0381,
|
| 534 |
+
"step": 7500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.9281875915974597,
|
| 538 |
+
"grad_norm": 1.066666603088379,
|
| 539 |
+
"learning_rate": 3.453020680670901e-05,
|
| 540 |
+
"loss": 0.0411,
|
| 541 |
+
"step": 7600
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.940400586223742,
|
| 545 |
+
"grad_norm": 2.3837034702301025,
|
| 546 |
+
"learning_rate": 3.432665689627097e-05,
|
| 547 |
+
"loss": 0.0471,
|
| 548 |
+
"step": 7700
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.9526135808500245,
|
| 552 |
+
"grad_norm": 0.2601478397846222,
|
| 553 |
+
"learning_rate": 3.4123106985832924e-05,
|
| 554 |
+
"loss": 0.0408,
|
| 555 |
+
"step": 7800
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.9648265754763068,
|
| 559 |
+
"grad_norm": 1.0532914400100708,
|
| 560 |
+
"learning_rate": 3.3919557075394886e-05,
|
| 561 |
+
"loss": 0.0422,
|
| 562 |
+
"step": 7900
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.9770395701025891,
|
| 566 |
+
"grad_norm": 0.16507047414779663,
|
| 567 |
+
"learning_rate": 3.371600716495685e-05,
|
| 568 |
+
"loss": 0.0464,
|
| 569 |
+
"step": 8000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.9892525647288715,
|
| 573 |
+
"grad_norm": 0.310465544462204,
|
| 574 |
+
"learning_rate": 3.351245725451881e-05,
|
| 575 |
+
"loss": 0.056,
|
| 576 |
+
"step": 8100
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.0,
|
| 580 |
+
"eval_f1": 0.8987804878048782,
|
| 581 |
+
"eval_loss": 0.04277478903532028,
|
| 582 |
+
"eval_precision": 0.8910749615300066,
|
| 583 |
+
"eval_recall": 0.9066204428539477,
|
| 584 |
+
"eval_runtime": 133.6334,
|
| 585 |
+
"eval_samples_per_second": 61.272,
|
| 586 |
+
"eval_steps_per_second": 7.663,
|
| 587 |
+
"step": 8188
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 1.0014655593551538,
|
| 591 |
+
"grad_norm": 0.8648662567138672,
|
| 592 |
+
"learning_rate": 3.330890734408077e-05,
|
| 593 |
+
"loss": 0.0441,
|
| 594 |
+
"step": 8200
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.0136785539814364,
|
| 598 |
+
"grad_norm": 0.16131815314292908,
|
| 599 |
+
"learning_rate": 3.310535743364273e-05,
|
| 600 |
+
"loss": 0.0306,
|
| 601 |
+
"step": 8300
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 1.0258915486077187,
|
| 605 |
+
"grad_norm": 4.484282970428467,
|
| 606 |
+
"learning_rate": 3.290180752320469e-05,
|
| 607 |
+
"loss": 0.0383,
|
| 608 |
+
"step": 8400
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 1.038104543234001,
|
| 612 |
+
"grad_norm": 0.5343158841133118,
|
| 613 |
+
"learning_rate": 3.2698257612766654e-05,
|
| 614 |
+
"loss": 0.0331,
|
| 615 |
+
"step": 8500
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.0503175378602834,
|
| 619 |
+
"grad_norm": 0.028084266930818558,
|
| 620 |
+
"learning_rate": 3.2494707702328615e-05,
|
| 621 |
+
"loss": 0.0381,
|
| 622 |
+
"step": 8600
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 1.0625305324865657,
|
| 626 |
+
"grad_norm": 0.483477920293808,
|
| 627 |
+
"learning_rate": 3.2291157791890576e-05,
|
| 628 |
+
"loss": 0.0462,
|
| 629 |
+
"step": 8700
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 1.074743527112848,
|
| 633 |
+
"grad_norm": 0.8194773197174072,
|
| 634 |
+
"learning_rate": 3.208760788145254e-05,
|
| 635 |
+
"loss": 0.0346,
|
| 636 |
+
"step": 8800
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 1.0869565217391304,
|
| 640 |
+
"grad_norm": 0.11062140762805939,
|
| 641 |
+
"learning_rate": 3.188405797101449e-05,
|
| 642 |
+
"loss": 0.0369,
|
| 643 |
+
"step": 8900
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 1.0991695163654127,
|
| 647 |
+
"grad_norm": 0.300889790058136,
|
| 648 |
+
"learning_rate": 3.1680508060576454e-05,
|
| 649 |
+
"loss": 0.0297,
|
| 650 |
+
"step": 9000
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 1.111382510991695,
|
| 654 |
+
"grad_norm": 0.6278924345970154,
|
| 655 |
+
"learning_rate": 3.1476958150138415e-05,
|
| 656 |
+
"loss": 0.0349,
|
| 657 |
+
"step": 9100
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 1.1235955056179776,
|
| 661 |
+
"grad_norm": 0.542029082775116,
|
| 662 |
+
"learning_rate": 3.1273408239700376e-05,
|
| 663 |
+
"loss": 0.0473,
|
| 664 |
+
"step": 9200
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 1.13580850024426,
|
| 668 |
+
"grad_norm": 0.6147358417510986,
|
| 669 |
+
"learning_rate": 3.106985832926234e-05,
|
| 670 |
+
"loss": 0.0356,
|
| 671 |
+
"step": 9300
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 1.1480214948705423,
|
| 675 |
+
"grad_norm": 1.301965355873108,
|
| 676 |
+
"learning_rate": 3.08663084188243e-05,
|
| 677 |
+
"loss": 0.0371,
|
| 678 |
+
"step": 9400
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 1.1602344894968246,
|
| 682 |
+
"grad_norm": 0.026711974292993546,
|
| 683 |
+
"learning_rate": 3.066275850838626e-05,
|
| 684 |
+
"loss": 0.0346,
|
| 685 |
+
"step": 9500
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 1.172447484123107,
|
| 689 |
+
"grad_norm": 1.258608102798462,
|
| 690 |
+
"learning_rate": 3.0459208597948218e-05,
|
| 691 |
+
"loss": 0.0334,
|
| 692 |
+
"step": 9600
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 1.1846604787493893,
|
| 696 |
+
"grad_norm": 0.36877045035362244,
|
| 697 |
+
"learning_rate": 3.025565868751018e-05,
|
| 698 |
+
"loss": 0.032,
|
| 699 |
+
"step": 9700
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.1968734733756716,
|
| 703 |
+
"grad_norm": 0.2519334852695465,
|
| 704 |
+
"learning_rate": 3.005210877707214e-05,
|
| 705 |
+
"loss": 0.0416,
|
| 706 |
+
"step": 9800
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.2090864680019542,
|
| 710 |
+
"grad_norm": 0.5204672813415527,
|
| 711 |
+
"learning_rate": 2.9848558866634102e-05,
|
| 712 |
+
"loss": 0.0366,
|
| 713 |
+
"step": 9900
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 1.2212994626282365,
|
| 717 |
+
"grad_norm": 0.43101000785827637,
|
| 718 |
+
"learning_rate": 2.9645008956196063e-05,
|
| 719 |
+
"loss": 0.0379,
|
| 720 |
+
"step": 10000
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 1.2335124572545189,
|
| 724 |
+
"grad_norm": 0.681117057800293,
|
| 725 |
+
"learning_rate": 2.9441459045758018e-05,
|
| 726 |
+
"loss": 0.0353,
|
| 727 |
+
"step": 10100
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 1.2457254518808012,
|
| 731 |
+
"grad_norm": 0.49889543652534485,
|
| 732 |
+
"learning_rate": 2.923790913531998e-05,
|
| 733 |
+
"loss": 0.0394,
|
| 734 |
+
"step": 10200
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 1.2579384465070835,
|
| 738 |
+
"grad_norm": 0.8064567446708679,
|
| 739 |
+
"learning_rate": 2.903435922488194e-05,
|
| 740 |
+
"loss": 0.034,
|
| 741 |
+
"step": 10300
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 1.2701514411333659,
|
| 745 |
+
"grad_norm": 0.21315552294254303,
|
| 746 |
+
"learning_rate": 2.8830809314443902e-05,
|
| 747 |
+
"loss": 0.0292,
|
| 748 |
+
"step": 10400
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 1.2823644357596482,
|
| 752 |
+
"grad_norm": 1.6466035842895508,
|
| 753 |
+
"learning_rate": 2.8627259404005863e-05,
|
| 754 |
+
"loss": 0.0333,
|
| 755 |
+
"step": 10500
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 1.2945774303859308,
|
| 759 |
+
"grad_norm": 1.1944749355316162,
|
| 760 |
+
"learning_rate": 2.8423709493567825e-05,
|
| 761 |
+
"loss": 0.0357,
|
| 762 |
+
"step": 10600
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 1.3067904250122129,
|
| 766 |
+
"grad_norm": 0.6488074064254761,
|
| 767 |
+
"learning_rate": 2.8220159583129786e-05,
|
| 768 |
+
"loss": 0.0315,
|
| 769 |
+
"step": 10700
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 1.3190034196384954,
|
| 773 |
+
"grad_norm": 0.030384689569473267,
|
| 774 |
+
"learning_rate": 2.8016609672691747e-05,
|
| 775 |
+
"loss": 0.0422,
|
| 776 |
+
"step": 10800
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 1.3312164142647778,
|
| 780 |
+
"grad_norm": 0.2363937795162201,
|
| 781 |
+
"learning_rate": 2.781305976225371e-05,
|
| 782 |
+
"loss": 0.0335,
|
| 783 |
+
"step": 10900
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 1.34342940889106,
|
| 787 |
+
"grad_norm": 0.04548358544707298,
|
| 788 |
+
"learning_rate": 2.7609509851815666e-05,
|
| 789 |
+
"loss": 0.0371,
|
| 790 |
+
"step": 11000
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 1.3556424035173424,
|
| 794 |
+
"grad_norm": 0.6259112358093262,
|
| 795 |
+
"learning_rate": 2.7405959941377628e-05,
|
| 796 |
+
"loss": 0.0412,
|
| 797 |
+
"step": 11100
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 1.3678553981436248,
|
| 801 |
+
"grad_norm": 0.42487379908561707,
|
| 802 |
+
"learning_rate": 2.720241003093959e-05,
|
| 803 |
+
"loss": 0.0252,
|
| 804 |
+
"step": 11200
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 1.3800683927699071,
|
| 808 |
+
"grad_norm": 0.9125863313674927,
|
| 809 |
+
"learning_rate": 2.6998860120501547e-05,
|
| 810 |
+
"loss": 0.0367,
|
| 811 |
+
"step": 11300
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 1.3922813873961895,
|
| 815 |
+
"grad_norm": 0.7670263051986694,
|
| 816 |
+
"learning_rate": 2.679531021006351e-05,
|
| 817 |
+
"loss": 0.0288,
|
| 818 |
+
"step": 11400
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 1.404494382022472,
|
| 822 |
+
"grad_norm": 0.1614452451467514,
|
| 823 |
+
"learning_rate": 2.6591760299625466e-05,
|
| 824 |
+
"loss": 0.0399,
|
| 825 |
+
"step": 11500
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 1.4167073766487543,
|
| 829 |
+
"grad_norm": 3.3551249504089355,
|
| 830 |
+
"learning_rate": 2.6388210389187428e-05,
|
| 831 |
+
"loss": 0.0391,
|
| 832 |
+
"step": 11600
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 1.4289203712750367,
|
| 836 |
+
"grad_norm": 0.7188284397125244,
|
| 837 |
+
"learning_rate": 2.618466047874939e-05,
|
| 838 |
+
"loss": 0.0315,
|
| 839 |
+
"step": 11700
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 1.441133365901319,
|
| 843 |
+
"grad_norm": 0.48031413555145264,
|
| 844 |
+
"learning_rate": 2.598111056831135e-05,
|
| 845 |
+
"loss": 0.0244,
|
| 846 |
+
"step": 11800
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 1.4533463605276014,
|
| 850 |
+
"grad_norm": 0.7492583394050598,
|
| 851 |
+
"learning_rate": 2.577756065787331e-05,
|
| 852 |
+
"loss": 0.0359,
|
| 853 |
+
"step": 11900
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 1.4655593551538837,
|
| 857 |
+
"grad_norm": 0.6593573689460754,
|
| 858 |
+
"learning_rate": 2.5574010747435273e-05,
|
| 859 |
+
"loss": 0.0327,
|
| 860 |
+
"step": 12000
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 1.477772349780166,
|
| 864 |
+
"grad_norm": 0.2940855026245117,
|
| 865 |
+
"learning_rate": 2.5370460836997234e-05,
|
| 866 |
+
"loss": 0.0336,
|
| 867 |
+
"step": 12100
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 1.4899853444064486,
|
| 871 |
+
"grad_norm": 0.45900267362594604,
|
| 872 |
+
"learning_rate": 2.5166910926559195e-05,
|
| 873 |
+
"loss": 0.0242,
|
| 874 |
+
"step": 12200
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 1.5021983390327307,
|
| 878 |
+
"grad_norm": 2.2023909091949463,
|
| 879 |
+
"learning_rate": 2.4963361016121153e-05,
|
| 880 |
+
"loss": 0.0348,
|
| 881 |
+
"step": 12300
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 1.5144113336590133,
|
| 885 |
+
"grad_norm": 0.12489739805459976,
|
| 886 |
+
"learning_rate": 2.4759811105683115e-05,
|
| 887 |
+
"loss": 0.0335,
|
| 888 |
+
"step": 12400
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 1.5266243282852956,
|
| 892 |
+
"grad_norm": 1.0575867891311646,
|
| 893 |
+
"learning_rate": 2.4556261195245076e-05,
|
| 894 |
+
"loss": 0.0199,
|
| 895 |
+
"step": 12500
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 1.538837322911578,
|
| 899 |
+
"grad_norm": 1.7309564352035522,
|
| 900 |
+
"learning_rate": 2.4352711284807037e-05,
|
| 901 |
+
"loss": 0.0316,
|
| 902 |
+
"step": 12600
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 1.5510503175378603,
|
| 906 |
+
"grad_norm": 0.925658643245697,
|
| 907 |
+
"learning_rate": 2.4149161374369e-05,
|
| 908 |
+
"loss": 0.0445,
|
| 909 |
+
"step": 12700
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 1.5632633121641426,
|
| 913 |
+
"grad_norm": 0.48667579889297485,
|
| 914 |
+
"learning_rate": 2.3945611463930957e-05,
|
| 915 |
+
"loss": 0.0437,
|
| 916 |
+
"step": 12800
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 1.5754763067904252,
|
| 920 |
+
"grad_norm": 0.11213243752717972,
|
| 921 |
+
"learning_rate": 2.3742061553492918e-05,
|
| 922 |
+
"loss": 0.0387,
|
| 923 |
+
"step": 12900
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 1.5876893014167073,
|
| 927 |
+
"grad_norm": 0.14116732776165009,
|
| 928 |
+
"learning_rate": 2.353851164305488e-05,
|
| 929 |
+
"loss": 0.033,
|
| 930 |
+
"step": 13000
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 1.5999022960429898,
|
| 934 |
+
"grad_norm": 0.686268150806427,
|
| 935 |
+
"learning_rate": 2.333496173261684e-05,
|
| 936 |
+
"loss": 0.0281,
|
| 937 |
+
"step": 13100
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 1.612115290669272,
|
| 941 |
+
"grad_norm": 0.4795430898666382,
|
| 942 |
+
"learning_rate": 2.31314118221788e-05,
|
| 943 |
+
"loss": 0.0436,
|
| 944 |
+
"step": 13200
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 1.6243282852955545,
|
| 948 |
+
"grad_norm": 0.026416413486003876,
|
| 949 |
+
"learning_rate": 2.292786191174076e-05,
|
| 950 |
+
"loss": 0.0343,
|
| 951 |
+
"step": 13300
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 1.6365412799218368,
|
| 955 |
+
"grad_norm": 0.582073986530304,
|
| 956 |
+
"learning_rate": 2.2724312001302718e-05,
|
| 957 |
+
"loss": 0.0312,
|
| 958 |
+
"step": 13400
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 1.6487542745481192,
|
| 962 |
+
"grad_norm": 1.669487476348877,
|
| 963 |
+
"learning_rate": 2.252076209086468e-05,
|
| 964 |
+
"loss": 0.0384,
|
| 965 |
+
"step": 13500
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 1.6609672691744015,
|
| 969 |
+
"grad_norm": 0.19379857182502747,
|
| 970 |
+
"learning_rate": 2.231721218042664e-05,
|
| 971 |
+
"loss": 0.0322,
|
| 972 |
+
"step": 13600
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 1.6731802638006839,
|
| 976 |
+
"grad_norm": 4.540911674499512,
|
| 977 |
+
"learning_rate": 2.2113662269988602e-05,
|
| 978 |
+
"loss": 0.0363,
|
| 979 |
+
"step": 13700
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 1.6853932584269664,
|
| 983 |
+
"grad_norm": 0.24804505705833435,
|
| 984 |
+
"learning_rate": 2.1910112359550563e-05,
|
| 985 |
+
"loss": 0.0326,
|
| 986 |
+
"step": 13800
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 1.6976062530532485,
|
| 990 |
+
"grad_norm": 1.8535521030426025,
|
| 991 |
+
"learning_rate": 2.1706562449112524e-05,
|
| 992 |
+
"loss": 0.0316,
|
| 993 |
+
"step": 13900
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 1.709819247679531,
|
| 997 |
+
"grad_norm": 0.04862889647483826,
|
| 998 |
+
"learning_rate": 2.1503012538674482e-05,
|
| 999 |
+
"loss": 0.0248,
|
| 1000 |
+
"step": 14000
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 1.7220322423058134,
|
| 1004 |
+
"grad_norm": 0.3953320384025574,
|
| 1005 |
+
"learning_rate": 2.1299462628236444e-05,
|
| 1006 |
+
"loss": 0.0393,
|
| 1007 |
+
"step": 14100
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 1.7342452369320958,
|
| 1011 |
+
"grad_norm": 0.5966042876243591,
|
| 1012 |
+
"learning_rate": 2.1095912717798405e-05,
|
| 1013 |
+
"loss": 0.0358,
|
| 1014 |
+
"step": 14200
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 1.746458231558378,
|
| 1018 |
+
"grad_norm": 0.1555975377559662,
|
| 1019 |
+
"learning_rate": 2.0892362807360366e-05,
|
| 1020 |
+
"loss": 0.0425,
|
| 1021 |
+
"step": 14300
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 1.7586712261846604,
|
| 1025 |
+
"grad_norm": 0.8556230068206787,
|
| 1026 |
+
"learning_rate": 2.0688812896922328e-05,
|
| 1027 |
+
"loss": 0.0267,
|
| 1028 |
+
"step": 14400
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 1.770884220810943,
|
| 1032 |
+
"grad_norm": 0.03833279386162758,
|
| 1033 |
+
"learning_rate": 2.048526298648429e-05,
|
| 1034 |
+
"loss": 0.034,
|
| 1035 |
+
"step": 14500
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 1.783097215437225,
|
| 1039 |
+
"grad_norm": 0.043861281126737595,
|
| 1040 |
+
"learning_rate": 2.0281713076046247e-05,
|
| 1041 |
+
"loss": 0.0288,
|
| 1042 |
+
"step": 14600
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 1.7953102100635077,
|
| 1046 |
+
"grad_norm": 0.28712257742881775,
|
| 1047 |
+
"learning_rate": 2.0078163165608208e-05,
|
| 1048 |
+
"loss": 0.0285,
|
| 1049 |
+
"step": 14700
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 1.8075232046897898,
|
| 1053 |
+
"grad_norm": 1.3535864353179932,
|
| 1054 |
+
"learning_rate": 1.987461325517017e-05,
|
| 1055 |
+
"loss": 0.0377,
|
| 1056 |
+
"step": 14800
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 1.8197361993160723,
|
| 1060 |
+
"grad_norm": 3.164818048477173,
|
| 1061 |
+
"learning_rate": 1.967106334473213e-05,
|
| 1062 |
+
"loss": 0.0334,
|
| 1063 |
+
"step": 14900
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 1.8319491939423547,
|
| 1067 |
+
"grad_norm": 0.08736918866634369,
|
| 1068 |
+
"learning_rate": 1.9467513434294092e-05,
|
| 1069 |
+
"loss": 0.0294,
|
| 1070 |
+
"step": 15000
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 1.844162188568637,
|
| 1074 |
+
"grad_norm": 1.25545072555542,
|
| 1075 |
+
"learning_rate": 1.926396352385605e-05,
|
| 1076 |
+
"loss": 0.0285,
|
| 1077 |
+
"step": 15100
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 1.8563751831949193,
|
| 1081 |
+
"grad_norm": 0.030480826273560524,
|
| 1082 |
+
"learning_rate": 1.906041361341801e-05,
|
| 1083 |
+
"loss": 0.0328,
|
| 1084 |
+
"step": 15200
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 1.8685881778212017,
|
| 1088 |
+
"grad_norm": 1.6334197521209717,
|
| 1089 |
+
"learning_rate": 1.8856863702979973e-05,
|
| 1090 |
+
"loss": 0.037,
|
| 1091 |
+
"step": 15300
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 1.8808011724474842,
|
| 1095 |
+
"grad_norm": 1.2553733587265015,
|
| 1096 |
+
"learning_rate": 1.865331379254193e-05,
|
| 1097 |
+
"loss": 0.0256,
|
| 1098 |
+
"step": 15400
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 1.8930141670737664,
|
| 1102 |
+
"grad_norm": 0.061297524720430374,
|
| 1103 |
+
"learning_rate": 1.8449763882103892e-05,
|
| 1104 |
+
"loss": 0.0276,
|
| 1105 |
+
"step": 15500
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 1.905227161700049,
|
| 1109 |
+
"grad_norm": 1.0915943384170532,
|
| 1110 |
+
"learning_rate": 1.8246213971665853e-05,
|
| 1111 |
+
"loss": 0.0362,
|
| 1112 |
+
"step": 15600
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 1.9174401563263312,
|
| 1116 |
+
"grad_norm": 0.020990842953324318,
|
| 1117 |
+
"learning_rate": 1.8042664061227815e-05,
|
| 1118 |
+
"loss": 0.025,
|
| 1119 |
+
"step": 15700
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 1.9296531509526136,
|
| 1123 |
+
"grad_norm": 0.09211856126785278,
|
| 1124 |
+
"learning_rate": 1.7839114150789773e-05,
|
| 1125 |
+
"loss": 0.0265,
|
| 1126 |
+
"step": 15800
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 1.941866145578896,
|
| 1130 |
+
"grad_norm": 1.5800979137420654,
|
| 1131 |
+
"learning_rate": 1.7635564240351734e-05,
|
| 1132 |
+
"loss": 0.0256,
|
| 1133 |
+
"step": 15900
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 1.9540791402051783,
|
| 1137 |
+
"grad_norm": 0.39250850677490234,
|
| 1138 |
+
"learning_rate": 1.7432014329913695e-05,
|
| 1139 |
+
"loss": 0.0249,
|
| 1140 |
+
"step": 16000
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 1.9662921348314608,
|
| 1144 |
+
"grad_norm": 0.8597753047943115,
|
| 1145 |
+
"learning_rate": 1.7228464419475657e-05,
|
| 1146 |
+
"loss": 0.0355,
|
| 1147 |
+
"step": 16100
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 1.978505129457743,
|
| 1151 |
+
"grad_norm": 0.16734100878238678,
|
| 1152 |
+
"learning_rate": 1.7024914509037618e-05,
|
| 1153 |
+
"loss": 0.032,
|
| 1154 |
+
"step": 16200
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 1.9907181240840255,
|
| 1158 |
+
"grad_norm": 0.11750225722789764,
|
| 1159 |
+
"learning_rate": 1.682136459859958e-05,
|
| 1160 |
+
"loss": 0.0227,
|
| 1161 |
+
"step": 16300
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 2.0,
|
| 1165 |
+
"eval_f1": 0.9197428223035141,
|
| 1166 |
+
"eval_loss": 0.036899276077747345,
|
| 1167 |
+
"eval_precision": 0.9117582417582417,
|
| 1168 |
+
"eval_recall": 0.9278684857973608,
|
| 1169 |
+
"eval_runtime": 75.3931,
|
| 1170 |
+
"eval_samples_per_second": 108.604,
|
| 1171 |
+
"eval_steps_per_second": 13.582,
|
| 1172 |
+
"step": 16376
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 2.0029311187103076,
|
| 1176 |
+
"grad_norm": 0.6276179552078247,
|
| 1177 |
+
"learning_rate": 1.6617814688161537e-05,
|
| 1178 |
+
"loss": 0.0326,
|
| 1179 |
+
"step": 16400
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 2.01514411333659,
|
| 1183 |
+
"grad_norm": 0.27882876992225647,
|
| 1184 |
+
"learning_rate": 1.64142647777235e-05,
|
| 1185 |
+
"loss": 0.0206,
|
| 1186 |
+
"step": 16500
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 2.0273571079628727,
|
| 1190 |
+
"grad_norm": 0.9930168986320496,
|
| 1191 |
+
"learning_rate": 1.621071486728546e-05,
|
| 1192 |
+
"loss": 0.0135,
|
| 1193 |
+
"step": 16600
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 2.039570102589155,
|
| 1197 |
+
"grad_norm": 0.21392406523227692,
|
| 1198 |
+
"learning_rate": 1.600716495684742e-05,
|
| 1199 |
+
"loss": 0.028,
|
| 1200 |
+
"step": 16700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 2.0517830972154374,
|
| 1204 |
+
"grad_norm": 2.1995363235473633,
|
| 1205 |
+
"learning_rate": 1.5803615046409382e-05,
|
| 1206 |
+
"loss": 0.0273,
|
| 1207 |
+
"step": 16800
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 2.0639960918417195,
|
| 1211 |
+
"grad_norm": 1.91357421875,
|
| 1212 |
+
"learning_rate": 1.560006513597134e-05,
|
| 1213 |
+
"loss": 0.0152,
|
| 1214 |
+
"step": 16900
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 2.076209086468002,
|
| 1218 |
+
"grad_norm": 0.057265687733888626,
|
| 1219 |
+
"learning_rate": 1.53965152255333e-05,
|
| 1220 |
+
"loss": 0.0206,
|
| 1221 |
+
"step": 17000
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 2.088422081094284,
|
| 1225 |
+
"grad_norm": 0.05291162431240082,
|
| 1226 |
+
"learning_rate": 1.5192965315095261e-05,
|
| 1227 |
+
"loss": 0.022,
|
| 1228 |
+
"step": 17100
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 2.1006350757205667,
|
| 1232 |
+
"grad_norm": 2.424394369125366,
|
| 1233 |
+
"learning_rate": 1.4989415404657223e-05,
|
| 1234 |
+
"loss": 0.0178,
|
| 1235 |
+
"step": 17200
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 2.112848070346849,
|
| 1239 |
+
"grad_norm": 8.053882598876953,
|
| 1240 |
+
"learning_rate": 1.4785865494219184e-05,
|
| 1241 |
+
"loss": 0.0256,
|
| 1242 |
+
"step": 17300
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 2.1250610649731314,
|
| 1246 |
+
"grad_norm": 1.606079339981079,
|
| 1247 |
+
"learning_rate": 1.4582315583781145e-05,
|
| 1248 |
+
"loss": 0.017,
|
| 1249 |
+
"step": 17400
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 2.137274059599414,
|
| 1253 |
+
"grad_norm": 0.26984503865242004,
|
| 1254 |
+
"learning_rate": 1.4378765673343103e-05,
|
| 1255 |
+
"loss": 0.0202,
|
| 1256 |
+
"step": 17500
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.149487054225696,
|
| 1260 |
+
"grad_norm": 0.044966306537389755,
|
| 1261 |
+
"learning_rate": 1.4175215762905064e-05,
|
| 1262 |
+
"loss": 0.0234,
|
| 1263 |
+
"step": 17600
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.1617000488519786,
|
| 1267 |
+
"grad_norm": 0.05067300796508789,
|
| 1268 |
+
"learning_rate": 1.3971665852467026e-05,
|
| 1269 |
+
"loss": 0.0263,
|
| 1270 |
+
"step": 17700
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.1739130434782608,
|
| 1274 |
+
"grad_norm": 0.5125128030776978,
|
| 1275 |
+
"learning_rate": 1.3768115942028985e-05,
|
| 1276 |
+
"loss": 0.0216,
|
| 1277 |
+
"step": 17800
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 2.1861260381045433,
|
| 1281 |
+
"grad_norm": 0.04719540849328041,
|
| 1282 |
+
"learning_rate": 1.3564566031590947e-05,
|
| 1283 |
+
"loss": 0.0256,
|
| 1284 |
+
"step": 17900
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.1983390327308254,
|
| 1288 |
+
"grad_norm": 0.11627175658941269,
|
| 1289 |
+
"learning_rate": 1.3361016121152908e-05,
|
| 1290 |
+
"loss": 0.0185,
|
| 1291 |
+
"step": 18000
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.210552027357108,
|
| 1295 |
+
"grad_norm": 0.2016720473766327,
|
| 1296 |
+
"learning_rate": 1.3157466210714866e-05,
|
| 1297 |
+
"loss": 0.0111,
|
| 1298 |
+
"step": 18100
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 2.22276502198339,
|
| 1302 |
+
"grad_norm": 1.6914150714874268,
|
| 1303 |
+
"learning_rate": 1.2953916300276827e-05,
|
| 1304 |
+
"loss": 0.0237,
|
| 1305 |
+
"step": 18200
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 2.2349780166096727,
|
| 1309 |
+
"grad_norm": 0.3582985997200012,
|
| 1310 |
+
"learning_rate": 1.2750366389838789e-05,
|
| 1311 |
+
"loss": 0.0188,
|
| 1312 |
+
"step": 18300
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 2.247191011235955,
|
| 1316 |
+
"grad_norm": 0.9769508838653564,
|
| 1317 |
+
"learning_rate": 1.254681647940075e-05,
|
| 1318 |
+
"loss": 0.024,
|
| 1319 |
+
"step": 18400
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 2.2594040058622373,
|
| 1323 |
+
"grad_norm": 0.03454025089740753,
|
| 1324 |
+
"learning_rate": 1.2343266568962711e-05,
|
| 1325 |
+
"loss": 0.0307,
|
| 1326 |
+
"step": 18500
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 2.27161700048852,
|
| 1330 |
+
"grad_norm": 0.0919230654835701,
|
| 1331 |
+
"learning_rate": 1.2139716658524671e-05,
|
| 1332 |
+
"loss": 0.0183,
|
| 1333 |
+
"step": 18600
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 2.283829995114802,
|
| 1337 |
+
"grad_norm": 0.05342525988817215,
|
| 1338 |
+
"learning_rate": 1.1936166748086632e-05,
|
| 1339 |
+
"loss": 0.0295,
|
| 1340 |
+
"step": 18700
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 2.2960429897410846,
|
| 1344 |
+
"grad_norm": 0.11520762741565704,
|
| 1345 |
+
"learning_rate": 1.1732616837648592e-05,
|
| 1346 |
+
"loss": 0.0187,
|
| 1347 |
+
"step": 18800
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 2.308255984367367,
|
| 1351 |
+
"grad_norm": 1.8612200021743774,
|
| 1352 |
+
"learning_rate": 1.1529066927210551e-05,
|
| 1353 |
+
"loss": 0.0228,
|
| 1354 |
+
"step": 18900
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 2.3204689789936492,
|
| 1358 |
+
"grad_norm": 0.9779945611953735,
|
| 1359 |
+
"learning_rate": 1.1325517016772513e-05,
|
| 1360 |
+
"loss": 0.0182,
|
| 1361 |
+
"step": 19000
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 2.332681973619932,
|
| 1365 |
+
"grad_norm": 1.9669654369354248,
|
| 1366 |
+
"learning_rate": 1.1121967106334474e-05,
|
| 1367 |
+
"loss": 0.0247,
|
| 1368 |
+
"step": 19100
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 2.344894968246214,
|
| 1372 |
+
"grad_norm": 0.1722841113805771,
|
| 1373 |
+
"learning_rate": 1.0918417195896434e-05,
|
| 1374 |
+
"loss": 0.0206,
|
| 1375 |
+
"step": 19200
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 2.3571079628724965,
|
| 1379 |
+
"grad_norm": 0.1652793437242508,
|
| 1380 |
+
"learning_rate": 1.0714867285458395e-05,
|
| 1381 |
+
"loss": 0.0146,
|
| 1382 |
+
"step": 19300
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 2.3693209574987786,
|
| 1386 |
+
"grad_norm": 0.07285087555646896,
|
| 1387 |
+
"learning_rate": 1.0511317375020356e-05,
|
| 1388 |
+
"loss": 0.0151,
|
| 1389 |
+
"step": 19400
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 2.381533952125061,
|
| 1393 |
+
"grad_norm": 2.59061861038208,
|
| 1394 |
+
"learning_rate": 1.0307767464582316e-05,
|
| 1395 |
+
"loss": 0.0192,
|
| 1396 |
+
"step": 19500
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 2.3937469467513433,
|
| 1400 |
+
"grad_norm": 0.02776254341006279,
|
| 1401 |
+
"learning_rate": 1.0104217554144277e-05,
|
| 1402 |
+
"loss": 0.0245,
|
| 1403 |
+
"step": 19600
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 2.405959941377626,
|
| 1407 |
+
"grad_norm": 0.48207101225852966,
|
| 1408 |
+
"learning_rate": 9.900667643706239e-06,
|
| 1409 |
+
"loss": 0.0147,
|
| 1410 |
+
"step": 19700
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 2.4181729360039084,
|
| 1414 |
+
"grad_norm": 0.7725105285644531,
|
| 1415 |
+
"learning_rate": 9.697117733268198e-06,
|
| 1416 |
+
"loss": 0.0206,
|
| 1417 |
+
"step": 19800
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 2.4303859306301905,
|
| 1421 |
+
"grad_norm": 1.8201816082000732,
|
| 1422 |
+
"learning_rate": 9.493567822830158e-06,
|
| 1423 |
+
"loss": 0.0205,
|
| 1424 |
+
"step": 19900
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 2.442598925256473,
|
| 1428 |
+
"grad_norm": 0.2930428385734558,
|
| 1429 |
+
"learning_rate": 9.29001791239212e-06,
|
| 1430 |
+
"loss": 0.0163,
|
| 1431 |
+
"step": 20000
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 2.454811919882755,
|
| 1435 |
+
"grad_norm": 0.7441920638084412,
|
| 1436 |
+
"learning_rate": 9.086468001954079e-06,
|
| 1437 |
+
"loss": 0.0181,
|
| 1438 |
+
"step": 20100
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 2.4670249145090377,
|
| 1442 |
+
"grad_norm": 0.5970872640609741,
|
| 1443 |
+
"learning_rate": 8.88291809151604e-06,
|
| 1444 |
+
"loss": 0.0172,
|
| 1445 |
+
"step": 20200
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 2.47923790913532,
|
| 1449 |
+
"grad_norm": 0.17312058806419373,
|
| 1450 |
+
"learning_rate": 8.679368181078002e-06,
|
| 1451 |
+
"loss": 0.0163,
|
| 1452 |
+
"step": 20300
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 2.4914509037616024,
|
| 1456 |
+
"grad_norm": 0.26520836353302,
|
| 1457 |
+
"learning_rate": 8.475818270639961e-06,
|
| 1458 |
+
"loss": 0.016,
|
| 1459 |
+
"step": 20400
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 2.5036638983878845,
|
| 1463 |
+
"grad_norm": 0.08623456209897995,
|
| 1464 |
+
"learning_rate": 8.272268360201922e-06,
|
| 1465 |
+
"loss": 0.018,
|
| 1466 |
+
"step": 20500
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 2.515876893014167,
|
| 1470 |
+
"grad_norm": 0.16404370963573456,
|
| 1471 |
+
"learning_rate": 8.068718449763882e-06,
|
| 1472 |
+
"loss": 0.0164,
|
| 1473 |
+
"step": 20600
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 2.5280898876404496,
|
| 1477 |
+
"grad_norm": 0.051970474421978,
|
| 1478 |
+
"learning_rate": 7.865168539325843e-06,
|
| 1479 |
+
"loss": 0.0203,
|
| 1480 |
+
"step": 20700
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 2.5403028822667317,
|
| 1484 |
+
"grad_norm": 0.08457406610250473,
|
| 1485 |
+
"learning_rate": 7.661618628887805e-06,
|
| 1486 |
+
"loss": 0.0211,
|
| 1487 |
+
"step": 20800
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 2.5525158768930143,
|
| 1491 |
+
"grad_norm": 0.35134220123291016,
|
| 1492 |
+
"learning_rate": 7.4580687184497635e-06,
|
| 1493 |
+
"loss": 0.018,
|
| 1494 |
+
"step": 20900
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 2.5647288715192964,
|
| 1498 |
+
"grad_norm": 0.487570196390152,
|
| 1499 |
+
"learning_rate": 7.254518808011725e-06,
|
| 1500 |
+
"loss": 0.0281,
|
| 1501 |
+
"step": 21000
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 2.576941866145579,
|
| 1505 |
+
"grad_norm": 2.1460368633270264,
|
| 1506 |
+
"learning_rate": 7.050968897573685e-06,
|
| 1507 |
+
"loss": 0.0196,
|
| 1508 |
+
"step": 21100
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 2.5891548607718615,
|
| 1512 |
+
"grad_norm": 0.3036395311355591,
|
| 1513 |
+
"learning_rate": 6.847418987135645e-06,
|
| 1514 |
+
"loss": 0.0191,
|
| 1515 |
+
"step": 21200
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 2.6013678553981436,
|
| 1519 |
+
"grad_norm": 0.3689348101615906,
|
| 1520 |
+
"learning_rate": 6.643869076697606e-06,
|
| 1521 |
+
"loss": 0.0173,
|
| 1522 |
+
"step": 21300
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 2.6135808500244258,
|
| 1526 |
+
"grad_norm": 1.0098440647125244,
|
| 1527 |
+
"learning_rate": 6.440319166259568e-06,
|
| 1528 |
+
"loss": 0.0162,
|
| 1529 |
+
"step": 21400
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 2.6257938446507083,
|
| 1533 |
+
"grad_norm": 0.30733248591423035,
|
| 1534 |
+
"learning_rate": 6.236769255821528e-06,
|
| 1535 |
+
"loss": 0.0194,
|
| 1536 |
+
"step": 21500
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 2.638006839276991,
|
| 1540 |
+
"grad_norm": 0.4835430085659027,
|
| 1541 |
+
"learning_rate": 6.0332193453834885e-06,
|
| 1542 |
+
"loss": 0.0295,
|
| 1543 |
+
"step": 21600
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 2.650219833903273,
|
| 1547 |
+
"grad_norm": 0.041551847010850906,
|
| 1548 |
+
"learning_rate": 5.829669434945449e-06,
|
| 1549 |
+
"loss": 0.0209,
|
| 1550 |
+
"step": 21700
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 2.6624328285295555,
|
| 1554 |
+
"grad_norm": 1.990522027015686,
|
| 1555 |
+
"learning_rate": 5.6261195245074095e-06,
|
| 1556 |
+
"loss": 0.0269,
|
| 1557 |
+
"step": 21800
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.6746458231558377,
|
| 1561 |
+
"grad_norm": 0.04139232635498047,
|
| 1562 |
+
"learning_rate": 5.42256961406937e-06,
|
| 1563 |
+
"loss": 0.0226,
|
| 1564 |
+
"step": 21900
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 2.68685881778212,
|
| 1568 |
+
"grad_norm": 0.9341286420822144,
|
| 1569 |
+
"learning_rate": 5.219019703631331e-06,
|
| 1570 |
+
"loss": 0.0201,
|
| 1571 |
+
"step": 22000
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.6990718124084028,
|
| 1575 |
+
"grad_norm": 0.11153418570756912,
|
| 1576 |
+
"learning_rate": 5.015469793193292e-06,
|
| 1577 |
+
"loss": 0.0222,
|
| 1578 |
+
"step": 22100
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 2.711284807034685,
|
| 1582 |
+
"grad_norm": 1.0574121475219727,
|
| 1583 |
+
"learning_rate": 4.811919882755251e-06,
|
| 1584 |
+
"loss": 0.0212,
|
| 1585 |
+
"step": 22200
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 2.723497801660967,
|
| 1589 |
+
"grad_norm": 0.9357222318649292,
|
| 1590 |
+
"learning_rate": 4.608369972317213e-06,
|
| 1591 |
+
"loss": 0.0219,
|
| 1592 |
+
"step": 22300
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.7357107962872496,
|
| 1596 |
+
"grad_norm": 0.18769215047359467,
|
| 1597 |
+
"learning_rate": 4.404820061879173e-06,
|
| 1598 |
+
"loss": 0.0192,
|
| 1599 |
+
"step": 22400
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 2.747923790913532,
|
| 1603 |
+
"grad_norm": 1.0952208042144775,
|
| 1604 |
+
"learning_rate": 4.201270151441134e-06,
|
| 1605 |
+
"loss": 0.0165,
|
| 1606 |
+
"step": 22500
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 2.7601367855398142,
|
| 1610 |
+
"grad_norm": 0.046009525656700134,
|
| 1611 |
+
"learning_rate": 3.997720241003094e-06,
|
| 1612 |
+
"loss": 0.0161,
|
| 1613 |
+
"step": 22600
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 2.772349780166097,
|
| 1617 |
+
"grad_norm": 0.3359615206718445,
|
| 1618 |
+
"learning_rate": 3.794170330565055e-06,
|
| 1619 |
+
"loss": 0.0198,
|
| 1620 |
+
"step": 22700
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 2.784562774792379,
|
| 1624 |
+
"grad_norm": 0.03583957999944687,
|
| 1625 |
+
"learning_rate": 3.590620420127015e-06,
|
| 1626 |
+
"loss": 0.0157,
|
| 1627 |
+
"step": 22800
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 2.7967757694186615,
|
| 1631 |
+
"grad_norm": 2.4570398330688477,
|
| 1632 |
+
"learning_rate": 3.3870705096889755e-06,
|
| 1633 |
+
"loss": 0.0183,
|
| 1634 |
+
"step": 22900
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 2.808988764044944,
|
| 1638 |
+
"grad_norm": 0.0799492597579956,
|
| 1639 |
+
"learning_rate": 3.1835205992509364e-06,
|
| 1640 |
+
"loss": 0.0154,
|
| 1641 |
+
"step": 23000
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 2.821201758671226,
|
| 1645 |
+
"grad_norm": 0.17097431421279907,
|
| 1646 |
+
"learning_rate": 2.979970688812897e-06,
|
| 1647 |
+
"loss": 0.0208,
|
| 1648 |
+
"step": 23100
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 2.8334147532975087,
|
| 1652 |
+
"grad_norm": 0.042323142290115356,
|
| 1653 |
+
"learning_rate": 2.776420778374858e-06,
|
| 1654 |
+
"loss": 0.0107,
|
| 1655 |
+
"step": 23200
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 2.845627747923791,
|
| 1659 |
+
"grad_norm": 0.6305797100067139,
|
| 1660 |
+
"learning_rate": 2.5728708679368183e-06,
|
| 1661 |
+
"loss": 0.0225,
|
| 1662 |
+
"step": 23300
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 2.8578407425500734,
|
| 1666 |
+
"grad_norm": 0.05080363526940346,
|
| 1667 |
+
"learning_rate": 2.3693209574987788e-06,
|
| 1668 |
+
"loss": 0.0238,
|
| 1669 |
+
"step": 23400
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 2.8700537371763555,
|
| 1673 |
+
"grad_norm": 0.04388800263404846,
|
| 1674 |
+
"learning_rate": 2.1657710470607397e-06,
|
| 1675 |
+
"loss": 0.0184,
|
| 1676 |
+
"step": 23500
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 2.882266731802638,
|
| 1680 |
+
"grad_norm": 2.4991371631622314,
|
| 1681 |
+
"learning_rate": 1.9622211366226997e-06,
|
| 1682 |
+
"loss": 0.0196,
|
| 1683 |
+
"step": 23600
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 2.89447972642892,
|
| 1687 |
+
"grad_norm": 0.059519946575164795,
|
| 1688 |
+
"learning_rate": 1.7586712261846606e-06,
|
| 1689 |
+
"loss": 0.0156,
|
| 1690 |
+
"step": 23700
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 2.9066927210552027,
|
| 1694 |
+
"grad_norm": 0.044085703790187836,
|
| 1695 |
+
"learning_rate": 1.5551213157466213e-06,
|
| 1696 |
+
"loss": 0.0161,
|
| 1697 |
+
"step": 23800
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 2.9189057156814853,
|
| 1701 |
+
"grad_norm": 0.024006502702832222,
|
| 1702 |
+
"learning_rate": 1.3515714053085818e-06,
|
| 1703 |
+
"loss": 0.0172,
|
| 1704 |
+
"step": 23900
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 2.9311187103077674,
|
| 1708 |
+
"grad_norm": 0.7654680609703064,
|
| 1709 |
+
"learning_rate": 1.1480214948705422e-06,
|
| 1710 |
+
"loss": 0.0165,
|
| 1711 |
+
"step": 24000
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 2.94333170493405,
|
| 1715 |
+
"grad_norm": 0.8878483772277832,
|
| 1716 |
+
"learning_rate": 9.444715844325028e-07,
|
| 1717 |
+
"loss": 0.0174,
|
| 1718 |
+
"step": 24100
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 2.955544699560332,
|
| 1722 |
+
"grad_norm": 3.2117550373077393,
|
| 1723 |
+
"learning_rate": 7.409216739944635e-07,
|
| 1724 |
+
"loss": 0.0171,
|
| 1725 |
+
"step": 24200
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 2.9677576941866146,
|
| 1729 |
+
"grad_norm": 0.6114596128463745,
|
| 1730 |
+
"learning_rate": 5.373717635564241e-07,
|
| 1731 |
+
"loss": 0.0136,
|
| 1732 |
+
"step": 24300
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 2.979970688812897,
|
| 1736 |
+
"grad_norm": 0.0984087809920311,
|
| 1737 |
+
"learning_rate": 3.3382185311838467e-07,
|
| 1738 |
+
"loss": 0.0166,
|
| 1739 |
+
"step": 24400
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 2.9921836834391793,
|
| 1743 |
+
"grad_norm": 0.01637178845703602,
|
| 1744 |
+
"learning_rate": 1.3027194268034525e-07,
|
| 1745 |
+
"loss": 0.0133,
|
| 1746 |
+
"step": 24500
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 3.0,
|
| 1750 |
+
"eval_f1": 0.9273861231763003,
|
| 1751 |
+
"eval_loss": 0.03446226194500923,
|
| 1752 |
+
"eval_precision": 0.9235803016858918,
|
| 1753 |
+
"eval_recall": 0.9312234399463207,
|
| 1754 |
+
"eval_runtime": 62.6474,
|
| 1755 |
+
"eval_samples_per_second": 130.7,
|
| 1756 |
+
"eval_steps_per_second": 16.345,
|
| 1757 |
+
"step": 24564
|
| 1758 |
+
}
|
| 1759 |
+
],
|
| 1760 |
+
"logging_steps": 100,
|
| 1761 |
+
"max_steps": 24564,
|
| 1762 |
+
"num_input_tokens_seen": 0,
|
| 1763 |
+
"num_train_epochs": 3,
|
| 1764 |
+
"save_steps": 500,
|
| 1765 |
+
"stateful_callbacks": {
|
| 1766 |
+
"TrainerControl": {
|
| 1767 |
+
"args": {
|
| 1768 |
+
"should_epoch_stop": false,
|
| 1769 |
+
"should_evaluate": false,
|
| 1770 |
+
"should_log": false,
|
| 1771 |
+
"should_save": true,
|
| 1772 |
+
"should_training_stop": true
|
| 1773 |
+
},
|
| 1774 |
+
"attributes": {}
|
| 1775 |
+
}
|
| 1776 |
+
},
|
| 1777 |
+
"total_flos": 1.283942398980096e+16,
|
| 1778 |
+
"train_batch_size": 8,
|
| 1779 |
+
"trial_name": null,
|
| 1780 |
+
"trial_params": null
|
| 1781 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86236a94c71126c4c9e02defd2355db2ce54c91a5182055eb3aedadbce92747c
|
| 3 |
+
size 5368
|