Training in progress, step 1432, checkpoint
Browse files- checkpoint-1432/1_Pooling/config.json +10 -0
- checkpoint-1432/added_tokens.json +3 -0
- checkpoint-1432/config.json +35 -0
- checkpoint-1432/config_sentence_transformers.json +10 -0
- checkpoint-1432/modules.json +14 -0
- checkpoint-1432/optimizer.pt +3 -0
- checkpoint-1432/pytorch_model.bin +3 -0
- checkpoint-1432/rng_state.pth +3 -0
- checkpoint-1432/scheduler.pt +3 -0
- checkpoint-1432/sentence_bert_config.json +4 -0
- checkpoint-1432/special_tokens_map.json +51 -0
- checkpoint-1432/spm.model +3 -0
- checkpoint-1432/tokenizer.json +0 -0
- checkpoint-1432/tokenizer_config.json +65 -0
- checkpoint-1432/trainer_state.json +1690 -0
- checkpoint-1432/training_args.bin +3 -0
checkpoint-1432/1_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-1432/added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[MASK]": 128000
|
3 |
+
}
|
checkpoint-1432/config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bobox/DeBERTa-ST-AllLayers-v3-checkpoints-tmp",
|
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-1432/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": "2.3.0+cu121"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null,
|
9 |
+
"similarity_fn_name": null
|
10 |
+
}
|
checkpoint-1432/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-1432/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:239fbceac60e9499b467af1be36ed56aee96bc15f4ba35b7569bbc78ec95333a
|
3 |
+
size 1130520122
|
checkpoint-1432/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97f2e2aa245235855072290a58c4d35ab2ea1ca7530942adb20aaf5dd9e80580
|
3 |
+
size 565251810
|
checkpoint-1432/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a4adad4ca0a34a6d8195feb4c5e7bbdd96ee3cd8cb2e15871cf86957df9ccf3
|
3 |
+
size 14244
|
checkpoint-1432/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b08c7e64666c89d99b38421d5fdaf78bd03bd507fa095d9e56a9a2128bd13151
|
3 |
+
size 1064
|
checkpoint-1432/sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 512,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|
checkpoint-1432/special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "[CLS]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "[SEP]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "[MASK]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "[PAD]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "[SEP]",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "[UNK]",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
checkpoint-1432/spm.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
3 |
+
size 2464616
|
checkpoint-1432/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1432/tokenizer_config.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"max_length": 512,
|
51 |
+
"model_max_length": 1000000000000000019884624838656,
|
52 |
+
"pad_to_multiple_of": null,
|
53 |
+
"pad_token": "[PAD]",
|
54 |
+
"pad_token_type_id": 0,
|
55 |
+
"padding_side": "right",
|
56 |
+
"sep_token": "[SEP]",
|
57 |
+
"sp_model_kwargs": {},
|
58 |
+
"split_by_punct": false,
|
59 |
+
"stride": 0,
|
60 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
61 |
+
"truncation_side": "right",
|
62 |
+
"truncation_strategy": "longest_first",
|
63 |
+
"unk_token": "[UNK]",
|
64 |
+
"vocab_type": "spm"
|
65 |
+
}
|
checkpoint-1432/trainer_state.json
ADDED
@@ -0,0 +1,1690 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.4,
|
5 |
+
"eval_steps": 179,
|
6 |
+
"global_step": 1432,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.005027932960893855,
|
13 |
+
"grad_norm": 28.300092697143555,
|
14 |
+
"learning_rate": 6.331471135940411e-07,
|
15 |
+
"loss": 1.0198,
|
16 |
+
"step": 18
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.01005586592178771,
|
20 |
+
"grad_norm": 1.059788465499878,
|
21 |
+
"learning_rate": 1.303538175046555e-06,
|
22 |
+
"loss": 0.8564,
|
23 |
+
"step": 36
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.015083798882681564,
|
27 |
+
"grad_norm": 9.368417739868164,
|
28 |
+
"learning_rate": 1.9739292364990693e-06,
|
29 |
+
"loss": 0.685,
|
30 |
+
"step": 54
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.02011173184357542,
|
34 |
+
"grad_norm": 3.4458816051483154,
|
35 |
+
"learning_rate": 2.644320297951583e-06,
|
36 |
+
"loss": 0.7667,
|
37 |
+
"step": 72
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.025139664804469275,
|
41 |
+
"grad_norm": 4.497154712677002,
|
42 |
+
"learning_rate": 3.314711359404097e-06,
|
43 |
+
"loss": 0.7907,
|
44 |
+
"step": 90
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.030167597765363128,
|
48 |
+
"grad_norm": 4.394736289978027,
|
49 |
+
"learning_rate": 3.985102420856611e-06,
|
50 |
+
"loss": 0.9719,
|
51 |
+
"step": 108
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.03519553072625698,
|
55 |
+
"grad_norm": 10.305765151977539,
|
56 |
+
"learning_rate": 4.655493482309125e-06,
|
57 |
+
"loss": 1.1097,
|
58 |
+
"step": 126
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.04022346368715084,
|
62 |
+
"grad_norm": 5.402688980102539,
|
63 |
+
"learning_rate": 5.325884543761639e-06,
|
64 |
+
"loss": 1.0463,
|
65 |
+
"step": 144
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.045251396648044694,
|
69 |
+
"grad_norm": 0.2811428904533386,
|
70 |
+
"learning_rate": 5.996275605214154e-06,
|
71 |
+
"loss": 0.8796,
|
72 |
+
"step": 162
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.05,
|
76 |
+
"eval_nli-pairs_loss": 0.9358150959014893,
|
77 |
+
"eval_nli-pairs_runtime": 3.7163,
|
78 |
+
"eval_nli-pairs_samples_per_second": 40.363,
|
79 |
+
"eval_nli-pairs_steps_per_second": 0.538,
|
80 |
+
"eval_sts-test_pearson_cosine": 0.7920907827756308,
|
81 |
+
"eval_sts-test_pearson_dot": 0.553905804338793,
|
82 |
+
"eval_sts-test_pearson_euclidean": 0.7477067417028286,
|
83 |
+
"eval_sts-test_pearson_manhattan": 0.7454637009944656,
|
84 |
+
"eval_sts-test_pearson_max": 0.7920907827756308,
|
85 |
+
"eval_sts-test_spearman_cosine": 0.8050902340286232,
|
86 |
+
"eval_sts-test_spearman_dot": 0.5325926730168974,
|
87 |
+
"eval_sts-test_spearman_euclidean": 0.73705041377373,
|
88 |
+
"eval_sts-test_spearman_manhattan": 0.7373939486807765,
|
89 |
+
"eval_sts-test_spearman_max": 0.8050902340286232,
|
90 |
+
"step": 179
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 0.05,
|
94 |
+
"eval_vitaminc-pairs_loss": 4.57532262802124,
|
95 |
+
"eval_vitaminc-pairs_runtime": 0.8386,
|
96 |
+
"eval_vitaminc-pairs_samples_per_second": 149.066,
|
97 |
+
"eval_vitaminc-pairs_steps_per_second": 2.385,
|
98 |
+
"step": 179
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.05,
|
102 |
+
"eval_qnli-contrastive_loss": 0.260235071182251,
|
103 |
+
"eval_qnli-contrastive_runtime": 0.1227,
|
104 |
+
"eval_qnli-contrastive_samples_per_second": 1222.824,
|
105 |
+
"eval_qnli-contrastive_steps_per_second": 16.304,
|
106 |
+
"step": 179
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 0.05,
|
110 |
+
"eval_scitail-pairs-qa_loss": 0.06116430461406708,
|
111 |
+
"eval_scitail-pairs-qa_runtime": 0.6972,
|
112 |
+
"eval_scitail-pairs-qa_samples_per_second": 215.142,
|
113 |
+
"eval_scitail-pairs-qa_steps_per_second": 2.869,
|
114 |
+
"step": 179
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.05,
|
118 |
+
"eval_scitail-pairs-pos_loss": 0.3001463711261749,
|
119 |
+
"eval_scitail-pairs-pos_runtime": 1.8226,
|
120 |
+
"eval_scitail-pairs-pos_samples_per_second": 82.299,
|
121 |
+
"eval_scitail-pairs-pos_steps_per_second": 1.097,
|
122 |
+
"step": 179
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.05,
|
126 |
+
"eval_xsum-pairs_loss": 0.43996042013168335,
|
127 |
+
"eval_xsum-pairs_runtime": 0.1548,
|
128 |
+
"eval_xsum-pairs_samples_per_second": 529.555,
|
129 |
+
"eval_xsum-pairs_steps_per_second": 6.458,
|
130 |
+
"step": 179
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 0.05,
|
134 |
+
"eval_compression-pairs_loss": 0.10088926553726196,
|
135 |
+
"eval_compression-pairs_runtime": 0.1051,
|
136 |
+
"eval_compression-pairs_samples_per_second": 1427.213,
|
137 |
+
"eval_compression-pairs_steps_per_second": 19.03,
|
138 |
+
"step": 179
|
139 |
+
},
|
140 |
+
{
|
141 |
+
"epoch": 0.05,
|
142 |
+
"eval_sciq_pairs_loss": 0.15509434044361115,
|
143 |
+
"eval_sciq_pairs_runtime": 4.9415,
|
144 |
+
"eval_sciq_pairs_samples_per_second": 30.355,
|
145 |
+
"eval_sciq_pairs_steps_per_second": 0.405,
|
146 |
+
"step": 179
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.05,
|
150 |
+
"eval_qasc_pairs_loss": 0.24072103202342987,
|
151 |
+
"eval_qasc_pairs_runtime": 0.6453,
|
152 |
+
"eval_qasc_pairs_samples_per_second": 232.455,
|
153 |
+
"eval_qasc_pairs_steps_per_second": 3.099,
|
154 |
+
"step": 179
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 0.05,
|
158 |
+
"eval_openbookqa_pairs_loss": 1.5241280794143677,
|
159 |
+
"eval_openbookqa_pairs_runtime": 0.7059,
|
160 |
+
"eval_openbookqa_pairs_samples_per_second": 212.48,
|
161 |
+
"eval_openbookqa_pairs_steps_per_second": 2.833,
|
162 |
+
"step": 179
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 0.05,
|
166 |
+
"eval_msmarco_pairs_loss": 0.6149919629096985,
|
167 |
+
"eval_msmarco_pairs_runtime": 1.2013,
|
168 |
+
"eval_msmarco_pairs_samples_per_second": 124.863,
|
169 |
+
"eval_msmarco_pairs_steps_per_second": 1.665,
|
170 |
+
"step": 179
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.05,
|
174 |
+
"eval_nq_pairs_loss": 0.591522216796875,
|
175 |
+
"eval_nq_pairs_runtime": 2.2917,
|
176 |
+
"eval_nq_pairs_samples_per_second": 65.455,
|
177 |
+
"eval_nq_pairs_steps_per_second": 0.873,
|
178 |
+
"step": 179
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.05,
|
182 |
+
"eval_trivia_pairs_loss": 1.0899044275283813,
|
183 |
+
"eval_trivia_pairs_runtime": 3.1583,
|
184 |
+
"eval_trivia_pairs_samples_per_second": 47.494,
|
185 |
+
"eval_trivia_pairs_steps_per_second": 0.633,
|
186 |
+
"step": 179
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 0.05,
|
190 |
+
"eval_quora_pairs_loss": 0.21252885460853577,
|
191 |
+
"eval_quora_pairs_runtime": 0.3861,
|
192 |
+
"eval_quora_pairs_samples_per_second": 388.452,
|
193 |
+
"eval_quora_pairs_steps_per_second": 5.179,
|
194 |
+
"step": 179
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.05,
|
198 |
+
"eval_gooaq_pairs_loss": 0.5593109130859375,
|
199 |
+
"eval_gooaq_pairs_runtime": 0.7918,
|
200 |
+
"eval_gooaq_pairs_samples_per_second": 189.449,
|
201 |
+
"eval_gooaq_pairs_steps_per_second": 2.526,
|
202 |
+
"step": 179
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 0.05,
|
206 |
+
"eval_mrpc_pairs_loss": 0.055620357394218445,
|
207 |
+
"eval_mrpc_pairs_runtime": 0.1048,
|
208 |
+
"eval_mrpc_pairs_samples_per_second": 1431.291,
|
209 |
+
"eval_mrpc_pairs_steps_per_second": 19.084,
|
210 |
+
"step": 179
|
211 |
+
},
|
212 |
+
{
|
213 |
+
"epoch": 0.05027932960893855,
|
214 |
+
"grad_norm": 9.769979476928711,
|
215 |
+
"learning_rate": 6.666666666666667e-06,
|
216 |
+
"loss": 0.7777,
|
217 |
+
"step": 180
|
218 |
+
},
|
219 |
+
{
|
220 |
+
"epoch": 0.0553072625698324,
|
221 |
+
"grad_norm": 9.294490814208984,
|
222 |
+
"learning_rate": 7.337057728119181e-06,
|
223 |
+
"loss": 0.9075,
|
224 |
+
"step": 198
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.060335195530726256,
|
228 |
+
"grad_norm": 0.6179952621459961,
|
229 |
+
"learning_rate": 8.007448789571696e-06,
|
230 |
+
"loss": 0.8239,
|
231 |
+
"step": 216
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.06536312849162011,
|
235 |
+
"grad_norm": 6.369142532348633,
|
236 |
+
"learning_rate": 8.677839851024209e-06,
|
237 |
+
"loss": 0.949,
|
238 |
+
"step": 234
|
239 |
+
},
|
240 |
+
{
|
241 |
+
"epoch": 0.07039106145251396,
|
242 |
+
"grad_norm": 1.7066636085510254,
|
243 |
+
"learning_rate": 9.348230912476724e-06,
|
244 |
+
"loss": 1.2046,
|
245 |
+
"step": 252
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"epoch": 0.07541899441340782,
|
249 |
+
"grad_norm": 0.33892622590065,
|
250 |
+
"learning_rate": 1.0018621973929237e-05,
|
251 |
+
"loss": 0.8526,
|
252 |
+
"step": 270
|
253 |
+
},
|
254 |
+
{
|
255 |
+
"epoch": 0.08044692737430167,
|
256 |
+
"grad_norm": 24.46626091003418,
|
257 |
+
"learning_rate": 1.0689013035381753e-05,
|
258 |
+
"loss": 0.8629,
|
259 |
+
"step": 288
|
260 |
+
},
|
261 |
+
{
|
262 |
+
"epoch": 0.08547486033519552,
|
263 |
+
"grad_norm": 9.228001594543457,
|
264 |
+
"learning_rate": 1.1359404096834266e-05,
|
265 |
+
"loss": 1.1474,
|
266 |
+
"step": 306
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 0.09050279329608939,
|
270 |
+
"grad_norm": 3.441566228866577,
|
271 |
+
"learning_rate": 1.2029795158286779e-05,
|
272 |
+
"loss": 0.9141,
|
273 |
+
"step": 324
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.09553072625698324,
|
277 |
+
"grad_norm": 0.3621586859226227,
|
278 |
+
"learning_rate": 1.2700186219739294e-05,
|
279 |
+
"loss": 0.9756,
|
280 |
+
"step": 342
|
281 |
+
},
|
282 |
+
{
|
283 |
+
"epoch": 0.1,
|
284 |
+
"eval_nli-pairs_loss": 0.9455356001853943,
|
285 |
+
"eval_nli-pairs_runtime": 3.6115,
|
286 |
+
"eval_nli-pairs_samples_per_second": 41.533,
|
287 |
+
"eval_nli-pairs_steps_per_second": 0.554,
|
288 |
+
"eval_sts-test_pearson_cosine": 0.7944563743777492,
|
289 |
+
"eval_sts-test_pearson_dot": 0.554185693724103,
|
290 |
+
"eval_sts-test_pearson_euclidean": 0.7483225064388481,
|
291 |
+
"eval_sts-test_pearson_manhattan": 0.7454936340776467,
|
292 |
+
"eval_sts-test_pearson_max": 0.7944563743777492,
|
293 |
+
"eval_sts-test_spearman_cosine": 0.8064910811776218,
|
294 |
+
"eval_sts-test_spearman_dot": 0.5333761592947532,
|
295 |
+
"eval_sts-test_spearman_euclidean": 0.7382698586949932,
|
296 |
+
"eval_sts-test_spearman_manhattan": 0.7378149008082869,
|
297 |
+
"eval_sts-test_spearman_max": 0.8064910811776218,
|
298 |
+
"step": 358
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 0.1,
|
302 |
+
"eval_vitaminc-pairs_loss": 4.517832279205322,
|
303 |
+
"eval_vitaminc-pairs_runtime": 0.8908,
|
304 |
+
"eval_vitaminc-pairs_samples_per_second": 140.33,
|
305 |
+
"eval_vitaminc-pairs_steps_per_second": 2.245,
|
306 |
+
"step": 358
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 0.1,
|
310 |
+
"eval_qnli-contrastive_loss": 0.2627922296524048,
|
311 |
+
"eval_qnli-contrastive_runtime": 0.1229,
|
312 |
+
"eval_qnli-contrastive_samples_per_second": 1220.886,
|
313 |
+
"eval_qnli-contrastive_steps_per_second": 16.278,
|
314 |
+
"step": 358
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 0.1,
|
318 |
+
"eval_scitail-pairs-qa_loss": 0.06381849944591522,
|
319 |
+
"eval_scitail-pairs-qa_runtime": 0.7125,
|
320 |
+
"eval_scitail-pairs-qa_samples_per_second": 210.516,
|
321 |
+
"eval_scitail-pairs-qa_steps_per_second": 2.807,
|
322 |
+
"step": 358
|
323 |
+
},
|
324 |
+
{
|
325 |
+
"epoch": 0.1,
|
326 |
+
"eval_scitail-pairs-pos_loss": 0.30350035429000854,
|
327 |
+
"eval_scitail-pairs-pos_runtime": 1.877,
|
328 |
+
"eval_scitail-pairs-pos_samples_per_second": 79.916,
|
329 |
+
"eval_scitail-pairs-pos_steps_per_second": 1.066,
|
330 |
+
"step": 358
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"epoch": 0.1,
|
334 |
+
"eval_xsum-pairs_loss": 0.44631534814834595,
|
335 |
+
"eval_xsum-pairs_runtime": 0.1512,
|
336 |
+
"eval_xsum-pairs_samples_per_second": 542.377,
|
337 |
+
"eval_xsum-pairs_steps_per_second": 6.614,
|
338 |
+
"step": 358
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.1,
|
342 |
+
"eval_compression-pairs_loss": 0.10376789420843124,
|
343 |
+
"eval_compression-pairs_runtime": 0.1034,
|
344 |
+
"eval_compression-pairs_samples_per_second": 1450.105,
|
345 |
+
"eval_compression-pairs_steps_per_second": 19.335,
|
346 |
+
"step": 358
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 0.1,
|
350 |
+
"eval_sciq_pairs_loss": 0.15615364909172058,
|
351 |
+
"eval_sciq_pairs_runtime": 5.1236,
|
352 |
+
"eval_sciq_pairs_samples_per_second": 29.276,
|
353 |
+
"eval_sciq_pairs_steps_per_second": 0.39,
|
354 |
+
"step": 358
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.1,
|
358 |
+
"eval_qasc_pairs_loss": 0.24106402695178986,
|
359 |
+
"eval_qasc_pairs_runtime": 0.6663,
|
360 |
+
"eval_qasc_pairs_samples_per_second": 225.133,
|
361 |
+
"eval_qasc_pairs_steps_per_second": 3.002,
|
362 |
+
"step": 358
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 0.1,
|
366 |
+
"eval_openbookqa_pairs_loss": 1.5405189990997314,
|
367 |
+
"eval_openbookqa_pairs_runtime": 0.7365,
|
368 |
+
"eval_openbookqa_pairs_samples_per_second": 203.658,
|
369 |
+
"eval_openbookqa_pairs_steps_per_second": 2.715,
|
370 |
+
"step": 358
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"epoch": 0.1,
|
374 |
+
"eval_msmarco_pairs_loss": 0.6067730188369751,
|
375 |
+
"eval_msmarco_pairs_runtime": 1.2272,
|
376 |
+
"eval_msmarco_pairs_samples_per_second": 122.233,
|
377 |
+
"eval_msmarco_pairs_steps_per_second": 1.63,
|
378 |
+
"step": 358
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"epoch": 0.1,
|
382 |
+
"eval_nq_pairs_loss": 0.5683658123016357,
|
383 |
+
"eval_nq_pairs_runtime": 2.3358,
|
384 |
+
"eval_nq_pairs_samples_per_second": 64.219,
|
385 |
+
"eval_nq_pairs_steps_per_second": 0.856,
|
386 |
+
"step": 358
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 0.1,
|
390 |
+
"eval_trivia_pairs_loss": 1.1103042364120483,
|
391 |
+
"eval_trivia_pairs_runtime": 3.2191,
|
392 |
+
"eval_trivia_pairs_samples_per_second": 46.596,
|
393 |
+
"eval_trivia_pairs_steps_per_second": 0.621,
|
394 |
+
"step": 358
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.1,
|
398 |
+
"eval_quora_pairs_loss": 0.2291153520345688,
|
399 |
+
"eval_quora_pairs_runtime": 0.39,
|
400 |
+
"eval_quora_pairs_samples_per_second": 384.605,
|
401 |
+
"eval_quora_pairs_steps_per_second": 5.128,
|
402 |
+
"step": 358
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 0.1,
|
406 |
+
"eval_gooaq_pairs_loss": 0.5594914555549622,
|
407 |
+
"eval_gooaq_pairs_runtime": 0.814,
|
408 |
+
"eval_gooaq_pairs_samples_per_second": 184.276,
|
409 |
+
"eval_gooaq_pairs_steps_per_second": 2.457,
|
410 |
+
"step": 358
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.1,
|
414 |
+
"eval_mrpc_pairs_loss": 0.056830935180187225,
|
415 |
+
"eval_mrpc_pairs_runtime": 0.1099,
|
416 |
+
"eval_mrpc_pairs_samples_per_second": 1364.673,
|
417 |
+
"eval_mrpc_pairs_steps_per_second": 18.196,
|
418 |
+
"step": 358
|
419 |
+
},
|
420 |
+
{
|
421 |
+
"epoch": 0.1005586592178771,
|
422 |
+
"grad_norm": 0.40709275007247925,
|
423 |
+
"learning_rate": 1.3370577281191808e-05,
|
424 |
+
"loss": 0.7904,
|
425 |
+
"step": 360
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 0.10558659217877095,
|
429 |
+
"grad_norm": 8.056321144104004,
|
430 |
+
"learning_rate": 1.4040968342644321e-05,
|
431 |
+
"loss": 1.2543,
|
432 |
+
"step": 378
|
433 |
+
},
|
434 |
+
{
|
435 |
+
"epoch": 0.1106145251396648,
|
436 |
+
"grad_norm": 6.643378257751465,
|
437 |
+
"learning_rate": 1.4711359404096834e-05,
|
438 |
+
"loss": 0.854,
|
439 |
+
"step": 396
|
440 |
+
},
|
441 |
+
{
|
442 |
+
"epoch": 0.11564245810055866,
|
443 |
+
"grad_norm": 7.473087310791016,
|
444 |
+
"learning_rate": 1.538175046554935e-05,
|
445 |
+
"loss": 0.4719,
|
446 |
+
"step": 414
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.12067039106145251,
|
450 |
+
"grad_norm": 8.68940258026123,
|
451 |
+
"learning_rate": 1.6052141527001864e-05,
|
452 |
+
"loss": 1.4229,
|
453 |
+
"step": 432
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.12569832402234637,
|
457 |
+
"grad_norm": 8.564693450927734,
|
458 |
+
"learning_rate": 1.6722532588454377e-05,
|
459 |
+
"loss": 0.7646,
|
460 |
+
"step": 450
|
461 |
+
},
|
462 |
+
{
|
463 |
+
"epoch": 0.13072625698324022,
|
464 |
+
"grad_norm": 0.39765194058418274,
|
465 |
+
"learning_rate": 1.7392923649906893e-05,
|
466 |
+
"loss": 0.8512,
|
467 |
+
"step": 468
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 0.13575418994413407,
|
471 |
+
"grad_norm": 7.3941192626953125,
|
472 |
+
"learning_rate": 1.8063314711359406e-05,
|
473 |
+
"loss": 1.1333,
|
474 |
+
"step": 486
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.14078212290502792,
|
478 |
+
"grad_norm": 3.183729410171509,
|
479 |
+
"learning_rate": 1.873370577281192e-05,
|
480 |
+
"loss": 0.4451,
|
481 |
+
"step": 504
|
482 |
+
},
|
483 |
+
{
|
484 |
+
"epoch": 0.1458100558659218,
|
485 |
+
"grad_norm": 1.2496144771575928,
|
486 |
+
"learning_rate": 1.9404096834264436e-05,
|
487 |
+
"loss": 0.8859,
|
488 |
+
"step": 522
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 0.15,
|
492 |
+
"eval_nli-pairs_loss": 0.9459429979324341,
|
493 |
+
"eval_nli-pairs_runtime": 3.418,
|
494 |
+
"eval_nli-pairs_samples_per_second": 43.886,
|
495 |
+
"eval_nli-pairs_steps_per_second": 0.585,
|
496 |
+
"eval_sts-test_pearson_cosine": 0.7949855875446147,
|
497 |
+
"eval_sts-test_pearson_dot": 0.5640384325880634,
|
498 |
+
"eval_sts-test_pearson_euclidean": 0.751389277231376,
|
499 |
+
"eval_sts-test_pearson_manhattan": 0.7487497192657817,
|
500 |
+
"eval_sts-test_pearson_max": 0.7949855875446147,
|
501 |
+
"eval_sts-test_spearman_cosine": 0.8064088099185094,
|
502 |
+
"eval_sts-test_spearman_dot": 0.5419498621910633,
|
503 |
+
"eval_sts-test_spearman_euclidean": 0.7411803691316964,
|
504 |
+
"eval_sts-test_spearman_manhattan": 0.7408925147897409,
|
505 |
+
"eval_sts-test_spearman_max": 0.8064088099185094,
|
506 |
+
"step": 537
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.15,
|
510 |
+
"eval_vitaminc-pairs_loss": 4.557371139526367,
|
511 |
+
"eval_vitaminc-pairs_runtime": 0.8813,
|
512 |
+
"eval_vitaminc-pairs_samples_per_second": 141.843,
|
513 |
+
"eval_vitaminc-pairs_steps_per_second": 2.269,
|
514 |
+
"step": 537
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 0.15,
|
518 |
+
"eval_qnli-contrastive_loss": 0.2963089942932129,
|
519 |
+
"eval_qnli-contrastive_runtime": 0.1173,
|
520 |
+
"eval_qnli-contrastive_samples_per_second": 1279.24,
|
521 |
+
"eval_qnli-contrastive_steps_per_second": 17.057,
|
522 |
+
"step": 537
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 0.15,
|
526 |
+
"eval_scitail-pairs-qa_loss": 0.06569412350654602,
|
527 |
+
"eval_scitail-pairs-qa_runtime": 0.6754,
|
528 |
+
"eval_scitail-pairs-qa_samples_per_second": 222.091,
|
529 |
+
"eval_scitail-pairs-qa_steps_per_second": 2.961,
|
530 |
+
"step": 537
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 0.15,
|
534 |
+
"eval_scitail-pairs-pos_loss": 0.3104495108127594,
|
535 |
+
"eval_scitail-pairs-pos_runtime": 1.7852,
|
536 |
+
"eval_scitail-pairs-pos_samples_per_second": 84.022,
|
537 |
+
"eval_scitail-pairs-pos_steps_per_second": 1.12,
|
538 |
+
"step": 537
|
539 |
+
},
|
540 |
+
{
|
541 |
+
"epoch": 0.15,
|
542 |
+
"eval_xsum-pairs_loss": 0.44305890798568726,
|
543 |
+
"eval_xsum-pairs_runtime": 0.1668,
|
544 |
+
"eval_xsum-pairs_samples_per_second": 491.658,
|
545 |
+
"eval_xsum-pairs_steps_per_second": 5.996,
|
546 |
+
"step": 537
|
547 |
+
},
|
548 |
+
{
|
549 |
+
"epoch": 0.15,
|
550 |
+
"eval_compression-pairs_loss": 0.10611961036920547,
|
551 |
+
"eval_compression-pairs_runtime": 0.1033,
|
552 |
+
"eval_compression-pairs_samples_per_second": 1451.474,
|
553 |
+
"eval_compression-pairs_steps_per_second": 19.353,
|
554 |
+
"step": 537
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 0.15,
|
558 |
+
"eval_sciq_pairs_loss": 0.15942400693893433,
|
559 |
+
"eval_sciq_pairs_runtime": 4.8457,
|
560 |
+
"eval_sciq_pairs_samples_per_second": 30.955,
|
561 |
+
"eval_sciq_pairs_steps_per_second": 0.413,
|
562 |
+
"step": 537
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.15,
|
566 |
+
"eval_qasc_pairs_loss": 0.2380143702030182,
|
567 |
+
"eval_qasc_pairs_runtime": 0.6528,
|
568 |
+
"eval_qasc_pairs_samples_per_second": 229.78,
|
569 |
+
"eval_qasc_pairs_steps_per_second": 3.064,
|
570 |
+
"step": 537
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 0.15,
|
574 |
+
"eval_openbookqa_pairs_loss": 1.556572437286377,
|
575 |
+
"eval_openbookqa_pairs_runtime": 0.6905,
|
576 |
+
"eval_openbookqa_pairs_samples_per_second": 217.246,
|
577 |
+
"eval_openbookqa_pairs_steps_per_second": 2.897,
|
578 |
+
"step": 537
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.15,
|
582 |
+
"eval_msmarco_pairs_loss": 0.5950079560279846,
|
583 |
+
"eval_msmarco_pairs_runtime": 1.1541,
|
584 |
+
"eval_msmarco_pairs_samples_per_second": 129.968,
|
585 |
+
"eval_msmarco_pairs_steps_per_second": 1.733,
|
586 |
+
"step": 537
|
587 |
+
},
|
588 |
+
{
|
589 |
+
"epoch": 0.15,
|
590 |
+
"eval_nq_pairs_loss": 0.5976797938346863,
|
591 |
+
"eval_nq_pairs_runtime": 2.2683,
|
592 |
+
"eval_nq_pairs_samples_per_second": 66.128,
|
593 |
+
"eval_nq_pairs_steps_per_second": 0.882,
|
594 |
+
"step": 537
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.15,
|
598 |
+
"eval_trivia_pairs_loss": 1.1377041339874268,
|
599 |
+
"eval_trivia_pairs_runtime": 3.1791,
|
600 |
+
"eval_trivia_pairs_samples_per_second": 47.183,
|
601 |
+
"eval_trivia_pairs_steps_per_second": 0.629,
|
602 |
+
"step": 537
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 0.15,
|
606 |
+
"eval_quora_pairs_loss": 0.20836791396141052,
|
607 |
+
"eval_quora_pairs_runtime": 0.374,
|
608 |
+
"eval_quora_pairs_samples_per_second": 401.115,
|
609 |
+
"eval_quora_pairs_steps_per_second": 5.348,
|
610 |
+
"step": 537
|
611 |
+
},
|
612 |
+
{
|
613 |
+
"epoch": 0.15,
|
614 |
+
"eval_gooaq_pairs_loss": 0.5545207262039185,
|
615 |
+
"eval_gooaq_pairs_runtime": 0.7667,
|
616 |
+
"eval_gooaq_pairs_samples_per_second": 195.642,
|
617 |
+
"eval_gooaq_pairs_steps_per_second": 2.609,
|
618 |
+
"step": 537
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.15,
|
622 |
+
"eval_mrpc_pairs_loss": 0.060290463268756866,
|
623 |
+
"eval_mrpc_pairs_runtime": 0.1026,
|
624 |
+
"eval_mrpc_pairs_samples_per_second": 1462.106,
|
625 |
+
"eval_mrpc_pairs_steps_per_second": 19.495,
|
626 |
+
"step": 537
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.15083798882681565,
|
630 |
+
"grad_norm": 1.3315377235412598,
|
631 |
+
"learning_rate": 1.9999898748390674e-05,
|
632 |
+
"loss": 0.9245,
|
633 |
+
"step": 540
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.1558659217877095,
|
637 |
+
"grad_norm": 8.015869140625,
|
638 |
+
"learning_rate": 1.9989876718445097e-05,
|
639 |
+
"loss": 1.0384,
|
640 |
+
"step": 558
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 0.16089385474860335,
|
644 |
+
"grad_norm": 1.3641886711120605,
|
645 |
+
"learning_rate": 1.9963472835306562e-05,
|
646 |
+
"loss": 0.8826,
|
647 |
+
"step": 576
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 0.1659217877094972,
|
651 |
+
"grad_norm": 7.676197528839111,
|
652 |
+
"learning_rate": 1.9920735213598995e-05,
|
653 |
+
"loss": 0.6693,
|
654 |
+
"step": 594
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.17094972067039105,
|
658 |
+
"grad_norm": 8.144271850585938,
|
659 |
+
"learning_rate": 1.9861741732192866e-05,
|
660 |
+
"loss": 0.8437,
|
661 |
+
"step": 612
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 0.17597765363128492,
|
665 |
+
"grad_norm": 11.723029136657715,
|
666 |
+
"learning_rate": 1.9786599892290035e-05,
|
667 |
+
"loss": 1.2241,
|
668 |
+
"step": 630
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.18100558659217877,
|
672 |
+
"grad_norm": 12.107389450073242,
|
673 |
+
"learning_rate": 1.9695446621529053e-05,
|
674 |
+
"loss": 0.7169,
|
675 |
+
"step": 648
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.18603351955307262,
|
679 |
+
"grad_norm": 0.671999454498291,
|
680 |
+
"learning_rate": 1.9588448024468015e-05,
|
681 |
+
"loss": 0.7937,
|
682 |
+
"step": 666
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 0.19106145251396647,
|
686 |
+
"grad_norm": 2.9247829914093018,
|
687 |
+
"learning_rate": 1.9465799079899608e-05,
|
688 |
+
"loss": 0.8666,
|
689 |
+
"step": 684
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 0.19608938547486032,
|
693 |
+
"grad_norm": 9.634854316711426,
|
694 |
+
"learning_rate": 1.932772328554989e-05,
|
695 |
+
"loss": 0.8002,
|
696 |
+
"step": 702
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 0.2,
|
700 |
+
"eval_nli-pairs_loss": 0.9524073004722595,
|
701 |
+
"eval_nli-pairs_runtime": 3.3652,
|
702 |
+
"eval_nli-pairs_samples_per_second": 44.573,
|
703 |
+
"eval_nli-pairs_steps_per_second": 0.594,
|
704 |
+
"eval_sts-test_pearson_cosine": 0.7960974627777679,
|
705 |
+
"eval_sts-test_pearson_dot": 0.5653927619143873,
|
706 |
+
"eval_sts-test_pearson_euclidean": 0.7510324476182012,
|
707 |
+
"eval_sts-test_pearson_manhattan": 0.7478581635465753,
|
708 |
+
"eval_sts-test_pearson_max": 0.7960974627777679,
|
709 |
+
"eval_sts-test_spearman_cosine": 0.8076217698074869,
|
710 |
+
"eval_sts-test_spearman_dot": 0.5437275169754562,
|
711 |
+
"eval_sts-test_spearman_euclidean": 0.7394612354069316,
|
712 |
+
"eval_sts-test_spearman_manhattan": 0.7383580125266631,
|
713 |
+
"eval_sts-test_spearman_max": 0.8076217698074869,
|
714 |
+
"step": 716
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 0.2,
|
718 |
+
"eval_vitaminc-pairs_loss": 4.544824600219727,
|
719 |
+
"eval_vitaminc-pairs_runtime": 0.8209,
|
720 |
+
"eval_vitaminc-pairs_samples_per_second": 152.27,
|
721 |
+
"eval_vitaminc-pairs_steps_per_second": 2.436,
|
722 |
+
"step": 716
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 0.2,
|
726 |
+
"eval_qnli-contrastive_loss": 0.2854141891002655,
|
727 |
+
"eval_qnli-contrastive_runtime": 0.116,
|
728 |
+
"eval_qnli-contrastive_samples_per_second": 1293.335,
|
729 |
+
"eval_qnli-contrastive_steps_per_second": 17.244,
|
730 |
+
"step": 716
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.2,
|
734 |
+
"eval_scitail-pairs-qa_loss": 0.06479831039905548,
|
735 |
+
"eval_scitail-pairs-qa_runtime": 0.6668,
|
736 |
+
"eval_scitail-pairs-qa_samples_per_second": 224.963,
|
737 |
+
"eval_scitail-pairs-qa_steps_per_second": 3.0,
|
738 |
+
"step": 716
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 0.2,
|
742 |
+
"eval_scitail-pairs-pos_loss": 0.30356064438819885,
|
743 |
+
"eval_scitail-pairs-pos_runtime": 1.7895,
|
744 |
+
"eval_scitail-pairs-pos_samples_per_second": 83.823,
|
745 |
+
"eval_scitail-pairs-pos_steps_per_second": 1.118,
|
746 |
+
"step": 716
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 0.2,
|
750 |
+
"eval_xsum-pairs_loss": 0.4510384202003479,
|
751 |
+
"eval_xsum-pairs_runtime": 0.1513,
|
752 |
+
"eval_xsum-pairs_samples_per_second": 541.869,
|
753 |
+
"eval_xsum-pairs_steps_per_second": 6.608,
|
754 |
+
"step": 716
|
755 |
+
},
|
756 |
+
{
|
757 |
+
"epoch": 0.2,
|
758 |
+
"eval_compression-pairs_loss": 0.10218393057584763,
|
759 |
+
"eval_compression-pairs_runtime": 0.1063,
|
760 |
+
"eval_compression-pairs_samples_per_second": 1410.495,
|
761 |
+
"eval_compression-pairs_steps_per_second": 18.807,
|
762 |
+
"step": 716
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 0.2,
|
766 |
+
"eval_sciq_pairs_loss": 0.16117030382156372,
|
767 |
+
"eval_sciq_pairs_runtime": 4.8842,
|
768 |
+
"eval_sciq_pairs_samples_per_second": 30.711,
|
769 |
+
"eval_sciq_pairs_steps_per_second": 0.409,
|
770 |
+
"step": 716
|
771 |
+
},
|
772 |
+
{
|
773 |
+
"epoch": 0.2,
|
774 |
+
"eval_qasc_pairs_loss": 0.25312450528144836,
|
775 |
+
"eval_qasc_pairs_runtime": 0.626,
|
776 |
+
"eval_qasc_pairs_samples_per_second": 239.619,
|
777 |
+
"eval_qasc_pairs_steps_per_second": 3.195,
|
778 |
+
"step": 716
|
779 |
+
},
|
780 |
+
{
|
781 |
+
"epoch": 0.2,
|
782 |
+
"eval_openbookqa_pairs_loss": 1.560429573059082,
|
783 |
+
"eval_openbookqa_pairs_runtime": 0.6856,
|
784 |
+
"eval_openbookqa_pairs_samples_per_second": 218.787,
|
785 |
+
"eval_openbookqa_pairs_steps_per_second": 2.917,
|
786 |
+
"step": 716
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.2,
|
790 |
+
"eval_msmarco_pairs_loss": 0.6264744997024536,
|
791 |
+
"eval_msmarco_pairs_runtime": 1.1496,
|
792 |
+
"eval_msmarco_pairs_samples_per_second": 130.479,
|
793 |
+
"eval_msmarco_pairs_steps_per_second": 1.74,
|
794 |
+
"step": 716
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 0.2,
|
798 |
+
"eval_nq_pairs_loss": 0.602968692779541,
|
799 |
+
"eval_nq_pairs_runtime": 2.2714,
|
800 |
+
"eval_nq_pairs_samples_per_second": 66.038,
|
801 |
+
"eval_nq_pairs_steps_per_second": 0.881,
|
802 |
+
"step": 716
|
803 |
+
},
|
804 |
+
{
|
805 |
+
"epoch": 0.2,
|
806 |
+
"eval_trivia_pairs_loss": 1.1763343811035156,
|
807 |
+
"eval_trivia_pairs_runtime": 3.1779,
|
808 |
+
"eval_trivia_pairs_samples_per_second": 47.201,
|
809 |
+
"eval_trivia_pairs_steps_per_second": 0.629,
|
810 |
+
"step": 716
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 0.2,
|
814 |
+
"eval_quora_pairs_loss": 0.25559327006340027,
|
815 |
+
"eval_quora_pairs_runtime": 0.3926,
|
816 |
+
"eval_quora_pairs_samples_per_second": 382.056,
|
817 |
+
"eval_quora_pairs_steps_per_second": 5.094,
|
818 |
+
"step": 716
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 0.2,
|
822 |
+
"eval_gooaq_pairs_loss": 0.5762031078338623,
|
823 |
+
"eval_gooaq_pairs_runtime": 0.7962,
|
824 |
+
"eval_gooaq_pairs_samples_per_second": 188.399,
|
825 |
+
"eval_gooaq_pairs_steps_per_second": 2.512,
|
826 |
+
"step": 716
|
827 |
+
},
|
828 |
+
{
|
829 |
+
"epoch": 0.2,
|
830 |
+
"eval_mrpc_pairs_loss": 0.05901935696601868,
|
831 |
+
"eval_mrpc_pairs_runtime": 0.1022,
|
832 |
+
"eval_mrpc_pairs_samples_per_second": 1467.265,
|
833 |
+
"eval_mrpc_pairs_steps_per_second": 19.564,
|
834 |
+
"step": 716
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 0.2011173184357542,
|
838 |
+
"grad_norm": 2.0602877140045166,
|
839 |
+
"learning_rate": 1.9174472250808337e-05,
|
840 |
+
"loss": 0.9815,
|
841 |
+
"step": 720
|
842 |
+
},
|
843 |
+
{
|
844 |
+
"epoch": 0.20614525139664805,
|
845 |
+
"grad_norm": 10.161604881286621,
|
846 |
+
"learning_rate": 1.90063252382312e-05,
|
847 |
+
"loss": 0.568,
|
848 |
+
"step": 738
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"epoch": 0.2111731843575419,
|
852 |
+
"grad_norm": 18.392881393432617,
|
853 |
+
"learning_rate": 1.882358865465376e-05,
|
854 |
+
"loss": 0.8045,
|
855 |
+
"step": 756
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 0.21620111731843575,
|
859 |
+
"grad_norm": 1.8240203857421875,
|
860 |
+
"learning_rate": 1.8626595492838756e-05,
|
861 |
+
"loss": 0.9535,
|
862 |
+
"step": 774
|
863 |
+
},
|
864 |
+
{
|
865 |
+
"epoch": 0.2212290502793296,
|
866 |
+
"grad_norm": 0.7226653099060059,
|
867 |
+
"learning_rate": 1.8415704724678457e-05,
|
868 |
+
"loss": 0.8132,
|
869 |
+
"step": 792
|
870 |
+
},
|
871 |
+
{
|
872 |
+
"epoch": 0.22625698324022347,
|
873 |
+
"grad_norm": 5.971342086791992,
|
874 |
+
"learning_rate": 1.819130064705612e-05,
|
875 |
+
"loss": 0.6948,
|
876 |
+
"step": 810
|
877 |
+
},
|
878 |
+
{
|
879 |
+
"epoch": 0.23128491620111732,
|
880 |
+
"grad_norm": 8.432775497436523,
|
881 |
+
"learning_rate": 1.795379218155883e-05,
|
882 |
+
"loss": 1.2272,
|
883 |
+
"step": 828
|
884 |
+
},
|
885 |
+
{
|
886 |
+
"epoch": 0.23631284916201117,
|
887 |
+
"grad_norm": 18.75815200805664,
|
888 |
+
"learning_rate": 1.7703612129317886e-05,
|
889 |
+
"loss": 0.9203,
|
890 |
+
"step": 846
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"epoch": 0.24134078212290502,
|
894 |
+
"grad_norm": 0.6807297468185425,
|
895 |
+
"learning_rate": 1.7441216382334472e-05,
|
896 |
+
"loss": 0.6491,
|
897 |
+
"step": 864
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 0.24636871508379887,
|
901 |
+
"grad_norm": 0.27311134338378906,
|
902 |
+
"learning_rate": 1.716708309272793e-05,
|
903 |
+
"loss": 0.7194,
|
904 |
+
"step": 882
|
905 |
+
},
|
906 |
+
{
|
907 |
+
"epoch": 0.25,
|
908 |
+
"eval_nli-pairs_loss": 0.9641673564910889,
|
909 |
+
"eval_nli-pairs_runtime": 3.4016,
|
910 |
+
"eval_nli-pairs_samples_per_second": 44.097,
|
911 |
+
"eval_nli-pairs_steps_per_second": 0.588,
|
912 |
+
"eval_sts-test_pearson_cosine": 0.7984203994030687,
|
913 |
+
"eval_sts-test_pearson_dot": 0.5718132073426122,
|
914 |
+
"eval_sts-test_pearson_euclidean": 0.751738033448039,
|
915 |
+
"eval_sts-test_pearson_manhattan": 0.7480386170862788,
|
916 |
+
"eval_sts-test_pearson_max": 0.7984203994030687,
|
917 |
+
"eval_sts-test_spearman_cosine": 0.8106824393227386,
|
918 |
+
"eval_sts-test_spearman_dot": 0.5505203809846263,
|
919 |
+
"eval_sts-test_spearman_euclidean": 0.7424109996455601,
|
920 |
+
"eval_sts-test_spearman_manhattan": 0.740994183877676,
|
921 |
+
"eval_sts-test_spearman_max": 0.8106824393227386,
|
922 |
+
"step": 895
|
923 |
+
},
|
924 |
+
{
|
925 |
+
"epoch": 0.25,
|
926 |
+
"eval_vitaminc-pairs_loss": 4.445808410644531,
|
927 |
+
"eval_vitaminc-pairs_runtime": 0.8341,
|
928 |
+
"eval_vitaminc-pairs_samples_per_second": 149.86,
|
929 |
+
"eval_vitaminc-pairs_steps_per_second": 2.398,
|
930 |
+
"step": 895
|
931 |
+
},
|
932 |
+
{
|
933 |
+
"epoch": 0.25,
|
934 |
+
"eval_qnli-contrastive_loss": 0.26446962356567383,
|
935 |
+
"eval_qnli-contrastive_runtime": 0.1192,
|
936 |
+
"eval_qnli-contrastive_samples_per_second": 1258.221,
|
937 |
+
"eval_qnli-contrastive_steps_per_second": 16.776,
|
938 |
+
"step": 895
|
939 |
+
},
|
940 |
+
{
|
941 |
+
"epoch": 0.25,
|
942 |
+
"eval_scitail-pairs-qa_loss": 0.06552065908908844,
|
943 |
+
"eval_scitail-pairs-qa_runtime": 0.685,
|
944 |
+
"eval_scitail-pairs-qa_samples_per_second": 218.99,
|
945 |
+
"eval_scitail-pairs-qa_steps_per_second": 2.92,
|
946 |
+
"step": 895
|
947 |
+
},
|
948 |
+
{
|
949 |
+
"epoch": 0.25,
|
950 |
+
"eval_scitail-pairs-pos_loss": 0.2940276265144348,
|
951 |
+
"eval_scitail-pairs-pos_runtime": 1.7906,
|
952 |
+
"eval_scitail-pairs-pos_samples_per_second": 83.773,
|
953 |
+
"eval_scitail-pairs-pos_steps_per_second": 1.117,
|
954 |
+
"step": 895
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.25,
|
958 |
+
"eval_xsum-pairs_loss": 0.46034616231918335,
|
959 |
+
"eval_xsum-pairs_runtime": 0.1605,
|
960 |
+
"eval_xsum-pairs_samples_per_second": 510.946,
|
961 |
+
"eval_xsum-pairs_steps_per_second": 6.231,
|
962 |
+
"step": 895
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 0.25,
|
966 |
+
"eval_compression-pairs_loss": 0.10285492241382599,
|
967 |
+
"eval_compression-pairs_runtime": 0.1054,
|
968 |
+
"eval_compression-pairs_samples_per_second": 1423.451,
|
969 |
+
"eval_compression-pairs_steps_per_second": 18.979,
|
970 |
+
"step": 895
|
971 |
+
},
|
972 |
+
{
|
973 |
+
"epoch": 0.25,
|
974 |
+
"eval_sciq_pairs_loss": 0.16273371875286102,
|
975 |
+
"eval_sciq_pairs_runtime": 4.8468,
|
976 |
+
"eval_sciq_pairs_samples_per_second": 30.948,
|
977 |
+
"eval_sciq_pairs_steps_per_second": 0.413,
|
978 |
+
"step": 895
|
979 |
+
},
|
980 |
+
{
|
981 |
+
"epoch": 0.25,
|
982 |
+
"eval_qasc_pairs_loss": 0.24400106072425842,
|
983 |
+
"eval_qasc_pairs_runtime": 0.6336,
|
984 |
+
"eval_qasc_pairs_samples_per_second": 236.76,
|
985 |
+
"eval_qasc_pairs_steps_per_second": 3.157,
|
986 |
+
"step": 895
|
987 |
+
},
|
988 |
+
{
|
989 |
+
"epoch": 0.25,
|
990 |
+
"eval_openbookqa_pairs_loss": 1.5389502048492432,
|
991 |
+
"eval_openbookqa_pairs_runtime": 0.6864,
|
992 |
+
"eval_openbookqa_pairs_samples_per_second": 218.536,
|
993 |
+
"eval_openbookqa_pairs_steps_per_second": 2.914,
|
994 |
+
"step": 895
|
995 |
+
},
|
996 |
+
{
|
997 |
+
"epoch": 0.25,
|
998 |
+
"eval_msmarco_pairs_loss": 0.6092618703842163,
|
999 |
+
"eval_msmarco_pairs_runtime": 1.1561,
|
1000 |
+
"eval_msmarco_pairs_samples_per_second": 129.746,
|
1001 |
+
"eval_msmarco_pairs_steps_per_second": 1.73,
|
1002 |
+
"step": 895
|
1003 |
+
},
|
1004 |
+
{
|
1005 |
+
"epoch": 0.25,
|
1006 |
+
"eval_nq_pairs_loss": 0.5972890853881836,
|
1007 |
+
"eval_nq_pairs_runtime": 2.2849,
|
1008 |
+
"eval_nq_pairs_samples_per_second": 65.648,
|
1009 |
+
"eval_nq_pairs_steps_per_second": 0.875,
|
1010 |
+
"step": 895
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 0.25,
|
1014 |
+
"eval_trivia_pairs_loss": 1.1646121740341187,
|
1015 |
+
"eval_trivia_pairs_runtime": 3.1713,
|
1016 |
+
"eval_trivia_pairs_samples_per_second": 47.299,
|
1017 |
+
"eval_trivia_pairs_steps_per_second": 0.631,
|
1018 |
+
"step": 895
|
1019 |
+
},
|
1020 |
+
{
|
1021 |
+
"epoch": 0.25,
|
1022 |
+
"eval_quora_pairs_loss": 0.2002115696668625,
|
1023 |
+
"eval_quora_pairs_runtime": 0.3724,
|
1024 |
+
"eval_quora_pairs_samples_per_second": 402.785,
|
1025 |
+
"eval_quora_pairs_steps_per_second": 5.37,
|
1026 |
+
"step": 895
|
1027 |
+
},
|
1028 |
+
{
|
1029 |
+
"epoch": 0.25,
|
1030 |
+
"eval_gooaq_pairs_loss": 0.5770832300186157,
|
1031 |
+
"eval_gooaq_pairs_runtime": 0.7637,
|
1032 |
+
"eval_gooaq_pairs_samples_per_second": 196.419,
|
1033 |
+
"eval_gooaq_pairs_steps_per_second": 2.619,
|
1034 |
+
"step": 895
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"epoch": 0.25,
|
1038 |
+
"eval_mrpc_pairs_loss": 0.060786984860897064,
|
1039 |
+
"eval_mrpc_pairs_runtime": 0.1004,
|
1040 |
+
"eval_mrpc_pairs_samples_per_second": 1493.964,
|
1041 |
+
"eval_mrpc_pairs_steps_per_second": 19.92,
|
1042 |
+
"step": 895
|
1043 |
+
},
|
1044 |
+
{
|
1045 |
+
"epoch": 0.25139664804469275,
|
1046 |
+
"grad_norm": 9.622016906738281,
|
1047 |
+
"learning_rate": 1.6881711801420374e-05,
|
1048 |
+
"loss": 0.9089,
|
1049 |
+
"step": 900
|
1050 |
+
},
|
1051 |
+
{
|
1052 |
+
"epoch": 0.25642458100558657,
|
1053 |
+
"grad_norm": 3.134366035461426,
|
1054 |
+
"learning_rate": 1.658562252784545e-05,
|
1055 |
+
"loss": 0.9682,
|
1056 |
+
"step": 918
|
1057 |
+
},
|
1058 |
+
{
|
1059 |
+
"epoch": 0.26145251396648045,
|
1060 |
+
"grad_norm": 11.332123756408691,
|
1061 |
+
"learning_rate": 1.627935482234001e-05,
|
1062 |
+
"loss": 1.0025,
|
1063 |
+
"step": 936
|
1064 |
+
},
|
1065 |
+
{
|
1066 |
+
"epoch": 0.2664804469273743,
|
1067 |
+
"grad_norm": 10.678857803344727,
|
1068 |
+
"learning_rate": 1.5963466782945497e-05,
|
1069 |
+
"loss": 1.0259,
|
1070 |
+
"step": 954
|
1071 |
+
},
|
1072 |
+
{
|
1073 |
+
"epoch": 0.27150837988826815,
|
1074 |
+
"grad_norm": 0.8130522966384888,
|
1075 |
+
"learning_rate": 1.5638534038410646e-05,
|
1076 |
+
"loss": 0.8946,
|
1077 |
+
"step": 972
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 0.276536312849162,
|
1081 |
+
"grad_norm": 25.857967376708984,
|
1082 |
+
"learning_rate": 1.5305148699248803e-05,
|
1083 |
+
"loss": 0.72,
|
1084 |
+
"step": 990
|
1085 |
+
},
|
1086 |
+
{
|
1087 |
+
"epoch": 0.28156424581005585,
|
1088 |
+
"grad_norm": 8.641229629516602,
|
1089 |
+
"learning_rate": 1.4963918278761172e-05,
|
1090 |
+
"loss": 0.8911,
|
1091 |
+
"step": 1008
|
1092 |
+
},
|
1093 |
+
{
|
1094 |
+
"epoch": 0.2865921787709497,
|
1095 |
+
"grad_norm": 5.093626499176025,
|
1096 |
+
"learning_rate": 1.4615464585992371e-05,
|
1097 |
+
"loss": 0.8059,
|
1098 |
+
"step": 1026
|
1099 |
+
},
|
1100 |
+
{
|
1101 |
+
"epoch": 0.2916201117318436,
|
1102 |
+
"grad_norm": 0.18065588176250458,
|
1103 |
+
"learning_rate": 1.4260422592635362e-05,
|
1104 |
+
"loss": 1.0758,
|
1105 |
+
"step": 1044
|
1106 |
+
},
|
1107 |
+
{
|
1108 |
+
"epoch": 0.2966480446927374,
|
1109 |
+
"grad_norm": 10.29207706451416,
|
1110 |
+
"learning_rate": 1.3899439275950759e-05,
|
1111 |
+
"loss": 0.8875,
|
1112 |
+
"step": 1062
|
1113 |
+
},
|
1114 |
+
{
|
1115 |
+
"epoch": 0.3,
|
1116 |
+
"eval_nli-pairs_loss": 0.9130206108093262,
|
1117 |
+
"eval_nli-pairs_runtime": 3.3804,
|
1118 |
+
"eval_nli-pairs_samples_per_second": 44.373,
|
1119 |
+
"eval_nli-pairs_steps_per_second": 0.592,
|
1120 |
+
"eval_sts-test_pearson_cosine": 0.7935564606718174,
|
1121 |
+
"eval_sts-test_pearson_dot": 0.5781608636588449,
|
1122 |
+
"eval_sts-test_pearson_euclidean": 0.7502295476446079,
|
1123 |
+
"eval_sts-test_pearson_manhattan": 0.746737096593109,
|
1124 |
+
"eval_sts-test_pearson_max": 0.7935564606718174,
|
1125 |
+
"eval_sts-test_spearman_cosine": 0.8086930151421495,
|
1126 |
+
"eval_sts-test_spearman_dot": 0.5549031403563933,
|
1127 |
+
"eval_sts-test_spearman_euclidean": 0.739389609130169,
|
1128 |
+
"eval_sts-test_spearman_manhattan": 0.7380312227930571,
|
1129 |
+
"eval_sts-test_spearman_max": 0.8086930151421495,
|
1130 |
+
"step": 1074
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"epoch": 0.3,
|
1134 |
+
"eval_vitaminc-pairs_loss": 4.481905937194824,
|
1135 |
+
"eval_vitaminc-pairs_runtime": 0.8115,
|
1136 |
+
"eval_vitaminc-pairs_samples_per_second": 154.041,
|
1137 |
+
"eval_vitaminc-pairs_steps_per_second": 2.465,
|
1138 |
+
"step": 1074
|
1139 |
+
},
|
1140 |
+
{
|
1141 |
+
"epoch": 0.3,
|
1142 |
+
"eval_qnli-contrastive_loss": 0.271823525428772,
|
1143 |
+
"eval_qnli-contrastive_runtime": 0.1166,
|
1144 |
+
"eval_qnli-contrastive_samples_per_second": 1286.546,
|
1145 |
+
"eval_qnli-contrastive_steps_per_second": 17.154,
|
1146 |
+
"step": 1074
|
1147 |
+
},
|
1148 |
+
{
|
1149 |
+
"epoch": 0.3,
|
1150 |
+
"eval_scitail-pairs-qa_loss": 0.06460323184728622,
|
1151 |
+
"eval_scitail-pairs-qa_runtime": 0.6655,
|
1152 |
+
"eval_scitail-pairs-qa_samples_per_second": 225.379,
|
1153 |
+
"eval_scitail-pairs-qa_steps_per_second": 3.005,
|
1154 |
+
"step": 1074
|
1155 |
+
},
|
1156 |
+
{
|
1157 |
+
"epoch": 0.3,
|
1158 |
+
"eval_scitail-pairs-pos_loss": 0.28618788719177246,
|
1159 |
+
"eval_scitail-pairs-pos_runtime": 1.7829,
|
1160 |
+
"eval_scitail-pairs-pos_samples_per_second": 84.131,
|
1161 |
+
"eval_scitail-pairs-pos_steps_per_second": 1.122,
|
1162 |
+
"step": 1074
|
1163 |
+
},
|
1164 |
+
{
|
1165 |
+
"epoch": 0.3,
|
1166 |
+
"eval_xsum-pairs_loss": 0.46461817622184753,
|
1167 |
+
"eval_xsum-pairs_runtime": 0.1506,
|
1168 |
+
"eval_xsum-pairs_samples_per_second": 544.581,
|
1169 |
+
"eval_xsum-pairs_steps_per_second": 6.641,
|
1170 |
+
"step": 1074
|
1171 |
+
},
|
1172 |
+
{
|
1173 |
+
"epoch": 0.3,
|
1174 |
+
"eval_compression-pairs_loss": 0.0993683859705925,
|
1175 |
+
"eval_compression-pairs_runtime": 0.1041,
|
1176 |
+
"eval_compression-pairs_samples_per_second": 1440.48,
|
1177 |
+
"eval_compression-pairs_steps_per_second": 19.206,
|
1178 |
+
"step": 1074
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 0.3,
|
1182 |
+
"eval_sciq_pairs_loss": 0.16428890824317932,
|
1183 |
+
"eval_sciq_pairs_runtime": 4.9141,
|
1184 |
+
"eval_sciq_pairs_samples_per_second": 30.524,
|
1185 |
+
"eval_sciq_pairs_steps_per_second": 0.407,
|
1186 |
+
"step": 1074
|
1187 |
+
},
|
1188 |
+
{
|
1189 |
+
"epoch": 0.3,
|
1190 |
+
"eval_qasc_pairs_loss": 0.2515706419944763,
|
1191 |
+
"eval_qasc_pairs_runtime": 0.6397,
|
1192 |
+
"eval_qasc_pairs_samples_per_second": 234.494,
|
1193 |
+
"eval_qasc_pairs_steps_per_second": 3.127,
|
1194 |
+
"step": 1074
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 0.3,
|
1198 |
+
"eval_openbookqa_pairs_loss": 1.5371934175491333,
|
1199 |
+
"eval_openbookqa_pairs_runtime": 0.6887,
|
1200 |
+
"eval_openbookqa_pairs_samples_per_second": 217.793,
|
1201 |
+
"eval_openbookqa_pairs_steps_per_second": 2.904,
|
1202 |
+
"step": 1074
|
1203 |
+
},
|
1204 |
+
{
|
1205 |
+
"epoch": 0.3,
|
1206 |
+
"eval_msmarco_pairs_loss": 0.6019803881645203,
|
1207 |
+
"eval_msmarco_pairs_runtime": 1.1582,
|
1208 |
+
"eval_msmarco_pairs_samples_per_second": 129.515,
|
1209 |
+
"eval_msmarco_pairs_steps_per_second": 1.727,
|
1210 |
+
"step": 1074
|
1211 |
+
},
|
1212 |
+
{
|
1213 |
+
"epoch": 0.3,
|
1214 |
+
"eval_nq_pairs_loss": 0.6118470430374146,
|
1215 |
+
"eval_nq_pairs_runtime": 2.2708,
|
1216 |
+
"eval_nq_pairs_samples_per_second": 66.056,
|
1217 |
+
"eval_nq_pairs_steps_per_second": 0.881,
|
1218 |
+
"step": 1074
|
1219 |
+
},
|
1220 |
+
{
|
1221 |
+
"epoch": 0.3,
|
1222 |
+
"eval_trivia_pairs_loss": 1.12074613571167,
|
1223 |
+
"eval_trivia_pairs_runtime": 3.1611,
|
1224 |
+
"eval_trivia_pairs_samples_per_second": 47.452,
|
1225 |
+
"eval_trivia_pairs_steps_per_second": 0.633,
|
1226 |
+
"step": 1074
|
1227 |
+
},
|
1228 |
+
{
|
1229 |
+
"epoch": 0.3,
|
1230 |
+
"eval_quora_pairs_loss": 0.22596687078475952,
|
1231 |
+
"eval_quora_pairs_runtime": 0.3879,
|
1232 |
+
"eval_quora_pairs_samples_per_second": 386.741,
|
1233 |
+
"eval_quora_pairs_steps_per_second": 5.157,
|
1234 |
+
"step": 1074
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 0.3,
|
1238 |
+
"eval_gooaq_pairs_loss": 0.5833558440208435,
|
1239 |
+
"eval_gooaq_pairs_runtime": 0.7697,
|
1240 |
+
"eval_gooaq_pairs_samples_per_second": 194.881,
|
1241 |
+
"eval_gooaq_pairs_steps_per_second": 2.598,
|
1242 |
+
"step": 1074
|
1243 |
+
},
|
1244 |
+
{
|
1245 |
+
"epoch": 0.3,
|
1246 |
+
"eval_mrpc_pairs_loss": 0.058091748505830765,
|
1247 |
+
"eval_mrpc_pairs_runtime": 0.1053,
|
1248 |
+
"eval_mrpc_pairs_samples_per_second": 1424.202,
|
1249 |
+
"eval_mrpc_pairs_steps_per_second": 18.989,
|
1250 |
+
"step": 1074
|
1251 |
+
},
|
1252 |
+
{
|
1253 |
+
"epoch": 0.3016759776536313,
|
1254 |
+
"grad_norm": 3.0486669540405273,
|
1255 |
+
"learning_rate": 1.3533172439808864e-05,
|
1256 |
+
"loss": 1.1998,
|
1257 |
+
"step": 1080
|
1258 |
+
},
|
1259 |
+
{
|
1260 |
+
"epoch": 0.3067039106145251,
|
1261 |
+
"grad_norm": 9.376039505004883,
|
1262 |
+
"learning_rate": 1.3162289516002921e-05,
|
1263 |
+
"loss": 0.7894,
|
1264 |
+
"step": 1098
|
1265 |
+
},
|
1266 |
+
{
|
1267 |
+
"epoch": 0.311731843575419,
|
1268 |
+
"grad_norm": 2.824523448944092,
|
1269 |
+
"learning_rate": 1.2787466348017752e-05,
|
1270 |
+
"loss": 1.1598,
|
1271 |
+
"step": 1116
|
1272 |
+
},
|
1273 |
+
{
|
1274 |
+
"epoch": 0.3167597765363129,
|
1275 |
+
"grad_norm": 13.443314552307129,
|
1276 |
+
"learning_rate": 1.2430464185616653e-05,
|
1277 |
+
"loss": 1.0983,
|
1278 |
+
"step": 1134
|
1279 |
+
},
|
1280 |
+
{
|
1281 |
+
"epoch": 0.3217877094972067,
|
1282 |
+
"grad_norm": 7.764914035797119,
|
1283 |
+
"learning_rate": 1.2049940057022904e-05,
|
1284 |
+
"loss": 0.8006,
|
1285 |
+
"step": 1152
|
1286 |
+
},
|
1287 |
+
{
|
1288 |
+
"epoch": 0.3268156424581006,
|
1289 |
+
"grad_norm": 7.54190731048584,
|
1290 |
+
"learning_rate": 1.1667502669280646e-05,
|
1291 |
+
"loss": 0.6122,
|
1292 |
+
"step": 1170
|
1293 |
+
},
|
1294 |
+
{
|
1295 |
+
"epoch": 0.3318435754189944,
|
1296 |
+
"grad_norm": 9.039295196533203,
|
1297 |
+
"learning_rate": 1.1283848921061318e-05,
|
1298 |
+
"loss": 0.5932,
|
1299 |
+
"step": 1188
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 0.3368715083798883,
|
1303 |
+
"grad_norm": 7.766181468963623,
|
1304 |
+
"learning_rate": 1.0899677927556045e-05,
|
1305 |
+
"loss": 0.6522,
|
1306 |
+
"step": 1206
|
1307 |
+
},
|
1308 |
+
{
|
1309 |
+
"epoch": 0.3418994413407821,
|
1310 |
+
"grad_norm": 17.672466278076172,
|
1311 |
+
"learning_rate": 1.0515689746509086e-05,
|
1312 |
+
"loss": 1.0307,
|
1313 |
+
"step": 1224
|
1314 |
+
},
|
1315 |
+
{
|
1316 |
+
"epoch": 0.346927374301676,
|
1317 |
+
"grad_norm": 8.456610679626465,
|
1318 |
+
"learning_rate": 1.0132584102533657e-05,
|
1319 |
+
"loss": 1.0892,
|
1320 |
+
"step": 1242
|
1321 |
+
},
|
1322 |
+
{
|
1323 |
+
"epoch": 0.35,
|
1324 |
+
"eval_nli-pairs_loss": 0.9248345494270325,
|
1325 |
+
"eval_nli-pairs_runtime": 3.3923,
|
1326 |
+
"eval_nli-pairs_samples_per_second": 44.218,
|
1327 |
+
"eval_nli-pairs_steps_per_second": 0.59,
|
1328 |
+
"eval_sts-test_pearson_cosine": 0.7948484764216447,
|
1329 |
+
"eval_sts-test_pearson_dot": 0.5671123561184989,
|
1330 |
+
"eval_sts-test_pearson_euclidean": 0.7505417118786587,
|
1331 |
+
"eval_sts-test_pearson_manhattan": 0.7471600903913781,
|
1332 |
+
"eval_sts-test_pearson_max": 0.7948484764216447,
|
1333 |
+
"eval_sts-test_spearman_cosine": 0.8098066598796416,
|
1334 |
+
"eval_sts-test_spearman_dot": 0.5445125288737649,
|
1335 |
+
"eval_sts-test_spearman_euclidean": 0.7404259515118012,
|
1336 |
+
"eval_sts-test_spearman_manhattan": 0.7397832260792029,
|
1337 |
+
"eval_sts-test_spearman_max": 0.8098066598796416,
|
1338 |
+
"step": 1253
|
1339 |
+
},
|
1340 |
+
{
|
1341 |
+
"epoch": 0.35,
|
1342 |
+
"eval_vitaminc-pairs_loss": 4.364264965057373,
|
1343 |
+
"eval_vitaminc-pairs_runtime": 0.8126,
|
1344 |
+
"eval_vitaminc-pairs_samples_per_second": 153.831,
|
1345 |
+
"eval_vitaminc-pairs_steps_per_second": 2.461,
|
1346 |
+
"step": 1253
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 0.35,
|
1350 |
+
"eval_qnli-contrastive_loss": 0.2623118460178375,
|
1351 |
+
"eval_qnli-contrastive_runtime": 0.1187,
|
1352 |
+
"eval_qnli-contrastive_samples_per_second": 1264.134,
|
1353 |
+
"eval_qnli-contrastive_steps_per_second": 16.855,
|
1354 |
+
"step": 1253
|
1355 |
+
},
|
1356 |
+
{
|
1357 |
+
"epoch": 0.35,
|
1358 |
+
"eval_scitail-pairs-qa_loss": 0.0632135197520256,
|
1359 |
+
"eval_scitail-pairs-qa_runtime": 0.6764,
|
1360 |
+
"eval_scitail-pairs-qa_samples_per_second": 221.754,
|
1361 |
+
"eval_scitail-pairs-qa_steps_per_second": 2.957,
|
1362 |
+
"step": 1253
|
1363 |
+
},
|
1364 |
+
{
|
1365 |
+
"epoch": 0.35,
|
1366 |
+
"eval_scitail-pairs-pos_loss": 0.2840258777141571,
|
1367 |
+
"eval_scitail-pairs-pos_runtime": 1.7876,
|
1368 |
+
"eval_scitail-pairs-pos_samples_per_second": 83.913,
|
1369 |
+
"eval_scitail-pairs-pos_steps_per_second": 1.119,
|
1370 |
+
"step": 1253
|
1371 |
+
},
|
1372 |
+
{
|
1373 |
+
"epoch": 0.35,
|
1374 |
+
"eval_xsum-pairs_loss": 0.45192036032676697,
|
1375 |
+
"eval_xsum-pairs_runtime": 0.1525,
|
1376 |
+
"eval_xsum-pairs_samples_per_second": 537.578,
|
1377 |
+
"eval_xsum-pairs_steps_per_second": 6.556,
|
1378 |
+
"step": 1253
|
1379 |
+
},
|
1380 |
+
{
|
1381 |
+
"epoch": 0.35,
|
1382 |
+
"eval_compression-pairs_loss": 0.09640318900346756,
|
1383 |
+
"eval_compression-pairs_runtime": 0.1083,
|
1384 |
+
"eval_compression-pairs_samples_per_second": 1385.341,
|
1385 |
+
"eval_compression-pairs_steps_per_second": 18.471,
|
1386 |
+
"step": 1253
|
1387 |
+
},
|
1388 |
+
{
|
1389 |
+
"epoch": 0.35,
|
1390 |
+
"eval_sciq_pairs_loss": 0.16294126212596893,
|
1391 |
+
"eval_sciq_pairs_runtime": 4.9672,
|
1392 |
+
"eval_sciq_pairs_samples_per_second": 30.198,
|
1393 |
+
"eval_sciq_pairs_steps_per_second": 0.403,
|
1394 |
+
"step": 1253
|
1395 |
+
},
|
1396 |
+
{
|
1397 |
+
"epoch": 0.35,
|
1398 |
+
"eval_qasc_pairs_loss": 0.24691826105117798,
|
1399 |
+
"eval_qasc_pairs_runtime": 0.6342,
|
1400 |
+
"eval_qasc_pairs_samples_per_second": 236.512,
|
1401 |
+
"eval_qasc_pairs_steps_per_second": 3.153,
|
1402 |
+
"step": 1253
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"epoch": 0.35,
|
1406 |
+
"eval_openbookqa_pairs_loss": 1.5197923183441162,
|
1407 |
+
"eval_openbookqa_pairs_runtime": 0.6915,
|
1408 |
+
"eval_openbookqa_pairs_samples_per_second": 216.924,
|
1409 |
+
"eval_openbookqa_pairs_steps_per_second": 2.892,
|
1410 |
+
"step": 1253
|
1411 |
+
},
|
1412 |
+
{
|
1413 |
+
"epoch": 0.35,
|
1414 |
+
"eval_msmarco_pairs_loss": 0.5905637145042419,
|
1415 |
+
"eval_msmarco_pairs_runtime": 1.1595,
|
1416 |
+
"eval_msmarco_pairs_samples_per_second": 129.367,
|
1417 |
+
"eval_msmarco_pairs_steps_per_second": 1.725,
|
1418 |
+
"step": 1253
|
1419 |
+
},
|
1420 |
+
{
|
1421 |
+
"epoch": 0.35,
|
1422 |
+
"eval_nq_pairs_loss": 0.5736532211303711,
|
1423 |
+
"eval_nq_pairs_runtime": 2.2864,
|
1424 |
+
"eval_nq_pairs_samples_per_second": 65.606,
|
1425 |
+
"eval_nq_pairs_steps_per_second": 0.875,
|
1426 |
+
"step": 1253
|
1427 |
+
},
|
1428 |
+
{
|
1429 |
+
"epoch": 0.35,
|
1430 |
+
"eval_trivia_pairs_loss": 1.1131163835525513,
|
1431 |
+
"eval_trivia_pairs_runtime": 3.1686,
|
1432 |
+
"eval_trivia_pairs_samples_per_second": 47.34,
|
1433 |
+
"eval_trivia_pairs_steps_per_second": 0.631,
|
1434 |
+
"step": 1253
|
1435 |
+
},
|
1436 |
+
{
|
1437 |
+
"epoch": 0.35,
|
1438 |
+
"eval_quora_pairs_loss": 0.2874162197113037,
|
1439 |
+
"eval_quora_pairs_runtime": 0.4087,
|
1440 |
+
"eval_quora_pairs_samples_per_second": 366.989,
|
1441 |
+
"eval_quora_pairs_steps_per_second": 4.893,
|
1442 |
+
"step": 1253
|
1443 |
+
},
|
1444 |
+
{
|
1445 |
+
"epoch": 0.35,
|
1446 |
+
"eval_gooaq_pairs_loss": 0.5454840660095215,
|
1447 |
+
"eval_gooaq_pairs_runtime": 0.7785,
|
1448 |
+
"eval_gooaq_pairs_samples_per_second": 192.683,
|
1449 |
+
"eval_gooaq_pairs_steps_per_second": 2.569,
|
1450 |
+
"step": 1253
|
1451 |
+
},
|
1452 |
+
{
|
1453 |
+
"epoch": 0.35,
|
1454 |
+
"eval_mrpc_pairs_loss": 0.05724556744098663,
|
1455 |
+
"eval_mrpc_pairs_runtime": 0.1564,
|
1456 |
+
"eval_mrpc_pairs_samples_per_second": 958.775,
|
1457 |
+
"eval_mrpc_pairs_steps_per_second": 12.784,
|
1458 |
+
"step": 1253
|
1459 |
+
},
|
1460 |
+
{
|
1461 |
+
"epoch": 0.35195530726256985,
|
1462 |
+
"grad_norm": 9.2592191696167,
|
1463 |
+
"learning_rate": 9.75105911203486e-06,
|
1464 |
+
"loss": 1.0845,
|
1465 |
+
"step": 1260
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 0.35698324022346367,
|
1469 |
+
"grad_norm": 8.712442398071289,
|
1470 |
+
"learning_rate": 9.371810011063151e-06,
|
1471 |
+
"loss": 0.931,
|
1472 |
+
"step": 1278
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 0.36201117318435755,
|
1476 |
+
"grad_norm": 12.440937995910645,
|
1477 |
+
"learning_rate": 8.995527888416549e-06,
|
1478 |
+
"loss": 0.6159,
|
1479 |
+
"step": 1296
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 0.36703910614525137,
|
1483 |
+
"grad_norm": 7.335140705108643,
|
1484 |
+
"learning_rate": 8.6228984263002e-06,
|
1485 |
+
"loss": 0.6498,
|
1486 |
+
"step": 1314
|
1487 |
+
},
|
1488 |
+
{
|
1489 |
+
"epoch": 0.37206703910614525,
|
1490 |
+
"grad_norm": 9.586339950561523,
|
1491 |
+
"learning_rate": 8.254600650838152e-06,
|
1492 |
+
"loss": 0.9762,
|
1493 |
+
"step": 1332
|
1494 |
+
},
|
1495 |
+
{
|
1496 |
+
"epoch": 0.3770949720670391,
|
1497 |
+
"grad_norm": 5.655767917633057,
|
1498 |
+
"learning_rate": 7.891305694714182e-06,
|
1499 |
+
"loss": 0.7534,
|
1500 |
+
"step": 1350
|
1501 |
+
},
|
1502 |
+
{
|
1503 |
+
"epoch": 0.38212290502793295,
|
1504 |
+
"grad_norm": 11.050688743591309,
|
1505 |
+
"learning_rate": 7.533675574196519e-06,
|
1506 |
+
"loss": 0.6792,
|
1507 |
+
"step": 1368
|
1508 |
+
},
|
1509 |
+
{
|
1510 |
+
"epoch": 0.3871508379888268,
|
1511 |
+
"grad_norm": 8.111286163330078,
|
1512 |
+
"learning_rate": 7.182361982774984e-06,
|
1513 |
+
"loss": 0.6524,
|
1514 |
+
"step": 1386
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 0.39217877094972065,
|
1518 |
+
"grad_norm": 0.9727733135223389,
|
1519 |
+
"learning_rate": 6.8380051036088735e-06,
|
1520 |
+
"loss": 0.8079,
|
1521 |
+
"step": 1404
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 0.3972067039106145,
|
1525 |
+
"grad_norm": 7.61720609664917,
|
1526 |
+
"learning_rate": 6.501232442949635e-06,
|
1527 |
+
"loss": 1.2497,
|
1528 |
+
"step": 1422
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 0.4,
|
1532 |
+
"eval_nli-pairs_loss": 0.9316923022270203,
|
1533 |
+
"eval_nli-pairs_runtime": 3.6665,
|
1534 |
+
"eval_nli-pairs_samples_per_second": 40.911,
|
1535 |
+
"eval_nli-pairs_steps_per_second": 0.545,
|
1536 |
+
"eval_sts-test_pearson_cosine": 0.7951706194225081,
|
1537 |
+
"eval_sts-test_pearson_dot": 0.5655762874531658,
|
1538 |
+
"eval_sts-test_pearson_euclidean": 0.748417242742893,
|
1539 |
+
"eval_sts-test_pearson_manhattan": 0.745117038641416,
|
1540 |
+
"eval_sts-test_pearson_max": 0.7951706194225081,
|
1541 |
+
"eval_sts-test_spearman_cosine": 0.808265389218048,
|
1542 |
+
"eval_sts-test_spearman_dot": 0.5439374661732892,
|
1543 |
+
"eval_sts-test_spearman_euclidean": 0.737979067648202,
|
1544 |
+
"eval_sts-test_spearman_manhattan": 0.7367152789420606,
|
1545 |
+
"eval_sts-test_spearman_max": 0.808265389218048,
|
1546 |
+
"step": 1432
|
1547 |
+
},
|
1548 |
+
{
|
1549 |
+
"epoch": 0.4,
|
1550 |
+
"eval_vitaminc-pairs_loss": 4.391602993011475,
|
1551 |
+
"eval_vitaminc-pairs_runtime": 0.8561,
|
1552 |
+
"eval_vitaminc-pairs_samples_per_second": 146.012,
|
1553 |
+
"eval_vitaminc-pairs_steps_per_second": 2.336,
|
1554 |
+
"step": 1432
|
1555 |
+
},
|
1556 |
+
{
|
1557 |
+
"epoch": 0.4,
|
1558 |
+
"eval_qnli-contrastive_loss": 0.2666786313056946,
|
1559 |
+
"eval_qnli-contrastive_runtime": 0.1247,
|
1560 |
+
"eval_qnli-contrastive_samples_per_second": 1202.967,
|
1561 |
+
"eval_qnli-contrastive_steps_per_second": 16.04,
|
1562 |
+
"step": 1432
|
1563 |
+
},
|
1564 |
+
{
|
1565 |
+
"epoch": 0.4,
|
1566 |
+
"eval_scitail-pairs-qa_loss": 0.06357826292514801,
|
1567 |
+
"eval_scitail-pairs-qa_runtime": 0.7031,
|
1568 |
+
"eval_scitail-pairs-qa_samples_per_second": 213.329,
|
1569 |
+
"eval_scitail-pairs-qa_steps_per_second": 2.844,
|
1570 |
+
"step": 1432
|
1571 |
+
},
|
1572 |
+
{
|
1573 |
+
"epoch": 0.4,
|
1574 |
+
"eval_scitail-pairs-pos_loss": 0.2862562835216522,
|
1575 |
+
"eval_scitail-pairs-pos_runtime": 1.9248,
|
1576 |
+
"eval_scitail-pairs-pos_samples_per_second": 77.929,
|
1577 |
+
"eval_scitail-pairs-pos_steps_per_second": 1.039,
|
1578 |
+
"step": 1432
|
1579 |
+
},
|
1580 |
+
{
|
1581 |
+
"epoch": 0.4,
|
1582 |
+
"eval_xsum-pairs_loss": 0.4477728009223938,
|
1583 |
+
"eval_xsum-pairs_runtime": 0.1563,
|
1584 |
+
"eval_xsum-pairs_samples_per_second": 524.667,
|
1585 |
+
"eval_xsum-pairs_steps_per_second": 6.398,
|
1586 |
+
"step": 1432
|
1587 |
+
},
|
1588 |
+
{
|
1589 |
+
"epoch": 0.4,
|
1590 |
+
"eval_compression-pairs_loss": 0.09554792195558548,
|
1591 |
+
"eval_compression-pairs_runtime": 0.1113,
|
1592 |
+
"eval_compression-pairs_samples_per_second": 1348.03,
|
1593 |
+
"eval_compression-pairs_steps_per_second": 17.974,
|
1594 |
+
"step": 1432
|
1595 |
+
},
|
1596 |
+
{
|
1597 |
+
"epoch": 0.4,
|
1598 |
+
"eval_sciq_pairs_loss": 0.16296182572841644,
|
1599 |
+
"eval_sciq_pairs_runtime": 4.8695,
|
1600 |
+
"eval_sciq_pairs_samples_per_second": 30.804,
|
1601 |
+
"eval_sciq_pairs_steps_per_second": 0.411,
|
1602 |
+
"step": 1432
|
1603 |
+
},
|
1604 |
+
{
|
1605 |
+
"epoch": 0.4,
|
1606 |
+
"eval_qasc_pairs_loss": 0.2451217621564865,
|
1607 |
+
"eval_qasc_pairs_runtime": 0.6585,
|
1608 |
+
"eval_qasc_pairs_samples_per_second": 227.783,
|
1609 |
+
"eval_qasc_pairs_steps_per_second": 3.037,
|
1610 |
+
"step": 1432
|
1611 |
+
},
|
1612 |
+
{
|
1613 |
+
"epoch": 0.4,
|
1614 |
+
"eval_openbookqa_pairs_loss": 1.5293627977371216,
|
1615 |
+
"eval_openbookqa_pairs_runtime": 0.6922,
|
1616 |
+
"eval_openbookqa_pairs_samples_per_second": 216.714,
|
1617 |
+
"eval_openbookqa_pairs_steps_per_second": 2.89,
|
1618 |
+
"step": 1432
|
1619 |
+
},
|
1620 |
+
{
|
1621 |
+
"epoch": 0.4,
|
1622 |
+
"eval_msmarco_pairs_loss": 0.5807374119758606,
|
1623 |
+
"eval_msmarco_pairs_runtime": 1.1603,
|
1624 |
+
"eval_msmarco_pairs_samples_per_second": 129.282,
|
1625 |
+
"eval_msmarco_pairs_steps_per_second": 1.724,
|
1626 |
+
"step": 1432
|
1627 |
+
},
|
1628 |
+
{
|
1629 |
+
"epoch": 0.4,
|
1630 |
+
"eval_nq_pairs_loss": 0.5674509406089783,
|
1631 |
+
"eval_nq_pairs_runtime": 2.2725,
|
1632 |
+
"eval_nq_pairs_samples_per_second": 66.007,
|
1633 |
+
"eval_nq_pairs_steps_per_second": 0.88,
|
1634 |
+
"step": 1432
|
1635 |
+
},
|
1636 |
+
{
|
1637 |
+
"epoch": 0.4,
|
1638 |
+
"eval_trivia_pairs_loss": 1.0616999864578247,
|
1639 |
+
"eval_trivia_pairs_runtime": 3.1673,
|
1640 |
+
"eval_trivia_pairs_samples_per_second": 47.359,
|
1641 |
+
"eval_trivia_pairs_steps_per_second": 0.631,
|
1642 |
+
"step": 1432
|
1643 |
+
},
|
1644 |
+
{
|
1645 |
+
"epoch": 0.4,
|
1646 |
+
"eval_quora_pairs_loss": 0.18273381888866425,
|
1647 |
+
"eval_quora_pairs_runtime": 0.384,
|
1648 |
+
"eval_quora_pairs_samples_per_second": 390.615,
|
1649 |
+
"eval_quora_pairs_steps_per_second": 5.208,
|
1650 |
+
"step": 1432
|
1651 |
+
},
|
1652 |
+
{
|
1653 |
+
"epoch": 0.4,
|
1654 |
+
"eval_gooaq_pairs_loss": 0.5485998392105103,
|
1655 |
+
"eval_gooaq_pairs_runtime": 0.7712,
|
1656 |
+
"eval_gooaq_pairs_samples_per_second": 194.508,
|
1657 |
+
"eval_gooaq_pairs_steps_per_second": 2.593,
|
1658 |
+
"step": 1432
|
1659 |
+
},
|
1660 |
+
{
|
1661 |
+
"epoch": 0.4,
|
1662 |
+
"eval_mrpc_pairs_loss": 0.05663560330867767,
|
1663 |
+
"eval_mrpc_pairs_runtime": 0.1016,
|
1664 |
+
"eval_mrpc_pairs_samples_per_second": 1475.752,
|
1665 |
+
"eval_mrpc_pairs_steps_per_second": 19.677,
|
1666 |
+
"step": 1432
|
1667 |
+
}
|
1668 |
+
],
|
1669 |
+
"logging_steps": 18,
|
1670 |
+
"max_steps": 7160,
|
1671 |
+
"num_input_tokens_seen": 0,
|
1672 |
+
"num_train_epochs": 2,
|
1673 |
+
"save_steps": 716,
|
1674 |
+
"stateful_callbacks": {
|
1675 |
+
"TrainerControl": {
|
1676 |
+
"args": {
|
1677 |
+
"should_epoch_stop": false,
|
1678 |
+
"should_evaluate": false,
|
1679 |
+
"should_log": false,
|
1680 |
+
"should_save": true,
|
1681 |
+
"should_training_stop": false
|
1682 |
+
},
|
1683 |
+
"attributes": {}
|
1684 |
+
}
|
1685 |
+
},
|
1686 |
+
"total_flos": 0.0,
|
1687 |
+
"train_batch_size": 82,
|
1688 |
+
"trial_name": null,
|
1689 |
+
"trial_params": null
|
1690 |
+
}
|
checkpoint-1432/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5ad0ebae5d54ccad20b596d9ef597aaa6d8c8f398f1064eecf9dd488a2646a3
|
3 |
+
size 5688
|