Training in progress, step 3712, checkpoint
Browse files- checkpoint-3712/1_Pooling/config.json +10 -0
- checkpoint-3712/README.md +0 -0
- checkpoint-3712/added_tokens.json +3 -0
- checkpoint-3712/config.json +35 -0
- checkpoint-3712/config_sentence_transformers.json +10 -0
- checkpoint-3712/modules.json +14 -0
- checkpoint-3712/optimizer.pt +3 -0
- checkpoint-3712/pytorch_model.bin +3 -0
- checkpoint-3712/rng_state.pth +3 -0
- checkpoint-3712/scheduler.pt +3 -0
- checkpoint-3712/sentence_bert_config.json +4 -0
- checkpoint-3712/special_tokens_map.json +15 -0
- checkpoint-3712/spm.model +3 -0
- checkpoint-3712/tokenizer.json +0 -0
- checkpoint-3712/tokenizer_config.json +58 -0
- checkpoint-3712/trainer_state.json +1086 -0
- checkpoint-3712/training_args.bin +3 -0
checkpoint-3712/1_Pooling/config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 768,
|
3 |
+
"pooling_mode_cls_token": false,
|
4 |
+
"pooling_mode_mean_tokens": true,
|
5 |
+
"pooling_mode_max_tokens": false,
|
6 |
+
"pooling_mode_mean_sqrt_len_tokens": false,
|
7 |
+
"pooling_mode_weightedmean_tokens": false,
|
8 |
+
"pooling_mode_lasttoken": false,
|
9 |
+
"include_prompt": true
|
10 |
+
}
|
checkpoint-3712/README.md
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-3712/added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[MASK]": 128000
|
3 |
+
}
|
checkpoint-3712/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": "4.41.2",
|
33 |
+
"type_vocab_size": 0,
|
34 |
+
"vocab_size": 128100
|
35 |
+
}
|
checkpoint-3712/config_sentence_transformers.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "3.0.1",
|
4 |
+
"transformers": "4.41.2",
|
5 |
+
"pytorch": "2.1.2"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null,
|
9 |
+
"similarity_fn_name": null
|
10 |
+
}
|
checkpoint-3712/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_Pooling",
|
12 |
+
"type": "sentence_transformers.models.Pooling"
|
13 |
+
}
|
14 |
+
]
|
checkpoint-3712/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44754d8c1611de98f474ee27fc0265a60130ee99fcbd75e3e2701aed361df231
|
3 |
+
size 1130520122
|
checkpoint-3712/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49a7c3e3134321904d0bbc3b6996d58cbe0277ac7050014dc069ab1c84c4fbf0
|
3 |
+
size 565251810
|
checkpoint-3712/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5644c96b5b744e97f5fdafc674a08615e21baf82b06ff7ecd16de460c2d8f188
|
3 |
+
size 14180
|
checkpoint-3712/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a079dc3f9dbed3bacfa13a90ad5fa42d63ef03c8b95e15baf0b6069fd1214043
|
3 |
+
size 1064
|
checkpoint-3712/sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 512,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|
checkpoint-3712/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-3712/spm.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
3 |
+
size 2464616
|
checkpoint-3712/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-3712/tokenizer_config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "[CLS]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[SEP]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[UNK]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"128000": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "[CLS]",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "[CLS]",
|
47 |
+
"do_lower_case": false,
|
48 |
+
"eos_token": "[SEP]",
|
49 |
+
"mask_token": "[MASK]",
|
50 |
+
"model_max_length": 1000000000000000019884624838656,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"sp_model_kwargs": {},
|
54 |
+
"split_by_punct": false,
|
55 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
56 |
+
"unk_token": "[UNK]",
|
57 |
+
"vocab_type": "spm"
|
58 |
+
}
|
checkpoint-3712/trainer_state.json
ADDED
@@ -0,0 +1,1086 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.6000646621403168,
|
5 |
+
"eval_steps": 557,
|
6 |
+
"global_step": 3712,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.015033947623666343,
|
13 |
+
"grad_norm": 63.938453674316406,
|
14 |
+
"learning_rate": 4.741379310344828e-07,
|
15 |
+
"loss": 11.7791,
|
16 |
+
"step": 93
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.030067895247332686,
|
20 |
+
"grad_norm": 28.60324478149414,
|
21 |
+
"learning_rate": 9.752155172413793e-07,
|
22 |
+
"loss": 10.5226,
|
23 |
+
"step": 186
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.04510184287099903,
|
27 |
+
"grad_norm": 17.869054794311523,
|
28 |
+
"learning_rate": 1.476293103448276e-06,
|
29 |
+
"loss": 9.3586,
|
30 |
+
"step": 279
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.06013579049466537,
|
34 |
+
"grad_norm": 18.835189819335938,
|
35 |
+
"learning_rate": 1.977370689655172e-06,
|
36 |
+
"loss": 8.4548,
|
37 |
+
"step": 372
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.07516973811833172,
|
41 |
+
"grad_norm": 55.06333541870117,
|
42 |
+
"learning_rate": 2.4784482758620692e-06,
|
43 |
+
"loss": 8.3449,
|
44 |
+
"step": 465
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.09004203039120595,
|
48 |
+
"eval_nli-pairs_loss": 7.450161933898926,
|
49 |
+
"eval_nli-pairs_runtime": 14.8176,
|
50 |
+
"eval_nli-pairs_samples_per_second": 101.231,
|
51 |
+
"eval_nli-pairs_steps_per_second": 3.172,
|
52 |
+
"eval_sts-test_pearson_cosine": 0.3696416595298566,
|
53 |
+
"eval_sts-test_pearson_dot": 0.13300273461809956,
|
54 |
+
"eval_sts-test_pearson_euclidean": 0.3836877008752716,
|
55 |
+
"eval_sts-test_pearson_manhattan": 0.41477338080789633,
|
56 |
+
"eval_sts-test_pearson_max": 0.41477338080789633,
|
57 |
+
"eval_sts-test_spearman_cosine": 0.3694134524358256,
|
58 |
+
"eval_sts-test_spearman_dot": 0.12058818576425179,
|
59 |
+
"eval_sts-test_spearman_euclidean": 0.38615620458370276,
|
60 |
+
"eval_sts-test_spearman_manhattan": 0.4121304311152658,
|
61 |
+
"eval_sts-test_spearman_max": 0.4121304311152658,
|
62 |
+
"step": 557
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.09004203039120595,
|
66 |
+
"eval_vitaminc-pairs_loss": 5.403733730316162,
|
67 |
+
"eval_vitaminc-pairs_runtime": 14.4427,
|
68 |
+
"eval_vitaminc-pairs_samples_per_second": 69.17,
|
69 |
+
"eval_vitaminc-pairs_steps_per_second": 2.216,
|
70 |
+
"step": 557
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 0.09004203039120595,
|
74 |
+
"eval_qnli-contrastive_loss": 8.863805770874023,
|
75 |
+
"eval_qnli-contrastive_runtime": 4.835,
|
76 |
+
"eval_qnli-contrastive_samples_per_second": 310.238,
|
77 |
+
"eval_qnli-contrastive_steps_per_second": 9.721,
|
78 |
+
"step": 557
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 0.09004203039120595,
|
82 |
+
"eval_scitail-pairs-qa_loss": 4.2781147956848145,
|
83 |
+
"eval_scitail-pairs-qa_runtime": 5.761,
|
84 |
+
"eval_scitail-pairs-qa_samples_per_second": 130.186,
|
85 |
+
"eval_scitail-pairs-qa_steps_per_second": 4.166,
|
86 |
+
"step": 557
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.09004203039120595,
|
90 |
+
"eval_scitail-pairs-pos_loss": 4.930431365966797,
|
91 |
+
"eval_scitail-pairs-pos_runtime": 15.2161,
|
92 |
+
"eval_scitail-pairs-pos_samples_per_second": 85.699,
|
93 |
+
"eval_scitail-pairs-pos_steps_per_second": 2.695,
|
94 |
+
"step": 557
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.09004203039120595,
|
98 |
+
"eval_xsum-pairs_loss": 4.778657913208008,
|
99 |
+
"eval_xsum-pairs_runtime": 3.0397,
|
100 |
+
"eval_xsum-pairs_samples_per_second": 65.795,
|
101 |
+
"eval_xsum-pairs_steps_per_second": 2.303,
|
102 |
+
"step": 557
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"epoch": 0.09004203039120595,
|
106 |
+
"eval_compression-pairs_loss": 3.489774465560913,
|
107 |
+
"eval_compression-pairs_runtime": 1.2758,
|
108 |
+
"eval_compression-pairs_samples_per_second": 391.924,
|
109 |
+
"eval_compression-pairs_steps_per_second": 12.542,
|
110 |
+
"step": 557
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.09004203039120595,
|
114 |
+
"eval_sciq_pairs_loss": 7.707857131958008,
|
115 |
+
"eval_sciq_pairs_runtime": 28.932,
|
116 |
+
"eval_sciq_pairs_samples_per_second": 20.185,
|
117 |
+
"eval_sciq_pairs_steps_per_second": 0.657,
|
118 |
+
"step": 557
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 0.09004203039120595,
|
122 |
+
"eval_qasc_pairs_loss": 12.320230484008789,
|
123 |
+
"eval_qasc_pairs_runtime": 5.2561,
|
124 |
+
"eval_qasc_pairs_samples_per_second": 77.434,
|
125 |
+
"eval_qasc_pairs_steps_per_second": 2.473,
|
126 |
+
"step": 557
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 0.09004203039120595,
|
130 |
+
"eval_openbookqa_pairs_loss": 7.607065677642822,
|
131 |
+
"eval_openbookqa_pairs_runtime": 1.189,
|
132 |
+
"eval_openbookqa_pairs_samples_per_second": 115.224,
|
133 |
+
"eval_openbookqa_pairs_steps_per_second": 4.205,
|
134 |
+
"step": 557
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.09004203039120595,
|
138 |
+
"eval_msmarco_pairs_loss": 8.519609451293945,
|
139 |
+
"eval_msmarco_pairs_runtime": 19.7371,
|
140 |
+
"eval_msmarco_pairs_samples_per_second": 50.666,
|
141 |
+
"eval_msmarco_pairs_steps_per_second": 1.621,
|
142 |
+
"step": 557
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.09004203039120595,
|
146 |
+
"eval_nq_pairs_loss": 8.43966007232666,
|
147 |
+
"eval_nq_pairs_runtime": 37.2943,
|
148 |
+
"eval_nq_pairs_samples_per_second": 26.814,
|
149 |
+
"eval_nq_pairs_steps_per_second": 0.858,
|
150 |
+
"step": 557
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.09004203039120595,
|
154 |
+
"eval_trivia_pairs_loss": 8.689275741577148,
|
155 |
+
"eval_trivia_pairs_runtime": 64.6902,
|
156 |
+
"eval_trivia_pairs_samples_per_second": 15.458,
|
157 |
+
"eval_trivia_pairs_steps_per_second": 0.495,
|
158 |
+
"step": 557
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.09004203039120595,
|
162 |
+
"eval_quora_pairs_loss": 4.54755163192749,
|
163 |
+
"eval_quora_pairs_runtime": 3.7394,
|
164 |
+
"eval_quora_pairs_samples_per_second": 133.71,
|
165 |
+
"eval_quora_pairs_steps_per_second": 4.279,
|
166 |
+
"step": 557
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"epoch": 0.09004203039120595,
|
170 |
+
"eval_gooaq_pairs_loss": 7.57412052154541,
|
171 |
+
"eval_gooaq_pairs_runtime": 13.3648,
|
172 |
+
"eval_gooaq_pairs_samples_per_second": 74.824,
|
173 |
+
"eval_gooaq_pairs_steps_per_second": 2.394,
|
174 |
+
"step": 557
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.09020368574199807,
|
178 |
+
"grad_norm": 21.490495681762695,
|
179 |
+
"learning_rate": 2.9795258620689654e-06,
|
180 |
+
"loss": 7.4107,
|
181 |
+
"step": 558
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 0.1052376333656644,
|
185 |
+
"grad_norm": 35.23164367675781,
|
186 |
+
"learning_rate": 3.480603448275862e-06,
|
187 |
+
"loss": 7.0111,
|
188 |
+
"step": 651
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.12027158098933075,
|
192 |
+
"grad_norm": 28.60922622680664,
|
193 |
+
"learning_rate": 3.981681034482759e-06,
|
194 |
+
"loss": 5.9488,
|
195 |
+
"step": 744
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.13530552861299708,
|
199 |
+
"grad_norm": 22.0839786529541,
|
200 |
+
"learning_rate": 4.482758620689656e-06,
|
201 |
+
"loss": 6.3051,
|
202 |
+
"step": 837
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 0.15033947623666344,
|
206 |
+
"grad_norm": 34.64767837524414,
|
207 |
+
"learning_rate": 4.983836206896552e-06,
|
208 |
+
"loss": 5.2056,
|
209 |
+
"step": 930
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.16537342386032977,
|
213 |
+
"grad_norm": 13.605194091796875,
|
214 |
+
"learning_rate": 5.484913793103448e-06,
|
215 |
+
"loss": 5.0794,
|
216 |
+
"step": 1023
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 0.1800840607824119,
|
220 |
+
"eval_nli-pairs_loss": 4.693160057067871,
|
221 |
+
"eval_nli-pairs_runtime": 14.776,
|
222 |
+
"eval_nli-pairs_samples_per_second": 101.516,
|
223 |
+
"eval_nli-pairs_steps_per_second": 3.181,
|
224 |
+
"eval_sts-test_pearson_cosine": 0.6672572282189017,
|
225 |
+
"eval_sts-test_pearson_dot": 0.5110207654364226,
|
226 |
+
"eval_sts-test_pearson_euclidean": 0.65934512843155,
|
227 |
+
"eval_sts-test_pearson_manhattan": 0.6615633016003417,
|
228 |
+
"eval_sts-test_pearson_max": 0.6672572282189017,
|
229 |
+
"eval_sts-test_spearman_cosine": 0.6364241996636473,
|
230 |
+
"eval_sts-test_spearman_dot": 0.4920702168931027,
|
231 |
+
"eval_sts-test_spearman_euclidean": 0.638848044048013,
|
232 |
+
"eval_sts-test_spearman_manhattan": 0.6407402326117282,
|
233 |
+
"eval_sts-test_spearman_max": 0.6407402326117282,
|
234 |
+
"step": 1114
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.1800840607824119,
|
238 |
+
"eval_vitaminc-pairs_loss": 3.5585296154022217,
|
239 |
+
"eval_vitaminc-pairs_runtime": 14.3661,
|
240 |
+
"eval_vitaminc-pairs_samples_per_second": 69.538,
|
241 |
+
"eval_vitaminc-pairs_steps_per_second": 2.227,
|
242 |
+
"step": 1114
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.1800840607824119,
|
246 |
+
"eval_qnli-contrastive_loss": 11.759393692016602,
|
247 |
+
"eval_qnli-contrastive_runtime": 4.7771,
|
248 |
+
"eval_qnli-contrastive_samples_per_second": 313.999,
|
249 |
+
"eval_qnli-contrastive_steps_per_second": 9.839,
|
250 |
+
"step": 1114
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"epoch": 0.1800840607824119,
|
254 |
+
"eval_scitail-pairs-qa_loss": 1.3339837789535522,
|
255 |
+
"eval_scitail-pairs-qa_runtime": 5.8445,
|
256 |
+
"eval_scitail-pairs-qa_samples_per_second": 128.326,
|
257 |
+
"eval_scitail-pairs-qa_steps_per_second": 4.106,
|
258 |
+
"step": 1114
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"epoch": 0.1800840607824119,
|
262 |
+
"eval_scitail-pairs-pos_loss": 2.508178234100342,
|
263 |
+
"eval_scitail-pairs-pos_runtime": 15.12,
|
264 |
+
"eval_scitail-pairs-pos_samples_per_second": 86.244,
|
265 |
+
"eval_scitail-pairs-pos_steps_per_second": 2.712,
|
266 |
+
"step": 1114
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 0.1800840607824119,
|
270 |
+
"eval_xsum-pairs_loss": 2.727797508239746,
|
271 |
+
"eval_xsum-pairs_runtime": 3.0382,
|
272 |
+
"eval_xsum-pairs_samples_per_second": 65.828,
|
273 |
+
"eval_xsum-pairs_steps_per_second": 2.304,
|
274 |
+
"step": 1114
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 0.1800840607824119,
|
278 |
+
"eval_compression-pairs_loss": 1.769970178604126,
|
279 |
+
"eval_compression-pairs_runtime": 1.3017,
|
280 |
+
"eval_compression-pairs_samples_per_second": 384.105,
|
281 |
+
"eval_compression-pairs_steps_per_second": 12.291,
|
282 |
+
"step": 1114
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.1800840607824119,
|
286 |
+
"eval_sciq_pairs_loss": 6.772756576538086,
|
287 |
+
"eval_sciq_pairs_runtime": 29.0556,
|
288 |
+
"eval_sciq_pairs_samples_per_second": 20.099,
|
289 |
+
"eval_sciq_pairs_steps_per_second": 0.654,
|
290 |
+
"step": 1114
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.1800840607824119,
|
294 |
+
"eval_qasc_pairs_loss": 10.429397583007812,
|
295 |
+
"eval_qasc_pairs_runtime": 5.2915,
|
296 |
+
"eval_qasc_pairs_samples_per_second": 76.916,
|
297 |
+
"eval_qasc_pairs_steps_per_second": 2.457,
|
298 |
+
"step": 1114
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 0.1800840607824119,
|
302 |
+
"eval_openbookqa_pairs_loss": 5.441987037658691,
|
303 |
+
"eval_openbookqa_pairs_runtime": 1.1725,
|
304 |
+
"eval_openbookqa_pairs_samples_per_second": 116.843,
|
305 |
+
"eval_openbookqa_pairs_steps_per_second": 4.264,
|
306 |
+
"step": 1114
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 0.1800840607824119,
|
310 |
+
"eval_msmarco_pairs_loss": 4.586305618286133,
|
311 |
+
"eval_msmarco_pairs_runtime": 19.8051,
|
312 |
+
"eval_msmarco_pairs_samples_per_second": 50.492,
|
313 |
+
"eval_msmarco_pairs_steps_per_second": 1.616,
|
314 |
+
"step": 1114
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 0.1800840607824119,
|
318 |
+
"eval_nq_pairs_loss": 5.193580150604248,
|
319 |
+
"eval_nq_pairs_runtime": 37.2293,
|
320 |
+
"eval_nq_pairs_samples_per_second": 26.861,
|
321 |
+
"eval_nq_pairs_steps_per_second": 0.86,
|
322 |
+
"step": 1114
|
323 |
+
},
|
324 |
+
{
|
325 |
+
"epoch": 0.1800840607824119,
|
326 |
+
"eval_trivia_pairs_loss": 5.120319366455078,
|
327 |
+
"eval_trivia_pairs_runtime": 64.3021,
|
328 |
+
"eval_trivia_pairs_samples_per_second": 15.552,
|
329 |
+
"eval_trivia_pairs_steps_per_second": 0.498,
|
330 |
+
"step": 1114
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"epoch": 0.1800840607824119,
|
334 |
+
"eval_quora_pairs_loss": 1.4382946491241455,
|
335 |
+
"eval_quora_pairs_runtime": 3.7168,
|
336 |
+
"eval_quora_pairs_samples_per_second": 134.525,
|
337 |
+
"eval_quora_pairs_steps_per_second": 4.305,
|
338 |
+
"step": 1114
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.1800840607824119,
|
342 |
+
"eval_gooaq_pairs_loss": 3.7513082027435303,
|
343 |
+
"eval_gooaq_pairs_runtime": 13.2594,
|
344 |
+
"eval_gooaq_pairs_samples_per_second": 75.418,
|
345 |
+
"eval_gooaq_pairs_steps_per_second": 2.413,
|
346 |
+
"step": 1114
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 0.18040737148399613,
|
350 |
+
"grad_norm": 39.661067962646484,
|
351 |
+
"learning_rate": 5.9859913793103445e-06,
|
352 |
+
"loss": 4.362,
|
353 |
+
"step": 1116
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.19544131910766246,
|
357 |
+
"grad_norm": 34.55929946899414,
|
358 |
+
"learning_rate": 6.487068965517242e-06,
|
359 |
+
"loss": 4.3245,
|
360 |
+
"step": 1209
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 0.2104752667313288,
|
364 |
+
"grad_norm": 25.775623321533203,
|
365 |
+
"learning_rate": 6.988146551724138e-06,
|
366 |
+
"loss": 4.359,
|
367 |
+
"step": 1302
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 0.22550921435499516,
|
371 |
+
"grad_norm": 57.751529693603516,
|
372 |
+
"learning_rate": 7.489224137931035e-06,
|
373 |
+
"loss": 4.0488,
|
374 |
+
"step": 1395
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.2405431619786615,
|
378 |
+
"grad_norm": 33.448768615722656,
|
379 |
+
"learning_rate": 7.990301724137931e-06,
|
380 |
+
"loss": 4.0499,
|
381 |
+
"step": 1488
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.2555771096023278,
|
385 |
+
"grad_norm": 29.5295467376709,
|
386 |
+
"learning_rate": 8.491379310344827e-06,
|
387 |
+
"loss": 3.7256,
|
388 |
+
"step": 1581
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 0.27012609117361785,
|
392 |
+
"eval_nli-pairs_loss": 3.6348764896392822,
|
393 |
+
"eval_nli-pairs_runtime": 14.761,
|
394 |
+
"eval_nli-pairs_samples_per_second": 101.619,
|
395 |
+
"eval_nli-pairs_steps_per_second": 3.184,
|
396 |
+
"eval_sts-test_pearson_cosine": 0.6972871286019413,
|
397 |
+
"eval_sts-test_pearson_dot": 0.5667394576060958,
|
398 |
+
"eval_sts-test_pearson_euclidean": 0.6946767725059286,
|
399 |
+
"eval_sts-test_pearson_manhattan": 0.7031948219809795,
|
400 |
+
"eval_sts-test_pearson_max": 0.7031948219809795,
|
401 |
+
"eval_sts-test_spearman_cosine": 0.6666257059052387,
|
402 |
+
"eval_sts-test_spearman_dot": 0.5430589355737897,
|
403 |
+
"eval_sts-test_spearman_euclidean": 0.6727104999188346,
|
404 |
+
"eval_sts-test_spearman_manhattan": 0.6812486382298032,
|
405 |
+
"eval_sts-test_spearman_max": 0.6812486382298032,
|
406 |
+
"step": 1671
|
407 |
+
},
|
408 |
+
{
|
409 |
+
"epoch": 0.27012609117361785,
|
410 |
+
"eval_vitaminc-pairs_loss": 2.811436653137207,
|
411 |
+
"eval_vitaminc-pairs_runtime": 14.4779,
|
412 |
+
"eval_vitaminc-pairs_samples_per_second": 69.002,
|
413 |
+
"eval_vitaminc-pairs_steps_per_second": 2.21,
|
414 |
+
"step": 1671
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 0.27012609117361785,
|
418 |
+
"eval_qnli-contrastive_loss": 9.688385009765625,
|
419 |
+
"eval_qnli-contrastive_runtime": 4.8234,
|
420 |
+
"eval_qnli-contrastive_samples_per_second": 310.984,
|
421 |
+
"eval_qnli-contrastive_steps_per_second": 9.744,
|
422 |
+
"step": 1671
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.27012609117361785,
|
426 |
+
"eval_scitail-pairs-qa_loss": 0.8966398239135742,
|
427 |
+
"eval_scitail-pairs-qa_runtime": 5.8274,
|
428 |
+
"eval_scitail-pairs-qa_samples_per_second": 128.702,
|
429 |
+
"eval_scitail-pairs-qa_steps_per_second": 4.118,
|
430 |
+
"step": 1671
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 0.27012609117361785,
|
434 |
+
"eval_scitail-pairs-pos_loss": 1.9770935773849487,
|
435 |
+
"eval_scitail-pairs-pos_runtime": 15.5498,
|
436 |
+
"eval_scitail-pairs-pos_samples_per_second": 83.859,
|
437 |
+
"eval_scitail-pairs-pos_steps_per_second": 2.637,
|
438 |
+
"step": 1671
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 0.27012609117361785,
|
442 |
+
"eval_xsum-pairs_loss": 2.1290199756622314,
|
443 |
+
"eval_xsum-pairs_runtime": 3.0544,
|
444 |
+
"eval_xsum-pairs_samples_per_second": 65.479,
|
445 |
+
"eval_xsum-pairs_steps_per_second": 2.292,
|
446 |
+
"step": 1671
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.27012609117361785,
|
450 |
+
"eval_compression-pairs_loss": 1.2427340745925903,
|
451 |
+
"eval_compression-pairs_runtime": 1.3179,
|
452 |
+
"eval_compression-pairs_samples_per_second": 379.389,
|
453 |
+
"eval_compression-pairs_steps_per_second": 12.14,
|
454 |
+
"step": 1671
|
455 |
+
},
|
456 |
+
{
|
457 |
+
"epoch": 0.27012609117361785,
|
458 |
+
"eval_sciq_pairs_loss": 6.424961090087891,
|
459 |
+
"eval_sciq_pairs_runtime": 29.2749,
|
460 |
+
"eval_sciq_pairs_samples_per_second": 19.949,
|
461 |
+
"eval_sciq_pairs_steps_per_second": 0.649,
|
462 |
+
"step": 1671
|
463 |
+
},
|
464 |
+
{
|
465 |
+
"epoch": 0.27012609117361785,
|
466 |
+
"eval_qasc_pairs_loss": 9.239206314086914,
|
467 |
+
"eval_qasc_pairs_runtime": 5.2408,
|
468 |
+
"eval_qasc_pairs_samples_per_second": 77.66,
|
469 |
+
"eval_qasc_pairs_steps_per_second": 2.481,
|
470 |
+
"step": 1671
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 0.27012609117361785,
|
474 |
+
"eval_openbookqa_pairs_loss": 4.784058570861816,
|
475 |
+
"eval_openbookqa_pairs_runtime": 1.2088,
|
476 |
+
"eval_openbookqa_pairs_samples_per_second": 113.332,
|
477 |
+
"eval_openbookqa_pairs_steps_per_second": 4.136,
|
478 |
+
"step": 1671
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.27012609117361785,
|
482 |
+
"eval_msmarco_pairs_loss": 3.655301094055176,
|
483 |
+
"eval_msmarco_pairs_runtime": 19.7273,
|
484 |
+
"eval_msmarco_pairs_samples_per_second": 50.691,
|
485 |
+
"eval_msmarco_pairs_steps_per_second": 1.622,
|
486 |
+
"step": 1671
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 0.27012609117361785,
|
490 |
+
"eval_nq_pairs_loss": 4.114762783050537,
|
491 |
+
"eval_nq_pairs_runtime": 37.3924,
|
492 |
+
"eval_nq_pairs_samples_per_second": 26.743,
|
493 |
+
"eval_nq_pairs_steps_per_second": 0.856,
|
494 |
+
"step": 1671
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.27012609117361785,
|
498 |
+
"eval_trivia_pairs_loss": 4.019989967346191,
|
499 |
+
"eval_trivia_pairs_runtime": 64.3836,
|
500 |
+
"eval_trivia_pairs_samples_per_second": 15.532,
|
501 |
+
"eval_trivia_pairs_steps_per_second": 0.497,
|
502 |
+
"step": 1671
|
503 |
+
},
|
504 |
+
{
|
505 |
+
"epoch": 0.27012609117361785,
|
506 |
+
"eval_quora_pairs_loss": 1.002946138381958,
|
507 |
+
"eval_quora_pairs_runtime": 3.7091,
|
508 |
+
"eval_quora_pairs_samples_per_second": 134.803,
|
509 |
+
"eval_quora_pairs_steps_per_second": 4.314,
|
510 |
+
"step": 1671
|
511 |
+
},
|
512 |
+
{
|
513 |
+
"epoch": 0.27012609117361785,
|
514 |
+
"eval_gooaq_pairs_loss": 2.87351131439209,
|
515 |
+
"eval_gooaq_pairs_runtime": 13.2151,
|
516 |
+
"eval_gooaq_pairs_samples_per_second": 75.671,
|
517 |
+
"eval_gooaq_pairs_steps_per_second": 2.421,
|
518 |
+
"step": 1671
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 0.27061105722599416,
|
522 |
+
"grad_norm": 142.8954315185547,
|
523 |
+
"learning_rate": 8.992456896551725e-06,
|
524 |
+
"loss": 3.6978,
|
525 |
+
"step": 1674
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 0.28564500484966054,
|
529 |
+
"grad_norm": 35.244972229003906,
|
530 |
+
"learning_rate": 9.493534482758622e-06,
|
531 |
+
"loss": 3.9547,
|
532 |
+
"step": 1767
|
533 |
+
},
|
534 |
+
{
|
535 |
+
"epoch": 0.3006789524733269,
|
536 |
+
"grad_norm": 24.055269241333008,
|
537 |
+
"learning_rate": 9.994612068965518e-06,
|
538 |
+
"loss": 4.162,
|
539 |
+
"step": 1860
|
540 |
+
},
|
541 |
+
{
|
542 |
+
"epoch": 0.3157129000969932,
|
543 |
+
"grad_norm": 39.16152572631836,
|
544 |
+
"learning_rate": 1.0495689655172414e-05,
|
545 |
+
"loss": 3.739,
|
546 |
+
"step": 1953
|
547 |
+
},
|
548 |
+
{
|
549 |
+
"epoch": 0.33074684772065954,
|
550 |
+
"grad_norm": 30.219701766967773,
|
551 |
+
"learning_rate": 1.099676724137931e-05,
|
552 |
+
"loss": 4.2688,
|
553 |
+
"step": 2046
|
554 |
+
},
|
555 |
+
{
|
556 |
+
"epoch": 0.3457807953443259,
|
557 |
+
"grad_norm": 35.78736114501953,
|
558 |
+
"learning_rate": 1.1497844827586206e-05,
|
559 |
+
"loss": 3.3462,
|
560 |
+
"step": 2139
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 0.3601681215648238,
|
564 |
+
"eval_nli-pairs_loss": 3.1179466247558594,
|
565 |
+
"eval_nli-pairs_runtime": 14.8963,
|
566 |
+
"eval_nli-pairs_samples_per_second": 100.696,
|
567 |
+
"eval_nli-pairs_steps_per_second": 3.155,
|
568 |
+
"eval_sts-test_pearson_cosine": 0.7110231765083281,
|
569 |
+
"eval_sts-test_pearson_dot": 0.5911922048259769,
|
570 |
+
"eval_sts-test_pearson_euclidean": 0.7113733036920562,
|
571 |
+
"eval_sts-test_pearson_manhattan": 0.7195266505149516,
|
572 |
+
"eval_sts-test_pearson_max": 0.7195266505149516,
|
573 |
+
"eval_sts-test_spearman_cosine": 0.6844829069963456,
|
574 |
+
"eval_sts-test_spearman_dot": 0.567786285795314,
|
575 |
+
"eval_sts-test_spearman_euclidean": 0.6897367727395519,
|
576 |
+
"eval_sts-test_spearman_manhattan": 0.6977703060020186,
|
577 |
+
"eval_sts-test_spearman_max": 0.6977703060020186,
|
578 |
+
"step": 2228
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.3601681215648238,
|
582 |
+
"eval_vitaminc-pairs_loss": 2.4076764583587646,
|
583 |
+
"eval_vitaminc-pairs_runtime": 14.3487,
|
584 |
+
"eval_vitaminc-pairs_samples_per_second": 69.623,
|
585 |
+
"eval_vitaminc-pairs_steps_per_second": 2.23,
|
586 |
+
"step": 2228
|
587 |
+
},
|
588 |
+
{
|
589 |
+
"epoch": 0.3601681215648238,
|
590 |
+
"eval_qnli-contrastive_loss": 6.651412010192871,
|
591 |
+
"eval_qnli-contrastive_runtime": 4.759,
|
592 |
+
"eval_qnli-contrastive_samples_per_second": 315.189,
|
593 |
+
"eval_qnli-contrastive_steps_per_second": 9.876,
|
594 |
+
"step": 2228
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.3601681215648238,
|
598 |
+
"eval_scitail-pairs-qa_loss": 0.6640239357948303,
|
599 |
+
"eval_scitail-pairs-qa_runtime": 5.8178,
|
600 |
+
"eval_scitail-pairs-qa_samples_per_second": 128.916,
|
601 |
+
"eval_scitail-pairs-qa_steps_per_second": 4.125,
|
602 |
+
"step": 2228
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 0.3601681215648238,
|
606 |
+
"eval_scitail-pairs-pos_loss": 1.6727737188339233,
|
607 |
+
"eval_scitail-pairs-pos_runtime": 15.3144,
|
608 |
+
"eval_scitail-pairs-pos_samples_per_second": 85.149,
|
609 |
+
"eval_scitail-pairs-pos_steps_per_second": 2.677,
|
610 |
+
"step": 2228
|
611 |
+
},
|
612 |
+
{
|
613 |
+
"epoch": 0.3601681215648238,
|
614 |
+
"eval_xsum-pairs_loss": 1.7385025024414062,
|
615 |
+
"eval_xsum-pairs_runtime": 3.0465,
|
616 |
+
"eval_xsum-pairs_samples_per_second": 65.649,
|
617 |
+
"eval_xsum-pairs_steps_per_second": 2.298,
|
618 |
+
"step": 2228
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.3601681215648238,
|
622 |
+
"eval_compression-pairs_loss": 1.0110334157943726,
|
623 |
+
"eval_compression-pairs_runtime": 1.2863,
|
624 |
+
"eval_compression-pairs_samples_per_second": 388.706,
|
625 |
+
"eval_compression-pairs_steps_per_second": 12.439,
|
626 |
+
"step": 2228
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.3601681215648238,
|
630 |
+
"eval_sciq_pairs_loss": 6.164596080780029,
|
631 |
+
"eval_sciq_pairs_runtime": 28.909,
|
632 |
+
"eval_sciq_pairs_samples_per_second": 20.201,
|
633 |
+
"eval_sciq_pairs_steps_per_second": 0.657,
|
634 |
+
"step": 2228
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 0.3601681215648238,
|
638 |
+
"eval_qasc_pairs_loss": 7.898203372955322,
|
639 |
+
"eval_qasc_pairs_runtime": 5.2211,
|
640 |
+
"eval_qasc_pairs_samples_per_second": 77.953,
|
641 |
+
"eval_qasc_pairs_steps_per_second": 2.49,
|
642 |
+
"step": 2228
|
643 |
+
},
|
644 |
+
{
|
645 |
+
"epoch": 0.3601681215648238,
|
646 |
+
"eval_openbookqa_pairs_loss": 4.36992073059082,
|
647 |
+
"eval_openbookqa_pairs_runtime": 1.1844,
|
648 |
+
"eval_openbookqa_pairs_samples_per_second": 115.667,
|
649 |
+
"eval_openbookqa_pairs_steps_per_second": 4.221,
|
650 |
+
"step": 2228
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 0.3601681215648238,
|
654 |
+
"eval_msmarco_pairs_loss": 3.067087411880493,
|
655 |
+
"eval_msmarco_pairs_runtime": 19.7205,
|
656 |
+
"eval_msmarco_pairs_samples_per_second": 50.709,
|
657 |
+
"eval_msmarco_pairs_steps_per_second": 1.623,
|
658 |
+
"step": 2228
|
659 |
+
},
|
660 |
+
{
|
661 |
+
"epoch": 0.3601681215648238,
|
662 |
+
"eval_nq_pairs_loss": 3.3717246055603027,
|
663 |
+
"eval_nq_pairs_runtime": 37.1177,
|
664 |
+
"eval_nq_pairs_samples_per_second": 26.941,
|
665 |
+
"eval_nq_pairs_steps_per_second": 0.862,
|
666 |
+
"step": 2228
|
667 |
+
},
|
668 |
+
{
|
669 |
+
"epoch": 0.3601681215648238,
|
670 |
+
"eval_trivia_pairs_loss": 3.4189703464508057,
|
671 |
+
"eval_trivia_pairs_runtime": 64.257,
|
672 |
+
"eval_trivia_pairs_samples_per_second": 15.563,
|
673 |
+
"eval_trivia_pairs_steps_per_second": 0.498,
|
674 |
+
"step": 2228
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.3601681215648238,
|
678 |
+
"eval_quora_pairs_loss": 0.8419531583786011,
|
679 |
+
"eval_quora_pairs_runtime": 3.7448,
|
680 |
+
"eval_quora_pairs_samples_per_second": 133.518,
|
681 |
+
"eval_quora_pairs_steps_per_second": 4.273,
|
682 |
+
"step": 2228
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 0.3601681215648238,
|
686 |
+
"eval_gooaq_pairs_loss": 2.4530532360076904,
|
687 |
+
"eval_gooaq_pairs_runtime": 13.3141,
|
688 |
+
"eval_gooaq_pairs_samples_per_second": 75.108,
|
689 |
+
"eval_gooaq_pairs_steps_per_second": 2.403,
|
690 |
+
"step": 2228
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 0.36081474296799226,
|
694 |
+
"grad_norm": 33.25382614135742,
|
695 |
+
"learning_rate": 1.1998922413793104e-05,
|
696 |
+
"loss": 3.8272,
|
697 |
+
"step": 2232
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.3758486905916586,
|
701 |
+
"grad_norm": 22.22249984741211,
|
702 |
+
"learning_rate": 1.25e-05,
|
703 |
+
"loss": 3.4532,
|
704 |
+
"step": 2325
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.39088263821532493,
|
708 |
+
"grad_norm": 32.02521514892578,
|
709 |
+
"learning_rate": 1.3001077586206897e-05,
|
710 |
+
"loss": 3.7391,
|
711 |
+
"step": 2418
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.40591658583899126,
|
715 |
+
"grad_norm": 84.23457336425781,
|
716 |
+
"learning_rate": 1.3502155172413793e-05,
|
717 |
+
"loss": 3.4451,
|
718 |
+
"step": 2511
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.4209505334626576,
|
722 |
+
"grad_norm": 82.23103332519531,
|
723 |
+
"learning_rate": 1.400323275862069e-05,
|
724 |
+
"loss": 3.2086,
|
725 |
+
"step": 2604
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.435984481086324,
|
729 |
+
"grad_norm": 128.5042266845703,
|
730 |
+
"learning_rate": 1.4504310344827587e-05,
|
731 |
+
"loss": 3.153,
|
732 |
+
"step": 2697
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 0.45021015195602976,
|
736 |
+
"eval_nli-pairs_loss": 2.7247567176818848,
|
737 |
+
"eval_nli-pairs_runtime": 14.7363,
|
738 |
+
"eval_nli-pairs_samples_per_second": 101.79,
|
739 |
+
"eval_nli-pairs_steps_per_second": 3.189,
|
740 |
+
"eval_sts-test_pearson_cosine": 0.7313032856033084,
|
741 |
+
"eval_sts-test_pearson_dot": 0.639231944179888,
|
742 |
+
"eval_sts-test_pearson_euclidean": 0.7299296327875673,
|
743 |
+
"eval_sts-test_pearson_manhattan": 0.7376485877411852,
|
744 |
+
"eval_sts-test_pearson_max": 0.7376485877411852,
|
745 |
+
"eval_sts-test_spearman_cosine": 0.713852235440012,
|
746 |
+
"eval_sts-test_spearman_dot": 0.6141091584560591,
|
747 |
+
"eval_sts-test_spearman_euclidean": 0.7125938749269385,
|
748 |
+
"eval_sts-test_spearman_manhattan": 0.7209089187255475,
|
749 |
+
"eval_sts-test_spearman_max": 0.7209089187255475,
|
750 |
+
"step": 2785
|
751 |
+
},
|
752 |
+
{
|
753 |
+
"epoch": 0.45021015195602976,
|
754 |
+
"eval_vitaminc-pairs_loss": 2.1636030673980713,
|
755 |
+
"eval_vitaminc-pairs_runtime": 14.3573,
|
756 |
+
"eval_vitaminc-pairs_samples_per_second": 69.582,
|
757 |
+
"eval_vitaminc-pairs_steps_per_second": 2.229,
|
758 |
+
"step": 2785
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.45021015195602976,
|
762 |
+
"eval_qnli-contrastive_loss": 6.1082000732421875,
|
763 |
+
"eval_qnli-contrastive_runtime": 4.8812,
|
764 |
+
"eval_qnli-contrastive_samples_per_second": 307.299,
|
765 |
+
"eval_qnli-contrastive_steps_per_second": 9.629,
|
766 |
+
"step": 2785
|
767 |
+
},
|
768 |
+
{
|
769 |
+
"epoch": 0.45021015195602976,
|
770 |
+
"eval_scitail-pairs-qa_loss": 0.47009098529815674,
|
771 |
+
"eval_scitail-pairs-qa_runtime": 5.8135,
|
772 |
+
"eval_scitail-pairs-qa_samples_per_second": 129.011,
|
773 |
+
"eval_scitail-pairs-qa_steps_per_second": 4.128,
|
774 |
+
"step": 2785
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.45021015195602976,
|
778 |
+
"eval_scitail-pairs-pos_loss": 1.38162362575531,
|
779 |
+
"eval_scitail-pairs-pos_runtime": 15.0892,
|
780 |
+
"eval_scitail-pairs-pos_samples_per_second": 86.42,
|
781 |
+
"eval_scitail-pairs-pos_steps_per_second": 2.717,
|
782 |
+
"step": 2785
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 0.45021015195602976,
|
786 |
+
"eval_xsum-pairs_loss": 1.4567902088165283,
|
787 |
+
"eval_xsum-pairs_runtime": 3.0536,
|
788 |
+
"eval_xsum-pairs_samples_per_second": 65.496,
|
789 |
+
"eval_xsum-pairs_steps_per_second": 2.292,
|
790 |
+
"step": 2785
|
791 |
+
},
|
792 |
+
{
|
793 |
+
"epoch": 0.45021015195602976,
|
794 |
+
"eval_compression-pairs_loss": 0.8824976682662964,
|
795 |
+
"eval_compression-pairs_runtime": 1.2907,
|
796 |
+
"eval_compression-pairs_samples_per_second": 387.382,
|
797 |
+
"eval_compression-pairs_steps_per_second": 12.396,
|
798 |
+
"step": 2785
|
799 |
+
},
|
800 |
+
{
|
801 |
+
"epoch": 0.45021015195602976,
|
802 |
+
"eval_sciq_pairs_loss": 5.971975326538086,
|
803 |
+
"eval_sciq_pairs_runtime": 28.8816,
|
804 |
+
"eval_sciq_pairs_samples_per_second": 20.22,
|
805 |
+
"eval_sciq_pairs_steps_per_second": 0.658,
|
806 |
+
"step": 2785
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 0.45021015195602976,
|
810 |
+
"eval_qasc_pairs_loss": 7.14296817779541,
|
811 |
+
"eval_qasc_pairs_runtime": 5.2619,
|
812 |
+
"eval_qasc_pairs_samples_per_second": 77.348,
|
813 |
+
"eval_qasc_pairs_steps_per_second": 2.471,
|
814 |
+
"step": 2785
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 0.45021015195602976,
|
818 |
+
"eval_openbookqa_pairs_loss": 3.890052080154419,
|
819 |
+
"eval_openbookqa_pairs_runtime": 1.1822,
|
820 |
+
"eval_openbookqa_pairs_samples_per_second": 115.884,
|
821 |
+
"eval_openbookqa_pairs_steps_per_second": 4.229,
|
822 |
+
"step": 2785
|
823 |
+
},
|
824 |
+
{
|
825 |
+
"epoch": 0.45021015195602976,
|
826 |
+
"eval_msmarco_pairs_loss": 2.6956124305725098,
|
827 |
+
"eval_msmarco_pairs_runtime": 19.7685,
|
828 |
+
"eval_msmarco_pairs_samples_per_second": 50.586,
|
829 |
+
"eval_msmarco_pairs_steps_per_second": 1.619,
|
830 |
+
"step": 2785
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 0.45021015195602976,
|
834 |
+
"eval_nq_pairs_loss": 2.9799299240112305,
|
835 |
+
"eval_nq_pairs_runtime": 37.2854,
|
836 |
+
"eval_nq_pairs_samples_per_second": 26.82,
|
837 |
+
"eval_nq_pairs_steps_per_second": 0.858,
|
838 |
+
"step": 2785
|
839 |
+
},
|
840 |
+
{
|
841 |
+
"epoch": 0.45021015195602976,
|
842 |
+
"eval_trivia_pairs_loss": 3.0525760650634766,
|
843 |
+
"eval_trivia_pairs_runtime": 64.286,
|
844 |
+
"eval_trivia_pairs_samples_per_second": 15.555,
|
845 |
+
"eval_trivia_pairs_steps_per_second": 0.498,
|
846 |
+
"step": 2785
|
847 |
+
},
|
848 |
+
{
|
849 |
+
"epoch": 0.45021015195602976,
|
850 |
+
"eval_quora_pairs_loss": 0.7019712924957275,
|
851 |
+
"eval_quora_pairs_runtime": 3.759,
|
852 |
+
"eval_quora_pairs_samples_per_second": 133.013,
|
853 |
+
"eval_quora_pairs_steps_per_second": 4.256,
|
854 |
+
"step": 2785
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 0.45021015195602976,
|
858 |
+
"eval_gooaq_pairs_loss": 2.1218321323394775,
|
859 |
+
"eval_gooaq_pairs_runtime": 13.3843,
|
860 |
+
"eval_gooaq_pairs_samples_per_second": 74.715,
|
861 |
+
"eval_gooaq_pairs_steps_per_second": 2.391,
|
862 |
+
"step": 2785
|
863 |
+
},
|
864 |
+
{
|
865 |
+
"epoch": 0.4510184287099903,
|
866 |
+
"grad_norm": 7.123088836669922,
|
867 |
+
"learning_rate": 1.5e-05,
|
868 |
+
"loss": 2.9093,
|
869 |
+
"step": 2790
|
870 |
+
},
|
871 |
+
{
|
872 |
+
"epoch": 0.46605237633365665,
|
873 |
+
"grad_norm": 26.165264129638672,
|
874 |
+
"learning_rate": 1.5501077586206898e-05,
|
875 |
+
"loss": 2.6223,
|
876 |
+
"step": 2883
|
877 |
+
},
|
878 |
+
{
|
879 |
+
"epoch": 0.481086323957323,
|
880 |
+
"grad_norm": 7.543350696563721,
|
881 |
+
"learning_rate": 1.6002155172413795e-05,
|
882 |
+
"loss": 2.8362,
|
883 |
+
"step": 2976
|
884 |
+
},
|
885 |
+
{
|
886 |
+
"epoch": 0.4961202715809893,
|
887 |
+
"grad_norm": 26.791278839111328,
|
888 |
+
"learning_rate": 1.6503232758620687e-05,
|
889 |
+
"loss": 2.6383,
|
890 |
+
"step": 3069
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"epoch": 0.5111542192046556,
|
894 |
+
"grad_norm": 24.906707763671875,
|
895 |
+
"learning_rate": 1.7004310344827587e-05,
|
896 |
+
"loss": 2.6265,
|
897 |
+
"step": 3162
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 0.526188166828322,
|
901 |
+
"grad_norm": 17.12710189819336,
|
902 |
+
"learning_rate": 1.7505387931034483e-05,
|
903 |
+
"loss": 2.8718,
|
904 |
+
"step": 3255
|
905 |
+
},
|
906 |
+
{
|
907 |
+
"epoch": 0.5402521823472357,
|
908 |
+
"eval_nli-pairs_loss": 2.4381556510925293,
|
909 |
+
"eval_nli-pairs_runtime": 14.7362,
|
910 |
+
"eval_nli-pairs_samples_per_second": 101.79,
|
911 |
+
"eval_nli-pairs_steps_per_second": 3.189,
|
912 |
+
"eval_sts-test_pearson_cosine": 0.7355921455984917,
|
913 |
+
"eval_sts-test_pearson_dot": 0.6441608711789287,
|
914 |
+
"eval_sts-test_pearson_euclidean": 0.7293547151744354,
|
915 |
+
"eval_sts-test_pearson_manhattan": 0.7409243217735156,
|
916 |
+
"eval_sts-test_pearson_max": 0.7409243217735156,
|
917 |
+
"eval_sts-test_spearman_cosine": 0.7175266639957124,
|
918 |
+
"eval_sts-test_spearman_dot": 0.6242096516614428,
|
919 |
+
"eval_sts-test_spearman_euclidean": 0.7122336979289147,
|
920 |
+
"eval_sts-test_spearman_manhattan": 0.7250251572437655,
|
921 |
+
"eval_sts-test_spearman_max": 0.7250251572437655,
|
922 |
+
"step": 3342
|
923 |
+
},
|
924 |
+
{
|
925 |
+
"epoch": 0.5402521823472357,
|
926 |
+
"eval_vitaminc-pairs_loss": 1.8586883544921875,
|
927 |
+
"eval_vitaminc-pairs_runtime": 14.319,
|
928 |
+
"eval_vitaminc-pairs_samples_per_second": 69.767,
|
929 |
+
"eval_vitaminc-pairs_steps_per_second": 2.235,
|
930 |
+
"step": 3342
|
931 |
+
},
|
932 |
+
{
|
933 |
+
"epoch": 0.5402521823472357,
|
934 |
+
"eval_qnli-contrastive_loss": 3.9992873668670654,
|
935 |
+
"eval_qnli-contrastive_runtime": 4.8306,
|
936 |
+
"eval_qnli-contrastive_samples_per_second": 310.523,
|
937 |
+
"eval_qnli-contrastive_steps_per_second": 9.73,
|
938 |
+
"step": 3342
|
939 |
+
},
|
940 |
+
{
|
941 |
+
"epoch": 0.5402521823472357,
|
942 |
+
"eval_scitail-pairs-qa_loss": 0.3319751024246216,
|
943 |
+
"eval_scitail-pairs-qa_runtime": 5.7118,
|
944 |
+
"eval_scitail-pairs-qa_samples_per_second": 131.308,
|
945 |
+
"eval_scitail-pairs-qa_steps_per_second": 4.202,
|
946 |
+
"step": 3342
|
947 |
+
},
|
948 |
+
{
|
949 |
+
"epoch": 0.5402521823472357,
|
950 |
+
"eval_scitail-pairs-pos_loss": 1.288506269454956,
|
951 |
+
"eval_scitail-pairs-pos_runtime": 15.2101,
|
952 |
+
"eval_scitail-pairs-pos_samples_per_second": 85.732,
|
953 |
+
"eval_scitail-pairs-pos_steps_per_second": 2.696,
|
954 |
+
"step": 3342
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.5402521823472357,
|
958 |
+
"eval_xsum-pairs_loss": 1.3039193153381348,
|
959 |
+
"eval_xsum-pairs_runtime": 3.0719,
|
960 |
+
"eval_xsum-pairs_samples_per_second": 65.106,
|
961 |
+
"eval_xsum-pairs_steps_per_second": 2.279,
|
962 |
+
"step": 3342
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 0.5402521823472357,
|
966 |
+
"eval_compression-pairs_loss": 0.6815783977508545,
|
967 |
+
"eval_compression-pairs_runtime": 1.2859,
|
968 |
+
"eval_compression-pairs_samples_per_second": 388.839,
|
969 |
+
"eval_compression-pairs_steps_per_second": 12.443,
|
970 |
+
"step": 3342
|
971 |
+
},
|
972 |
+
{
|
973 |
+
"epoch": 0.5402521823472357,
|
974 |
+
"eval_sciq_pairs_loss": 5.809567451477051,
|
975 |
+
"eval_sciq_pairs_runtime": 29.0991,
|
976 |
+
"eval_sciq_pairs_samples_per_second": 20.069,
|
977 |
+
"eval_sciq_pairs_steps_per_second": 0.653,
|
978 |
+
"step": 3342
|
979 |
+
},
|
980 |
+
{
|
981 |
+
"epoch": 0.5402521823472357,
|
982 |
+
"eval_qasc_pairs_loss": 6.919505596160889,
|
983 |
+
"eval_qasc_pairs_runtime": 5.2734,
|
984 |
+
"eval_qasc_pairs_samples_per_second": 77.179,
|
985 |
+
"eval_qasc_pairs_steps_per_second": 2.465,
|
986 |
+
"step": 3342
|
987 |
+
},
|
988 |
+
{
|
989 |
+
"epoch": 0.5402521823472357,
|
990 |
+
"eval_openbookqa_pairs_loss": 3.8856022357940674,
|
991 |
+
"eval_openbookqa_pairs_runtime": 1.1676,
|
992 |
+
"eval_openbookqa_pairs_samples_per_second": 117.334,
|
993 |
+
"eval_openbookqa_pairs_steps_per_second": 4.282,
|
994 |
+
"step": 3342
|
995 |
+
},
|
996 |
+
{
|
997 |
+
"epoch": 0.5402521823472357,
|
998 |
+
"eval_msmarco_pairs_loss": 2.367374897003174,
|
999 |
+
"eval_msmarco_pairs_runtime": 19.5819,
|
1000 |
+
"eval_msmarco_pairs_samples_per_second": 51.068,
|
1001 |
+
"eval_msmarco_pairs_steps_per_second": 1.634,
|
1002 |
+
"step": 3342
|
1003 |
+
},
|
1004 |
+
{
|
1005 |
+
"epoch": 0.5402521823472357,
|
1006 |
+
"eval_nq_pairs_loss": 2.5974488258361816,
|
1007 |
+
"eval_nq_pairs_runtime": 37.1479,
|
1008 |
+
"eval_nq_pairs_samples_per_second": 26.919,
|
1009 |
+
"eval_nq_pairs_steps_per_second": 0.861,
|
1010 |
+
"step": 3342
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 0.5402521823472357,
|
1014 |
+
"eval_trivia_pairs_loss": 2.8283140659332275,
|
1015 |
+
"eval_trivia_pairs_runtime": 63.9593,
|
1016 |
+
"eval_trivia_pairs_samples_per_second": 15.635,
|
1017 |
+
"eval_trivia_pairs_steps_per_second": 0.5,
|
1018 |
+
"step": 3342
|
1019 |
+
},
|
1020 |
+
{
|
1021 |
+
"epoch": 0.5402521823472357,
|
1022 |
+
"eval_quora_pairs_loss": 0.5709843039512634,
|
1023 |
+
"eval_quora_pairs_runtime": 3.6911,
|
1024 |
+
"eval_quora_pairs_samples_per_second": 135.462,
|
1025 |
+
"eval_quora_pairs_steps_per_second": 4.335,
|
1026 |
+
"step": 3342
|
1027 |
+
},
|
1028 |
+
{
|
1029 |
+
"epoch": 0.5402521823472357,
|
1030 |
+
"eval_gooaq_pairs_loss": 1.9126713275909424,
|
1031 |
+
"eval_gooaq_pairs_runtime": 13.0893,
|
1032 |
+
"eval_gooaq_pairs_samples_per_second": 76.398,
|
1033 |
+
"eval_gooaq_pairs_steps_per_second": 2.445,
|
1034 |
+
"step": 3342
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"epoch": 0.5412221144519883,
|
1038 |
+
"grad_norm": 25.740751266479492,
|
1039 |
+
"learning_rate": 1.800646551724138e-05,
|
1040 |
+
"loss": 2.4683,
|
1041 |
+
"step": 3348
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 0.5562560620756547,
|
1045 |
+
"grad_norm": 26.303068161010742,
|
1046 |
+
"learning_rate": 1.850754310344828e-05,
|
1047 |
+
"loss": 2.3363,
|
1048 |
+
"step": 3441
|
1049 |
+
},
|
1050 |
+
{
|
1051 |
+
"epoch": 0.5712900096993211,
|
1052 |
+
"grad_norm": 29.08409881591797,
|
1053 |
+
"learning_rate": 1.9008620689655172e-05,
|
1054 |
+
"loss": 2.474,
|
1055 |
+
"step": 3534
|
1056 |
+
},
|
1057 |
+
{
|
1058 |
+
"epoch": 0.5863239573229874,
|
1059 |
+
"grad_norm": 39.23952865600586,
|
1060 |
+
"learning_rate": 1.9509698275862068e-05,
|
1061 |
+
"loss": 2.4987,
|
1062 |
+
"step": 3627
|
1063 |
+
}
|
1064 |
+
],
|
1065 |
+
"logging_steps": 93,
|
1066 |
+
"max_steps": 18558,
|
1067 |
+
"num_input_tokens_seen": 0,
|
1068 |
+
"num_train_epochs": 3,
|
1069 |
+
"save_steps": 1856,
|
1070 |
+
"stateful_callbacks": {
|
1071 |
+
"TrainerControl": {
|
1072 |
+
"args": {
|
1073 |
+
"should_epoch_stop": false,
|
1074 |
+
"should_evaluate": false,
|
1075 |
+
"should_log": false,
|
1076 |
+
"should_save": true,
|
1077 |
+
"should_training_stop": false
|
1078 |
+
},
|
1079 |
+
"attributes": {}
|
1080 |
+
}
|
1081 |
+
},
|
1082 |
+
"total_flos": 0.0,
|
1083 |
+
"train_batch_size": 32,
|
1084 |
+
"trial_name": null,
|
1085 |
+
"trial_params": null
|
1086 |
+
}
|
checkpoint-3712/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee8c0e50c0dd4c52a0f05547246281a5456854ea82a3d1989795e12ea957e233
|
3 |
+
size 5624
|