bobox commited on
Commit
9223a91
1 Parent(s): 5863d9c

Training in progress, step 240, checkpoint

Browse files
checkpoint-240/1_AdvancedWeightedPooling/config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "embed_dim": 768,
3
+ "num_heads": 8,
4
+ "dropout": 0.0,
5
+ "bias": true,
6
+ "gate_min": 0.2,
7
+ "gate_max": 0.8
8
+ }
checkpoint-240/1_AdvancedWeightedPooling/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38c6c51f5847981488c57095d2773a7858827440df2eb2db9dbf5b019de86527
3
+ size 11828367
checkpoint-240/README.md ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-240/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
checkpoint-240/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-small",
3
+ "architectures": [
4
+ "DebertaV2Model"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 3072,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 6,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 768,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.45.1",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
checkpoint-240/config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.2.0",
4
+ "transformers": "4.45.1",
5
+ "pytorch": "2.4.0"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": null
10
+ }
checkpoint-240/modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_AdvancedWeightedPooling",
12
+ "type": "__main__.AdvancedWeightedPooling"
13
+ }
14
+ ]
checkpoint-240/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:529d337341da36667bc147537eb13a08459e9aee8945204041087315584cdcd0
3
+ size 245742074
checkpoint-240/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70e8db736edfd1de6899cf83b8f3a74f5dd029f913a5784c973bafaa85bcd49f
3
+ size 565251810
checkpoint-240/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b92a0ad15d6e819d361cc6bd7bd4d7439b591cc0abea2ed979638e17cae2cc5
3
+ size 14244
checkpoint-240/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3848c93dad5c8d8e4cbdce461bdcb43330ef79e42328640e3bfe1e59461dcc6
3
+ size 1192
checkpoint-240/sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": false
4
+ }
checkpoint-240/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": {
9
+ "content": "[UNK]",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ }
15
+ }
checkpoint-240/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
checkpoint-240/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-240/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "sp_model_kwargs": {},
54
+ "split_by_punct": false,
55
+ "tokenizer_class": "DebertaV2Tokenizer",
56
+ "unk_token": "[UNK]",
57
+ "vocab_type": "spm"
58
+ }
checkpoint-240/trainer_state.json ADDED
@@ -0,0 +1,2871 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.21238938053097345,
5
+ "eval_steps": 40,
6
+ "global_step": 240,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0008849557522123894,
13
+ "grad_norm": NaN,
14
+ "learning_rate": 0.0,
15
+ "loss": 5.8564,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0017699115044247787,
20
+ "grad_norm": NaN,
21
+ "learning_rate": 0.0,
22
+ "loss": 7.1716,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.002654867256637168,
27
+ "grad_norm": NaN,
28
+ "learning_rate": 0.0,
29
+ "loss": 5.9095,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.0035398230088495575,
34
+ "grad_norm": 21.95326805114746,
35
+ "learning_rate": 3.5377358490566036e-09,
36
+ "loss": 5.0841,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.004424778761061947,
41
+ "grad_norm": 16.607179641723633,
42
+ "learning_rate": 7.075471698113207e-09,
43
+ "loss": 4.0184,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.005309734513274336,
48
+ "grad_norm": 33.789615631103516,
49
+ "learning_rate": 1.0613207547169811e-08,
50
+ "loss": 6.2191,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.006194690265486726,
55
+ "grad_norm": 28.073551177978516,
56
+ "learning_rate": 1.4150943396226414e-08,
57
+ "loss": 5.6124,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.007079646017699115,
62
+ "grad_norm": 17.365602493286133,
63
+ "learning_rate": 1.768867924528302e-08,
64
+ "loss": 3.9544,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.007964601769911504,
69
+ "grad_norm": 19.384475708007812,
70
+ "learning_rate": 2.1226415094339622e-08,
71
+ "loss": 4.7149,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.008849557522123894,
76
+ "grad_norm": 19.67770004272461,
77
+ "learning_rate": 2.4764150943396227e-08,
78
+ "loss": 4.9616,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.009734513274336283,
83
+ "grad_norm": 24.233421325683594,
84
+ "learning_rate": 2.830188679245283e-08,
85
+ "loss": 5.2794,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.010619469026548672,
90
+ "grad_norm": Infinity,
91
+ "learning_rate": 2.830188679245283e-08,
92
+ "loss": 8.8704,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.011504424778761062,
97
+ "grad_norm": 34.37785720825195,
98
+ "learning_rate": 3.183962264150943e-08,
99
+ "loss": 6.0707,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.012389380530973451,
104
+ "grad_norm": 25.11741065979004,
105
+ "learning_rate": 3.537735849056604e-08,
106
+ "loss": 5.4071,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.01327433628318584,
111
+ "grad_norm": 53.84364700317383,
112
+ "learning_rate": 3.891509433962264e-08,
113
+ "loss": 6.9104,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.01415929203539823,
118
+ "grad_norm": 32.0903434753418,
119
+ "learning_rate": 4.2452830188679244e-08,
120
+ "loss": 6.0276,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.01504424778761062,
125
+ "grad_norm": 39.742130279541016,
126
+ "learning_rate": 4.599056603773585e-08,
127
+ "loss": 6.737,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.01592920353982301,
132
+ "grad_norm": 45.267417907714844,
133
+ "learning_rate": 4.9528301886792454e-08,
134
+ "loss": 6.5354,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.016814159292035398,
139
+ "grad_norm": 22.39731788635254,
140
+ "learning_rate": 5.3066037735849055e-08,
141
+ "loss": 5.206,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.017699115044247787,
146
+ "grad_norm": 20.858232498168945,
147
+ "learning_rate": 5.660377358490566e-08,
148
+ "loss": 5.2469,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.018584070796460177,
153
+ "grad_norm": 23.96446990966797,
154
+ "learning_rate": 6.014150943396226e-08,
155
+ "loss": 5.3771,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.019469026548672566,
160
+ "grad_norm": 22.945741653442383,
161
+ "learning_rate": 6.367924528301887e-08,
162
+ "loss": 4.979,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.020353982300884955,
167
+ "grad_norm": 15.497300148010254,
168
+ "learning_rate": 6.721698113207547e-08,
169
+ "loss": 4.7909,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.021238938053097345,
174
+ "grad_norm": 20.039024353027344,
175
+ "learning_rate": 7.075471698113208e-08,
176
+ "loss": 4.9086,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.022123893805309734,
181
+ "grad_norm": 21.30576515197754,
182
+ "learning_rate": 7.429245283018869e-08,
183
+ "loss": 4.8826,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.023008849557522124,
188
+ "grad_norm": 64.5285873413086,
189
+ "learning_rate": 7.783018867924529e-08,
190
+ "loss": 8.2266,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.023893805309734513,
195
+ "grad_norm": 59.894893646240234,
196
+ "learning_rate": 8.13679245283019e-08,
197
+ "loss": 8.3024,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.024778761061946902,
202
+ "grad_norm": 25.504356384277344,
203
+ "learning_rate": 8.490566037735849e-08,
204
+ "loss": 5.8745,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.02566371681415929,
209
+ "grad_norm": 15.169568061828613,
210
+ "learning_rate": 8.84433962264151e-08,
211
+ "loss": 4.7298,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.02654867256637168,
216
+ "grad_norm": 24.09995460510254,
217
+ "learning_rate": 9.19811320754717e-08,
218
+ "loss": 5.4614,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.02743362831858407,
223
+ "grad_norm": 28.669275283813477,
224
+ "learning_rate": 9.55188679245283e-08,
225
+ "loss": 5.8594,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.02831858407079646,
230
+ "grad_norm": 23.37987518310547,
231
+ "learning_rate": 9.905660377358491e-08,
232
+ "loss": 5.2401,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.02920353982300885,
237
+ "grad_norm": 22.815292358398438,
238
+ "learning_rate": 1.0259433962264152e-07,
239
+ "loss": 5.1579,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.03008849557522124,
244
+ "grad_norm": 13.775344848632812,
245
+ "learning_rate": 1.0613207547169811e-07,
246
+ "loss": 5.2181,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.030973451327433628,
251
+ "grad_norm": 18.642087936401367,
252
+ "learning_rate": 1.0966981132075472e-07,
253
+ "loss": 4.6328,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.03185840707964602,
258
+ "grad_norm": 18.041406631469727,
259
+ "learning_rate": 1.1320754716981131e-07,
260
+ "loss": 2.121,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.03274336283185841,
265
+ "grad_norm": 23.423933029174805,
266
+ "learning_rate": 1.1674528301886792e-07,
267
+ "loss": 5.9026,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.033628318584070796,
272
+ "grad_norm": 46.25591278076172,
273
+ "learning_rate": 1.2028301886792452e-07,
274
+ "loss": 7.3796,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.034513274336283185,
279
+ "grad_norm": 20.376422882080078,
280
+ "learning_rate": 1.2382075471698114e-07,
281
+ "loss": 5.5361,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.035398230088495575,
286
+ "grad_norm": 12.82562255859375,
287
+ "learning_rate": 1.2735849056603773e-07,
288
+ "loss": 4.0243,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.035398230088495575,
293
+ "eval_Qnli-dev_cosine_accuracy": 0.5859375,
294
+ "eval_Qnli-dev_cosine_accuracy_threshold": 0.9302856922149658,
295
+ "eval_Qnli-dev_cosine_ap": 0.5480269179285036,
296
+ "eval_Qnli-dev_cosine_f1": 0.6315789473684211,
297
+ "eval_Qnli-dev_cosine_f1_threshold": 0.7634451389312744,
298
+ "eval_Qnli-dev_cosine_precision": 0.4633663366336634,
299
+ "eval_Qnli-dev_cosine_recall": 0.9915254237288136,
300
+ "eval_Qnli-dev_dot_accuracy": 0.5859375,
301
+ "eval_Qnli-dev_dot_accuracy_threshold": 714.4895629882812,
302
+ "eval_Qnli-dev_dot_ap": 0.548060663242546,
303
+ "eval_Qnli-dev_dot_f1": 0.6315789473684211,
304
+ "eval_Qnli-dev_dot_f1_threshold": 586.342529296875,
305
+ "eval_Qnli-dev_dot_precision": 0.4633663366336634,
306
+ "eval_Qnli-dev_dot_recall": 0.9915254237288136,
307
+ "eval_Qnli-dev_euclidean_accuracy": 0.5859375,
308
+ "eval_Qnli-dev_euclidean_accuracy_threshold": 10.348224639892578,
309
+ "eval_Qnli-dev_euclidean_ap": 0.5480269179285036,
310
+ "eval_Qnli-dev_euclidean_f1": 0.6315789473684211,
311
+ "eval_Qnli-dev_euclidean_f1_threshold": 19.05518341064453,
312
+ "eval_Qnli-dev_euclidean_precision": 0.4633663366336634,
313
+ "eval_Qnli-dev_euclidean_recall": 0.9915254237288136,
314
+ "eval_Qnli-dev_manhattan_accuracy": 0.59765625,
315
+ "eval_Qnli-dev_manhattan_accuracy_threshold": 175.22628784179688,
316
+ "eval_Qnli-dev_manhattan_ap": 0.5780924813828909,
317
+ "eval_Qnli-dev_manhattan_f1": 0.6291834002677376,
318
+ "eval_Qnli-dev_manhattan_f1_threshold": 334.39178466796875,
319
+ "eval_Qnli-dev_manhattan_precision": 0.4598825831702544,
320
+ "eval_Qnli-dev_manhattan_recall": 0.9957627118644068,
321
+ "eval_Qnli-dev_max_accuracy": 0.59765625,
322
+ "eval_Qnli-dev_max_accuracy_threshold": 714.4895629882812,
323
+ "eval_Qnli-dev_max_ap": 0.5780924813828909,
324
+ "eval_Qnli-dev_max_f1": 0.6315789473684211,
325
+ "eval_Qnli-dev_max_f1_threshold": 586.342529296875,
326
+ "eval_Qnli-dev_max_precision": 0.4633663366336634,
327
+ "eval_Qnli-dev_max_recall": 0.9957627118644068,
328
+ "eval_allNLI-dev_cosine_accuracy": 0.6640625,
329
+ "eval_allNLI-dev_cosine_accuracy_threshold": 0.9888672828674316,
330
+ "eval_allNLI-dev_cosine_ap": 0.32886365768247516,
331
+ "eval_allNLI-dev_cosine_f1": 0.5095729013254787,
332
+ "eval_allNLI-dev_cosine_f1_threshold": 0.7477295398712158,
333
+ "eval_allNLI-dev_cosine_precision": 0.34189723320158105,
334
+ "eval_allNLI-dev_cosine_recall": 1.0,
335
+ "eval_allNLI-dev_dot_accuracy": 0.6640625,
336
+ "eval_allNLI-dev_dot_accuracy_threshold": 759.483154296875,
337
+ "eval_allNLI-dev_dot_ap": 0.3288581611938815,
338
+ "eval_allNLI-dev_dot_f1": 0.5095729013254787,
339
+ "eval_allNLI-dev_dot_f1_threshold": 574.2760620117188,
340
+ "eval_allNLI-dev_dot_precision": 0.34189723320158105,
341
+ "eval_allNLI-dev_dot_recall": 1.0,
342
+ "eval_allNLI-dev_euclidean_accuracy": 0.6640625,
343
+ "eval_allNLI-dev_euclidean_accuracy_threshold": 3.8085508346557617,
344
+ "eval_allNLI-dev_euclidean_ap": 0.32886365768247516,
345
+ "eval_allNLI-dev_euclidean_f1": 0.5095729013254787,
346
+ "eval_allNLI-dev_euclidean_f1_threshold": 19.684810638427734,
347
+ "eval_allNLI-dev_euclidean_precision": 0.34189723320158105,
348
+ "eval_allNLI-dev_euclidean_recall": 1.0,
349
+ "eval_allNLI-dev_manhattan_accuracy": 0.6640625,
350
+ "eval_allNLI-dev_manhattan_accuracy_threshold": 65.93238830566406,
351
+ "eval_allNLI-dev_manhattan_ap": 0.33852594919898543,
352
+ "eval_allNLI-dev_manhattan_f1": 0.5058479532163743,
353
+ "eval_allNLI-dev_manhattan_f1_threshold": 335.4263916015625,
354
+ "eval_allNLI-dev_manhattan_precision": 0.3385518590998043,
355
+ "eval_allNLI-dev_manhattan_recall": 1.0,
356
+ "eval_allNLI-dev_max_accuracy": 0.6640625,
357
+ "eval_allNLI-dev_max_accuracy_threshold": 759.483154296875,
358
+ "eval_allNLI-dev_max_ap": 0.33852594919898543,
359
+ "eval_allNLI-dev_max_f1": 0.5095729013254787,
360
+ "eval_allNLI-dev_max_f1_threshold": 574.2760620117188,
361
+ "eval_allNLI-dev_max_precision": 0.34189723320158105,
362
+ "eval_allNLI-dev_max_recall": 1.0,
363
+ "eval_sequential_score": 0.5780924813828909,
364
+ "eval_sts-test_pearson_cosine": 0.1533465318414369,
365
+ "eval_sts-test_pearson_dot": 0.15333057450060855,
366
+ "eval_sts-test_pearson_euclidean": 0.1664717893342273,
367
+ "eval_sts-test_pearson_manhattan": 0.20717970064899288,
368
+ "eval_sts-test_pearson_max": 0.20717970064899288,
369
+ "eval_sts-test_spearman_cosine": 0.18786210334203038,
370
+ "eval_sts-test_spearman_dot": 0.1878347337472397,
371
+ "eval_sts-test_spearman_euclidean": 0.18786046572196458,
372
+ "eval_sts-test_spearman_manhattan": 0.22429466463153608,
373
+ "eval_sts-test_spearman_max": 0.22429466463153608,
374
+ "eval_vitaminc-pairs_loss": 2.901831865310669,
375
+ "eval_vitaminc-pairs_runtime": 4.078,
376
+ "eval_vitaminc-pairs_samples_per_second": 31.388,
377
+ "eval_vitaminc-pairs_steps_per_second": 0.245,
378
+ "step": 40
379
+ },
380
+ {
381
+ "epoch": 0.035398230088495575,
382
+ "eval_negation-triplets_loss": 5.690315246582031,
383
+ "eval_negation-triplets_runtime": 0.7141,
384
+ "eval_negation-triplets_samples_per_second": 179.254,
385
+ "eval_negation-triplets_steps_per_second": 1.4,
386
+ "step": 40
387
+ },
388
+ {
389
+ "epoch": 0.035398230088495575,
390
+ "eval_scitail-pairs-pos_loss": 2.1135852336883545,
391
+ "eval_scitail-pairs-pos_runtime": 0.8282,
392
+ "eval_scitail-pairs-pos_samples_per_second": 154.543,
393
+ "eval_scitail-pairs-pos_steps_per_second": 1.207,
394
+ "step": 40
395
+ },
396
+ {
397
+ "epoch": 0.035398230088495575,
398
+ "eval_scitail-pairs-qa_loss": 2.8052029609680176,
399
+ "eval_scitail-pairs-qa_runtime": 0.5471,
400
+ "eval_scitail-pairs-qa_samples_per_second": 233.943,
401
+ "eval_scitail-pairs-qa_steps_per_second": 1.828,
402
+ "step": 40
403
+ },
404
+ {
405
+ "epoch": 0.035398230088495575,
406
+ "eval_xsum-pairs_loss": 6.583061695098877,
407
+ "eval_xsum-pairs_runtime": 2.8921,
408
+ "eval_xsum-pairs_samples_per_second": 44.259,
409
+ "eval_xsum-pairs_steps_per_second": 0.346,
410
+ "step": 40
411
+ },
412
+ {
413
+ "epoch": 0.035398230088495575,
414
+ "eval_sciq_pairs_loss": 0.8882207870483398,
415
+ "eval_sciq_pairs_runtime": 3.7993,
416
+ "eval_sciq_pairs_samples_per_second": 33.69,
417
+ "eval_sciq_pairs_steps_per_second": 0.263,
418
+ "step": 40
419
+ },
420
+ {
421
+ "epoch": 0.035398230088495575,
422
+ "eval_qasc_pairs_loss": 4.1147541999816895,
423
+ "eval_qasc_pairs_runtime": 0.6768,
424
+ "eval_qasc_pairs_samples_per_second": 189.125,
425
+ "eval_qasc_pairs_steps_per_second": 1.478,
426
+ "step": 40
427
+ },
428
+ {
429
+ "epoch": 0.035398230088495575,
430
+ "eval_openbookqa_pairs_loss": 5.096628665924072,
431
+ "eval_openbookqa_pairs_runtime": 0.5776,
432
+ "eval_openbookqa_pairs_samples_per_second": 221.615,
433
+ "eval_openbookqa_pairs_steps_per_second": 1.731,
434
+ "step": 40
435
+ },
436
+ {
437
+ "epoch": 0.035398230088495575,
438
+ "eval_msmarco_pairs_loss": 10.391141891479492,
439
+ "eval_msmarco_pairs_runtime": 1.2577,
440
+ "eval_msmarco_pairs_samples_per_second": 101.77,
441
+ "eval_msmarco_pairs_steps_per_second": 0.795,
442
+ "step": 40
443
+ },
444
+ {
445
+ "epoch": 0.035398230088495575,
446
+ "eval_nq_pairs_loss": 10.903197288513184,
447
+ "eval_nq_pairs_runtime": 2.5051,
448
+ "eval_nq_pairs_samples_per_second": 51.095,
449
+ "eval_nq_pairs_steps_per_second": 0.399,
450
+ "step": 40
451
+ },
452
+ {
453
+ "epoch": 0.035398230088495575,
454
+ "eval_trivia_pairs_loss": 7.190384387969971,
455
+ "eval_trivia_pairs_runtime": 3.6482,
456
+ "eval_trivia_pairs_samples_per_second": 35.085,
457
+ "eval_trivia_pairs_steps_per_second": 0.274,
458
+ "step": 40
459
+ },
460
+ {
461
+ "epoch": 0.035398230088495575,
462
+ "eval_gooaq_pairs_loss": 8.193528175354004,
463
+ "eval_gooaq_pairs_runtime": 0.9648,
464
+ "eval_gooaq_pairs_samples_per_second": 132.67,
465
+ "eval_gooaq_pairs_steps_per_second": 1.036,
466
+ "step": 40
467
+ },
468
+ {
469
+ "epoch": 0.035398230088495575,
470
+ "eval_paws-pos_loss": 1.3942564725875854,
471
+ "eval_paws-pos_runtime": 0.6718,
472
+ "eval_paws-pos_samples_per_second": 190.538,
473
+ "eval_paws-pos_steps_per_second": 1.489,
474
+ "step": 40
475
+ },
476
+ {
477
+ "epoch": 0.035398230088495575,
478
+ "eval_global_dataset_loss": 5.671571731567383,
479
+ "eval_global_dataset_runtime": 23.0452,
480
+ "eval_global_dataset_samples_per_second": 28.77,
481
+ "eval_global_dataset_steps_per_second": 0.26,
482
+ "step": 40
483
+ },
484
+ {
485
+ "epoch": 0.036283185840707964,
486
+ "grad_norm": 18.026830673217773,
487
+ "learning_rate": 1.3089622641509433e-07,
488
+ "loss": 4.9072,
489
+ "step": 41
490
+ },
491
+ {
492
+ "epoch": 0.03716814159292035,
493
+ "grad_norm": 15.423810958862305,
494
+ "learning_rate": 1.3443396226415095e-07,
495
+ "loss": 3.4439,
496
+ "step": 42
497
+ },
498
+ {
499
+ "epoch": 0.03805309734513274,
500
+ "grad_norm": 16.31403160095215,
501
+ "learning_rate": 1.3797169811320754e-07,
502
+ "loss": 4.9787,
503
+ "step": 43
504
+ },
505
+ {
506
+ "epoch": 0.03893805309734513,
507
+ "grad_norm": 21.37955093383789,
508
+ "learning_rate": 1.4150943396226417e-07,
509
+ "loss": 5.8318,
510
+ "step": 44
511
+ },
512
+ {
513
+ "epoch": 0.03982300884955752,
514
+ "grad_norm": 18.23583984375,
515
+ "learning_rate": 1.4504716981132076e-07,
516
+ "loss": 5.3226,
517
+ "step": 45
518
+ },
519
+ {
520
+ "epoch": 0.04070796460176991,
521
+ "grad_norm": 20.878713607788086,
522
+ "learning_rate": 1.4858490566037738e-07,
523
+ "loss": 5.1181,
524
+ "step": 46
525
+ },
526
+ {
527
+ "epoch": 0.0415929203539823,
528
+ "grad_norm": 18.71149444580078,
529
+ "learning_rate": 1.5212264150943398e-07,
530
+ "loss": 4.7834,
531
+ "step": 47
532
+ },
533
+ {
534
+ "epoch": 0.04247787610619469,
535
+ "grad_norm": 38.85902786254883,
536
+ "learning_rate": 1.5566037735849057e-07,
537
+ "loss": 6.6303,
538
+ "step": 48
539
+ },
540
+ {
541
+ "epoch": 0.04336283185840708,
542
+ "grad_norm": 37.41562271118164,
543
+ "learning_rate": 1.591981132075472e-07,
544
+ "loss": 5.8171,
545
+ "step": 49
546
+ },
547
+ {
548
+ "epoch": 0.04424778761061947,
549
+ "grad_norm": 17.541080474853516,
550
+ "learning_rate": 1.627358490566038e-07,
551
+ "loss": 5.1962,
552
+ "step": 50
553
+ },
554
+ {
555
+ "epoch": 0.04513274336283186,
556
+ "grad_norm": 16.145116806030273,
557
+ "learning_rate": 1.6627358490566038e-07,
558
+ "loss": 5.2096,
559
+ "step": 51
560
+ },
561
+ {
562
+ "epoch": 0.04601769911504425,
563
+ "grad_norm": 20.175189971923828,
564
+ "learning_rate": 1.6981132075471698e-07,
565
+ "loss": 5.0943,
566
+ "step": 52
567
+ },
568
+ {
569
+ "epoch": 0.046902654867256637,
570
+ "grad_norm": 13.441214561462402,
571
+ "learning_rate": 1.733490566037736e-07,
572
+ "loss": 4.9038,
573
+ "step": 53
574
+ },
575
+ {
576
+ "epoch": 0.047787610619469026,
577
+ "grad_norm": 13.396607398986816,
578
+ "learning_rate": 1.768867924528302e-07,
579
+ "loss": 4.6479,
580
+ "step": 54
581
+ },
582
+ {
583
+ "epoch": 0.048672566371681415,
584
+ "grad_norm": 13.68046760559082,
585
+ "learning_rate": 1.804245283018868e-07,
586
+ "loss": 5.5098,
587
+ "step": 55
588
+ },
589
+ {
590
+ "epoch": 0.049557522123893805,
591
+ "grad_norm": 13.278443336486816,
592
+ "learning_rate": 1.839622641509434e-07,
593
+ "loss": 4.6979,
594
+ "step": 56
595
+ },
596
+ {
597
+ "epoch": 0.050442477876106194,
598
+ "grad_norm": 15.295453071594238,
599
+ "learning_rate": 1.875e-07,
600
+ "loss": 3.1969,
601
+ "step": 57
602
+ },
603
+ {
604
+ "epoch": 0.05132743362831858,
605
+ "grad_norm": 12.185781478881836,
606
+ "learning_rate": 1.910377358490566e-07,
607
+ "loss": 4.4127,
608
+ "step": 58
609
+ },
610
+ {
611
+ "epoch": 0.05221238938053097,
612
+ "grad_norm": 10.874494552612305,
613
+ "learning_rate": 1.9457547169811322e-07,
614
+ "loss": 3.7746,
615
+ "step": 59
616
+ },
617
+ {
618
+ "epoch": 0.05309734513274336,
619
+ "grad_norm": 9.654823303222656,
620
+ "learning_rate": 1.9811320754716982e-07,
621
+ "loss": 4.5378,
622
+ "step": 60
623
+ },
624
+ {
625
+ "epoch": 0.05398230088495575,
626
+ "grad_norm": 21.123645782470703,
627
+ "learning_rate": 2.016509433962264e-07,
628
+ "loss": 5.0209,
629
+ "step": 61
630
+ },
631
+ {
632
+ "epoch": 0.05486725663716814,
633
+ "grad_norm": 33.47934341430664,
634
+ "learning_rate": 2.0518867924528303e-07,
635
+ "loss": 6.5936,
636
+ "step": 62
637
+ },
638
+ {
639
+ "epoch": 0.05575221238938053,
640
+ "grad_norm": 10.2566556930542,
641
+ "learning_rate": 2.0872641509433963e-07,
642
+ "loss": 4.2315,
643
+ "step": 63
644
+ },
645
+ {
646
+ "epoch": 0.05663716814159292,
647
+ "grad_norm": 28.198625564575195,
648
+ "learning_rate": 2.1226415094339622e-07,
649
+ "loss": 6.4269,
650
+ "step": 64
651
+ },
652
+ {
653
+ "epoch": 0.05752212389380531,
654
+ "grad_norm": 9.386558532714844,
655
+ "learning_rate": 2.1580188679245282e-07,
656
+ "loss": 4.2644,
657
+ "step": 65
658
+ },
659
+ {
660
+ "epoch": 0.0584070796460177,
661
+ "grad_norm": 12.687555313110352,
662
+ "learning_rate": 2.1933962264150944e-07,
663
+ "loss": 5.1388,
664
+ "step": 66
665
+ },
666
+ {
667
+ "epoch": 0.05929203539823009,
668
+ "grad_norm": 14.834878921508789,
669
+ "learning_rate": 2.2287735849056603e-07,
670
+ "loss": 5.1852,
671
+ "step": 67
672
+ },
673
+ {
674
+ "epoch": 0.06017699115044248,
675
+ "grad_norm": 10.888677597045898,
676
+ "learning_rate": 2.2641509433962263e-07,
677
+ "loss": 4.8057,
678
+ "step": 68
679
+ },
680
+ {
681
+ "epoch": 0.061061946902654866,
682
+ "grad_norm": 13.97256851196289,
683
+ "learning_rate": 2.2995283018867925e-07,
684
+ "loss": 3.1725,
685
+ "step": 69
686
+ },
687
+ {
688
+ "epoch": 0.061946902654867256,
689
+ "grad_norm": 11.82534122467041,
690
+ "learning_rate": 2.3349056603773584e-07,
691
+ "loss": 3.3322,
692
+ "step": 70
693
+ },
694
+ {
695
+ "epoch": 0.06283185840707965,
696
+ "grad_norm": 16.99266242980957,
697
+ "learning_rate": 2.3702830188679244e-07,
698
+ "loss": 5.139,
699
+ "step": 71
700
+ },
701
+ {
702
+ "epoch": 0.06371681415929203,
703
+ "grad_norm": 8.74513053894043,
704
+ "learning_rate": 2.4056603773584903e-07,
705
+ "loss": 4.307,
706
+ "step": 72
707
+ },
708
+ {
709
+ "epoch": 0.06460176991150443,
710
+ "grad_norm": 11.715869903564453,
711
+ "learning_rate": 2.4410377358490563e-07,
712
+ "loss": 5.0133,
713
+ "step": 73
714
+ },
715
+ {
716
+ "epoch": 0.06548672566371681,
717
+ "grad_norm": 9.844196319580078,
718
+ "learning_rate": 2.476415094339623e-07,
719
+ "loss": 4.0507,
720
+ "step": 74
721
+ },
722
+ {
723
+ "epoch": 0.06637168141592921,
724
+ "grad_norm": 12.447444915771484,
725
+ "learning_rate": 2.5117924528301887e-07,
726
+ "loss": 3.3895,
727
+ "step": 75
728
+ },
729
+ {
730
+ "epoch": 0.06725663716814159,
731
+ "grad_norm": 23.91596794128418,
732
+ "learning_rate": 2.5471698113207547e-07,
733
+ "loss": 5.6736,
734
+ "step": 76
735
+ },
736
+ {
737
+ "epoch": 0.06814159292035399,
738
+ "grad_norm": 9.635603904724121,
739
+ "learning_rate": 2.5825471698113206e-07,
740
+ "loss": 4.2572,
741
+ "step": 77
742
+ },
743
+ {
744
+ "epoch": 0.06902654867256637,
745
+ "grad_norm": 14.971665382385254,
746
+ "learning_rate": 2.6179245283018866e-07,
747
+ "loss": 3.0796,
748
+ "step": 78
749
+ },
750
+ {
751
+ "epoch": 0.06991150442477877,
752
+ "grad_norm": 11.226128578186035,
753
+ "learning_rate": 2.6533018867924525e-07,
754
+ "loss": 5.0199,
755
+ "step": 79
756
+ },
757
+ {
758
+ "epoch": 0.07079646017699115,
759
+ "grad_norm": 11.01388931274414,
760
+ "learning_rate": 2.688679245283019e-07,
761
+ "loss": 4.1414,
762
+ "step": 80
763
+ },
764
+ {
765
+ "epoch": 0.07079646017699115,
766
+ "eval_Qnli-dev_cosine_accuracy": 0.591796875,
767
+ "eval_Qnli-dev_cosine_accuracy_threshold": 0.9258557558059692,
768
+ "eval_Qnli-dev_cosine_ap": 0.5585355274462735,
769
+ "eval_Qnli-dev_cosine_f1": 0.6291834002677376,
770
+ "eval_Qnli-dev_cosine_f1_threshold": 0.750666618347168,
771
+ "eval_Qnli-dev_cosine_precision": 0.4598825831702544,
772
+ "eval_Qnli-dev_cosine_recall": 0.9957627118644068,
773
+ "eval_Qnli-dev_dot_accuracy": 0.591796875,
774
+ "eval_Qnli-dev_dot_accuracy_threshold": 711.18359375,
775
+ "eval_Qnli-dev_dot_ap": 0.5585297234749824,
776
+ "eval_Qnli-dev_dot_f1": 0.6291834002677376,
777
+ "eval_Qnli-dev_dot_f1_threshold": 576.5970458984375,
778
+ "eval_Qnli-dev_dot_precision": 0.4598825831702544,
779
+ "eval_Qnli-dev_dot_recall": 0.9957627118644068,
780
+ "eval_Qnli-dev_euclidean_accuracy": 0.591796875,
781
+ "eval_Qnli-dev_euclidean_accuracy_threshold": 10.672666549682617,
782
+ "eval_Qnli-dev_euclidean_ap": 0.5585355274462735,
783
+ "eval_Qnli-dev_euclidean_f1": 0.6291834002677376,
784
+ "eval_Qnli-dev_euclidean_f1_threshold": 19.553747177124023,
785
+ "eval_Qnli-dev_euclidean_precision": 0.4598825831702544,
786
+ "eval_Qnli-dev_euclidean_recall": 0.9957627118644068,
787
+ "eval_Qnli-dev_manhattan_accuracy": 0.619140625,
788
+ "eval_Qnli-dev_manhattan_accuracy_threshold": 188.09068298339844,
789
+ "eval_Qnli-dev_manhattan_ap": 0.5898283705050701,
790
+ "eval_Qnli-dev_manhattan_f1": 0.6301775147928994,
791
+ "eval_Qnli-dev_manhattan_f1_threshold": 237.80462646484375,
792
+ "eval_Qnli-dev_manhattan_precision": 0.48409090909090907,
793
+ "eval_Qnli-dev_manhattan_recall": 0.902542372881356,
794
+ "eval_Qnli-dev_max_accuracy": 0.619140625,
795
+ "eval_Qnli-dev_max_accuracy_threshold": 711.18359375,
796
+ "eval_Qnli-dev_max_ap": 0.5898283705050701,
797
+ "eval_Qnli-dev_max_f1": 0.6301775147928994,
798
+ "eval_Qnli-dev_max_f1_threshold": 576.5970458984375,
799
+ "eval_Qnli-dev_max_precision": 0.48409090909090907,
800
+ "eval_Qnli-dev_max_recall": 0.9957627118644068,
801
+ "eval_allNLI-dev_cosine_accuracy": 0.666015625,
802
+ "eval_allNLI-dev_cosine_accuracy_threshold": 0.983686089515686,
803
+ "eval_allNLI-dev_cosine_ap": 0.34411819659341086,
804
+ "eval_allNLI-dev_cosine_f1": 0.5065885797950219,
805
+ "eval_allNLI-dev_cosine_f1_threshold": 0.7642872333526611,
806
+ "eval_allNLI-dev_cosine_precision": 0.3392156862745098,
807
+ "eval_allNLI-dev_cosine_recall": 1.0,
808
+ "eval_allNLI-dev_dot_accuracy": 0.666015625,
809
+ "eval_allNLI-dev_dot_accuracy_threshold": 755.60302734375,
810
+ "eval_allNLI-dev_dot_ap": 0.344109544232086,
811
+ "eval_allNLI-dev_dot_f1": 0.5065885797950219,
812
+ "eval_allNLI-dev_dot_f1_threshold": 587.0625,
813
+ "eval_allNLI-dev_dot_precision": 0.3392156862745098,
814
+ "eval_allNLI-dev_dot_recall": 1.0,
815
+ "eval_allNLI-dev_euclidean_accuracy": 0.666015625,
816
+ "eval_allNLI-dev_euclidean_accuracy_threshold": 5.00581693649292,
817
+ "eval_allNLI-dev_euclidean_ap": 0.3441246898925644,
818
+ "eval_allNLI-dev_euclidean_f1": 0.5065885797950219,
819
+ "eval_allNLI-dev_euclidean_f1_threshold": 19.022436141967773,
820
+ "eval_allNLI-dev_euclidean_precision": 0.3392156862745098,
821
+ "eval_allNLI-dev_euclidean_recall": 1.0,
822
+ "eval_allNLI-dev_manhattan_accuracy": 0.6640625,
823
+ "eval_allNLI-dev_manhattan_accuracy_threshold": 62.69102096557617,
824
+ "eval_allNLI-dev_manhattan_ap": 0.35131239981425566,
825
+ "eval_allNLI-dev_manhattan_f1": 0.5058479532163743,
826
+ "eval_allNLI-dev_manhattan_f1_threshold": 337.6861877441406,
827
+ "eval_allNLI-dev_manhattan_precision": 0.3385518590998043,
828
+ "eval_allNLI-dev_manhattan_recall": 1.0,
829
+ "eval_allNLI-dev_max_accuracy": 0.666015625,
830
+ "eval_allNLI-dev_max_accuracy_threshold": 755.60302734375,
831
+ "eval_allNLI-dev_max_ap": 0.35131239981425566,
832
+ "eval_allNLI-dev_max_f1": 0.5065885797950219,
833
+ "eval_allNLI-dev_max_f1_threshold": 587.0625,
834
+ "eval_allNLI-dev_max_precision": 0.3392156862745098,
835
+ "eval_allNLI-dev_max_recall": 1.0,
836
+ "eval_sequential_score": 0.5898283705050701,
837
+ "eval_sts-test_pearson_cosine": 0.22248205020578934,
838
+ "eval_sts-test_pearson_dot": 0.22239084967931927,
839
+ "eval_sts-test_pearson_euclidean": 0.2323160413842197,
840
+ "eval_sts-test_pearson_manhattan": 0.26632593273308647,
841
+ "eval_sts-test_pearson_max": 0.26632593273308647,
842
+ "eval_sts-test_spearman_cosine": 0.24802235964390085,
843
+ "eval_sts-test_spearman_dot": 0.24791612015173234,
844
+ "eval_sts-test_spearman_euclidean": 0.24799036249272113,
845
+ "eval_sts-test_spearman_manhattan": 0.2843623073856928,
846
+ "eval_sts-test_spearman_max": 0.2843623073856928,
847
+ "eval_vitaminc-pairs_loss": 2.7793872356414795,
848
+ "eval_vitaminc-pairs_runtime": 3.7649,
849
+ "eval_vitaminc-pairs_samples_per_second": 33.998,
850
+ "eval_vitaminc-pairs_steps_per_second": 0.266,
851
+ "step": 80
852
+ },
853
+ {
854
+ "epoch": 0.07079646017699115,
855
+ "eval_negation-triplets_loss": 4.888970851898193,
856
+ "eval_negation-triplets_runtime": 0.7134,
857
+ "eval_negation-triplets_samples_per_second": 179.432,
858
+ "eval_negation-triplets_steps_per_second": 1.402,
859
+ "step": 80
860
+ },
861
+ {
862
+ "epoch": 0.07079646017699115,
863
+ "eval_scitail-pairs-pos_loss": 1.8996644020080566,
864
+ "eval_scitail-pairs-pos_runtime": 0.8506,
865
+ "eval_scitail-pairs-pos_samples_per_second": 150.477,
866
+ "eval_scitail-pairs-pos_steps_per_second": 1.176,
867
+ "step": 80
868
+ },
869
+ {
870
+ "epoch": 0.07079646017699115,
871
+ "eval_scitail-pairs-qa_loss": 2.6760551929473877,
872
+ "eval_scitail-pairs-qa_runtime": 0.5685,
873
+ "eval_scitail-pairs-qa_samples_per_second": 225.171,
874
+ "eval_scitail-pairs-qa_steps_per_second": 1.759,
875
+ "step": 80
876
+ },
877
+ {
878
+ "epoch": 0.07079646017699115,
879
+ "eval_xsum-pairs_loss": 6.209648609161377,
880
+ "eval_xsum-pairs_runtime": 2.9221,
881
+ "eval_xsum-pairs_samples_per_second": 43.804,
882
+ "eval_xsum-pairs_steps_per_second": 0.342,
883
+ "step": 80
884
+ },
885
+ {
886
+ "epoch": 0.07079646017699115,
887
+ "eval_sciq_pairs_loss": 0.7622462511062622,
888
+ "eval_sciq_pairs_runtime": 3.7816,
889
+ "eval_sciq_pairs_samples_per_second": 33.848,
890
+ "eval_sciq_pairs_steps_per_second": 0.264,
891
+ "step": 80
892
+ },
893
+ {
894
+ "epoch": 0.07079646017699115,
895
+ "eval_qasc_pairs_loss": 3.3129472732543945,
896
+ "eval_qasc_pairs_runtime": 0.6761,
897
+ "eval_qasc_pairs_samples_per_second": 189.334,
898
+ "eval_qasc_pairs_steps_per_second": 1.479,
899
+ "step": 80
900
+ },
901
+ {
902
+ "epoch": 0.07079646017699115,
903
+ "eval_openbookqa_pairs_loss": 4.549765586853027,
904
+ "eval_openbookqa_pairs_runtime": 0.5767,
905
+ "eval_openbookqa_pairs_samples_per_second": 221.954,
906
+ "eval_openbookqa_pairs_steps_per_second": 1.734,
907
+ "step": 80
908
+ },
909
+ {
910
+ "epoch": 0.07079646017699115,
911
+ "eval_msmarco_pairs_loss": 7.205582141876221,
912
+ "eval_msmarco_pairs_runtime": 1.2621,
913
+ "eval_msmarco_pairs_samples_per_second": 101.416,
914
+ "eval_msmarco_pairs_steps_per_second": 0.792,
915
+ "step": 80
916
+ },
917
+ {
918
+ "epoch": 0.07079646017699115,
919
+ "eval_nq_pairs_loss": 7.680945873260498,
920
+ "eval_nq_pairs_runtime": 2.5052,
921
+ "eval_nq_pairs_samples_per_second": 51.095,
922
+ "eval_nq_pairs_steps_per_second": 0.399,
923
+ "step": 80
924
+ },
925
+ {
926
+ "epoch": 0.07079646017699115,
927
+ "eval_trivia_pairs_loss": 6.37924861907959,
928
+ "eval_trivia_pairs_runtime": 3.6293,
929
+ "eval_trivia_pairs_samples_per_second": 35.268,
930
+ "eval_trivia_pairs_steps_per_second": 0.276,
931
+ "step": 80
932
+ },
933
+ {
934
+ "epoch": 0.07079646017699115,
935
+ "eval_gooaq_pairs_loss": 6.656675338745117,
936
+ "eval_gooaq_pairs_runtime": 0.9698,
937
+ "eval_gooaq_pairs_samples_per_second": 131.988,
938
+ "eval_gooaq_pairs_steps_per_second": 1.031,
939
+ "step": 80
940
+ },
941
+ {
942
+ "epoch": 0.07079646017699115,
943
+ "eval_paws-pos_loss": 1.3848179578781128,
944
+ "eval_paws-pos_runtime": 0.6727,
945
+ "eval_paws-pos_samples_per_second": 190.278,
946
+ "eval_paws-pos_steps_per_second": 1.487,
947
+ "step": 80
948
+ },
949
+ {
950
+ "epoch": 0.07079646017699115,
951
+ "eval_global_dataset_loss": 5.002967834472656,
952
+ "eval_global_dataset_runtime": 23.048,
953
+ "eval_global_dataset_samples_per_second": 28.766,
954
+ "eval_global_dataset_steps_per_second": 0.26,
955
+ "step": 80
956
+ },
957
+ {
958
+ "epoch": 0.07168141592920355,
959
+ "grad_norm": 18.9890193939209,
960
+ "learning_rate": 2.724056603773585e-07,
961
+ "loss": 5.8604,
962
+ "step": 81
963
+ },
964
+ {
965
+ "epoch": 0.07256637168141593,
966
+ "grad_norm": 8.206193923950195,
967
+ "learning_rate": 2.759433962264151e-07,
968
+ "loss": 4.3003,
969
+ "step": 82
970
+ },
971
+ {
972
+ "epoch": 0.07345132743362832,
973
+ "grad_norm": 10.03178882598877,
974
+ "learning_rate": 2.794811320754717e-07,
975
+ "loss": 4.4568,
976
+ "step": 83
977
+ },
978
+ {
979
+ "epoch": 0.0743362831858407,
980
+ "grad_norm": 14.74673080444336,
981
+ "learning_rate": 2.8301886792452833e-07,
982
+ "loss": 4.2747,
983
+ "step": 84
984
+ },
985
+ {
986
+ "epoch": 0.0752212389380531,
987
+ "grad_norm": 19.097232818603516,
988
+ "learning_rate": 2.865566037735849e-07,
989
+ "loss": 5.52,
990
+ "step": 85
991
+ },
992
+ {
993
+ "epoch": 0.07610619469026549,
994
+ "grad_norm": 14.828218460083008,
995
+ "learning_rate": 2.900943396226415e-07,
996
+ "loss": 2.7767,
997
+ "step": 86
998
+ },
999
+ {
1000
+ "epoch": 0.07699115044247788,
1001
+ "grad_norm": 9.30789566040039,
1002
+ "learning_rate": 2.936320754716981e-07,
1003
+ "loss": 4.397,
1004
+ "step": 87
1005
+ },
1006
+ {
1007
+ "epoch": 0.07787610619469026,
1008
+ "grad_norm": 15.119461059570312,
1009
+ "learning_rate": 2.9716981132075476e-07,
1010
+ "loss": 5.4449,
1011
+ "step": 88
1012
+ },
1013
+ {
1014
+ "epoch": 0.07876106194690266,
1015
+ "grad_norm": 8.459301948547363,
1016
+ "learning_rate": 3.0070754716981136e-07,
1017
+ "loss": 4.2706,
1018
+ "step": 89
1019
+ },
1020
+ {
1021
+ "epoch": 0.07964601769911504,
1022
+ "grad_norm": 23.59125518798828,
1023
+ "learning_rate": 3.0424528301886795e-07,
1024
+ "loss": 6.4759,
1025
+ "step": 90
1026
+ },
1027
+ {
1028
+ "epoch": 0.08053097345132744,
1029
+ "grad_norm": 8.729449272155762,
1030
+ "learning_rate": 3.0778301886792455e-07,
1031
+ "loss": 4.1951,
1032
+ "step": 91
1033
+ },
1034
+ {
1035
+ "epoch": 0.08141592920353982,
1036
+ "grad_norm": 8.37271785736084,
1037
+ "learning_rate": 3.1132075471698114e-07,
1038
+ "loss": 4.6328,
1039
+ "step": 92
1040
+ },
1041
+ {
1042
+ "epoch": 0.08230088495575222,
1043
+ "grad_norm": 10.029474258422852,
1044
+ "learning_rate": 3.1485849056603774e-07,
1045
+ "loss": 4.1278,
1046
+ "step": 93
1047
+ },
1048
+ {
1049
+ "epoch": 0.0831858407079646,
1050
+ "grad_norm": 8.706567764282227,
1051
+ "learning_rate": 3.183962264150944e-07,
1052
+ "loss": 4.1787,
1053
+ "step": 94
1054
+ },
1055
+ {
1056
+ "epoch": 0.084070796460177,
1057
+ "grad_norm": 13.88837718963623,
1058
+ "learning_rate": 3.21933962264151e-07,
1059
+ "loss": 5.2156,
1060
+ "step": 95
1061
+ },
1062
+ {
1063
+ "epoch": 0.08495575221238938,
1064
+ "grad_norm": 12.01068115234375,
1065
+ "learning_rate": 3.254716981132076e-07,
1066
+ "loss": 3.1403,
1067
+ "step": 96
1068
+ },
1069
+ {
1070
+ "epoch": 0.08584070796460178,
1071
+ "grad_norm": 8.432968139648438,
1072
+ "learning_rate": 3.2900943396226417e-07,
1073
+ "loss": 4.0273,
1074
+ "step": 97
1075
+ },
1076
+ {
1077
+ "epoch": 0.08672566371681416,
1078
+ "grad_norm": 12.645098686218262,
1079
+ "learning_rate": 3.3254716981132077e-07,
1080
+ "loss": 3.0624,
1081
+ "step": 98
1082
+ },
1083
+ {
1084
+ "epoch": 0.08761061946902655,
1085
+ "grad_norm": 11.483688354492188,
1086
+ "learning_rate": 3.3608490566037736e-07,
1087
+ "loss": 4.6786,
1088
+ "step": 99
1089
+ },
1090
+ {
1091
+ "epoch": 0.08849557522123894,
1092
+ "grad_norm": 8.645537376403809,
1093
+ "learning_rate": 3.3962264150943395e-07,
1094
+ "loss": 4.1505,
1095
+ "step": 100
1096
+ },
1097
+ {
1098
+ "epoch": 0.08938053097345133,
1099
+ "grad_norm": 13.053335189819336,
1100
+ "learning_rate": 3.431603773584906e-07,
1101
+ "loss": 2.9529,
1102
+ "step": 101
1103
+ },
1104
+ {
1105
+ "epoch": 0.09026548672566372,
1106
+ "grad_norm": 14.494400978088379,
1107
+ "learning_rate": 3.466981132075472e-07,
1108
+ "loss": 4.7048,
1109
+ "step": 102
1110
+ },
1111
+ {
1112
+ "epoch": 0.09115044247787611,
1113
+ "grad_norm": 9.513616561889648,
1114
+ "learning_rate": 3.502358490566038e-07,
1115
+ "loss": 4.7388,
1116
+ "step": 103
1117
+ },
1118
+ {
1119
+ "epoch": 0.0920353982300885,
1120
+ "grad_norm": 9.751347541809082,
1121
+ "learning_rate": 3.537735849056604e-07,
1122
+ "loss": 3.7879,
1123
+ "step": 104
1124
+ },
1125
+ {
1126
+ "epoch": 0.09292035398230089,
1127
+ "grad_norm": 9.06558895111084,
1128
+ "learning_rate": 3.57311320754717e-07,
1129
+ "loss": 4.0311,
1130
+ "step": 105
1131
+ },
1132
+ {
1133
+ "epoch": 0.09380530973451327,
1134
+ "grad_norm": 9.53257942199707,
1135
+ "learning_rate": 3.608490566037736e-07,
1136
+ "loss": 4.1314,
1137
+ "step": 106
1138
+ },
1139
+ {
1140
+ "epoch": 0.09469026548672567,
1141
+ "grad_norm": 11.554676055908203,
1142
+ "learning_rate": 3.643867924528302e-07,
1143
+ "loss": 4.9411,
1144
+ "step": 107
1145
+ },
1146
+ {
1147
+ "epoch": 0.09557522123893805,
1148
+ "grad_norm": 8.559597969055176,
1149
+ "learning_rate": 3.679245283018868e-07,
1150
+ "loss": 4.1118,
1151
+ "step": 108
1152
+ },
1153
+ {
1154
+ "epoch": 0.09646017699115045,
1155
+ "grad_norm": 10.008039474487305,
1156
+ "learning_rate": 3.714622641509434e-07,
1157
+ "loss": 3.6971,
1158
+ "step": 109
1159
+ },
1160
+ {
1161
+ "epoch": 0.09734513274336283,
1162
+ "grad_norm": 16.543254852294922,
1163
+ "learning_rate": 3.75e-07,
1164
+ "loss": 5.605,
1165
+ "step": 110
1166
+ },
1167
+ {
1168
+ "epoch": 0.09823008849557523,
1169
+ "grad_norm": 11.816540718078613,
1170
+ "learning_rate": 3.7853773584905666e-07,
1171
+ "loss": 3.4563,
1172
+ "step": 111
1173
+ },
1174
+ {
1175
+ "epoch": 0.09911504424778761,
1176
+ "grad_norm": 10.638028144836426,
1177
+ "learning_rate": 3.820754716981132e-07,
1178
+ "loss": 3.7422,
1179
+ "step": 112
1180
+ },
1181
+ {
1182
+ "epoch": 0.1,
1183
+ "grad_norm": 8.5276460647583,
1184
+ "learning_rate": 3.8561320754716985e-07,
1185
+ "loss": 3.8055,
1186
+ "step": 113
1187
+ },
1188
+ {
1189
+ "epoch": 0.10088495575221239,
1190
+ "grad_norm": 13.437420845031738,
1191
+ "learning_rate": 3.8915094339622644e-07,
1192
+ "loss": 5.2369,
1193
+ "step": 114
1194
+ },
1195
+ {
1196
+ "epoch": 0.10176991150442478,
1197
+ "grad_norm": 21.039424896240234,
1198
+ "learning_rate": 3.926886792452831e-07,
1199
+ "loss": 5.6518,
1200
+ "step": 115
1201
+ },
1202
+ {
1203
+ "epoch": 0.10265486725663717,
1204
+ "grad_norm": 13.487382888793945,
1205
+ "learning_rate": 3.9622641509433963e-07,
1206
+ "loss": 3.2906,
1207
+ "step": 116
1208
+ },
1209
+ {
1210
+ "epoch": 0.10353982300884956,
1211
+ "grad_norm": 11.895822525024414,
1212
+ "learning_rate": 3.997641509433963e-07,
1213
+ "loss": 3.4996,
1214
+ "step": 117
1215
+ },
1216
+ {
1217
+ "epoch": 0.10442477876106195,
1218
+ "grad_norm": 10.83902359008789,
1219
+ "learning_rate": 4.033018867924528e-07,
1220
+ "loss": 3.6283,
1221
+ "step": 118
1222
+ },
1223
+ {
1224
+ "epoch": 0.10530973451327434,
1225
+ "grad_norm": 10.552660942077637,
1226
+ "learning_rate": 4.0683962264150947e-07,
1227
+ "loss": 4.1487,
1228
+ "step": 119
1229
+ },
1230
+ {
1231
+ "epoch": 0.10619469026548672,
1232
+ "grad_norm": 9.924088478088379,
1233
+ "learning_rate": 4.1037735849056606e-07,
1234
+ "loss": 4.3996,
1235
+ "step": 120
1236
+ },
1237
+ {
1238
+ "epoch": 0.10619469026548672,
1239
+ "eval_Qnli-dev_cosine_accuracy": 0.595703125,
1240
+ "eval_Qnli-dev_cosine_accuracy_threshold": 0.9275249242782593,
1241
+ "eval_Qnli-dev_cosine_ap": 0.5645920090286662,
1242
+ "eval_Qnli-dev_cosine_f1": 0.6327077747989276,
1243
+ "eval_Qnli-dev_cosine_f1_threshold": 0.7267085313796997,
1244
+ "eval_Qnli-dev_cosine_precision": 0.4627450980392157,
1245
+ "eval_Qnli-dev_cosine_recall": 1.0,
1246
+ "eval_Qnli-dev_dot_accuracy": 0.595703125,
1247
+ "eval_Qnli-dev_dot_accuracy_threshold": 712.4608154296875,
1248
+ "eval_Qnli-dev_dot_ap": 0.5646837736357366,
1249
+ "eval_Qnli-dev_dot_f1": 0.6327077747989276,
1250
+ "eval_Qnli-dev_dot_f1_threshold": 558.2177734375,
1251
+ "eval_Qnli-dev_dot_precision": 0.4627450980392157,
1252
+ "eval_Qnli-dev_dot_recall": 1.0,
1253
+ "eval_Qnli-dev_euclidean_accuracy": 0.595703125,
1254
+ "eval_Qnli-dev_euclidean_accuracy_threshold": 10.551876068115234,
1255
+ "eval_Qnli-dev_euclidean_ap": 0.5645997569733668,
1256
+ "eval_Qnli-dev_euclidean_f1": 0.6327077747989276,
1257
+ "eval_Qnli-dev_euclidean_f1_threshold": 20.490163803100586,
1258
+ "eval_Qnli-dev_euclidean_precision": 0.4627450980392157,
1259
+ "eval_Qnli-dev_euclidean_recall": 1.0,
1260
+ "eval_Qnli-dev_manhattan_accuracy": 0.626953125,
1261
+ "eval_Qnli-dev_manhattan_accuracy_threshold": 195.12744140625,
1262
+ "eval_Qnli-dev_manhattan_ap": 0.5975206086733145,
1263
+ "eval_Qnli-dev_manhattan_f1": 0.6322008862629247,
1264
+ "eval_Qnli-dev_manhattan_f1_threshold": 256.6172180175781,
1265
+ "eval_Qnli-dev_manhattan_precision": 0.4852607709750567,
1266
+ "eval_Qnli-dev_manhattan_recall": 0.9067796610169492,
1267
+ "eval_Qnli-dev_max_accuracy": 0.626953125,
1268
+ "eval_Qnli-dev_max_accuracy_threshold": 712.4608154296875,
1269
+ "eval_Qnli-dev_max_ap": 0.5975206086733145,
1270
+ "eval_Qnli-dev_max_f1": 0.6327077747989276,
1271
+ "eval_Qnli-dev_max_f1_threshold": 558.2177734375,
1272
+ "eval_Qnli-dev_max_precision": 0.4852607709750567,
1273
+ "eval_Qnli-dev_max_recall": 1.0,
1274
+ "eval_allNLI-dev_cosine_accuracy": 0.666015625,
1275
+ "eval_allNLI-dev_cosine_accuracy_threshold": 0.983871340751648,
1276
+ "eval_allNLI-dev_cosine_ap": 0.36035507065342104,
1277
+ "eval_allNLI-dev_cosine_f1": 0.5051395007342143,
1278
+ "eval_allNLI-dev_cosine_f1_threshold": 0.7787582874298096,
1279
+ "eval_allNLI-dev_cosine_precision": 0.33858267716535434,
1280
+ "eval_allNLI-dev_cosine_recall": 0.9942196531791907,
1281
+ "eval_allNLI-dev_dot_accuracy": 0.666015625,
1282
+ "eval_allNLI-dev_dot_accuracy_threshold": 755.7670288085938,
1283
+ "eval_allNLI-dev_dot_ap": 0.36031241443166284,
1284
+ "eval_allNLI-dev_dot_f1": 0.5051395007342143,
1285
+ "eval_allNLI-dev_dot_f1_threshold": 598.2041625976562,
1286
+ "eval_allNLI-dev_dot_precision": 0.33858267716535434,
1287
+ "eval_allNLI-dev_dot_recall": 0.9942196531791907,
1288
+ "eval_allNLI-dev_euclidean_accuracy": 0.666015625,
1289
+ "eval_allNLI-dev_euclidean_accuracy_threshold": 4.964720249176025,
1290
+ "eval_allNLI-dev_euclidean_ap": 0.36035507065342104,
1291
+ "eval_allNLI-dev_euclidean_f1": 0.5051395007342143,
1292
+ "eval_allNLI-dev_euclidean_f1_threshold": 18.434789657592773,
1293
+ "eval_allNLI-dev_euclidean_precision": 0.33858267716535434,
1294
+ "eval_allNLI-dev_euclidean_recall": 0.9942196531791907,
1295
+ "eval_allNLI-dev_manhattan_accuracy": 0.6640625,
1296
+ "eval_allNLI-dev_manhattan_accuracy_threshold": 66.59053039550781,
1297
+ "eval_allNLI-dev_manhattan_ap": 0.3692975841596879,
1298
+ "eval_allNLI-dev_manhattan_f1": 0.5029239766081871,
1299
+ "eval_allNLI-dev_manhattan_f1_threshold": 380.123779296875,
1300
+ "eval_allNLI-dev_manhattan_precision": 0.33659491193737767,
1301
+ "eval_allNLI-dev_manhattan_recall": 0.9942196531791907,
1302
+ "eval_allNLI-dev_max_accuracy": 0.666015625,
1303
+ "eval_allNLI-dev_max_accuracy_threshold": 755.7670288085938,
1304
+ "eval_allNLI-dev_max_ap": 0.3692975841596879,
1305
+ "eval_allNLI-dev_max_f1": 0.5051395007342143,
1306
+ "eval_allNLI-dev_max_f1_threshold": 598.2041625976562,
1307
+ "eval_allNLI-dev_max_precision": 0.33858267716535434,
1308
+ "eval_allNLI-dev_max_recall": 0.9942196531791907,
1309
+ "eval_sequential_score": 0.5975206086733145,
1310
+ "eval_sts-test_pearson_cosine": 0.2980667522290251,
1311
+ "eval_sts-test_pearson_dot": 0.29795063801865274,
1312
+ "eval_sts-test_pearson_euclidean": 0.30279956330153407,
1313
+ "eval_sts-test_pearson_manhattan": 0.32939035635624725,
1314
+ "eval_sts-test_pearson_max": 0.32939035635624725,
1315
+ "eval_sts-test_spearman_cosine": 0.3148821747085771,
1316
+ "eval_sts-test_spearman_dot": 0.3149517475826025,
1317
+ "eval_sts-test_spearman_euclidean": 0.31489636085812106,
1318
+ "eval_sts-test_spearman_manhattan": 0.34558301612848313,
1319
+ "eval_sts-test_spearman_max": 0.34558301612848313,
1320
+ "eval_vitaminc-pairs_loss": 2.727938652038574,
1321
+ "eval_vitaminc-pairs_runtime": 3.7459,
1322
+ "eval_vitaminc-pairs_samples_per_second": 34.17,
1323
+ "eval_vitaminc-pairs_steps_per_second": 0.267,
1324
+ "step": 120
1325
+ },
1326
+ {
1327
+ "epoch": 0.10619469026548672,
1328
+ "eval_negation-triplets_loss": 4.394620418548584,
1329
+ "eval_negation-triplets_runtime": 0.7078,
1330
+ "eval_negation-triplets_samples_per_second": 180.852,
1331
+ "eval_negation-triplets_steps_per_second": 1.413,
1332
+ "step": 120
1333
+ },
1334
+ {
1335
+ "epoch": 0.10619469026548672,
1336
+ "eval_scitail-pairs-pos_loss": 1.4130322933197021,
1337
+ "eval_scitail-pairs-pos_runtime": 0.8587,
1338
+ "eval_scitail-pairs-pos_samples_per_second": 149.07,
1339
+ "eval_scitail-pairs-pos_steps_per_second": 1.165,
1340
+ "step": 120
1341
+ },
1342
+ {
1343
+ "epoch": 0.10619469026548672,
1344
+ "eval_scitail-pairs-qa_loss": 2.1150403022766113,
1345
+ "eval_scitail-pairs-qa_runtime": 0.549,
1346
+ "eval_scitail-pairs-qa_samples_per_second": 233.163,
1347
+ "eval_scitail-pairs-qa_steps_per_second": 1.822,
1348
+ "step": 120
1349
+ },
1350
+ {
1351
+ "epoch": 0.10619469026548672,
1352
+ "eval_xsum-pairs_loss": 6.048598289489746,
1353
+ "eval_xsum-pairs_runtime": 2.9142,
1354
+ "eval_xsum-pairs_samples_per_second": 43.923,
1355
+ "eval_xsum-pairs_steps_per_second": 0.343,
1356
+ "step": 120
1357
+ },
1358
+ {
1359
+ "epoch": 0.10619469026548672,
1360
+ "eval_sciq_pairs_loss": 0.7171850800514221,
1361
+ "eval_sciq_pairs_runtime": 3.7786,
1362
+ "eval_sciq_pairs_samples_per_second": 33.875,
1363
+ "eval_sciq_pairs_steps_per_second": 0.265,
1364
+ "step": 120
1365
+ },
1366
+ {
1367
+ "epoch": 0.10619469026548672,
1368
+ "eval_qasc_pairs_loss": 2.96693754196167,
1369
+ "eval_qasc_pairs_runtime": 0.6718,
1370
+ "eval_qasc_pairs_samples_per_second": 190.538,
1371
+ "eval_qasc_pairs_steps_per_second": 1.489,
1372
+ "step": 120
1373
+ },
1374
+ {
1375
+ "epoch": 0.10619469026548672,
1376
+ "eval_openbookqa_pairs_loss": 4.418018341064453,
1377
+ "eval_openbookqa_pairs_runtime": 0.577,
1378
+ "eval_openbookqa_pairs_samples_per_second": 221.852,
1379
+ "eval_openbookqa_pairs_steps_per_second": 1.733,
1380
+ "step": 120
1381
+ },
1382
+ {
1383
+ "epoch": 0.10619469026548672,
1384
+ "eval_msmarco_pairs_loss": 6.302182197570801,
1385
+ "eval_msmarco_pairs_runtime": 1.2547,
1386
+ "eval_msmarco_pairs_samples_per_second": 102.016,
1387
+ "eval_msmarco_pairs_steps_per_second": 0.797,
1388
+ "step": 120
1389
+ },
1390
+ {
1391
+ "epoch": 0.10619469026548672,
1392
+ "eval_nq_pairs_loss": 6.841231822967529,
1393
+ "eval_nq_pairs_runtime": 2.5052,
1394
+ "eval_nq_pairs_samples_per_second": 51.094,
1395
+ "eval_nq_pairs_steps_per_second": 0.399,
1396
+ "step": 120
1397
+ },
1398
+ {
1399
+ "epoch": 0.10619469026548672,
1400
+ "eval_trivia_pairs_loss": 6.201311111450195,
1401
+ "eval_trivia_pairs_runtime": 3.6311,
1402
+ "eval_trivia_pairs_samples_per_second": 35.251,
1403
+ "eval_trivia_pairs_steps_per_second": 0.275,
1404
+ "step": 120
1405
+ },
1406
+ {
1407
+ "epoch": 0.10619469026548672,
1408
+ "eval_gooaq_pairs_loss": 6.098212718963623,
1409
+ "eval_gooaq_pairs_runtime": 0.9643,
1410
+ "eval_gooaq_pairs_samples_per_second": 132.741,
1411
+ "eval_gooaq_pairs_steps_per_second": 1.037,
1412
+ "step": 120
1413
+ },
1414
+ {
1415
+ "epoch": 0.10619469026548672,
1416
+ "eval_paws-pos_loss": 0.9473956823348999,
1417
+ "eval_paws-pos_runtime": 0.6684,
1418
+ "eval_paws-pos_samples_per_second": 191.51,
1419
+ "eval_paws-pos_steps_per_second": 1.496,
1420
+ "step": 120
1421
+ },
1422
+ {
1423
+ "epoch": 0.10619469026548672,
1424
+ "eval_global_dataset_loss": 4.385201454162598,
1425
+ "eval_global_dataset_runtime": 23.0455,
1426
+ "eval_global_dataset_samples_per_second": 28.769,
1427
+ "eval_global_dataset_steps_per_second": 0.26,
1428
+ "step": 120
1429
+ },
1430
+ {
1431
+ "epoch": 0.10707964601769912,
1432
+ "grad_norm": 12.284002304077148,
1433
+ "learning_rate": 4.1391509433962266e-07,
1434
+ "loss": 3.5291,
1435
+ "step": 121
1436
+ },
1437
+ {
1438
+ "epoch": 0.1079646017699115,
1439
+ "grad_norm": 10.567977905273438,
1440
+ "learning_rate": 4.1745283018867925e-07,
1441
+ "loss": 3.8232,
1442
+ "step": 122
1443
+ },
1444
+ {
1445
+ "epoch": 0.1088495575221239,
1446
+ "grad_norm": 11.508279800415039,
1447
+ "learning_rate": 4.209905660377359e-07,
1448
+ "loss": 4.6035,
1449
+ "step": 123
1450
+ },
1451
+ {
1452
+ "epoch": 0.10973451327433628,
1453
+ "grad_norm": 10.180809020996094,
1454
+ "learning_rate": 4.2452830188679244e-07,
1455
+ "loss": 3.7607,
1456
+ "step": 124
1457
+ },
1458
+ {
1459
+ "epoch": 0.11061946902654868,
1460
+ "grad_norm": 9.519749641418457,
1461
+ "learning_rate": 4.280660377358491e-07,
1462
+ "loss": 3.8461,
1463
+ "step": 125
1464
+ },
1465
+ {
1466
+ "epoch": 0.11150442477876106,
1467
+ "grad_norm": 11.971588134765625,
1468
+ "learning_rate": 4.3160377358490563e-07,
1469
+ "loss": 3.3413,
1470
+ "step": 126
1471
+ },
1472
+ {
1473
+ "epoch": 0.11238938053097346,
1474
+ "grad_norm": 9.211153984069824,
1475
+ "learning_rate": 4.351415094339623e-07,
1476
+ "loss": 4.2777,
1477
+ "step": 127
1478
+ },
1479
+ {
1480
+ "epoch": 0.11327433628318584,
1481
+ "grad_norm": 12.393014907836914,
1482
+ "learning_rate": 4.386792452830189e-07,
1483
+ "loss": 4.3597,
1484
+ "step": 128
1485
+ },
1486
+ {
1487
+ "epoch": 0.11415929203539824,
1488
+ "grad_norm": 14.332024574279785,
1489
+ "learning_rate": 4.422169811320755e-07,
1490
+ "loss": 3.9046,
1491
+ "step": 129
1492
+ },
1493
+ {
1494
+ "epoch": 0.11504424778761062,
1495
+ "grad_norm": 10.091246604919434,
1496
+ "learning_rate": 4.4575471698113207e-07,
1497
+ "loss": 4.0527,
1498
+ "step": 130
1499
+ },
1500
+ {
1501
+ "epoch": 0.11592920353982301,
1502
+ "grad_norm": 15.043377876281738,
1503
+ "learning_rate": 4.492924528301887e-07,
1504
+ "loss": 5.0883,
1505
+ "step": 131
1506
+ },
1507
+ {
1508
+ "epoch": 0.1168141592920354,
1509
+ "grad_norm": 12.942100524902344,
1510
+ "learning_rate": 4.5283018867924526e-07,
1511
+ "loss": 3.8308,
1512
+ "step": 132
1513
+ },
1514
+ {
1515
+ "epoch": 0.11769911504424779,
1516
+ "grad_norm": 11.961737632751465,
1517
+ "learning_rate": 4.563679245283019e-07,
1518
+ "loss": 3.572,
1519
+ "step": 133
1520
+ },
1521
+ {
1522
+ "epoch": 0.11858407079646018,
1523
+ "grad_norm": 12.325026512145996,
1524
+ "learning_rate": 4.599056603773585e-07,
1525
+ "loss": 3.4299,
1526
+ "step": 134
1527
+ },
1528
+ {
1529
+ "epoch": 0.11946902654867257,
1530
+ "grad_norm": 12.118773460388184,
1531
+ "learning_rate": 4.6344339622641515e-07,
1532
+ "loss": 4.1541,
1533
+ "step": 135
1534
+ },
1535
+ {
1536
+ "epoch": 0.12035398230088495,
1537
+ "grad_norm": 11.99026107788086,
1538
+ "learning_rate": 4.669811320754717e-07,
1539
+ "loss": 3.584,
1540
+ "step": 136
1541
+ },
1542
+ {
1543
+ "epoch": 0.12123893805309735,
1544
+ "grad_norm": 15.083515167236328,
1545
+ "learning_rate": 4.7051886792452834e-07,
1546
+ "loss": 5.0977,
1547
+ "step": 137
1548
+ },
1549
+ {
1550
+ "epoch": 0.12212389380530973,
1551
+ "grad_norm": 15.059394836425781,
1552
+ "learning_rate": 4.740566037735849e-07,
1553
+ "loss": 4.6769,
1554
+ "step": 138
1555
+ },
1556
+ {
1557
+ "epoch": 0.12300884955752213,
1558
+ "grad_norm": 8.864882469177246,
1559
+ "learning_rate": 4.775943396226415e-07,
1560
+ "loss": 3.8396,
1561
+ "step": 139
1562
+ },
1563
+ {
1564
+ "epoch": 0.12389380530973451,
1565
+ "grad_norm": 12.116555213928223,
1566
+ "learning_rate": 4.811320754716981e-07,
1567
+ "loss": 3.2875,
1568
+ "step": 140
1569
+ },
1570
+ {
1571
+ "epoch": 0.12477876106194691,
1572
+ "grad_norm": 14.214646339416504,
1573
+ "learning_rate": 4.846698113207547e-07,
1574
+ "loss": 4.1946,
1575
+ "step": 141
1576
+ },
1577
+ {
1578
+ "epoch": 0.1256637168141593,
1579
+ "grad_norm": 16.207908630371094,
1580
+ "learning_rate": 4.882075471698113e-07,
1581
+ "loss": 4.9602,
1582
+ "step": 142
1583
+ },
1584
+ {
1585
+ "epoch": 0.12654867256637167,
1586
+ "grad_norm": 11.662668228149414,
1587
+ "learning_rate": 4.917452830188679e-07,
1588
+ "loss": 4.1531,
1589
+ "step": 143
1590
+ },
1591
+ {
1592
+ "epoch": 0.12743362831858407,
1593
+ "grad_norm": 12.429448127746582,
1594
+ "learning_rate": 4.952830188679246e-07,
1595
+ "loss": 3.8351,
1596
+ "step": 144
1597
+ },
1598
+ {
1599
+ "epoch": 0.12831858407079647,
1600
+ "grad_norm": 11.522616386413574,
1601
+ "learning_rate": 4.988207547169812e-07,
1602
+ "loss": 3.112,
1603
+ "step": 145
1604
+ },
1605
+ {
1606
+ "epoch": 0.12920353982300886,
1607
+ "grad_norm": 14.556803703308105,
1608
+ "learning_rate": 5.023584905660377e-07,
1609
+ "loss": 2.3145,
1610
+ "step": 146
1611
+ },
1612
+ {
1613
+ "epoch": 0.13008849557522123,
1614
+ "grad_norm": 12.348714828491211,
1615
+ "learning_rate": 5.058962264150944e-07,
1616
+ "loss": 4.0989,
1617
+ "step": 147
1618
+ },
1619
+ {
1620
+ "epoch": 0.13097345132743363,
1621
+ "grad_norm": 13.150403022766113,
1622
+ "learning_rate": 5.094339622641509e-07,
1623
+ "loss": 3.2173,
1624
+ "step": 148
1625
+ },
1626
+ {
1627
+ "epoch": 0.13185840707964602,
1628
+ "grad_norm": 12.066205978393555,
1629
+ "learning_rate": 5.129716981132076e-07,
1630
+ "loss": 2.7913,
1631
+ "step": 149
1632
+ },
1633
+ {
1634
+ "epoch": 0.13274336283185842,
1635
+ "grad_norm": 11.519116401672363,
1636
+ "learning_rate": 5.165094339622641e-07,
1637
+ "loss": 3.7627,
1638
+ "step": 150
1639
+ },
1640
+ {
1641
+ "epoch": 0.1336283185840708,
1642
+ "grad_norm": 12.59196662902832,
1643
+ "learning_rate": 5.200471698113208e-07,
1644
+ "loss": 3.3669,
1645
+ "step": 151
1646
+ },
1647
+ {
1648
+ "epoch": 0.13451327433628318,
1649
+ "grad_norm": 13.791536331176758,
1650
+ "learning_rate": 5.235849056603773e-07,
1651
+ "loss": 2.6775,
1652
+ "step": 152
1653
+ },
1654
+ {
1655
+ "epoch": 0.13539823008849558,
1656
+ "grad_norm": 11.906597137451172,
1657
+ "learning_rate": 5.27122641509434e-07,
1658
+ "loss": 3.2804,
1659
+ "step": 153
1660
+ },
1661
+ {
1662
+ "epoch": 0.13628318584070798,
1663
+ "grad_norm": 11.267363548278809,
1664
+ "learning_rate": 5.306603773584905e-07,
1665
+ "loss": 3.0676,
1666
+ "step": 154
1667
+ },
1668
+ {
1669
+ "epoch": 0.13716814159292035,
1670
+ "grad_norm": 12.373686790466309,
1671
+ "learning_rate": 5.341981132075471e-07,
1672
+ "loss": 3.1559,
1673
+ "step": 155
1674
+ },
1675
+ {
1676
+ "epoch": 0.13805309734513274,
1677
+ "grad_norm": 13.258451461791992,
1678
+ "learning_rate": 5.377358490566038e-07,
1679
+ "loss": 2.6638,
1680
+ "step": 156
1681
+ },
1682
+ {
1683
+ "epoch": 0.13893805309734514,
1684
+ "grad_norm": 12.79727554321289,
1685
+ "learning_rate": 5.412735849056604e-07,
1686
+ "loss": 2.8045,
1687
+ "step": 157
1688
+ },
1689
+ {
1690
+ "epoch": 0.13982300884955753,
1691
+ "grad_norm": 13.88683032989502,
1692
+ "learning_rate": 5.44811320754717e-07,
1693
+ "loss": 4.0568,
1694
+ "step": 158
1695
+ },
1696
+ {
1697
+ "epoch": 0.1407079646017699,
1698
+ "grad_norm": 12.57358169555664,
1699
+ "learning_rate": 5.483490566037736e-07,
1700
+ "loss": 2.7554,
1701
+ "step": 159
1702
+ },
1703
+ {
1704
+ "epoch": 0.1415929203539823,
1705
+ "grad_norm": 14.520818710327148,
1706
+ "learning_rate": 5.518867924528302e-07,
1707
+ "loss": 3.7407,
1708
+ "step": 160
1709
+ },
1710
+ {
1711
+ "epoch": 0.1415929203539823,
1712
+ "eval_Qnli-dev_cosine_accuracy": 0.62890625,
1713
+ "eval_Qnli-dev_cosine_accuracy_threshold": 0.9045097827911377,
1714
+ "eval_Qnli-dev_cosine_ap": 0.6193527955003784,
1715
+ "eval_Qnli-dev_cosine_f1": 0.6397415185783522,
1716
+ "eval_Qnli-dev_cosine_f1_threshold": 0.8351442813873291,
1717
+ "eval_Qnli-dev_cosine_precision": 0.5169712793733682,
1718
+ "eval_Qnli-dev_cosine_recall": 0.8389830508474576,
1719
+ "eval_Qnli-dev_dot_accuracy": 0.62890625,
1720
+ "eval_Qnli-dev_dot_accuracy_threshold": 694.7778930664062,
1721
+ "eval_Qnli-dev_dot_ap": 0.6194150916988216,
1722
+ "eval_Qnli-dev_dot_f1": 0.6397415185783522,
1723
+ "eval_Qnli-dev_dot_f1_threshold": 641.4969482421875,
1724
+ "eval_Qnli-dev_dot_precision": 0.5169712793733682,
1725
+ "eval_Qnli-dev_dot_recall": 0.8389830508474576,
1726
+ "eval_Qnli-dev_euclidean_accuracy": 0.62890625,
1727
+ "eval_Qnli-dev_euclidean_accuracy_threshold": 12.111844062805176,
1728
+ "eval_Qnli-dev_euclidean_ap": 0.6193576186776235,
1729
+ "eval_Qnli-dev_euclidean_f1": 0.6397415185783522,
1730
+ "eval_Qnli-dev_euclidean_f1_threshold": 15.914146423339844,
1731
+ "eval_Qnli-dev_euclidean_precision": 0.5169712793733682,
1732
+ "eval_Qnli-dev_euclidean_recall": 0.8389830508474576,
1733
+ "eval_Qnli-dev_manhattan_accuracy": 0.646484375,
1734
+ "eval_Qnli-dev_manhattan_accuracy_threshold": 245.2164306640625,
1735
+ "eval_Qnli-dev_manhattan_ap": 0.6417015148414534,
1736
+ "eval_Qnli-dev_manhattan_f1": 0.6521060842433698,
1737
+ "eval_Qnli-dev_manhattan_f1_threshold": 303.317626953125,
1738
+ "eval_Qnli-dev_manhattan_precision": 0.5160493827160494,
1739
+ "eval_Qnli-dev_manhattan_recall": 0.885593220338983,
1740
+ "eval_Qnli-dev_max_accuracy": 0.646484375,
1741
+ "eval_Qnli-dev_max_accuracy_threshold": 694.7778930664062,
1742
+ "eval_Qnli-dev_max_ap": 0.6417015148414534,
1743
+ "eval_Qnli-dev_max_f1": 0.6521060842433698,
1744
+ "eval_Qnli-dev_max_f1_threshold": 641.4969482421875,
1745
+ "eval_Qnli-dev_max_precision": 0.5169712793733682,
1746
+ "eval_Qnli-dev_max_recall": 0.885593220338983,
1747
+ "eval_allNLI-dev_cosine_accuracy": 0.66796875,
1748
+ "eval_allNLI-dev_cosine_accuracy_threshold": 0.9767438173294067,
1749
+ "eval_allNLI-dev_cosine_ap": 0.38624833037583434,
1750
+ "eval_allNLI-dev_cosine_f1": 0.5100182149362477,
1751
+ "eval_allNLI-dev_cosine_f1_threshold": 0.8540960550308228,
1752
+ "eval_allNLI-dev_cosine_precision": 0.3723404255319149,
1753
+ "eval_allNLI-dev_cosine_recall": 0.8092485549132948,
1754
+ "eval_allNLI-dev_dot_accuracy": 0.66796875,
1755
+ "eval_allNLI-dev_dot_accuracy_threshold": 750.345458984375,
1756
+ "eval_allNLI-dev_dot_ap": 0.3862261253421553,
1757
+ "eval_allNLI-dev_dot_f1": 0.5100182149362477,
1758
+ "eval_allNLI-dev_dot_f1_threshold": 656.0940551757812,
1759
+ "eval_allNLI-dev_dot_precision": 0.3723404255319149,
1760
+ "eval_allNLI-dev_dot_recall": 0.8092485549132948,
1761
+ "eval_allNLI-dev_euclidean_accuracy": 0.66796875,
1762
+ "eval_allNLI-dev_euclidean_accuracy_threshold": 5.977196216583252,
1763
+ "eval_allNLI-dev_euclidean_ap": 0.38624380046547035,
1764
+ "eval_allNLI-dev_euclidean_f1": 0.5100182149362477,
1765
+ "eval_allNLI-dev_euclidean_f1_threshold": 14.971920013427734,
1766
+ "eval_allNLI-dev_euclidean_precision": 0.3723404255319149,
1767
+ "eval_allNLI-dev_euclidean_recall": 0.8092485549132948,
1768
+ "eval_allNLI-dev_manhattan_accuracy": 0.6640625,
1769
+ "eval_allNLI-dev_manhattan_accuracy_threshold": 78.52637481689453,
1770
+ "eval_allNLI-dev_manhattan_ap": 0.3898187083180651,
1771
+ "eval_allNLI-dev_manhattan_f1": 0.5062388591800357,
1772
+ "eval_allNLI-dev_manhattan_f1_threshold": 285.7745361328125,
1773
+ "eval_allNLI-dev_manhattan_precision": 0.36597938144329895,
1774
+ "eval_allNLI-dev_manhattan_recall": 0.8208092485549133,
1775
+ "eval_allNLI-dev_max_accuracy": 0.66796875,
1776
+ "eval_allNLI-dev_max_accuracy_threshold": 750.345458984375,
1777
+ "eval_allNLI-dev_max_ap": 0.3898187083180651,
1778
+ "eval_allNLI-dev_max_f1": 0.5100182149362477,
1779
+ "eval_allNLI-dev_max_f1_threshold": 656.0940551757812,
1780
+ "eval_allNLI-dev_max_precision": 0.3723404255319149,
1781
+ "eval_allNLI-dev_max_recall": 0.8208092485549133,
1782
+ "eval_sequential_score": 0.6417015148414534,
1783
+ "eval_sts-test_pearson_cosine": 0.2853943019391156,
1784
+ "eval_sts-test_pearson_dot": 0.28526334639473966,
1785
+ "eval_sts-test_pearson_euclidean": 0.29405773952219494,
1786
+ "eval_sts-test_pearson_manhattan": 0.3110310476615048,
1787
+ "eval_sts-test_pearson_max": 0.3110310476615048,
1788
+ "eval_sts-test_spearman_cosine": 0.31414239162305135,
1789
+ "eval_sts-test_spearman_dot": 0.31380407209449446,
1790
+ "eval_sts-test_spearman_euclidean": 0.3141516551339523,
1791
+ "eval_sts-test_spearman_manhattan": 0.3366243060620438,
1792
+ "eval_sts-test_spearman_max": 0.3366243060620438,
1793
+ "eval_vitaminc-pairs_loss": 2.7439002990722656,
1794
+ "eval_vitaminc-pairs_runtime": 3.7639,
1795
+ "eval_vitaminc-pairs_samples_per_second": 34.007,
1796
+ "eval_vitaminc-pairs_steps_per_second": 0.266,
1797
+ "step": 160
1798
+ },
1799
+ {
1800
+ "epoch": 0.1415929203539823,
1801
+ "eval_negation-triplets_loss": 4.63640022277832,
1802
+ "eval_negation-triplets_runtime": 0.7072,
1803
+ "eval_negation-triplets_samples_per_second": 180.999,
1804
+ "eval_negation-triplets_steps_per_second": 1.414,
1805
+ "step": 160
1806
+ },
1807
+ {
1808
+ "epoch": 0.1415929203539823,
1809
+ "eval_scitail-pairs-pos_loss": 1.0088545083999634,
1810
+ "eval_scitail-pairs-pos_runtime": 0.8123,
1811
+ "eval_scitail-pairs-pos_samples_per_second": 157.577,
1812
+ "eval_scitail-pairs-pos_steps_per_second": 1.231,
1813
+ "step": 160
1814
+ },
1815
+ {
1816
+ "epoch": 0.1415929203539823,
1817
+ "eval_scitail-pairs-qa_loss": 1.1228678226470947,
1818
+ "eval_scitail-pairs-qa_runtime": 0.5444,
1819
+ "eval_scitail-pairs-qa_samples_per_second": 235.115,
1820
+ "eval_scitail-pairs-qa_steps_per_second": 1.837,
1821
+ "step": 160
1822
+ },
1823
+ {
1824
+ "epoch": 0.1415929203539823,
1825
+ "eval_xsum-pairs_loss": 5.4869818687438965,
1826
+ "eval_xsum-pairs_runtime": 2.8888,
1827
+ "eval_xsum-pairs_samples_per_second": 44.308,
1828
+ "eval_xsum-pairs_steps_per_second": 0.346,
1829
+ "step": 160
1830
+ },
1831
+ {
1832
+ "epoch": 0.1415929203539823,
1833
+ "eval_sciq_pairs_loss": 0.628353476524353,
1834
+ "eval_sciq_pairs_runtime": 3.8061,
1835
+ "eval_sciq_pairs_samples_per_second": 33.631,
1836
+ "eval_sciq_pairs_steps_per_second": 0.263,
1837
+ "step": 160
1838
+ },
1839
+ {
1840
+ "epoch": 0.1415929203539823,
1841
+ "eval_qasc_pairs_loss": 2.593322277069092,
1842
+ "eval_qasc_pairs_runtime": 0.6728,
1843
+ "eval_qasc_pairs_samples_per_second": 190.241,
1844
+ "eval_qasc_pairs_steps_per_second": 1.486,
1845
+ "step": 160
1846
+ },
1847
+ {
1848
+ "epoch": 0.1415929203539823,
1849
+ "eval_openbookqa_pairs_loss": 4.394308090209961,
1850
+ "eval_openbookqa_pairs_runtime": 0.5852,
1851
+ "eval_openbookqa_pairs_samples_per_second": 218.729,
1852
+ "eval_openbookqa_pairs_steps_per_second": 1.709,
1853
+ "step": 160
1854
+ },
1855
+ {
1856
+ "epoch": 0.1415929203539823,
1857
+ "eval_msmarco_pairs_loss": 5.656517505645752,
1858
+ "eval_msmarco_pairs_runtime": 1.2571,
1859
+ "eval_msmarco_pairs_samples_per_second": 101.822,
1860
+ "eval_msmarco_pairs_steps_per_second": 0.795,
1861
+ "step": 160
1862
+ },
1863
+ {
1864
+ "epoch": 0.1415929203539823,
1865
+ "eval_nq_pairs_loss": 5.986983776092529,
1866
+ "eval_nq_pairs_runtime": 2.5075,
1867
+ "eval_nq_pairs_samples_per_second": 51.047,
1868
+ "eval_nq_pairs_steps_per_second": 0.399,
1869
+ "step": 160
1870
+ },
1871
+ {
1872
+ "epoch": 0.1415929203539823,
1873
+ "eval_trivia_pairs_loss": 5.694415092468262,
1874
+ "eval_trivia_pairs_runtime": 3.6302,
1875
+ "eval_trivia_pairs_samples_per_second": 35.26,
1876
+ "eval_trivia_pairs_steps_per_second": 0.275,
1877
+ "step": 160
1878
+ },
1879
+ {
1880
+ "epoch": 0.1415929203539823,
1881
+ "eval_gooaq_pairs_loss": 5.3856658935546875,
1882
+ "eval_gooaq_pairs_runtime": 0.9618,
1883
+ "eval_gooaq_pairs_samples_per_second": 133.082,
1884
+ "eval_gooaq_pairs_steps_per_second": 1.04,
1885
+ "step": 160
1886
+ },
1887
+ {
1888
+ "epoch": 0.1415929203539823,
1889
+ "eval_paws-pos_loss": 0.3622308671474457,
1890
+ "eval_paws-pos_runtime": 0.6678,
1891
+ "eval_paws-pos_samples_per_second": 191.674,
1892
+ "eval_paws-pos_steps_per_second": 1.497,
1893
+ "step": 160
1894
+ },
1895
+ {
1896
+ "epoch": 0.1415929203539823,
1897
+ "eval_global_dataset_loss": 3.401135206222534,
1898
+ "eval_global_dataset_runtime": 23.0422,
1899
+ "eval_global_dataset_samples_per_second": 28.773,
1900
+ "eval_global_dataset_steps_per_second": 0.26,
1901
+ "step": 160
1902
+ },
1903
+ {
1904
+ "epoch": 0.1424778761061947,
1905
+ "grad_norm": 15.203566551208496,
1906
+ "learning_rate": 5.554245283018868e-07,
1907
+ "loss": 3.4324,
1908
+ "step": 161
1909
+ },
1910
+ {
1911
+ "epoch": 0.1433628318584071,
1912
+ "grad_norm": 17.9180850982666,
1913
+ "learning_rate": 5.589622641509434e-07,
1914
+ "loss": 3.6658,
1915
+ "step": 162
1916
+ },
1917
+ {
1918
+ "epoch": 0.14424778761061946,
1919
+ "grad_norm": 15.438867568969727,
1920
+ "learning_rate": 5.625e-07,
1921
+ "loss": 3.96,
1922
+ "step": 163
1923
+ },
1924
+ {
1925
+ "epoch": 0.14513274336283186,
1926
+ "grad_norm": 11.754356384277344,
1927
+ "learning_rate": 5.660377358490567e-07,
1928
+ "loss": 2.3167,
1929
+ "step": 164
1930
+ },
1931
+ {
1932
+ "epoch": 0.14601769911504425,
1933
+ "grad_norm": 14.934159278869629,
1934
+ "learning_rate": 5.695754716981132e-07,
1935
+ "loss": 3.6345,
1936
+ "step": 165
1937
+ },
1938
+ {
1939
+ "epoch": 0.14690265486725665,
1940
+ "grad_norm": 12.897971153259277,
1941
+ "learning_rate": 5.731132075471699e-07,
1942
+ "loss": 2.462,
1943
+ "step": 166
1944
+ },
1945
+ {
1946
+ "epoch": 0.14778761061946902,
1947
+ "grad_norm": 9.75023365020752,
1948
+ "learning_rate": 5.766509433962264e-07,
1949
+ "loss": 1.4742,
1950
+ "step": 167
1951
+ },
1952
+ {
1953
+ "epoch": 0.1486725663716814,
1954
+ "grad_norm": 19.08034324645996,
1955
+ "learning_rate": 5.80188679245283e-07,
1956
+ "loss": 4.7312,
1957
+ "step": 168
1958
+ },
1959
+ {
1960
+ "epoch": 0.1495575221238938,
1961
+ "grad_norm": 11.19345760345459,
1962
+ "learning_rate": 5.837264150943396e-07,
1963
+ "loss": 2.6785,
1964
+ "step": 169
1965
+ },
1966
+ {
1967
+ "epoch": 0.1504424778761062,
1968
+ "grad_norm": 15.673795700073242,
1969
+ "learning_rate": 5.872641509433962e-07,
1970
+ "loss": 3.449,
1971
+ "step": 170
1972
+ },
1973
+ {
1974
+ "epoch": 0.15132743362831858,
1975
+ "grad_norm": 13.0908842086792,
1976
+ "learning_rate": 5.908018867924529e-07,
1977
+ "loss": 2.437,
1978
+ "step": 171
1979
+ },
1980
+ {
1981
+ "epoch": 0.15221238938053097,
1982
+ "grad_norm": 18.692623138427734,
1983
+ "learning_rate": 5.943396226415095e-07,
1984
+ "loss": 4.2431,
1985
+ "step": 172
1986
+ },
1987
+ {
1988
+ "epoch": 0.15309734513274337,
1989
+ "grad_norm": 18.569456100463867,
1990
+ "learning_rate": 5.978773584905661e-07,
1991
+ "loss": 4.4848,
1992
+ "step": 173
1993
+ },
1994
+ {
1995
+ "epoch": 0.15398230088495576,
1996
+ "grad_norm": 13.657751083374023,
1997
+ "learning_rate": 6.014150943396227e-07,
1998
+ "loss": 2.5575,
1999
+ "step": 174
2000
+ },
2001
+ {
2002
+ "epoch": 0.15486725663716813,
2003
+ "grad_norm": 13.810693740844727,
2004
+ "learning_rate": 6.049528301886793e-07,
2005
+ "loss": 2.3798,
2006
+ "step": 175
2007
+ },
2008
+ {
2009
+ "epoch": 0.15575221238938053,
2010
+ "grad_norm": 19.44959831237793,
2011
+ "learning_rate": 6.084905660377359e-07,
2012
+ "loss": 4.4939,
2013
+ "step": 176
2014
+ },
2015
+ {
2016
+ "epoch": 0.15663716814159293,
2017
+ "grad_norm": 18.276161193847656,
2018
+ "learning_rate": 6.120283018867924e-07,
2019
+ "loss": 4.1285,
2020
+ "step": 177
2021
+ },
2022
+ {
2023
+ "epoch": 0.15752212389380532,
2024
+ "grad_norm": 12.755691528320312,
2025
+ "learning_rate": 6.155660377358491e-07,
2026
+ "loss": 3.0096,
2027
+ "step": 178
2028
+ },
2029
+ {
2030
+ "epoch": 0.1584070796460177,
2031
+ "grad_norm": 17.114940643310547,
2032
+ "learning_rate": 6.191037735849056e-07,
2033
+ "loss": 4.4431,
2034
+ "step": 179
2035
+ },
2036
+ {
2037
+ "epoch": 0.1592920353982301,
2038
+ "grad_norm": 16.182861328125,
2039
+ "learning_rate": 6.226415094339623e-07,
2040
+ "loss": 3.1172,
2041
+ "step": 180
2042
+ },
2043
+ {
2044
+ "epoch": 0.16017699115044248,
2045
+ "grad_norm": 11.372871398925781,
2046
+ "learning_rate": 6.261792452830188e-07,
2047
+ "loss": 2.3576,
2048
+ "step": 181
2049
+ },
2050
+ {
2051
+ "epoch": 0.16106194690265488,
2052
+ "grad_norm": 15.957989692687988,
2053
+ "learning_rate": 6.297169811320755e-07,
2054
+ "loss": 3.7849,
2055
+ "step": 182
2056
+ },
2057
+ {
2058
+ "epoch": 0.16194690265486725,
2059
+ "grad_norm": 16.545942306518555,
2060
+ "learning_rate": 6.332547169811321e-07,
2061
+ "loss": 3.679,
2062
+ "step": 183
2063
+ },
2064
+ {
2065
+ "epoch": 0.16283185840707964,
2066
+ "grad_norm": 12.20029354095459,
2067
+ "learning_rate": 6.367924528301888e-07,
2068
+ "loss": 3.1949,
2069
+ "step": 184
2070
+ },
2071
+ {
2072
+ "epoch": 0.16371681415929204,
2073
+ "grad_norm": 12.985442161560059,
2074
+ "learning_rate": 6.403301886792453e-07,
2075
+ "loss": 3.2422,
2076
+ "step": 185
2077
+ },
2078
+ {
2079
+ "epoch": 0.16460176991150444,
2080
+ "grad_norm": 16.652189254760742,
2081
+ "learning_rate": 6.43867924528302e-07,
2082
+ "loss": 2.9905,
2083
+ "step": 186
2084
+ },
2085
+ {
2086
+ "epoch": 0.1654867256637168,
2087
+ "grad_norm": 13.374595642089844,
2088
+ "learning_rate": 6.474056603773585e-07,
2089
+ "loss": 2.2697,
2090
+ "step": 187
2091
+ },
2092
+ {
2093
+ "epoch": 0.1663716814159292,
2094
+ "grad_norm": 13.449297904968262,
2095
+ "learning_rate": 6.509433962264152e-07,
2096
+ "loss": 1.7685,
2097
+ "step": 188
2098
+ },
2099
+ {
2100
+ "epoch": 0.1672566371681416,
2101
+ "grad_norm": 11.019112586975098,
2102
+ "learning_rate": 6.544811320754717e-07,
2103
+ "loss": 2.0971,
2104
+ "step": 189
2105
+ },
2106
+ {
2107
+ "epoch": 0.168141592920354,
2108
+ "grad_norm": 14.534268379211426,
2109
+ "learning_rate": 6.580188679245283e-07,
2110
+ "loss": 3.4689,
2111
+ "step": 190
2112
+ },
2113
+ {
2114
+ "epoch": 0.16902654867256636,
2115
+ "grad_norm": 10.543577194213867,
2116
+ "learning_rate": 6.615566037735849e-07,
2117
+ "loss": 1.6614,
2118
+ "step": 191
2119
+ },
2120
+ {
2121
+ "epoch": 0.16991150442477876,
2122
+ "grad_norm": 11.60018539428711,
2123
+ "learning_rate": 6.650943396226415e-07,
2124
+ "loss": 1.9574,
2125
+ "step": 192
2126
+ },
2127
+ {
2128
+ "epoch": 0.17079646017699116,
2129
+ "grad_norm": 12.020721435546875,
2130
+ "learning_rate": 6.686320754716981e-07,
2131
+ "loss": 1.9313,
2132
+ "step": 193
2133
+ },
2134
+ {
2135
+ "epoch": 0.17168141592920355,
2136
+ "grad_norm": 13.000722885131836,
2137
+ "learning_rate": 6.721698113207547e-07,
2138
+ "loss": 2.2316,
2139
+ "step": 194
2140
+ },
2141
+ {
2142
+ "epoch": 0.17256637168141592,
2143
+ "grad_norm": 14.97183609008789,
2144
+ "learning_rate": 6.757075471698113e-07,
2145
+ "loss": 1.9854,
2146
+ "step": 195
2147
+ },
2148
+ {
2149
+ "epoch": 0.17345132743362832,
2150
+ "grad_norm": 13.239171028137207,
2151
+ "learning_rate": 6.792452830188679e-07,
2152
+ "loss": 2.8428,
2153
+ "step": 196
2154
+ },
2155
+ {
2156
+ "epoch": 0.1743362831858407,
2157
+ "grad_norm": 14.02790355682373,
2158
+ "learning_rate": 6.827830188679246e-07,
2159
+ "loss": 2.6916,
2160
+ "step": 197
2161
+ },
2162
+ {
2163
+ "epoch": 0.1752212389380531,
2164
+ "grad_norm": 19.518878936767578,
2165
+ "learning_rate": 6.863207547169812e-07,
2166
+ "loss": 3.5193,
2167
+ "step": 198
2168
+ },
2169
+ {
2170
+ "epoch": 0.17610619469026548,
2171
+ "grad_norm": 13.07220458984375,
2172
+ "learning_rate": 6.898584905660377e-07,
2173
+ "loss": 3.1681,
2174
+ "step": 199
2175
+ },
2176
+ {
2177
+ "epoch": 0.17699115044247787,
2178
+ "grad_norm": 17.351106643676758,
2179
+ "learning_rate": 6.933962264150944e-07,
2180
+ "loss": 2.7377,
2181
+ "step": 200
2182
+ },
2183
+ {
2184
+ "epoch": 0.17699115044247787,
2185
+ "eval_Qnli-dev_cosine_accuracy": 0.654296875,
2186
+ "eval_Qnli-dev_cosine_accuracy_threshold": 0.8833130598068237,
2187
+ "eval_Qnli-dev_cosine_ap": 0.6580270250237132,
2188
+ "eval_Qnli-dev_cosine_f1": 0.6530014641288434,
2189
+ "eval_Qnli-dev_cosine_f1_threshold": 0.7697122097015381,
2190
+ "eval_Qnli-dev_cosine_precision": 0.4988814317673378,
2191
+ "eval_Qnli-dev_cosine_recall": 0.9449152542372882,
2192
+ "eval_Qnli-dev_dot_accuracy": 0.654296875,
2193
+ "eval_Qnli-dev_dot_accuracy_threshold": 678.5490112304688,
2194
+ "eval_Qnli-dev_dot_ap": 0.6575507232408317,
2195
+ "eval_Qnli-dev_dot_f1": 0.6530014641288434,
2196
+ "eval_Qnli-dev_dot_f1_threshold": 591.318115234375,
2197
+ "eval_Qnli-dev_dot_precision": 0.4988814317673378,
2198
+ "eval_Qnli-dev_dot_recall": 0.9449152542372882,
2199
+ "eval_Qnli-dev_euclidean_accuracy": 0.654296875,
2200
+ "eval_Qnli-dev_euclidean_accuracy_threshold": 13.389348983764648,
2201
+ "eval_Qnli-dev_euclidean_ap": 0.6580673873885579,
2202
+ "eval_Qnli-dev_euclidean_f1": 0.6530014641288434,
2203
+ "eval_Qnli-dev_euclidean_f1_threshold": 18.810344696044922,
2204
+ "eval_Qnli-dev_euclidean_precision": 0.4988814317673378,
2205
+ "eval_Qnli-dev_euclidean_recall": 0.9449152542372882,
2206
+ "eval_Qnli-dev_manhattan_accuracy": 0.654296875,
2207
+ "eval_Qnli-dev_manhattan_accuracy_threshold": 261.8469543457031,
2208
+ "eval_Qnli-dev_manhattan_ap": 0.6702231337150942,
2209
+ "eval_Qnli-dev_manhattan_f1": 0.6515397082658022,
2210
+ "eval_Qnli-dev_manhattan_f1_threshold": 327.61407470703125,
2211
+ "eval_Qnli-dev_manhattan_precision": 0.5275590551181102,
2212
+ "eval_Qnli-dev_manhattan_recall": 0.8516949152542372,
2213
+ "eval_Qnli-dev_max_accuracy": 0.654296875,
2214
+ "eval_Qnli-dev_max_accuracy_threshold": 678.5490112304688,
2215
+ "eval_Qnli-dev_max_ap": 0.6702231337150942,
2216
+ "eval_Qnli-dev_max_f1": 0.6530014641288434,
2217
+ "eval_Qnli-dev_max_f1_threshold": 591.318115234375,
2218
+ "eval_Qnli-dev_max_precision": 0.5275590551181102,
2219
+ "eval_Qnli-dev_max_recall": 0.9449152542372882,
2220
+ "eval_allNLI-dev_cosine_accuracy": 0.66796875,
2221
+ "eval_allNLI-dev_cosine_accuracy_threshold": 0.9789057970046997,
2222
+ "eval_allNLI-dev_cosine_ap": 0.4149758651874867,
2223
+ "eval_allNLI-dev_cosine_f1": 0.5295404814004376,
2224
+ "eval_allNLI-dev_cosine_f1_threshold": 0.8845139741897583,
2225
+ "eval_allNLI-dev_cosine_precision": 0.426056338028169,
2226
+ "eval_allNLI-dev_cosine_recall": 0.6994219653179191,
2227
+ "eval_allNLI-dev_dot_accuracy": 0.66796875,
2228
+ "eval_allNLI-dev_dot_accuracy_threshold": 752.1302490234375,
2229
+ "eval_allNLI-dev_dot_ap": 0.4148843825453817,
2230
+ "eval_allNLI-dev_dot_f1": 0.5295404814004376,
2231
+ "eval_allNLI-dev_dot_f1_threshold": 679.59765625,
2232
+ "eval_allNLI-dev_dot_precision": 0.426056338028169,
2233
+ "eval_allNLI-dev_dot_recall": 0.6994219653179191,
2234
+ "eval_allNLI-dev_euclidean_accuracy": 0.66796875,
2235
+ "eval_allNLI-dev_euclidean_accuracy_threshold": 5.692765712738037,
2236
+ "eval_allNLI-dev_euclidean_ap": 0.4149715623944703,
2237
+ "eval_allNLI-dev_euclidean_f1": 0.5295404814004376,
2238
+ "eval_allNLI-dev_euclidean_f1_threshold": 13.321504592895508,
2239
+ "eval_allNLI-dev_euclidean_precision": 0.426056338028169,
2240
+ "eval_allNLI-dev_euclidean_recall": 0.6994219653179191,
2241
+ "eval_allNLI-dev_manhattan_accuracy": 0.66796875,
2242
+ "eval_allNLI-dev_manhattan_accuracy_threshold": 108.60708618164062,
2243
+ "eval_allNLI-dev_manhattan_ap": 0.4226938762919136,
2244
+ "eval_allNLI-dev_manhattan_f1": 0.5261261261261262,
2245
+ "eval_allNLI-dev_manhattan_f1_threshold": 292.82879638671875,
2246
+ "eval_allNLI-dev_manhattan_precision": 0.38219895287958117,
2247
+ "eval_allNLI-dev_manhattan_recall": 0.8439306358381503,
2248
+ "eval_allNLI-dev_max_accuracy": 0.66796875,
2249
+ "eval_allNLI-dev_max_accuracy_threshold": 752.1302490234375,
2250
+ "eval_allNLI-dev_max_ap": 0.4226938762919136,
2251
+ "eval_allNLI-dev_max_f1": 0.5295404814004376,
2252
+ "eval_allNLI-dev_max_f1_threshold": 679.59765625,
2253
+ "eval_allNLI-dev_max_precision": 0.426056338028169,
2254
+ "eval_allNLI-dev_max_recall": 0.8439306358381503,
2255
+ "eval_sequential_score": 0.6702231337150942,
2256
+ "eval_sts-test_pearson_cosine": 0.2940990176248945,
2257
+ "eval_sts-test_pearson_dot": 0.2937915867258836,
2258
+ "eval_sts-test_pearson_euclidean": 0.3181750373778839,
2259
+ "eval_sts-test_pearson_manhattan": 0.3345827566037396,
2260
+ "eval_sts-test_pearson_max": 0.3345827566037396,
2261
+ "eval_sts-test_spearman_cosine": 0.3520659969675645,
2262
+ "eval_sts-test_spearman_dot": 0.3519276260704351,
2263
+ "eval_sts-test_spearman_euclidean": 0.35206747375915737,
2264
+ "eval_sts-test_spearman_manhattan": 0.3786100728147803,
2265
+ "eval_sts-test_spearman_max": 0.3786100728147803,
2266
+ "eval_vitaminc-pairs_loss": 2.7042157649993896,
2267
+ "eval_vitaminc-pairs_runtime": 3.7507,
2268
+ "eval_vitaminc-pairs_samples_per_second": 34.127,
2269
+ "eval_vitaminc-pairs_steps_per_second": 0.267,
2270
+ "step": 200
2271
+ },
2272
+ {
2273
+ "epoch": 0.17699115044247787,
2274
+ "eval_negation-triplets_loss": 4.873472213745117,
2275
+ "eval_negation-triplets_runtime": 0.7086,
2276
+ "eval_negation-triplets_samples_per_second": 180.65,
2277
+ "eval_negation-triplets_steps_per_second": 1.411,
2278
+ "step": 200
2279
+ },
2280
+ {
2281
+ "epoch": 0.17699115044247787,
2282
+ "eval_scitail-pairs-pos_loss": 0.6427631974220276,
2283
+ "eval_scitail-pairs-pos_runtime": 0.8081,
2284
+ "eval_scitail-pairs-pos_samples_per_second": 158.403,
2285
+ "eval_scitail-pairs-pos_steps_per_second": 1.238,
2286
+ "step": 200
2287
+ },
2288
+ {
2289
+ "epoch": 0.17699115044247787,
2290
+ "eval_scitail-pairs-qa_loss": 0.6247898936271667,
2291
+ "eval_scitail-pairs-qa_runtime": 0.5409,
2292
+ "eval_scitail-pairs-qa_samples_per_second": 236.639,
2293
+ "eval_scitail-pairs-qa_steps_per_second": 1.849,
2294
+ "step": 200
2295
+ },
2296
+ {
2297
+ "epoch": 0.17699115044247787,
2298
+ "eval_xsum-pairs_loss": 4.36387300491333,
2299
+ "eval_xsum-pairs_runtime": 2.8937,
2300
+ "eval_xsum-pairs_samples_per_second": 44.234,
2301
+ "eval_xsum-pairs_steps_per_second": 0.346,
2302
+ "step": 200
2303
+ },
2304
+ {
2305
+ "epoch": 0.17699115044247787,
2306
+ "eval_sciq_pairs_loss": 0.47759732604026794,
2307
+ "eval_sciq_pairs_runtime": 3.7844,
2308
+ "eval_sciq_pairs_samples_per_second": 33.823,
2309
+ "eval_sciq_pairs_steps_per_second": 0.264,
2310
+ "step": 200
2311
+ },
2312
+ {
2313
+ "epoch": 0.17699115044247787,
2314
+ "eval_qasc_pairs_loss": 1.8949910402297974,
2315
+ "eval_qasc_pairs_runtime": 0.6749,
2316
+ "eval_qasc_pairs_samples_per_second": 189.661,
2317
+ "eval_qasc_pairs_steps_per_second": 1.482,
2318
+ "step": 200
2319
+ },
2320
+ {
2321
+ "epoch": 0.17699115044247787,
2322
+ "eval_openbookqa_pairs_loss": 3.398245334625244,
2323
+ "eval_openbookqa_pairs_runtime": 0.5848,
2324
+ "eval_openbookqa_pairs_samples_per_second": 218.88,
2325
+ "eval_openbookqa_pairs_steps_per_second": 1.71,
2326
+ "step": 200
2327
+ },
2328
+ {
2329
+ "epoch": 0.17699115044247787,
2330
+ "eval_msmarco_pairs_loss": 4.104819297790527,
2331
+ "eval_msmarco_pairs_runtime": 1.2633,
2332
+ "eval_msmarco_pairs_samples_per_second": 101.324,
2333
+ "eval_msmarco_pairs_steps_per_second": 0.792,
2334
+ "step": 200
2335
+ },
2336
+ {
2337
+ "epoch": 0.17699115044247787,
2338
+ "eval_nq_pairs_loss": 4.759064197540283,
2339
+ "eval_nq_pairs_runtime": 2.5126,
2340
+ "eval_nq_pairs_samples_per_second": 50.943,
2341
+ "eval_nq_pairs_steps_per_second": 0.398,
2342
+ "step": 200
2343
+ },
2344
+ {
2345
+ "epoch": 0.17699115044247787,
2346
+ "eval_trivia_pairs_loss": 4.4567718505859375,
2347
+ "eval_trivia_pairs_runtime": 3.6274,
2348
+ "eval_trivia_pairs_samples_per_second": 35.287,
2349
+ "eval_trivia_pairs_steps_per_second": 0.276,
2350
+ "step": 200
2351
+ },
2352
+ {
2353
+ "epoch": 0.17699115044247787,
2354
+ "eval_gooaq_pairs_loss": 4.16129207611084,
2355
+ "eval_gooaq_pairs_runtime": 0.9594,
2356
+ "eval_gooaq_pairs_samples_per_second": 133.413,
2357
+ "eval_gooaq_pairs_steps_per_second": 1.042,
2358
+ "step": 200
2359
+ },
2360
+ {
2361
+ "epoch": 0.17699115044247787,
2362
+ "eval_paws-pos_loss": 0.18016286194324493,
2363
+ "eval_paws-pos_runtime": 0.6707,
2364
+ "eval_paws-pos_samples_per_second": 190.836,
2365
+ "eval_paws-pos_steps_per_second": 1.491,
2366
+ "step": 200
2367
+ },
2368
+ {
2369
+ "epoch": 0.17699115044247787,
2370
+ "eval_global_dataset_loss": 2.4958598613739014,
2371
+ "eval_global_dataset_runtime": 23.0263,
2372
+ "eval_global_dataset_samples_per_second": 28.793,
2373
+ "eval_global_dataset_steps_per_second": 0.261,
2374
+ "step": 200
2375
+ },
2376
+ {
2377
+ "epoch": 0.17787610619469027,
2378
+ "grad_norm": 11.437249183654785,
2379
+ "learning_rate": 6.969339622641509e-07,
2380
+ "loss": 1.6408,
2381
+ "step": 201
2382
+ },
2383
+ {
2384
+ "epoch": 0.17876106194690267,
2385
+ "grad_norm": 11.460991859436035,
2386
+ "learning_rate": 7.004716981132076e-07,
2387
+ "loss": 2.3864,
2388
+ "step": 202
2389
+ },
2390
+ {
2391
+ "epoch": 0.17964601769911503,
2392
+ "grad_norm": 11.440958976745605,
2393
+ "learning_rate": 7.040094339622641e-07,
2394
+ "loss": 2.0848,
2395
+ "step": 203
2396
+ },
2397
+ {
2398
+ "epoch": 0.18053097345132743,
2399
+ "grad_norm": 14.584334373474121,
2400
+ "learning_rate": 7.075471698113208e-07,
2401
+ "loss": 2.9074,
2402
+ "step": 204
2403
+ },
2404
+ {
2405
+ "epoch": 0.18141592920353983,
2406
+ "grad_norm": 13.474750518798828,
2407
+ "learning_rate": 7.110849056603773e-07,
2408
+ "loss": 2.542,
2409
+ "step": 205
2410
+ },
2411
+ {
2412
+ "epoch": 0.18230088495575222,
2413
+ "grad_norm": 11.853781700134277,
2414
+ "learning_rate": 7.14622641509434e-07,
2415
+ "loss": 1.7312,
2416
+ "step": 206
2417
+ },
2418
+ {
2419
+ "epoch": 0.1831858407079646,
2420
+ "grad_norm": 12.289971351623535,
2421
+ "learning_rate": 7.181603773584905e-07,
2422
+ "loss": 1.6768,
2423
+ "step": 207
2424
+ },
2425
+ {
2426
+ "epoch": 0.184070796460177,
2427
+ "grad_norm": 16.296539306640625,
2428
+ "learning_rate": 7.216981132075472e-07,
2429
+ "loss": 2.531,
2430
+ "step": 208
2431
+ },
2432
+ {
2433
+ "epoch": 0.18495575221238938,
2434
+ "grad_norm": 17.131324768066406,
2435
+ "learning_rate": 7.252358490566038e-07,
2436
+ "loss": 2.9222,
2437
+ "step": 209
2438
+ },
2439
+ {
2440
+ "epoch": 0.18584070796460178,
2441
+ "grad_norm": 12.739492416381836,
2442
+ "learning_rate": 7.287735849056604e-07,
2443
+ "loss": 2.4152,
2444
+ "step": 210
2445
+ },
2446
+ {
2447
+ "epoch": 0.18672566371681415,
2448
+ "grad_norm": 10.511398315429688,
2449
+ "learning_rate": 7.32311320754717e-07,
2450
+ "loss": 1.4345,
2451
+ "step": 211
2452
+ },
2453
+ {
2454
+ "epoch": 0.18761061946902655,
2455
+ "grad_norm": 12.478878021240234,
2456
+ "learning_rate": 7.358490566037736e-07,
2457
+ "loss": 1.5864,
2458
+ "step": 212
2459
+ },
2460
+ {
2461
+ "epoch": 0.18849557522123894,
2462
+ "grad_norm": 10.100104331970215,
2463
+ "learning_rate": 7.393867924528302e-07,
2464
+ "loss": 1.272,
2465
+ "step": 213
2466
+ },
2467
+ {
2468
+ "epoch": 0.18938053097345134,
2469
+ "grad_norm": 10.771380424499512,
2470
+ "learning_rate": 7.429245283018868e-07,
2471
+ "loss": 1.7011,
2472
+ "step": 214
2473
+ },
2474
+ {
2475
+ "epoch": 0.1902654867256637,
2476
+ "grad_norm": 15.291692733764648,
2477
+ "learning_rate": 7.464622641509434e-07,
2478
+ "loss": 3.0076,
2479
+ "step": 215
2480
+ },
2481
+ {
2482
+ "epoch": 0.1911504424778761,
2483
+ "grad_norm": 15.702594757080078,
2484
+ "learning_rate": 7.5e-07,
2485
+ "loss": 2.468,
2486
+ "step": 216
2487
+ },
2488
+ {
2489
+ "epoch": 0.1920353982300885,
2490
+ "grad_norm": 14.604419708251953,
2491
+ "learning_rate": 7.535377358490567e-07,
2492
+ "loss": 2.0796,
2493
+ "step": 217
2494
+ },
2495
+ {
2496
+ "epoch": 0.1929203539823009,
2497
+ "grad_norm": 18.808080673217773,
2498
+ "learning_rate": 7.570754716981133e-07,
2499
+ "loss": 2.9735,
2500
+ "step": 218
2501
+ },
2502
+ {
2503
+ "epoch": 0.19380530973451326,
2504
+ "grad_norm": 15.642558097839355,
2505
+ "learning_rate": 7.606132075471698e-07,
2506
+ "loss": 2.5506,
2507
+ "step": 219
2508
+ },
2509
+ {
2510
+ "epoch": 0.19469026548672566,
2511
+ "grad_norm": 11.20150089263916,
2512
+ "learning_rate": 7.641509433962264e-07,
2513
+ "loss": 1.7307,
2514
+ "step": 220
2515
+ },
2516
+ {
2517
+ "epoch": 0.19557522123893806,
2518
+ "grad_norm": 11.246394157409668,
2519
+ "learning_rate": 7.67688679245283e-07,
2520
+ "loss": 1.4519,
2521
+ "step": 221
2522
+ },
2523
+ {
2524
+ "epoch": 0.19646017699115045,
2525
+ "grad_norm": 11.744650840759277,
2526
+ "learning_rate": 7.712264150943397e-07,
2527
+ "loss": 1.7292,
2528
+ "step": 222
2529
+ },
2530
+ {
2531
+ "epoch": 0.19734513274336282,
2532
+ "grad_norm": 11.411338806152344,
2533
+ "learning_rate": 7.747641509433962e-07,
2534
+ "loss": 1.4664,
2535
+ "step": 223
2536
+ },
2537
+ {
2538
+ "epoch": 0.19823008849557522,
2539
+ "grad_norm": 12.0331392288208,
2540
+ "learning_rate": 7.783018867924529e-07,
2541
+ "loss": 1.6201,
2542
+ "step": 224
2543
+ },
2544
+ {
2545
+ "epoch": 0.19911504424778761,
2546
+ "grad_norm": 15.52979564666748,
2547
+ "learning_rate": 7.818396226415095e-07,
2548
+ "loss": 2.3483,
2549
+ "step": 225
2550
+ },
2551
+ {
2552
+ "epoch": 0.2,
2553
+ "grad_norm": 12.872408866882324,
2554
+ "learning_rate": 7.853773584905662e-07,
2555
+ "loss": 2.1311,
2556
+ "step": 226
2557
+ },
2558
+ {
2559
+ "epoch": 0.20088495575221238,
2560
+ "grad_norm": 15.520133018493652,
2561
+ "learning_rate": 7.889150943396226e-07,
2562
+ "loss": 2.3272,
2563
+ "step": 227
2564
+ },
2565
+ {
2566
+ "epoch": 0.20176991150442478,
2567
+ "grad_norm": 14.214468955993652,
2568
+ "learning_rate": 7.924528301886793e-07,
2569
+ "loss": 2.6164,
2570
+ "step": 228
2571
+ },
2572
+ {
2573
+ "epoch": 0.20265486725663717,
2574
+ "grad_norm": 11.147010803222656,
2575
+ "learning_rate": 7.959905660377359e-07,
2576
+ "loss": 1.6261,
2577
+ "step": 229
2578
+ },
2579
+ {
2580
+ "epoch": 0.20353982300884957,
2581
+ "grad_norm": 14.623574256896973,
2582
+ "learning_rate": 7.995283018867926e-07,
2583
+ "loss": 2.5293,
2584
+ "step": 230
2585
+ },
2586
+ {
2587
+ "epoch": 0.20442477876106194,
2588
+ "grad_norm": 11.993956565856934,
2589
+ "learning_rate": 8.03066037735849e-07,
2590
+ "loss": 1.2885,
2591
+ "step": 231
2592
+ },
2593
+ {
2594
+ "epoch": 0.20530973451327433,
2595
+ "grad_norm": 17.700708389282227,
2596
+ "learning_rate": 8.066037735849056e-07,
2597
+ "loss": 2.0039,
2598
+ "step": 232
2599
+ },
2600
+ {
2601
+ "epoch": 0.20619469026548673,
2602
+ "grad_norm": 19.518352508544922,
2603
+ "learning_rate": 8.101415094339623e-07,
2604
+ "loss": 3.0003,
2605
+ "step": 233
2606
+ },
2607
+ {
2608
+ "epoch": 0.20707964601769913,
2609
+ "grad_norm": 12.744159698486328,
2610
+ "learning_rate": 8.136792452830189e-07,
2611
+ "loss": 2.0491,
2612
+ "step": 234
2613
+ },
2614
+ {
2615
+ "epoch": 0.2079646017699115,
2616
+ "grad_norm": 11.839001655578613,
2617
+ "learning_rate": 8.172169811320755e-07,
2618
+ "loss": 2.0178,
2619
+ "step": 235
2620
+ },
2621
+ {
2622
+ "epoch": 0.2088495575221239,
2623
+ "grad_norm": 15.795985221862793,
2624
+ "learning_rate": 8.207547169811321e-07,
2625
+ "loss": 1.8532,
2626
+ "step": 236
2627
+ },
2628
+ {
2629
+ "epoch": 0.2097345132743363,
2630
+ "grad_norm": 14.999555587768555,
2631
+ "learning_rate": 8.242924528301888e-07,
2632
+ "loss": 2.3614,
2633
+ "step": 237
2634
+ },
2635
+ {
2636
+ "epoch": 0.21061946902654868,
2637
+ "grad_norm": 10.802149772644043,
2638
+ "learning_rate": 8.278301886792453e-07,
2639
+ "loss": 1.1889,
2640
+ "step": 238
2641
+ },
2642
+ {
2643
+ "epoch": 0.21150442477876105,
2644
+ "grad_norm": 12.038461685180664,
2645
+ "learning_rate": 8.313679245283019e-07,
2646
+ "loss": 1.4833,
2647
+ "step": 239
2648
+ },
2649
+ {
2650
+ "epoch": 0.21238938053097345,
2651
+ "grad_norm": 17.69329071044922,
2652
+ "learning_rate": 8.349056603773585e-07,
2653
+ "loss": 2.8687,
2654
+ "step": 240
2655
+ },
2656
+ {
2657
+ "epoch": 0.21238938053097345,
2658
+ "eval_Qnli-dev_cosine_accuracy": 0.66015625,
2659
+ "eval_Qnli-dev_cosine_accuracy_threshold": 0.8744948506355286,
2660
+ "eval_Qnli-dev_cosine_ap": 0.6610633478265061,
2661
+ "eval_Qnli-dev_cosine_f1": 0.6646433990895295,
2662
+ "eval_Qnli-dev_cosine_f1_threshold": 0.753309965133667,
2663
+ "eval_Qnli-dev_cosine_precision": 0.5177304964539007,
2664
+ "eval_Qnli-dev_cosine_recall": 0.9279661016949152,
2665
+ "eval_Qnli-dev_dot_accuracy": 0.66015625,
2666
+ "eval_Qnli-dev_dot_accuracy_threshold": 670.719970703125,
2667
+ "eval_Qnli-dev_dot_ap": 0.6607472505349153,
2668
+ "eval_Qnli-dev_dot_f1": 0.6646433990895295,
2669
+ "eval_Qnli-dev_dot_f1_threshold": 578.874755859375,
2670
+ "eval_Qnli-dev_dot_precision": 0.5177304964539007,
2671
+ "eval_Qnli-dev_dot_recall": 0.9279661016949152,
2672
+ "eval_Qnli-dev_euclidean_accuracy": 0.66015625,
2673
+ "eval_Qnli-dev_euclidean_accuracy_threshold": 13.881525039672852,
2674
+ "eval_Qnli-dev_euclidean_ap": 0.6611053426809266,
2675
+ "eval_Qnli-dev_euclidean_f1": 0.6646433990895295,
2676
+ "eval_Qnli-dev_euclidean_f1_threshold": 19.471359252929688,
2677
+ "eval_Qnli-dev_euclidean_precision": 0.5177304964539007,
2678
+ "eval_Qnli-dev_euclidean_recall": 0.9279661016949152,
2679
+ "eval_Qnli-dev_manhattan_accuracy": 0.666015625,
2680
+ "eval_Qnli-dev_manhattan_accuracy_threshold": 281.9825134277344,
2681
+ "eval_Qnli-dev_manhattan_ap": 0.6664006509577655,
2682
+ "eval_Qnli-dev_manhattan_f1": 0.6678899082568808,
2683
+ "eval_Qnli-dev_manhattan_f1_threshold": 328.83447265625,
2684
+ "eval_Qnli-dev_manhattan_precision": 0.5889967637540453,
2685
+ "eval_Qnli-dev_manhattan_recall": 0.7711864406779662,
2686
+ "eval_Qnli-dev_max_accuracy": 0.666015625,
2687
+ "eval_Qnli-dev_max_accuracy_threshold": 670.719970703125,
2688
+ "eval_Qnli-dev_max_ap": 0.6664006509577655,
2689
+ "eval_Qnli-dev_max_f1": 0.6678899082568808,
2690
+ "eval_Qnli-dev_max_f1_threshold": 578.874755859375,
2691
+ "eval_Qnli-dev_max_precision": 0.5889967637540453,
2692
+ "eval_Qnli-dev_max_recall": 0.9279661016949152,
2693
+ "eval_allNLI-dev_cosine_accuracy": 0.66796875,
2694
+ "eval_allNLI-dev_cosine_accuracy_threshold": 0.9727417230606079,
2695
+ "eval_allNLI-dev_cosine_ap": 0.4443750308487611,
2696
+ "eval_allNLI-dev_cosine_f1": 0.5338983050847458,
2697
+ "eval_allNLI-dev_cosine_f1_threshold": 0.8509687781333923,
2698
+ "eval_allNLI-dev_cosine_precision": 0.4214046822742475,
2699
+ "eval_allNLI-dev_cosine_recall": 0.7283236994219653,
2700
+ "eval_allNLI-dev_dot_accuracy": 0.66796875,
2701
+ "eval_allNLI-dev_dot_accuracy_threshold": 747.4664916992188,
2702
+ "eval_allNLI-dev_dot_ap": 0.4447331164315086,
2703
+ "eval_allNLI-dev_dot_f1": 0.5347368421052632,
2704
+ "eval_allNLI-dev_dot_f1_threshold": 652.6121826171875,
2705
+ "eval_allNLI-dev_dot_precision": 0.4205298013245033,
2706
+ "eval_allNLI-dev_dot_recall": 0.7341040462427746,
2707
+ "eval_allNLI-dev_euclidean_accuracy": 0.66796875,
2708
+ "eval_allNLI-dev_euclidean_accuracy_threshold": 6.472302436828613,
2709
+ "eval_allNLI-dev_euclidean_ap": 0.44436910603457025,
2710
+ "eval_allNLI-dev_euclidean_f1": 0.5338983050847458,
2711
+ "eval_allNLI-dev_euclidean_f1_threshold": 15.134000778198242,
2712
+ "eval_allNLI-dev_euclidean_precision": 0.4214046822742475,
2713
+ "eval_allNLI-dev_euclidean_recall": 0.7283236994219653,
2714
+ "eval_allNLI-dev_manhattan_accuracy": 0.673828125,
2715
+ "eval_allNLI-dev_manhattan_accuracy_threshold": 185.35494995117188,
2716
+ "eval_allNLI-dev_manhattan_ap": 0.45330636568192945,
2717
+ "eval_allNLI-dev_manhattan_f1": 0.5340909090909091,
2718
+ "eval_allNLI-dev_manhattan_f1_threshold": 316.48419189453125,
2719
+ "eval_allNLI-dev_manhattan_precision": 0.3971830985915493,
2720
+ "eval_allNLI-dev_manhattan_recall": 0.815028901734104,
2721
+ "eval_allNLI-dev_max_accuracy": 0.673828125,
2722
+ "eval_allNLI-dev_max_accuracy_threshold": 747.4664916992188,
2723
+ "eval_allNLI-dev_max_ap": 0.45330636568192945,
2724
+ "eval_allNLI-dev_max_f1": 0.5347368421052632,
2725
+ "eval_allNLI-dev_max_f1_threshold": 652.6121826171875,
2726
+ "eval_allNLI-dev_max_precision": 0.4214046822742475,
2727
+ "eval_allNLI-dev_max_recall": 0.815028901734104,
2728
+ "eval_sequential_score": 0.6664006509577655,
2729
+ "eval_sts-test_pearson_cosine": 0.3977846210139704,
2730
+ "eval_sts-test_pearson_dot": 0.3974381713503513,
2731
+ "eval_sts-test_pearson_euclidean": 0.42060129087924125,
2732
+ "eval_sts-test_pearson_manhattan": 0.43174431600737306,
2733
+ "eval_sts-test_pearson_max": 0.43174431600737306,
2734
+ "eval_sts-test_spearman_cosine": 0.44299644096637864,
2735
+ "eval_sts-test_spearman_dot": 0.4426330607320026,
2736
+ "eval_sts-test_spearman_euclidean": 0.44300328790921845,
2737
+ "eval_sts-test_spearman_manhattan": 0.4553695033739603,
2738
+ "eval_sts-test_spearman_max": 0.4553695033739603,
2739
+ "eval_vitaminc-pairs_loss": 2.721532106399536,
2740
+ "eval_vitaminc-pairs_runtime": 3.756,
2741
+ "eval_vitaminc-pairs_samples_per_second": 34.079,
2742
+ "eval_vitaminc-pairs_steps_per_second": 0.266,
2743
+ "step": 240
2744
+ },
2745
+ {
2746
+ "epoch": 0.21238938053097345,
2747
+ "eval_negation-triplets_loss": 4.154361248016357,
2748
+ "eval_negation-triplets_runtime": 0.7084,
2749
+ "eval_negation-triplets_samples_per_second": 180.694,
2750
+ "eval_negation-triplets_steps_per_second": 1.412,
2751
+ "step": 240
2752
+ },
2753
+ {
2754
+ "epoch": 0.21238938053097345,
2755
+ "eval_scitail-pairs-pos_loss": 0.4166124761104584,
2756
+ "eval_scitail-pairs-pos_runtime": 0.8374,
2757
+ "eval_scitail-pairs-pos_samples_per_second": 152.85,
2758
+ "eval_scitail-pairs-pos_steps_per_second": 1.194,
2759
+ "step": 240
2760
+ },
2761
+ {
2762
+ "epoch": 0.21238938053097345,
2763
+ "eval_scitail-pairs-qa_loss": 0.3875552713871002,
2764
+ "eval_scitail-pairs-qa_runtime": 0.5637,
2765
+ "eval_scitail-pairs-qa_samples_per_second": 227.065,
2766
+ "eval_scitail-pairs-qa_steps_per_second": 1.774,
2767
+ "step": 240
2768
+ },
2769
+ {
2770
+ "epoch": 0.21238938053097345,
2771
+ "eval_xsum-pairs_loss": 3.315666437149048,
2772
+ "eval_xsum-pairs_runtime": 2.9088,
2773
+ "eval_xsum-pairs_samples_per_second": 44.004,
2774
+ "eval_xsum-pairs_steps_per_second": 0.344,
2775
+ "step": 240
2776
+ },
2777
+ {
2778
+ "epoch": 0.21238938053097345,
2779
+ "eval_sciq_pairs_loss": 0.37107861042022705,
2780
+ "eval_sciq_pairs_runtime": 3.7824,
2781
+ "eval_sciq_pairs_samples_per_second": 33.841,
2782
+ "eval_sciq_pairs_steps_per_second": 0.264,
2783
+ "step": 240
2784
+ },
2785
+ {
2786
+ "epoch": 0.21238938053097345,
2787
+ "eval_qasc_pairs_loss": 1.4818006753921509,
2788
+ "eval_qasc_pairs_runtime": 0.6698,
2789
+ "eval_qasc_pairs_samples_per_second": 191.109,
2790
+ "eval_qasc_pairs_steps_per_second": 1.493,
2791
+ "step": 240
2792
+ },
2793
+ {
2794
+ "epoch": 0.21238938053097345,
2795
+ "eval_openbookqa_pairs_loss": 2.693885564804077,
2796
+ "eval_openbookqa_pairs_runtime": 0.5747,
2797
+ "eval_openbookqa_pairs_samples_per_second": 222.725,
2798
+ "eval_openbookqa_pairs_steps_per_second": 1.74,
2799
+ "step": 240
2800
+ },
2801
+ {
2802
+ "epoch": 0.21238938053097345,
2803
+ "eval_msmarco_pairs_loss": 3.245403528213501,
2804
+ "eval_msmarco_pairs_runtime": 1.2573,
2805
+ "eval_msmarco_pairs_samples_per_second": 101.804,
2806
+ "eval_msmarco_pairs_steps_per_second": 0.795,
2807
+ "step": 240
2808
+ },
2809
+ {
2810
+ "epoch": 0.21238938053097345,
2811
+ "eval_nq_pairs_loss": 3.979779005050659,
2812
+ "eval_nq_pairs_runtime": 2.5086,
2813
+ "eval_nq_pairs_samples_per_second": 51.025,
2814
+ "eval_nq_pairs_steps_per_second": 0.399,
2815
+ "step": 240
2816
+ },
2817
+ {
2818
+ "epoch": 0.21238938053097345,
2819
+ "eval_trivia_pairs_loss": 3.594862937927246,
2820
+ "eval_trivia_pairs_runtime": 3.6534,
2821
+ "eval_trivia_pairs_samples_per_second": 35.036,
2822
+ "eval_trivia_pairs_steps_per_second": 0.274,
2823
+ "step": 240
2824
+ },
2825
+ {
2826
+ "epoch": 0.21238938053097345,
2827
+ "eval_gooaq_pairs_loss": 3.226611852645874,
2828
+ "eval_gooaq_pairs_runtime": 1.0202,
2829
+ "eval_gooaq_pairs_samples_per_second": 125.465,
2830
+ "eval_gooaq_pairs_steps_per_second": 0.98,
2831
+ "step": 240
2832
+ },
2833
+ {
2834
+ "epoch": 0.21238938053097345,
2835
+ "eval_paws-pos_loss": 0.12748712301254272,
2836
+ "eval_paws-pos_runtime": 0.6844,
2837
+ "eval_paws-pos_samples_per_second": 187.034,
2838
+ "eval_paws-pos_steps_per_second": 1.461,
2839
+ "step": 240
2840
+ },
2841
+ {
2842
+ "epoch": 0.21238938053097345,
2843
+ "eval_global_dataset_loss": 1.8867173194885254,
2844
+ "eval_global_dataset_runtime": 23.0217,
2845
+ "eval_global_dataset_samples_per_second": 28.799,
2846
+ "eval_global_dataset_steps_per_second": 0.261,
2847
+ "step": 240
2848
+ }
2849
+ ],
2850
+ "logging_steps": 1,
2851
+ "max_steps": 3390,
2852
+ "num_input_tokens_seen": 0,
2853
+ "num_train_epochs": 3,
2854
+ "save_steps": 80,
2855
+ "stateful_callbacks": {
2856
+ "TrainerControl": {
2857
+ "args": {
2858
+ "should_epoch_stop": false,
2859
+ "should_evaluate": false,
2860
+ "should_log": false,
2861
+ "should_save": true,
2862
+ "should_training_stop": false
2863
+ },
2864
+ "attributes": {}
2865
+ }
2866
+ },
2867
+ "total_flos": 0.0,
2868
+ "train_batch_size": 42,
2869
+ "trial_name": null,
2870
+ "trial_params": null
2871
+ }
checkpoint-240/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bfb21b1a8b0022475cba81f0306eaa079a06c682d78c599327457cfd397d216
3
+ size 5688