Training in progress, step 5874, checkpoint
Browse files- checkpoint-5874/1_Pooling/config.json +10 -0
- checkpoint-5874/README.md +0 -0
- checkpoint-5874/added_tokens.json +3 -0
- checkpoint-5874/config.json +35 -0
- checkpoint-5874/config_sentence_transformers.json +10 -0
- checkpoint-5874/modules.json +14 -0
- checkpoint-5874/optimizer.pt +3 -0
- checkpoint-5874/pytorch_model.bin +3 -0
- checkpoint-5874/rng_state.pth +3 -0
- checkpoint-5874/scheduler.pt +3 -0
- checkpoint-5874/sentence_bert_config.json +4 -0
- checkpoint-5874/special_tokens_map.json +15 -0
- checkpoint-5874/spm.model +3 -0
- checkpoint-5874/tokenizer.json +0 -0
- checkpoint-5874/tokenizer_config.json +58 -0
- checkpoint-5874/trainer_state.json +1216 -0
- checkpoint-5874/training_args.bin +3 -0
checkpoint-5874/1_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-5874/README.md
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-5874/added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[MASK]": 128000
|
3 |
+
}
|
checkpoint-5874/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-5874/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-5874/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-5874/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e40f1a6974c6b0db10ee817ed4b2ddd7ba929e0f9810d6ebe7fcc6cd0b16322
|
3 |
+
size 1130520122
|
checkpoint-5874/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9acb557e65a3f5bbf015002ac1d6e3e10e8845fb0e79f638c10c2c90f2694846
|
3 |
+
size 565251810
|
checkpoint-5874/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50dfd0959b6b97a02356a1ba031b87e14e8e016101c223d79680fc0194ecb992
|
3 |
+
size 14244
|
checkpoint-5874/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3db10af0257d6d4a944e1697babca24768a0af887bdbdc8def22f154cdae7b4a
|
3 |
+
size 1064
|
checkpoint-5874/sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 512,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|
checkpoint-5874/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-5874/spm.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
3 |
+
size 2464616
|
checkpoint-5874/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-5874/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-5874/trainer_state.json
ADDED
@@ -0,0 +1,1216 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 735,
|
6 |
+
"global_step": 5874,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.02502553626149132,
|
13 |
+
"grad_norm": 65.55949401855469,
|
14 |
+
"learning_rate": 4.834865509022812e-07,
|
15 |
+
"loss": 16.851,
|
16 |
+
"step": 147
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.05005107252298264,
|
20 |
+
"grad_norm": 23.207971572875977,
|
21 |
+
"learning_rate": 9.805924412665985e-07,
|
22 |
+
"loss": 11.2787,
|
23 |
+
"step": 294
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.07507660878447395,
|
27 |
+
"grad_norm": 176.1532440185547,
|
28 |
+
"learning_rate": 1.481103166496425e-06,
|
29 |
+
"loss": 8.9166,
|
30 |
+
"step": 441
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.10010214504596528,
|
34 |
+
"grad_norm": 22.1564998626709,
|
35 |
+
"learning_rate": 1.981613891726251e-06,
|
36 |
+
"loss": 7.9463,
|
37 |
+
"step": 588
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.12512768130745658,
|
41 |
+
"grad_norm": 20.11876106262207,
|
42 |
+
"learning_rate": 2.4821246169560777e-06,
|
43 |
+
"loss": 7.2108,
|
44 |
+
"step": 735
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.12512768130745658,
|
48 |
+
"eval_nli-pairs_loss": 6.905651569366455,
|
49 |
+
"eval_nli-pairs_runtime": 4.0844,
|
50 |
+
"eval_nli-pairs_samples_per_second": 36.725,
|
51 |
+
"eval_nli-pairs_steps_per_second": 1.224,
|
52 |
+
"eval_sts-test_pearson_cosine": 0.3740256550072784,
|
53 |
+
"eval_sts-test_pearson_dot": 0.13384893803205677,
|
54 |
+
"eval_sts-test_pearson_euclidean": 0.3912387619869807,
|
55 |
+
"eval_sts-test_pearson_manhattan": 0.4202605137823524,
|
56 |
+
"eval_sts-test_pearson_max": 0.4202605137823524,
|
57 |
+
"eval_sts-test_spearman_cosine": 0.37210107338950205,
|
58 |
+
"eval_sts-test_spearman_dot": 0.12092409843417483,
|
59 |
+
"eval_sts-test_spearman_euclidean": 0.39172287978780546,
|
60 |
+
"eval_sts-test_spearman_manhattan": 0.4169664738563951,
|
61 |
+
"eval_sts-test_spearman_max": 0.4169664738563951,
|
62 |
+
"step": 735
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.12512768130745658,
|
66 |
+
"eval_vitaminc-pairs_loss": 5.720878601074219,
|
67 |
+
"eval_vitaminc-pairs_runtime": 2.1703,
|
68 |
+
"eval_vitaminc-pairs_samples_per_second": 69.115,
|
69 |
+
"eval_vitaminc-pairs_steps_per_second": 2.304,
|
70 |
+
"step": 735
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 0.12512768130745658,
|
74 |
+
"eval_qnli-contrastive_loss": 8.1649751663208,
|
75 |
+
"eval_qnli-contrastive_runtime": 0.4937,
|
76 |
+
"eval_qnli-contrastive_samples_per_second": 303.841,
|
77 |
+
"eval_qnli-contrastive_steps_per_second": 10.128,
|
78 |
+
"step": 735
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 0.12512768130745658,
|
82 |
+
"eval_scitail-pairs-qa_loss": 3.7859296798706055,
|
83 |
+
"eval_scitail-pairs-qa_runtime": 1.1509,
|
84 |
+
"eval_scitail-pairs-qa_samples_per_second": 130.329,
|
85 |
+
"eval_scitail-pairs-qa_steps_per_second": 4.344,
|
86 |
+
"step": 735
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.12512768130745658,
|
90 |
+
"eval_scitail-pairs-pos_loss": 3.9919917583465576,
|
91 |
+
"eval_scitail-pairs-pos_runtime": 2.1442,
|
92 |
+
"eval_scitail-pairs-pos_samples_per_second": 69.956,
|
93 |
+
"eval_scitail-pairs-pos_steps_per_second": 2.332,
|
94 |
+
"step": 735
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.12512768130745658,
|
98 |
+
"eval_xsum-pairs_loss": 4.600368976593018,
|
99 |
+
"eval_xsum-pairs_runtime": 2.26,
|
100 |
+
"eval_xsum-pairs_samples_per_second": 66.371,
|
101 |
+
"eval_xsum-pairs_steps_per_second": 2.212,
|
102 |
+
"step": 735
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"epoch": 0.12512768130745658,
|
106 |
+
"eval_compression-pairs_loss": 3.3037569522857666,
|
107 |
+
"eval_compression-pairs_runtime": 0.449,
|
108 |
+
"eval_compression-pairs_samples_per_second": 334.078,
|
109 |
+
"eval_compression-pairs_steps_per_second": 11.136,
|
110 |
+
"step": 735
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.12512768130745658,
|
114 |
+
"eval_sciq_pairs_loss": 10.214456558227539,
|
115 |
+
"eval_sciq_pairs_runtime": 7.1179,
|
116 |
+
"eval_sciq_pairs_samples_per_second": 21.074,
|
117 |
+
"eval_sciq_pairs_steps_per_second": 0.702,
|
118 |
+
"step": 735
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 0.12512768130745658,
|
122 |
+
"eval_qasc_pairs_loss": 10.58031940460205,
|
123 |
+
"eval_qasc_pairs_runtime": 2.0175,
|
124 |
+
"eval_qasc_pairs_samples_per_second": 74.348,
|
125 |
+
"eval_qasc_pairs_steps_per_second": 2.478,
|
126 |
+
"step": 735
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 0.12512768130745658,
|
130 |
+
"eval_openbookqa_pairs_loss": 7.862658977508545,
|
131 |
+
"eval_openbookqa_pairs_runtime": 0.8571,
|
132 |
+
"eval_openbookqa_pairs_samples_per_second": 120.168,
|
133 |
+
"eval_openbookqa_pairs_steps_per_second": 4.667,
|
134 |
+
"step": 735
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.12512768130745658,
|
138 |
+
"eval_msmarco_pairs_loss": 8.754273414611816,
|
139 |
+
"eval_msmarco_pairs_runtime": 2.7533,
|
140 |
+
"eval_msmarco_pairs_samples_per_second": 54.481,
|
141 |
+
"eval_msmarco_pairs_steps_per_second": 1.816,
|
142 |
+
"step": 735
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.12512768130745658,
|
146 |
+
"eval_nq_pairs_loss": 8.415486335754395,
|
147 |
+
"eval_nq_pairs_runtime": 5.0894,
|
148 |
+
"eval_nq_pairs_samples_per_second": 29.473,
|
149 |
+
"eval_nq_pairs_steps_per_second": 0.982,
|
150 |
+
"step": 735
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.12512768130745658,
|
154 |
+
"eval_trivia_pairs_loss": 9.051105499267578,
|
155 |
+
"eval_trivia_pairs_runtime": 9.5498,
|
156 |
+
"eval_trivia_pairs_samples_per_second": 15.707,
|
157 |
+
"eval_trivia_pairs_steps_per_second": 0.524,
|
158 |
+
"step": 735
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.12512768130745658,
|
162 |
+
"eval_quora_pairs_loss": 4.5232110023498535,
|
163 |
+
"eval_quora_pairs_runtime": 1.1469,
|
164 |
+
"eval_quora_pairs_samples_per_second": 130.785,
|
165 |
+
"eval_quora_pairs_steps_per_second": 4.36,
|
166 |
+
"step": 735
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"epoch": 0.12512768130745658,
|
170 |
+
"eval_gooaq_pairs_loss": 7.579105854034424,
|
171 |
+
"eval_gooaq_pairs_runtime": 2.0491,
|
172 |
+
"eval_gooaq_pairs_samples_per_second": 73.203,
|
173 |
+
"eval_gooaq_pairs_steps_per_second": 2.44,
|
174 |
+
"step": 735
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.1501532175689479,
|
178 |
+
"grad_norm": 31.7736759185791,
|
179 |
+
"learning_rate": 2.982635342185904e-06,
|
180 |
+
"loss": 6.7709,
|
181 |
+
"step": 882
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 0.1751787538304392,
|
185 |
+
"grad_norm": 31.57339096069336,
|
186 |
+
"learning_rate": 3.4831460674157306e-06,
|
187 |
+
"loss": 6.1746,
|
188 |
+
"step": 1029
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.20020429009193055,
|
192 |
+
"grad_norm": 25.392702102661133,
|
193 |
+
"learning_rate": 3.9836567926455565e-06,
|
194 |
+
"loss": 5.7706,
|
195 |
+
"step": 1176
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.22522982635342187,
|
199 |
+
"grad_norm": 32.390472412109375,
|
200 |
+
"learning_rate": 4.484167517875383e-06,
|
201 |
+
"loss": 5.7283,
|
202 |
+
"step": 1323
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 0.25025536261491316,
|
206 |
+
"grad_norm": 18.85039520263672,
|
207 |
+
"learning_rate": 4.98467824310521e-06,
|
208 |
+
"loss": 5.1856,
|
209 |
+
"step": 1470
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.25025536261491316,
|
213 |
+
"eval_nli-pairs_loss": 4.352054119110107,
|
214 |
+
"eval_nli-pairs_runtime": 4.1476,
|
215 |
+
"eval_nli-pairs_samples_per_second": 36.165,
|
216 |
+
"eval_nli-pairs_steps_per_second": 1.206,
|
217 |
+
"eval_sts-test_pearson_cosine": 0.6694155778571752,
|
218 |
+
"eval_sts-test_pearson_dot": 0.5201102118957572,
|
219 |
+
"eval_sts-test_pearson_euclidean": 0.6613028243200022,
|
220 |
+
"eval_sts-test_pearson_manhattan": 0.6670710500315469,
|
221 |
+
"eval_sts-test_pearson_max": 0.6694155778571752,
|
222 |
+
"eval_sts-test_spearman_cosine": 0.6367853204388882,
|
223 |
+
"eval_sts-test_spearman_dot": 0.4940207180607985,
|
224 |
+
"eval_sts-test_spearman_euclidean": 0.6391132775161348,
|
225 |
+
"eval_sts-test_spearman_manhattan": 0.6446159957787251,
|
226 |
+
"eval_sts-test_spearman_max": 0.6446159957787251,
|
227 |
+
"step": 1470
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.25025536261491316,
|
231 |
+
"eval_vitaminc-pairs_loss": 3.4987735748291016,
|
232 |
+
"eval_vitaminc-pairs_runtime": 2.1678,
|
233 |
+
"eval_vitaminc-pairs_samples_per_second": 69.194,
|
234 |
+
"eval_vitaminc-pairs_steps_per_second": 2.306,
|
235 |
+
"step": 1470
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 0.25025536261491316,
|
239 |
+
"eval_qnli-contrastive_loss": 12.915559768676758,
|
240 |
+
"eval_qnli-contrastive_runtime": 0.4918,
|
241 |
+
"eval_qnli-contrastive_samples_per_second": 304.99,
|
242 |
+
"eval_qnli-contrastive_steps_per_second": 10.166,
|
243 |
+
"step": 1470
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.25025536261491316,
|
247 |
+
"eval_scitail-pairs-qa_loss": 1.3250077962875366,
|
248 |
+
"eval_scitail-pairs-qa_runtime": 1.154,
|
249 |
+
"eval_scitail-pairs-qa_samples_per_second": 129.984,
|
250 |
+
"eval_scitail-pairs-qa_steps_per_second": 4.333,
|
251 |
+
"step": 1470
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 0.25025536261491316,
|
255 |
+
"eval_scitail-pairs-pos_loss": 2.457335948944092,
|
256 |
+
"eval_scitail-pairs-pos_runtime": 2.1475,
|
257 |
+
"eval_scitail-pairs-pos_samples_per_second": 69.85,
|
258 |
+
"eval_scitail-pairs-pos_steps_per_second": 2.328,
|
259 |
+
"step": 1470
|
260 |
+
},
|
261 |
+
{
|
262 |
+
"epoch": 0.25025536261491316,
|
263 |
+
"eval_xsum-pairs_loss": 3.071201801300049,
|
264 |
+
"eval_xsum-pairs_runtime": 2.2634,
|
265 |
+
"eval_xsum-pairs_samples_per_second": 66.271,
|
266 |
+
"eval_xsum-pairs_steps_per_second": 2.209,
|
267 |
+
"step": 1470
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.25025536261491316,
|
271 |
+
"eval_compression-pairs_loss": 2.0629916191101074,
|
272 |
+
"eval_compression-pairs_runtime": 0.4529,
|
273 |
+
"eval_compression-pairs_samples_per_second": 331.23,
|
274 |
+
"eval_compression-pairs_steps_per_second": 11.041,
|
275 |
+
"step": 1470
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.25025536261491316,
|
279 |
+
"eval_sciq_pairs_loss": 9.06814193725586,
|
280 |
+
"eval_sciq_pairs_runtime": 7.1445,
|
281 |
+
"eval_sciq_pairs_samples_per_second": 20.995,
|
282 |
+
"eval_sciq_pairs_steps_per_second": 0.7,
|
283 |
+
"step": 1470
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 0.25025536261491316,
|
287 |
+
"eval_qasc_pairs_loss": 9.245658874511719,
|
288 |
+
"eval_qasc_pairs_runtime": 2.0471,
|
289 |
+
"eval_qasc_pairs_samples_per_second": 73.274,
|
290 |
+
"eval_qasc_pairs_steps_per_second": 2.442,
|
291 |
+
"step": 1470
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.25025536261491316,
|
295 |
+
"eval_openbookqa_pairs_loss": 5.652446746826172,
|
296 |
+
"eval_openbookqa_pairs_runtime": 0.8946,
|
297 |
+
"eval_openbookqa_pairs_samples_per_second": 115.14,
|
298 |
+
"eval_openbookqa_pairs_steps_per_second": 4.471,
|
299 |
+
"step": 1470
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 0.25025536261491316,
|
303 |
+
"eval_msmarco_pairs_loss": 4.844855785369873,
|
304 |
+
"eval_msmarco_pairs_runtime": 2.7887,
|
305 |
+
"eval_msmarco_pairs_samples_per_second": 53.788,
|
306 |
+
"eval_msmarco_pairs_steps_per_second": 1.793,
|
307 |
+
"step": 1470
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 0.25025536261491316,
|
311 |
+
"eval_nq_pairs_loss": 5.023958206176758,
|
312 |
+
"eval_nq_pairs_runtime": 5.0823,
|
313 |
+
"eval_nq_pairs_samples_per_second": 29.514,
|
314 |
+
"eval_nq_pairs_steps_per_second": 0.984,
|
315 |
+
"step": 1470
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 0.25025536261491316,
|
319 |
+
"eval_trivia_pairs_loss": 5.2907304763793945,
|
320 |
+
"eval_trivia_pairs_runtime": 9.6673,
|
321 |
+
"eval_trivia_pairs_samples_per_second": 15.516,
|
322 |
+
"eval_trivia_pairs_steps_per_second": 0.517,
|
323 |
+
"step": 1470
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 0.25025536261491316,
|
327 |
+
"eval_quora_pairs_loss": 1.5572240352630615,
|
328 |
+
"eval_quora_pairs_runtime": 1.1979,
|
329 |
+
"eval_quora_pairs_samples_per_second": 125.218,
|
330 |
+
"eval_quora_pairs_steps_per_second": 4.174,
|
331 |
+
"step": 1470
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.25025536261491316,
|
335 |
+
"eval_gooaq_pairs_loss": 3.970768928527832,
|
336 |
+
"eval_gooaq_pairs_runtime": 2.117,
|
337 |
+
"eval_gooaq_pairs_samples_per_second": 70.855,
|
338 |
+
"eval_gooaq_pairs_steps_per_second": 2.362,
|
339 |
+
"step": 1470
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.2752808988764045,
|
343 |
+
"grad_norm": 40.67585754394531,
|
344 |
+
"learning_rate": 5.4851889683350365e-06,
|
345 |
+
"loss": 4.185,
|
346 |
+
"step": 1617
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 0.3003064351378958,
|
350 |
+
"grad_norm": 45.92570495605469,
|
351 |
+
"learning_rate": 5.985699693564862e-06,
|
352 |
+
"loss": 4.6367,
|
353 |
+
"step": 1764
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.32533197139938713,
|
357 |
+
"grad_norm": 13.566838264465332,
|
358 |
+
"learning_rate": 6.486210418794688e-06,
|
359 |
+
"loss": 4.3615,
|
360 |
+
"step": 1911
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 0.3503575076608784,
|
364 |
+
"grad_norm": 9.495999336242676,
|
365 |
+
"learning_rate": 6.986721144024515e-06,
|
366 |
+
"loss": 4.1791,
|
367 |
+
"step": 2058
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 0.37538304392236976,
|
371 |
+
"grad_norm": 32.735416412353516,
|
372 |
+
"learning_rate": 7.487231869254341e-06,
|
373 |
+
"loss": 4.1051,
|
374 |
+
"step": 2205
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.37538304392236976,
|
378 |
+
"eval_nli-pairs_loss": 3.2717113494873047,
|
379 |
+
"eval_nli-pairs_runtime": 4.0124,
|
380 |
+
"eval_nli-pairs_samples_per_second": 37.384,
|
381 |
+
"eval_nli-pairs_steps_per_second": 1.246,
|
382 |
+
"eval_sts-test_pearson_cosine": 0.6958570089637609,
|
383 |
+
"eval_sts-test_pearson_dot": 0.5824298957890577,
|
384 |
+
"eval_sts-test_pearson_euclidean": 0.6893962819387462,
|
385 |
+
"eval_sts-test_pearson_manhattan": 0.6993681181979946,
|
386 |
+
"eval_sts-test_pearson_max": 0.6993681181979946,
|
387 |
+
"eval_sts-test_spearman_cosine": 0.6652712160836801,
|
388 |
+
"eval_sts-test_spearman_dot": 0.5536505624407877,
|
389 |
+
"eval_sts-test_spearman_euclidean": 0.6659844314307678,
|
390 |
+
"eval_sts-test_spearman_manhattan": 0.675740852112121,
|
391 |
+
"eval_sts-test_spearman_max": 0.675740852112121,
|
392 |
+
"step": 2205
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 0.37538304392236976,
|
396 |
+
"eval_vitaminc-pairs_loss": 2.7197911739349365,
|
397 |
+
"eval_vitaminc-pairs_runtime": 2.1625,
|
398 |
+
"eval_vitaminc-pairs_samples_per_second": 69.365,
|
399 |
+
"eval_vitaminc-pairs_steps_per_second": 2.312,
|
400 |
+
"step": 2205
|
401 |
+
},
|
402 |
+
{
|
403 |
+
"epoch": 0.37538304392236976,
|
404 |
+
"eval_qnli-contrastive_loss": 9.638714790344238,
|
405 |
+
"eval_qnli-contrastive_runtime": 0.4877,
|
406 |
+
"eval_qnli-contrastive_samples_per_second": 307.567,
|
407 |
+
"eval_qnli-contrastive_steps_per_second": 10.252,
|
408 |
+
"step": 2205
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.37538304392236976,
|
412 |
+
"eval_scitail-pairs-qa_loss": 0.8106752634048462,
|
413 |
+
"eval_scitail-pairs-qa_runtime": 1.1588,
|
414 |
+
"eval_scitail-pairs-qa_samples_per_second": 129.449,
|
415 |
+
"eval_scitail-pairs-qa_steps_per_second": 4.315,
|
416 |
+
"step": 2205
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.37538304392236976,
|
420 |
+
"eval_scitail-pairs-pos_loss": 1.8894625902175903,
|
421 |
+
"eval_scitail-pairs-pos_runtime": 2.1181,
|
422 |
+
"eval_scitail-pairs-pos_samples_per_second": 70.817,
|
423 |
+
"eval_scitail-pairs-pos_steps_per_second": 2.361,
|
424 |
+
"step": 2205
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 0.37538304392236976,
|
428 |
+
"eval_xsum-pairs_loss": 2.262718439102173,
|
429 |
+
"eval_xsum-pairs_runtime": 2.2585,
|
430 |
+
"eval_xsum-pairs_samples_per_second": 66.416,
|
431 |
+
"eval_xsum-pairs_steps_per_second": 2.214,
|
432 |
+
"step": 2205
|
433 |
+
},
|
434 |
+
{
|
435 |
+
"epoch": 0.37538304392236976,
|
436 |
+
"eval_compression-pairs_loss": 1.4910633563995361,
|
437 |
+
"eval_compression-pairs_runtime": 0.4462,
|
438 |
+
"eval_compression-pairs_samples_per_second": 336.204,
|
439 |
+
"eval_compression-pairs_steps_per_second": 11.207,
|
440 |
+
"step": 2205
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 0.37538304392236976,
|
444 |
+
"eval_sciq_pairs_loss": 8.59740161895752,
|
445 |
+
"eval_sciq_pairs_runtime": 7.1845,
|
446 |
+
"eval_sciq_pairs_samples_per_second": 20.878,
|
447 |
+
"eval_sciq_pairs_steps_per_second": 0.696,
|
448 |
+
"step": 2205
|
449 |
+
},
|
450 |
+
{
|
451 |
+
"epoch": 0.37538304392236976,
|
452 |
+
"eval_qasc_pairs_loss": 8.103879928588867,
|
453 |
+
"eval_qasc_pairs_runtime": 2.0762,
|
454 |
+
"eval_qasc_pairs_samples_per_second": 72.246,
|
455 |
+
"eval_qasc_pairs_steps_per_second": 2.408,
|
456 |
+
"step": 2205
|
457 |
+
},
|
458 |
+
{
|
459 |
+
"epoch": 0.37538304392236976,
|
460 |
+
"eval_openbookqa_pairs_loss": 5.090969562530518,
|
461 |
+
"eval_openbookqa_pairs_runtime": 0.89,
|
462 |
+
"eval_openbookqa_pairs_samples_per_second": 115.726,
|
463 |
+
"eval_openbookqa_pairs_steps_per_second": 4.494,
|
464 |
+
"step": 2205
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.37538304392236976,
|
468 |
+
"eval_msmarco_pairs_loss": 3.9566943645477295,
|
469 |
+
"eval_msmarco_pairs_runtime": 2.8183,
|
470 |
+
"eval_msmarco_pairs_samples_per_second": 53.223,
|
471 |
+
"eval_msmarco_pairs_steps_per_second": 1.774,
|
472 |
+
"step": 2205
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 0.37538304392236976,
|
476 |
+
"eval_nq_pairs_loss": 4.009054183959961,
|
477 |
+
"eval_nq_pairs_runtime": 5.0219,
|
478 |
+
"eval_nq_pairs_samples_per_second": 29.869,
|
479 |
+
"eval_nq_pairs_steps_per_second": 0.996,
|
480 |
+
"step": 2205
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 0.37538304392236976,
|
484 |
+
"eval_trivia_pairs_loss": 4.286431312561035,
|
485 |
+
"eval_trivia_pairs_runtime": 9.4975,
|
486 |
+
"eval_trivia_pairs_samples_per_second": 15.794,
|
487 |
+
"eval_trivia_pairs_steps_per_second": 0.526,
|
488 |
+
"step": 2205
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 0.37538304392236976,
|
492 |
+
"eval_quora_pairs_loss": 1.123273491859436,
|
493 |
+
"eval_quora_pairs_runtime": 1.1487,
|
494 |
+
"eval_quora_pairs_samples_per_second": 130.586,
|
495 |
+
"eval_quora_pairs_steps_per_second": 4.353,
|
496 |
+
"step": 2205
|
497 |
+
},
|
498 |
+
{
|
499 |
+
"epoch": 0.37538304392236976,
|
500 |
+
"eval_gooaq_pairs_loss": 3.222414255142212,
|
501 |
+
"eval_gooaq_pairs_runtime": 2.0173,
|
502 |
+
"eval_gooaq_pairs_samples_per_second": 74.357,
|
503 |
+
"eval_gooaq_pairs_steps_per_second": 2.479,
|
504 |
+
"step": 2205
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 0.4004085801838611,
|
508 |
+
"grad_norm": 218.56105041503906,
|
509 |
+
"learning_rate": 7.987742594484168e-06,
|
510 |
+
"loss": 3.7674,
|
511 |
+
"step": 2352
|
512 |
+
},
|
513 |
+
{
|
514 |
+
"epoch": 0.4254341164453524,
|
515 |
+
"grad_norm": 27.877609252929688,
|
516 |
+
"learning_rate": 8.488253319713993e-06,
|
517 |
+
"loss": 3.8729,
|
518 |
+
"step": 2499
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 0.45045965270684374,
|
522 |
+
"grad_norm": 33.50013732910156,
|
523 |
+
"learning_rate": 8.988764044943822e-06,
|
524 |
+
"loss": 3.4527,
|
525 |
+
"step": 2646
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 0.475485188968335,
|
529 |
+
"grad_norm": 14.015911102294922,
|
530 |
+
"learning_rate": 9.489274770173647e-06,
|
531 |
+
"loss": 3.3545,
|
532 |
+
"step": 2793
|
533 |
+
},
|
534 |
+
{
|
535 |
+
"epoch": 0.5005107252298263,
|
536 |
+
"grad_norm": 33.59694290161133,
|
537 |
+
"learning_rate": 9.989785495403473e-06,
|
538 |
+
"loss": 3.3247,
|
539 |
+
"step": 2940
|
540 |
+
},
|
541 |
+
{
|
542 |
+
"epoch": 0.5005107252298263,
|
543 |
+
"eval_nli-pairs_loss": 2.7121565341949463,
|
544 |
+
"eval_nli-pairs_runtime": 4.1564,
|
545 |
+
"eval_nli-pairs_samples_per_second": 36.089,
|
546 |
+
"eval_nli-pairs_steps_per_second": 1.203,
|
547 |
+
"eval_sts-test_pearson_cosine": 0.716623047702725,
|
548 |
+
"eval_sts-test_pearson_dot": 0.6128451070598809,
|
549 |
+
"eval_sts-test_pearson_euclidean": 0.7138791236031807,
|
550 |
+
"eval_sts-test_pearson_manhattan": 0.7213151818687454,
|
551 |
+
"eval_sts-test_pearson_max": 0.7213151818687454,
|
552 |
+
"eval_sts-test_spearman_cosine": 0.6919792400941177,
|
553 |
+
"eval_sts-test_spearman_dot": 0.5867158357121192,
|
554 |
+
"eval_sts-test_spearman_euclidean": 0.6925037259567834,
|
555 |
+
"eval_sts-test_spearman_manhattan": 0.7008895667910079,
|
556 |
+
"eval_sts-test_spearman_max": 0.7008895667910079,
|
557 |
+
"step": 2940
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.5005107252298263,
|
561 |
+
"eval_vitaminc-pairs_loss": 2.225992441177368,
|
562 |
+
"eval_vitaminc-pairs_runtime": 2.253,
|
563 |
+
"eval_vitaminc-pairs_samples_per_second": 66.577,
|
564 |
+
"eval_vitaminc-pairs_steps_per_second": 2.219,
|
565 |
+
"step": 2940
|
566 |
+
},
|
567 |
+
{
|
568 |
+
"epoch": 0.5005107252298263,
|
569 |
+
"eval_qnli-contrastive_loss": 4.92629861831665,
|
570 |
+
"eval_qnli-contrastive_runtime": 0.5005,
|
571 |
+
"eval_qnli-contrastive_samples_per_second": 299.691,
|
572 |
+
"eval_qnli-contrastive_steps_per_second": 9.99,
|
573 |
+
"step": 2940
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.5005107252298263,
|
577 |
+
"eval_scitail-pairs-qa_loss": 0.5898066163063049,
|
578 |
+
"eval_scitail-pairs-qa_runtime": 1.2227,
|
579 |
+
"eval_scitail-pairs-qa_samples_per_second": 122.682,
|
580 |
+
"eval_scitail-pairs-qa_steps_per_second": 4.089,
|
581 |
+
"step": 2940
|
582 |
+
},
|
583 |
+
{
|
584 |
+
"epoch": 0.5005107252298263,
|
585 |
+
"eval_scitail-pairs-pos_loss": 1.4237287044525146,
|
586 |
+
"eval_scitail-pairs-pos_runtime": 2.4409,
|
587 |
+
"eval_scitail-pairs-pos_samples_per_second": 61.452,
|
588 |
+
"eval_scitail-pairs-pos_steps_per_second": 2.048,
|
589 |
+
"step": 2940
|
590 |
+
},
|
591 |
+
{
|
592 |
+
"epoch": 0.5005107252298263,
|
593 |
+
"eval_xsum-pairs_loss": 1.8388895988464355,
|
594 |
+
"eval_xsum-pairs_runtime": 2.2831,
|
595 |
+
"eval_xsum-pairs_samples_per_second": 65.7,
|
596 |
+
"eval_xsum-pairs_steps_per_second": 2.19,
|
597 |
+
"step": 2940
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.5005107252298263,
|
601 |
+
"eval_compression-pairs_loss": 1.1590967178344727,
|
602 |
+
"eval_compression-pairs_runtime": 0.5152,
|
603 |
+
"eval_compression-pairs_samples_per_second": 291.165,
|
604 |
+
"eval_compression-pairs_steps_per_second": 9.706,
|
605 |
+
"step": 2940
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 0.5005107252298263,
|
609 |
+
"eval_sciq_pairs_loss": 8.282496452331543,
|
610 |
+
"eval_sciq_pairs_runtime": 7.2871,
|
611 |
+
"eval_sciq_pairs_samples_per_second": 20.584,
|
612 |
+
"eval_sciq_pairs_steps_per_second": 0.686,
|
613 |
+
"step": 2940
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 0.5005107252298263,
|
617 |
+
"eval_qasc_pairs_loss": 7.817965507507324,
|
618 |
+
"eval_qasc_pairs_runtime": 2.0211,
|
619 |
+
"eval_qasc_pairs_samples_per_second": 74.218,
|
620 |
+
"eval_qasc_pairs_steps_per_second": 2.474,
|
621 |
+
"step": 2940
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 0.5005107252298263,
|
625 |
+
"eval_openbookqa_pairs_loss": 4.619383811950684,
|
626 |
+
"eval_openbookqa_pairs_runtime": 0.8531,
|
627 |
+
"eval_openbookqa_pairs_samples_per_second": 120.731,
|
628 |
+
"eval_openbookqa_pairs_steps_per_second": 4.689,
|
629 |
+
"step": 2940
|
630 |
+
},
|
631 |
+
{
|
632 |
+
"epoch": 0.5005107252298263,
|
633 |
+
"eval_msmarco_pairs_loss": 3.478559970855713,
|
634 |
+
"eval_msmarco_pairs_runtime": 2.7512,
|
635 |
+
"eval_msmarco_pairs_samples_per_second": 54.522,
|
636 |
+
"eval_msmarco_pairs_steps_per_second": 1.817,
|
637 |
+
"step": 2940
|
638 |
+
},
|
639 |
+
{
|
640 |
+
"epoch": 0.5005107252298263,
|
641 |
+
"eval_nq_pairs_loss": 3.3449866771698,
|
642 |
+
"eval_nq_pairs_runtime": 5.0591,
|
643 |
+
"eval_nq_pairs_samples_per_second": 29.649,
|
644 |
+
"eval_nq_pairs_steps_per_second": 0.988,
|
645 |
+
"step": 2940
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 0.5005107252298263,
|
649 |
+
"eval_trivia_pairs_loss": 3.524484872817993,
|
650 |
+
"eval_trivia_pairs_runtime": 9.662,
|
651 |
+
"eval_trivia_pairs_samples_per_second": 15.525,
|
652 |
+
"eval_trivia_pairs_steps_per_second": 0.517,
|
653 |
+
"step": 2940
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.5005107252298263,
|
657 |
+
"eval_quora_pairs_loss": 0.9095575213432312,
|
658 |
+
"eval_quora_pairs_runtime": 1.2482,
|
659 |
+
"eval_quora_pairs_samples_per_second": 120.175,
|
660 |
+
"eval_quora_pairs_steps_per_second": 4.006,
|
661 |
+
"step": 2940
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 0.5005107252298263,
|
665 |
+
"eval_gooaq_pairs_loss": 2.6586034297943115,
|
666 |
+
"eval_gooaq_pairs_runtime": 2.1091,
|
667 |
+
"eval_gooaq_pairs_samples_per_second": 71.12,
|
668 |
+
"eval_gooaq_pairs_steps_per_second": 2.371,
|
669 |
+
"step": 2940
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.5255362614913177,
|
673 |
+
"grad_norm": 35.33409118652344,
|
674 |
+
"learning_rate": 1.04902962206333e-05,
|
675 |
+
"loss": 3.116,
|
676 |
+
"step": 3087
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 0.550561797752809,
|
680 |
+
"grad_norm": 22.29003143310547,
|
681 |
+
"learning_rate": 1.0990806945863125e-05,
|
682 |
+
"loss": 3.2418,
|
683 |
+
"step": 3234
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 0.5755873340143003,
|
687 |
+
"grad_norm": 31.277965545654297,
|
688 |
+
"learning_rate": 1.1491317671092953e-05,
|
689 |
+
"loss": 3.0757,
|
690 |
+
"step": 3381
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 0.6006128702757916,
|
694 |
+
"grad_norm": 24.612506866455078,
|
695 |
+
"learning_rate": 1.1991828396322778e-05,
|
696 |
+
"loss": 2.8524,
|
697 |
+
"step": 3528
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.625638406537283,
|
701 |
+
"grad_norm": 25.11741065979004,
|
702 |
+
"learning_rate": 1.2492339121552605e-05,
|
703 |
+
"loss": 2.6875,
|
704 |
+
"step": 3675
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.625638406537283,
|
708 |
+
"eval_nli-pairs_loss": 2.479051113128662,
|
709 |
+
"eval_nli-pairs_runtime": 3.9943,
|
710 |
+
"eval_nli-pairs_samples_per_second": 37.553,
|
711 |
+
"eval_nli-pairs_steps_per_second": 1.252,
|
712 |
+
"eval_sts-test_pearson_cosine": 0.7278742453545186,
|
713 |
+
"eval_sts-test_pearson_dot": 0.6217650825208566,
|
714 |
+
"eval_sts-test_pearson_euclidean": 0.7243228472931561,
|
715 |
+
"eval_sts-test_pearson_manhattan": 0.7333297580184588,
|
716 |
+
"eval_sts-test_pearson_max": 0.7333297580184588,
|
717 |
+
"eval_sts-test_spearman_cosine": 0.7013110457844404,
|
718 |
+
"eval_sts-test_spearman_dot": 0.5970993074902947,
|
719 |
+
"eval_sts-test_spearman_euclidean": 0.701564129266252,
|
720 |
+
"eval_sts-test_spearman_manhattan": 0.7116482009924582,
|
721 |
+
"eval_sts-test_spearman_max": 0.7116482009924582,
|
722 |
+
"step": 3675
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 0.625638406537283,
|
726 |
+
"eval_vitaminc-pairs_loss": 1.974273681640625,
|
727 |
+
"eval_vitaminc-pairs_runtime": 2.1754,
|
728 |
+
"eval_vitaminc-pairs_samples_per_second": 68.953,
|
729 |
+
"eval_vitaminc-pairs_steps_per_second": 2.298,
|
730 |
+
"step": 3675
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.625638406537283,
|
734 |
+
"eval_qnli-contrastive_loss": 1.7706010341644287,
|
735 |
+
"eval_qnli-contrastive_runtime": 0.4866,
|
736 |
+
"eval_qnli-contrastive_samples_per_second": 308.244,
|
737 |
+
"eval_qnli-contrastive_steps_per_second": 10.275,
|
738 |
+
"step": 3675
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 0.625638406537283,
|
742 |
+
"eval_scitail-pairs-qa_loss": 0.4400452673435211,
|
743 |
+
"eval_scitail-pairs-qa_runtime": 1.1519,
|
744 |
+
"eval_scitail-pairs-qa_samples_per_second": 130.222,
|
745 |
+
"eval_scitail-pairs-qa_steps_per_second": 4.341,
|
746 |
+
"step": 3675
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 0.625638406537283,
|
750 |
+
"eval_scitail-pairs-pos_loss": 1.1909903287887573,
|
751 |
+
"eval_scitail-pairs-pos_runtime": 2.1319,
|
752 |
+
"eval_scitail-pairs-pos_samples_per_second": 70.36,
|
753 |
+
"eval_scitail-pairs-pos_steps_per_second": 2.345,
|
754 |
+
"step": 3675
|
755 |
+
},
|
756 |
+
{
|
757 |
+
"epoch": 0.625638406537283,
|
758 |
+
"eval_xsum-pairs_loss": 1.4811985492706299,
|
759 |
+
"eval_xsum-pairs_runtime": 2.254,
|
760 |
+
"eval_xsum-pairs_samples_per_second": 66.548,
|
761 |
+
"eval_xsum-pairs_steps_per_second": 2.218,
|
762 |
+
"step": 3675
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 0.625638406537283,
|
766 |
+
"eval_compression-pairs_loss": 0.8453781008720398,
|
767 |
+
"eval_compression-pairs_runtime": 0.4401,
|
768 |
+
"eval_compression-pairs_samples_per_second": 340.826,
|
769 |
+
"eval_compression-pairs_steps_per_second": 11.361,
|
770 |
+
"step": 3675
|
771 |
+
},
|
772 |
+
{
|
773 |
+
"epoch": 0.625638406537283,
|
774 |
+
"eval_sciq_pairs_loss": 8.014656066894531,
|
775 |
+
"eval_sciq_pairs_runtime": 7.0707,
|
776 |
+
"eval_sciq_pairs_samples_per_second": 21.214,
|
777 |
+
"eval_sciq_pairs_steps_per_second": 0.707,
|
778 |
+
"step": 3675
|
779 |
+
},
|
780 |
+
{
|
781 |
+
"epoch": 0.625638406537283,
|
782 |
+
"eval_qasc_pairs_loss": 6.9316277503967285,
|
783 |
+
"eval_qasc_pairs_runtime": 2.0338,
|
784 |
+
"eval_qasc_pairs_samples_per_second": 73.752,
|
785 |
+
"eval_qasc_pairs_steps_per_second": 2.458,
|
786 |
+
"step": 3675
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.625638406537283,
|
790 |
+
"eval_openbookqa_pairs_loss": 4.21690034866333,
|
791 |
+
"eval_openbookqa_pairs_runtime": 0.918,
|
792 |
+
"eval_openbookqa_pairs_samples_per_second": 112.202,
|
793 |
+
"eval_openbookqa_pairs_steps_per_second": 4.357,
|
794 |
+
"step": 3675
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 0.625638406537283,
|
798 |
+
"eval_msmarco_pairs_loss": 3.0209598541259766,
|
799 |
+
"eval_msmarco_pairs_runtime": 2.7749,
|
800 |
+
"eval_msmarco_pairs_samples_per_second": 54.056,
|
801 |
+
"eval_msmarco_pairs_steps_per_second": 1.802,
|
802 |
+
"step": 3675
|
803 |
+
},
|
804 |
+
{
|
805 |
+
"epoch": 0.625638406537283,
|
806 |
+
"eval_nq_pairs_loss": 2.956088066101074,
|
807 |
+
"eval_nq_pairs_runtime": 5.0024,
|
808 |
+
"eval_nq_pairs_samples_per_second": 29.986,
|
809 |
+
"eval_nq_pairs_steps_per_second": 1.0,
|
810 |
+
"step": 3675
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 0.625638406537283,
|
814 |
+
"eval_trivia_pairs_loss": 3.17364501953125,
|
815 |
+
"eval_trivia_pairs_runtime": 9.4856,
|
816 |
+
"eval_trivia_pairs_samples_per_second": 15.813,
|
817 |
+
"eval_trivia_pairs_steps_per_second": 0.527,
|
818 |
+
"step": 3675
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 0.625638406537283,
|
822 |
+
"eval_quora_pairs_loss": 0.763593852519989,
|
823 |
+
"eval_quora_pairs_runtime": 1.1441,
|
824 |
+
"eval_quora_pairs_samples_per_second": 131.104,
|
825 |
+
"eval_quora_pairs_steps_per_second": 4.37,
|
826 |
+
"step": 3675
|
827 |
+
},
|
828 |
+
{
|
829 |
+
"epoch": 0.625638406537283,
|
830 |
+
"eval_gooaq_pairs_loss": 2.3524909019470215,
|
831 |
+
"eval_gooaq_pairs_runtime": 2.0161,
|
832 |
+
"eval_gooaq_pairs_samples_per_second": 74.4,
|
833 |
+
"eval_gooaq_pairs_steps_per_second": 2.48,
|
834 |
+
"step": 3675
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 0.6506639427987743,
|
838 |
+
"grad_norm": 31.163997650146484,
|
839 |
+
"learning_rate": 1.2992849846782432e-05,
|
840 |
+
"loss": 2.7808,
|
841 |
+
"step": 3822
|
842 |
+
},
|
843 |
+
{
|
844 |
+
"epoch": 0.6756894790602656,
|
845 |
+
"grad_norm": 14.883658409118652,
|
846 |
+
"learning_rate": 1.3493360572012258e-05,
|
847 |
+
"loss": 2.5687,
|
848 |
+
"step": 3969
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"epoch": 0.7007150153217568,
|
852 |
+
"grad_norm": 5.874042987823486,
|
853 |
+
"learning_rate": 1.3993871297242083e-05,
|
854 |
+
"loss": 2.3034,
|
855 |
+
"step": 4116
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 0.7257405515832482,
|
859 |
+
"grad_norm": 31.464054107666016,
|
860 |
+
"learning_rate": 1.4494382022471912e-05,
|
861 |
+
"loss": 2.4412,
|
862 |
+
"step": 4263
|
863 |
+
},
|
864 |
+
{
|
865 |
+
"epoch": 0.7507660878447395,
|
866 |
+
"grad_norm": 16.43915367126465,
|
867 |
+
"learning_rate": 1.4994892747701737e-05,
|
868 |
+
"loss": 2.3293,
|
869 |
+
"step": 4410
|
870 |
+
},
|
871 |
+
{
|
872 |
+
"epoch": 0.7507660878447395,
|
873 |
+
"eval_nli-pairs_loss": 2.3226094245910645,
|
874 |
+
"eval_nli-pairs_runtime": 4.113,
|
875 |
+
"eval_nli-pairs_samples_per_second": 36.47,
|
876 |
+
"eval_nli-pairs_steps_per_second": 1.216,
|
877 |
+
"eval_sts-test_pearson_cosine": 0.7356971966139032,
|
878 |
+
"eval_sts-test_pearson_dot": 0.6150809513049869,
|
879 |
+
"eval_sts-test_pearson_euclidean": 0.7330733579988641,
|
880 |
+
"eval_sts-test_pearson_manhattan": 0.7423412248131348,
|
881 |
+
"eval_sts-test_pearson_max": 0.7423412248131348,
|
882 |
+
"eval_sts-test_spearman_cosine": 0.7121899723082045,
|
883 |
+
"eval_sts-test_spearman_dot": 0.5926505936679538,
|
884 |
+
"eval_sts-test_spearman_euclidean": 0.7130179905407037,
|
885 |
+
"eval_sts-test_spearman_manhattan": 0.7227257562995023,
|
886 |
+
"eval_sts-test_spearman_max": 0.7227257562995023,
|
887 |
+
"step": 4410
|
888 |
+
},
|
889 |
+
{
|
890 |
+
"epoch": 0.7507660878447395,
|
891 |
+
"eval_vitaminc-pairs_loss": 1.7956713438034058,
|
892 |
+
"eval_vitaminc-pairs_runtime": 2.174,
|
893 |
+
"eval_vitaminc-pairs_samples_per_second": 68.996,
|
894 |
+
"eval_vitaminc-pairs_steps_per_second": 2.3,
|
895 |
+
"step": 4410
|
896 |
+
},
|
897 |
+
{
|
898 |
+
"epoch": 0.7507660878447395,
|
899 |
+
"eval_qnli-contrastive_loss": 1.0078614950180054,
|
900 |
+
"eval_qnli-contrastive_runtime": 0.4874,
|
901 |
+
"eval_qnli-contrastive_samples_per_second": 307.763,
|
902 |
+
"eval_qnli-contrastive_steps_per_second": 10.259,
|
903 |
+
"step": 4410
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 0.7507660878447395,
|
907 |
+
"eval_scitail-pairs-qa_loss": 0.36971578001976013,
|
908 |
+
"eval_scitail-pairs-qa_runtime": 1.164,
|
909 |
+
"eval_scitail-pairs-qa_samples_per_second": 128.863,
|
910 |
+
"eval_scitail-pairs-qa_steps_per_second": 4.295,
|
911 |
+
"step": 4410
|
912 |
+
},
|
913 |
+
{
|
914 |
+
"epoch": 0.7507660878447395,
|
915 |
+
"eval_scitail-pairs-pos_loss": 1.0497769117355347,
|
916 |
+
"eval_scitail-pairs-pos_runtime": 2.1205,
|
917 |
+
"eval_scitail-pairs-pos_samples_per_second": 70.74,
|
918 |
+
"eval_scitail-pairs-pos_steps_per_second": 2.358,
|
919 |
+
"step": 4410
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.7507660878447395,
|
923 |
+
"eval_xsum-pairs_loss": 1.1691261529922485,
|
924 |
+
"eval_xsum-pairs_runtime": 2.259,
|
925 |
+
"eval_xsum-pairs_samples_per_second": 66.401,
|
926 |
+
"eval_xsum-pairs_steps_per_second": 2.213,
|
927 |
+
"step": 4410
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 0.7507660878447395,
|
931 |
+
"eval_compression-pairs_loss": 0.5027483105659485,
|
932 |
+
"eval_compression-pairs_runtime": 0.4403,
|
933 |
+
"eval_compression-pairs_samples_per_second": 340.682,
|
934 |
+
"eval_compression-pairs_steps_per_second": 11.356,
|
935 |
+
"step": 4410
|
936 |
+
},
|
937 |
+
{
|
938 |
+
"epoch": 0.7507660878447395,
|
939 |
+
"eval_sciq_pairs_loss": 7.823739528656006,
|
940 |
+
"eval_sciq_pairs_runtime": 7.0738,
|
941 |
+
"eval_sciq_pairs_samples_per_second": 21.205,
|
942 |
+
"eval_sciq_pairs_steps_per_second": 0.707,
|
943 |
+
"step": 4410
|
944 |
+
},
|
945 |
+
{
|
946 |
+
"epoch": 0.7507660878447395,
|
947 |
+
"eval_qasc_pairs_loss": 6.404655933380127,
|
948 |
+
"eval_qasc_pairs_runtime": 2.0346,
|
949 |
+
"eval_qasc_pairs_samples_per_second": 73.723,
|
950 |
+
"eval_qasc_pairs_steps_per_second": 2.457,
|
951 |
+
"step": 4410
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 0.7507660878447395,
|
955 |
+
"eval_openbookqa_pairs_loss": 3.857389211654663,
|
956 |
+
"eval_openbookqa_pairs_runtime": 0.8544,
|
957 |
+
"eval_openbookqa_pairs_samples_per_second": 120.547,
|
958 |
+
"eval_openbookqa_pairs_steps_per_second": 4.681,
|
959 |
+
"step": 4410
|
960 |
+
},
|
961 |
+
{
|
962 |
+
"epoch": 0.7507660878447395,
|
963 |
+
"eval_msmarco_pairs_loss": 2.7028510570526123,
|
964 |
+
"eval_msmarco_pairs_runtime": 2.7448,
|
965 |
+
"eval_msmarco_pairs_samples_per_second": 54.649,
|
966 |
+
"eval_msmarco_pairs_steps_per_second": 1.822,
|
967 |
+
"step": 4410
|
968 |
+
},
|
969 |
+
{
|
970 |
+
"epoch": 0.7507660878447395,
|
971 |
+
"eval_nq_pairs_loss": 2.679351329803467,
|
972 |
+
"eval_nq_pairs_runtime": 5.067,
|
973 |
+
"eval_nq_pairs_samples_per_second": 29.603,
|
974 |
+
"eval_nq_pairs_steps_per_second": 0.987,
|
975 |
+
"step": 4410
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.7507660878447395,
|
979 |
+
"eval_trivia_pairs_loss": 2.8798065185546875,
|
980 |
+
"eval_trivia_pairs_runtime": 9.5449,
|
981 |
+
"eval_trivia_pairs_samples_per_second": 15.715,
|
982 |
+
"eval_trivia_pairs_steps_per_second": 0.524,
|
983 |
+
"step": 4410
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"epoch": 0.7507660878447395,
|
987 |
+
"eval_quora_pairs_loss": 0.6825175285339355,
|
988 |
+
"eval_quora_pairs_runtime": 1.1431,
|
989 |
+
"eval_quora_pairs_samples_per_second": 131.221,
|
990 |
+
"eval_quora_pairs_steps_per_second": 4.374,
|
991 |
+
"step": 4410
|
992 |
+
},
|
993 |
+
{
|
994 |
+
"epoch": 0.7507660878447395,
|
995 |
+
"eval_gooaq_pairs_loss": 2.0472166538238525,
|
996 |
+
"eval_gooaq_pairs_runtime": 2.0218,
|
997 |
+
"eval_gooaq_pairs_samples_per_second": 74.191,
|
998 |
+
"eval_gooaq_pairs_steps_per_second": 2.473,
|
999 |
+
"step": 4410
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.7757916241062308,
|
1003 |
+
"grad_norm": 4.2425055503845215,
|
1004 |
+
"learning_rate": 1.5495403472931565e-05,
|
1005 |
+
"loss": 2.3651,
|
1006 |
+
"step": 4557
|
1007 |
+
},
|
1008 |
+
{
|
1009 |
+
"epoch": 0.8008171603677222,
|
1010 |
+
"grad_norm": 22.42776107788086,
|
1011 |
+
"learning_rate": 1.5995914198161388e-05,
|
1012 |
+
"loss": 2.6296,
|
1013 |
+
"step": 4704
|
1014 |
+
},
|
1015 |
+
{
|
1016 |
+
"epoch": 0.8258426966292135,
|
1017 |
+
"grad_norm": 21.169517517089844,
|
1018 |
+
"learning_rate": 1.6496424923391215e-05,
|
1019 |
+
"loss": 2.2108,
|
1020 |
+
"step": 4851
|
1021 |
+
},
|
1022 |
+
{
|
1023 |
+
"epoch": 0.8508682328907048,
|
1024 |
+
"grad_norm": 23.326181411743164,
|
1025 |
+
"learning_rate": 1.699693564862104e-05,
|
1026 |
+
"loss": 2.1852,
|
1027 |
+
"step": 4998
|
1028 |
+
},
|
1029 |
+
{
|
1030 |
+
"epoch": 0.8758937691521961,
|
1031 |
+
"grad_norm": 24.574176788330078,
|
1032 |
+
"learning_rate": 1.7497446373850868e-05,
|
1033 |
+
"loss": 2.2944,
|
1034 |
+
"step": 5145
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"epoch": 0.8758937691521961,
|
1038 |
+
"eval_nli-pairs_loss": 2.0634915828704834,
|
1039 |
+
"eval_nli-pairs_runtime": 4.0019,
|
1040 |
+
"eval_nli-pairs_samples_per_second": 37.482,
|
1041 |
+
"eval_nli-pairs_steps_per_second": 1.249,
|
1042 |
+
"eval_sts-test_pearson_cosine": 0.7466390532977636,
|
1043 |
+
"eval_sts-test_pearson_dot": 0.612259458274589,
|
1044 |
+
"eval_sts-test_pearson_euclidean": 0.7432536346376271,
|
1045 |
+
"eval_sts-test_pearson_manhattan": 0.7500490179501229,
|
1046 |
+
"eval_sts-test_pearson_max": 0.7500490179501229,
|
1047 |
+
"eval_sts-test_spearman_cosine": 0.728273260456201,
|
1048 |
+
"eval_sts-test_spearman_dot": 0.5960115087190596,
|
1049 |
+
"eval_sts-test_spearman_euclidean": 0.7272394395622148,
|
1050 |
+
"eval_sts-test_spearman_manhattan": 0.7334149564445704,
|
1051 |
+
"eval_sts-test_spearman_max": 0.7334149564445704,
|
1052 |
+
"step": 5145
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.8758937691521961,
|
1056 |
+
"eval_vitaminc-pairs_loss": 1.638654112815857,
|
1057 |
+
"eval_vitaminc-pairs_runtime": 2.1637,
|
1058 |
+
"eval_vitaminc-pairs_samples_per_second": 69.327,
|
1059 |
+
"eval_vitaminc-pairs_steps_per_second": 2.311,
|
1060 |
+
"step": 5145
|
1061 |
+
},
|
1062 |
+
{
|
1063 |
+
"epoch": 0.8758937691521961,
|
1064 |
+
"eval_qnli-contrastive_loss": 0.9639705419540405,
|
1065 |
+
"eval_qnli-contrastive_runtime": 0.4889,
|
1066 |
+
"eval_qnli-contrastive_samples_per_second": 306.825,
|
1067 |
+
"eval_qnli-contrastive_steps_per_second": 10.228,
|
1068 |
+
"step": 5145
|
1069 |
+
},
|
1070 |
+
{
|
1071 |
+
"epoch": 0.8758937691521961,
|
1072 |
+
"eval_scitail-pairs-qa_loss": 0.31595128774642944,
|
1073 |
+
"eval_scitail-pairs-qa_runtime": 1.1467,
|
1074 |
+
"eval_scitail-pairs-qa_samples_per_second": 130.806,
|
1075 |
+
"eval_scitail-pairs-qa_steps_per_second": 4.36,
|
1076 |
+
"step": 5145
|
1077 |
+
},
|
1078 |
+
{
|
1079 |
+
"epoch": 0.8758937691521961,
|
1080 |
+
"eval_scitail-pairs-pos_loss": 0.9187478423118591,
|
1081 |
+
"eval_scitail-pairs-pos_runtime": 2.1273,
|
1082 |
+
"eval_scitail-pairs-pos_samples_per_second": 70.512,
|
1083 |
+
"eval_scitail-pairs-pos_steps_per_second": 2.35,
|
1084 |
+
"step": 5145
|
1085 |
+
},
|
1086 |
+
{
|
1087 |
+
"epoch": 0.8758937691521961,
|
1088 |
+
"eval_xsum-pairs_loss": 1.060194492340088,
|
1089 |
+
"eval_xsum-pairs_runtime": 2.2836,
|
1090 |
+
"eval_xsum-pairs_samples_per_second": 65.686,
|
1091 |
+
"eval_xsum-pairs_steps_per_second": 2.19,
|
1092 |
+
"step": 5145
|
1093 |
+
},
|
1094 |
+
{
|
1095 |
+
"epoch": 0.8758937691521961,
|
1096 |
+
"eval_compression-pairs_loss": 0.41078585386276245,
|
1097 |
+
"eval_compression-pairs_runtime": 0.4434,
|
1098 |
+
"eval_compression-pairs_samples_per_second": 338.276,
|
1099 |
+
"eval_compression-pairs_steps_per_second": 11.276,
|
1100 |
+
"step": 5145
|
1101 |
+
},
|
1102 |
+
{
|
1103 |
+
"epoch": 0.8758937691521961,
|
1104 |
+
"eval_sciq_pairs_loss": 7.577760696411133,
|
1105 |
+
"eval_sciq_pairs_runtime": 7.1025,
|
1106 |
+
"eval_sciq_pairs_samples_per_second": 21.119,
|
1107 |
+
"eval_sciq_pairs_steps_per_second": 0.704,
|
1108 |
+
"step": 5145
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 0.8758937691521961,
|
1112 |
+
"eval_qasc_pairs_loss": 6.353766918182373,
|
1113 |
+
"eval_qasc_pairs_runtime": 2.0113,
|
1114 |
+
"eval_qasc_pairs_samples_per_second": 74.58,
|
1115 |
+
"eval_qasc_pairs_steps_per_second": 2.486,
|
1116 |
+
"step": 5145
|
1117 |
+
},
|
1118 |
+
{
|
1119 |
+
"epoch": 0.8758937691521961,
|
1120 |
+
"eval_openbookqa_pairs_loss": 3.7140932083129883,
|
1121 |
+
"eval_openbookqa_pairs_runtime": 0.8529,
|
1122 |
+
"eval_openbookqa_pairs_samples_per_second": 120.762,
|
1123 |
+
"eval_openbookqa_pairs_steps_per_second": 4.69,
|
1124 |
+
"step": 5145
|
1125 |
+
},
|
1126 |
+
{
|
1127 |
+
"epoch": 0.8758937691521961,
|
1128 |
+
"eval_msmarco_pairs_loss": 2.3862576484680176,
|
1129 |
+
"eval_msmarco_pairs_runtime": 2.8953,
|
1130 |
+
"eval_msmarco_pairs_samples_per_second": 51.808,
|
1131 |
+
"eval_msmarco_pairs_steps_per_second": 1.727,
|
1132 |
+
"step": 5145
|
1133 |
+
},
|
1134 |
+
{
|
1135 |
+
"epoch": 0.8758937691521961,
|
1136 |
+
"eval_nq_pairs_loss": 2.3543190956115723,
|
1137 |
+
"eval_nq_pairs_runtime": 5.0048,
|
1138 |
+
"eval_nq_pairs_samples_per_second": 29.971,
|
1139 |
+
"eval_nq_pairs_steps_per_second": 0.999,
|
1140 |
+
"step": 5145
|
1141 |
+
},
|
1142 |
+
{
|
1143 |
+
"epoch": 0.8758937691521961,
|
1144 |
+
"eval_trivia_pairs_loss": 2.494807481765747,
|
1145 |
+
"eval_trivia_pairs_runtime": 9.5513,
|
1146 |
+
"eval_trivia_pairs_samples_per_second": 15.705,
|
1147 |
+
"eval_trivia_pairs_steps_per_second": 0.523,
|
1148 |
+
"step": 5145
|
1149 |
+
},
|
1150 |
+
{
|
1151 |
+
"epoch": 0.8758937691521961,
|
1152 |
+
"eval_quora_pairs_loss": 0.6137441992759705,
|
1153 |
+
"eval_quora_pairs_runtime": 1.1541,
|
1154 |
+
"eval_quora_pairs_samples_per_second": 129.967,
|
1155 |
+
"eval_quora_pairs_steps_per_second": 4.332,
|
1156 |
+
"step": 5145
|
1157 |
+
},
|
1158 |
+
{
|
1159 |
+
"epoch": 0.8758937691521961,
|
1160 |
+
"eval_gooaq_pairs_loss": 1.8279658555984497,
|
1161 |
+
"eval_gooaq_pairs_runtime": 2.0951,
|
1162 |
+
"eval_gooaq_pairs_samples_per_second": 71.595,
|
1163 |
+
"eval_gooaq_pairs_steps_per_second": 2.387,
|
1164 |
+
"step": 5145
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.9009193054136875,
|
1168 |
+
"grad_norm": 10.590804100036621,
|
1169 |
+
"learning_rate": 1.7997957099080695e-05,
|
1170 |
+
"loss": 2.2133,
|
1171 |
+
"step": 5292
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 0.9259448416751788,
|
1175 |
+
"grad_norm": 18.527711868286133,
|
1176 |
+
"learning_rate": 1.849846782431052e-05,
|
1177 |
+
"loss": 2.2255,
|
1178 |
+
"step": 5439
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 0.95097037793667,
|
1182 |
+
"grad_norm": 2.617710828781128,
|
1183 |
+
"learning_rate": 1.8995573714674838e-05,
|
1184 |
+
"loss": 2.3502,
|
1185 |
+
"step": 5586
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.9759959141981613,
|
1189 |
+
"grad_norm": 19.551551818847656,
|
1190 |
+
"learning_rate": 1.9496084439904668e-05,
|
1191 |
+
"loss": 1.8964,
|
1192 |
+
"step": 5733
|
1193 |
+
}
|
1194 |
+
],
|
1195 |
+
"logging_steps": 147,
|
1196 |
+
"max_steps": 29370,
|
1197 |
+
"num_input_tokens_seen": 0,
|
1198 |
+
"num_train_epochs": 5,
|
1199 |
+
"save_steps": 2937,
|
1200 |
+
"stateful_callbacks": {
|
1201 |
+
"TrainerControl": {
|
1202 |
+
"args": {
|
1203 |
+
"should_epoch_stop": false,
|
1204 |
+
"should_evaluate": false,
|
1205 |
+
"should_log": false,
|
1206 |
+
"should_save": true,
|
1207 |
+
"should_training_stop": false
|
1208 |
+
},
|
1209 |
+
"attributes": {}
|
1210 |
+
}
|
1211 |
+
},
|
1212 |
+
"total_flos": 0.0,
|
1213 |
+
"train_batch_size": 32,
|
1214 |
+
"trial_name": null,
|
1215 |
+
"trial_params": null
|
1216 |
+
}
|
checkpoint-5874/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:298cfa7a9e669e98ab55937cac47ecfa89fb6a36f2afe18f46ba782a5f5bf5a4
|
3 |
+
size 5624
|