ajibawa-2023
commited on
Commit
•
330c4dd
1
Parent(s):
a81ed04
Upload folder using huggingface_hub
Browse files- .gitattributes +14 -0
- config.json +24 -0
- generation_config.json +7 -0
- pytorch_model.bin-aa +3 -0
- pytorch_model.bin-ab +3 -0
- pytorch_model.bin-ac +3 -0
- pytorch_model.bin-ad +3 -0
- pytorch_model.bin-ae +3 -0
- pytorch_model.bin-af +3 -0
- pytorch_model.bin-ag +3 -0
- pytorch_model.bin-ah +3 -0
- pytorch_model.bin-ai +3 -0
- pytorch_model.bin-aj +3 -0
- pytorch_model.bin-ak +3 -0
- pytorch_model.bin-al +3 -0
- pytorch_model.bin-am +3 -0
- pytorch_model.bin-an +3 -0
- special_tokens_map.json +24 -0
- tokenizer.model +3 -0
- tokenizer_config.json +34 -0
- trainer_state.json +871 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,17 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
pytorch_model.bin-aa filter=lfs diff=lfs merge=lfs -text
|
37 |
+
pytorch_model.bin-ab filter=lfs diff=lfs merge=lfs -text
|
38 |
+
pytorch_model.bin-ac filter=lfs diff=lfs merge=lfs -text
|
39 |
+
pytorch_model.bin-ad filter=lfs diff=lfs merge=lfs -text
|
40 |
+
pytorch_model.bin-ae filter=lfs diff=lfs merge=lfs -text
|
41 |
+
pytorch_model.bin-af filter=lfs diff=lfs merge=lfs -text
|
42 |
+
pytorch_model.bin-ag filter=lfs diff=lfs merge=lfs -text
|
43 |
+
pytorch_model.bin-ah filter=lfs diff=lfs merge=lfs -text
|
44 |
+
pytorch_model.bin-ai filter=lfs diff=lfs merge=lfs -text
|
45 |
+
pytorch_model.bin-aj filter=lfs diff=lfs merge=lfs -text
|
46 |
+
pytorch_model.bin-ak filter=lfs diff=lfs merge=lfs -text
|
47 |
+
pytorch_model.bin-al filter=lfs diff=lfs merge=lfs -text
|
48 |
+
pytorch_model.bin-am filter=lfs diff=lfs merge=lfs -text
|
49 |
+
pytorch_model.bin-an filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/mla100eus/Downloads/llama-30b",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 6656,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 17920,
|
12 |
+
"max_position_embeddings": 2048,
|
13 |
+
"max_sequence_length": 2048,
|
14 |
+
"model_type": "llama",
|
15 |
+
"num_attention_heads": 52,
|
16 |
+
"num_hidden_layers": 60,
|
17 |
+
"pad_token_id": 0,
|
18 |
+
"rms_norm_eps": 1e-06,
|
19 |
+
"tie_word_embeddings": false,
|
20 |
+
"torch_dtype": "bfloat16",
|
21 |
+
"transformers_version": "4.28.1",
|
22 |
+
"use_cache": false,
|
23 |
+
"vocab_size": 32000
|
24 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.28.1"
|
7 |
+
}
|
pytorch_model.bin-aa
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:995186565f930acb8287e356383288ebd0471fbb94ad6a1a204023fd6a94f66c
|
3 |
+
size 9663676416
|
pytorch_model.bin-ab
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe7dbc7c33aa1c8d6a7802854e61cdd0c3955de88213960021c26483add0cba6
|
3 |
+
size 9663676416
|
pytorch_model.bin-ac
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:455b889b58388945534fb6167dd5a49de2bae6ba100b879ecce073de45ca2070
|
3 |
+
size 9663676416
|
pytorch_model.bin-ad
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2acbf503a1751ae01eda6a9d1bdcafd86c9c8e83bb27ec8e527c98a61d5948dd
|
3 |
+
size 9663676416
|
pytorch_model.bin-ae
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eeab47e296509d8c377ae3049636246a72b48ee29478463a0b5e83e37eadbdf2
|
3 |
+
size 9663676416
|
pytorch_model.bin-af
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84beba477b9c6680788bb4cbd368dbaa1ccc4706aff99ca4e2e6d6824689f9fb
|
3 |
+
size 9663676416
|
pytorch_model.bin-ag
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47257d4dbf939fa13a168b680c99782e437291b8dd2b7bb041291ac950596aab
|
3 |
+
size 9663676416
|
pytorch_model.bin-ah
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a725003fcc95b6f9fe5decb8ad3259c8b27a7be9d451fe02e91fa6ec8da3cf4
|
3 |
+
size 9663676416
|
pytorch_model.bin-ai
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfe5ed68654b66bc85fdd8d9b7cc4abfdae756272ca8dd06f709d6b087f8f6b1
|
3 |
+
size 9663676416
|
pytorch_model.bin-aj
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9cde65cb14d7e820e7afc721ffcd9740e37070a394cb882e83b39bd62a3f8d37
|
3 |
+
size 9663676416
|
pytorch_model.bin-ak
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:390b01d6262ac90c60b1e814d28e28c08df1a06bc39f29f2795390c277352096
|
3 |
+
size 9663676416
|
pytorch_model.bin-al
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9368528cb8600a1880ffe0ff5e33b2afde0b3e7d01cb3a01192f0185f7dd7138
|
3 |
+
size 9663676416
|
pytorch_model.bin-am
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:daae0c0057c66546349ec6330f6bf376457de31cfb7d3a454c3cbd6ee4c52569
|
3 |
+
size 9663676416
|
pytorch_model.bin-an
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c939ab38fa9470416fc1a3aa1b43f8576c34fca7e11896e9425acc562745943
|
3 |
+
size 4488198525
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<unk>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"clean_up_tokenization_spaces": false,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"model_max_length": 2048,
|
22 |
+
"pad_token": null,
|
23 |
+
"padding_side": "right",
|
24 |
+
"sp_model_kwargs": {},
|
25 |
+
"tokenizer_class": "LlamaTokenizer",
|
26 |
+
"unk_token": {
|
27 |
+
"__type": "AddedToken",
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,871 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"global_step": 141,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.02,
|
12 |
+
"learning_rate": 3.3333333333333333e-06,
|
13 |
+
"loss": 1.5693,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.04,
|
18 |
+
"learning_rate": 6.666666666666667e-06,
|
19 |
+
"loss": 1.583,
|
20 |
+
"step": 2
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.06,
|
24 |
+
"learning_rate": 1e-05,
|
25 |
+
"loss": 1.5527,
|
26 |
+
"step": 3
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.09,
|
30 |
+
"learning_rate": 1.3333333333333333e-05,
|
31 |
+
"loss": 1.3408,
|
32 |
+
"step": 4
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.11,
|
36 |
+
"learning_rate": 1.6666666666666667e-05,
|
37 |
+
"loss": 1.2607,
|
38 |
+
"step": 5
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.13,
|
42 |
+
"learning_rate": 2e-05,
|
43 |
+
"loss": 1.21,
|
44 |
+
"step": 6
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.15,
|
48 |
+
"learning_rate": 1.999729241179462e-05,
|
49 |
+
"loss": 1.1992,
|
50 |
+
"step": 7
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.17,
|
54 |
+
"learning_rate": 1.998917111338525e-05,
|
55 |
+
"loss": 1.1406,
|
56 |
+
"step": 8
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.19,
|
60 |
+
"learning_rate": 1.9975640502598243e-05,
|
61 |
+
"loss": 1.1113,
|
62 |
+
"step": 9
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.21,
|
66 |
+
"learning_rate": 1.9956707906498046e-05,
|
67 |
+
"loss": 1.1289,
|
68 |
+
"step": 10
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.23,
|
72 |
+
"learning_rate": 1.9932383577419432e-05,
|
73 |
+
"loss": 1.1074,
|
74 |
+
"step": 11
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.26,
|
78 |
+
"learning_rate": 1.9902680687415704e-05,
|
79 |
+
"loss": 1.0898,
|
80 |
+
"step": 12
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.28,
|
84 |
+
"learning_rate": 1.9867615321125796e-05,
|
85 |
+
"loss": 1.0869,
|
86 |
+
"step": 13
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.3,
|
90 |
+
"learning_rate": 1.9827206467064133e-05,
|
91 |
+
"loss": 1.0664,
|
92 |
+
"step": 14
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.32,
|
96 |
+
"learning_rate": 1.9781476007338058e-05,
|
97 |
+
"loss": 1.0791,
|
98 |
+
"step": 15
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.34,
|
102 |
+
"learning_rate": 1.973044870579824e-05,
|
103 |
+
"loss": 1.0615,
|
104 |
+
"step": 16
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.36,
|
108 |
+
"learning_rate": 1.967415219462864e-05,
|
109 |
+
"loss": 1.0527,
|
110 |
+
"step": 17
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.38,
|
114 |
+
"learning_rate": 1.961261695938319e-05,
|
115 |
+
"loss": 1.042,
|
116 |
+
"step": 18
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.4,
|
120 |
+
"learning_rate": 1.954587632247732e-05,
|
121 |
+
"loss": 1.0581,
|
122 |
+
"step": 19
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.43,
|
126 |
+
"learning_rate": 1.9473966425143292e-05,
|
127 |
+
"loss": 1.0415,
|
128 |
+
"step": 20
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.45,
|
132 |
+
"learning_rate": 1.9396926207859085e-05,
|
133 |
+
"loss": 1.0454,
|
134 |
+
"step": 21
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.47,
|
138 |
+
"learning_rate": 1.9314797389261426e-05,
|
139 |
+
"loss": 1.0576,
|
140 |
+
"step": 22
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.49,
|
144 |
+
"learning_rate": 1.9227624443554425e-05,
|
145 |
+
"loss": 1.0098,
|
146 |
+
"step": 23
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.51,
|
150 |
+
"learning_rate": 1.913545457642601e-05,
|
151 |
+
"loss": 1.0063,
|
152 |
+
"step": 24
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.53,
|
156 |
+
"learning_rate": 1.9038337699485207e-05,
|
157 |
+
"loss": 1.0146,
|
158 |
+
"step": 25
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.55,
|
162 |
+
"learning_rate": 1.8936326403234125e-05,
|
163 |
+
"loss": 1.0127,
|
164 |
+
"step": 26
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.57,
|
168 |
+
"learning_rate": 1.8829475928589272e-05,
|
169 |
+
"loss": 1.0117,
|
170 |
+
"step": 27
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.6,
|
174 |
+
"learning_rate": 1.8717844136967626e-05,
|
175 |
+
"loss": 1.0054,
|
176 |
+
"step": 28
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.62,
|
180 |
+
"learning_rate": 1.860149147895366e-05,
|
181 |
+
"loss": 1.0068,
|
182 |
+
"step": 29
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.64,
|
186 |
+
"learning_rate": 1.848048096156426e-05,
|
187 |
+
"loss": 1.0024,
|
188 |
+
"step": 30
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.66,
|
192 |
+
"learning_rate": 1.8354878114129368e-05,
|
193 |
+
"loss": 1.0073,
|
194 |
+
"step": 31
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.68,
|
198 |
+
"learning_rate": 1.8224750952806626e-05,
|
199 |
+
"loss": 1.0137,
|
200 |
+
"step": 32
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.7,
|
204 |
+
"learning_rate": 1.8090169943749477e-05,
|
205 |
+
"loss": 1.0312,
|
206 |
+
"step": 33
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.72,
|
210 |
+
"learning_rate": 1.795120796494848e-05,
|
211 |
+
"loss": 0.9912,
|
212 |
+
"step": 34
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.74,
|
216 |
+
"learning_rate": 1.7807940266766595e-05,
|
217 |
+
"loss": 0.9966,
|
218 |
+
"step": 35
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.77,
|
222 |
+
"learning_rate": 1.766044443118978e-05,
|
223 |
+
"loss": 0.979,
|
224 |
+
"step": 36
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.79,
|
228 |
+
"learning_rate": 1.7508800329814993e-05,
|
229 |
+
"loss": 0.9883,
|
230 |
+
"step": 37
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.81,
|
234 |
+
"learning_rate": 1.735309008059829e-05,
|
235 |
+
"loss": 1.0137,
|
236 |
+
"step": 38
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.83,
|
240 |
+
"learning_rate": 1.7193398003386514e-05,
|
241 |
+
"loss": 0.9927,
|
242 |
+
"step": 39
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.85,
|
246 |
+
"learning_rate": 1.702981057425662e-05,
|
247 |
+
"loss": 0.9868,
|
248 |
+
"step": 40
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.87,
|
252 |
+
"learning_rate": 1.686241637868734e-05,
|
253 |
+
"loss": 0.9932,
|
254 |
+
"step": 41
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.89,
|
258 |
+
"learning_rate": 1.6691306063588583e-05,
|
259 |
+
"loss": 0.9741,
|
260 |
+
"step": 42
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 0.91,
|
264 |
+
"learning_rate": 1.6516572288214555e-05,
|
265 |
+
"loss": 0.981,
|
266 |
+
"step": 43
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 0.94,
|
270 |
+
"learning_rate": 1.63383096739871e-05,
|
271 |
+
"loss": 0.9893,
|
272 |
+
"step": 44
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 0.96,
|
276 |
+
"learning_rate": 1.6156614753256583e-05,
|
277 |
+
"loss": 0.9971,
|
278 |
+
"step": 45
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 0.98,
|
282 |
+
"learning_rate": 1.5971585917027864e-05,
|
283 |
+
"loss": 0.9731,
|
284 |
+
"step": 46
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 1.0,
|
288 |
+
"learning_rate": 1.5783323361679865e-05,
|
289 |
+
"loss": 0.9541,
|
290 |
+
"step": 47
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 1.02,
|
294 |
+
"learning_rate": 1.5591929034707468e-05,
|
295 |
+
"loss": 0.8223,
|
296 |
+
"step": 48
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 1.04,
|
300 |
+
"learning_rate": 1.539750657951513e-05,
|
301 |
+
"loss": 0.8345,
|
302 |
+
"step": 49
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 1.06,
|
306 |
+
"learning_rate": 1.5200161279292154e-05,
|
307 |
+
"loss": 0.8193,
|
308 |
+
"step": 50
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 1.09,
|
312 |
+
"learning_rate": 1.5000000000000002e-05,
|
313 |
+
"loss": 0.7939,
|
314 |
+
"step": 51
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 1.11,
|
318 |
+
"learning_rate": 1.4797131132502464e-05,
|
319 |
+
"loss": 0.8115,
|
320 |
+
"step": 52
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 1.13,
|
324 |
+
"learning_rate": 1.4591664533870118e-05,
|
325 |
+
"loss": 0.7896,
|
326 |
+
"step": 53
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 1.15,
|
330 |
+
"learning_rate": 1.4383711467890776e-05,
|
331 |
+
"loss": 0.772,
|
332 |
+
"step": 54
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 1.17,
|
336 |
+
"learning_rate": 1.417338454481818e-05,
|
337 |
+
"loss": 0.8052,
|
338 |
+
"step": 55
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 1.19,
|
342 |
+
"learning_rate": 1.396079766039157e-05,
|
343 |
+
"loss": 0.7891,
|
344 |
+
"step": 56
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 1.21,
|
348 |
+
"learning_rate": 1.3746065934159123e-05,
|
349 |
+
"loss": 0.7788,
|
350 |
+
"step": 57
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 1.23,
|
354 |
+
"learning_rate": 1.3529305647138689e-05,
|
355 |
+
"loss": 0.7856,
|
356 |
+
"step": 58
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 1.26,
|
360 |
+
"learning_rate": 1.3310634178849583e-05,
|
361 |
+
"loss": 0.7515,
|
362 |
+
"step": 59
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 1.28,
|
366 |
+
"learning_rate": 1.3090169943749475e-05,
|
367 |
+
"loss": 0.751,
|
368 |
+
"step": 60
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 1.3,
|
372 |
+
"learning_rate": 1.2868032327110904e-05,
|
373 |
+
"loss": 0.7681,
|
374 |
+
"step": 61
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 1.32,
|
378 |
+
"learning_rate": 1.2644341620372025e-05,
|
379 |
+
"loss": 0.7866,
|
380 |
+
"step": 62
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 1.34,
|
384 |
+
"learning_rate": 1.2419218955996677e-05,
|
385 |
+
"loss": 0.793,
|
386 |
+
"step": 63
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 1.36,
|
390 |
+
"learning_rate": 1.2192786241879033e-05,
|
391 |
+
"loss": 0.7754,
|
392 |
+
"step": 64
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 1.38,
|
396 |
+
"learning_rate": 1.1965166095328302e-05,
|
397 |
+
"loss": 0.7715,
|
398 |
+
"step": 65
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 1.4,
|
402 |
+
"learning_rate": 1.1736481776669307e-05,
|
403 |
+
"loss": 0.7773,
|
404 |
+
"step": 66
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 1.43,
|
408 |
+
"learning_rate": 1.1506857122494832e-05,
|
409 |
+
"loss": 0.7695,
|
410 |
+
"step": 67
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 1.45,
|
414 |
+
"learning_rate": 1.127641647860595e-05,
|
415 |
+
"loss": 0.7871,
|
416 |
+
"step": 68
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 1.47,
|
420 |
+
"learning_rate": 1.1045284632676535e-05,
|
421 |
+
"loss": 0.7744,
|
422 |
+
"step": 69
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 1.49,
|
426 |
+
"learning_rate": 1.0813586746678584e-05,
|
427 |
+
"loss": 0.7705,
|
428 |
+
"step": 70
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 1.51,
|
432 |
+
"learning_rate": 1.0581448289104759e-05,
|
433 |
+
"loss": 0.7681,
|
434 |
+
"step": 71
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 1.53,
|
438 |
+
"learning_rate": 1.0348994967025012e-05,
|
439 |
+
"loss": 0.7632,
|
440 |
+
"step": 72
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 1.55,
|
444 |
+
"learning_rate": 1.0116352658013973e-05,
|
445 |
+
"loss": 0.7856,
|
446 |
+
"step": 73
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 1.57,
|
450 |
+
"learning_rate": 9.883647341986032e-06,
|
451 |
+
"loss": 0.772,
|
452 |
+
"step": 74
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 1.6,
|
456 |
+
"learning_rate": 9.651005032974994e-06,
|
457 |
+
"loss": 0.7671,
|
458 |
+
"step": 75
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 1.62,
|
462 |
+
"learning_rate": 9.418551710895243e-06,
|
463 |
+
"loss": 0.7837,
|
464 |
+
"step": 76
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 1.64,
|
468 |
+
"learning_rate": 9.18641325332142e-06,
|
469 |
+
"loss": 0.7534,
|
470 |
+
"step": 77
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 1.66,
|
474 |
+
"learning_rate": 8.954715367323468e-06,
|
475 |
+
"loss": 0.7725,
|
476 |
+
"step": 78
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 1.68,
|
480 |
+
"learning_rate": 8.723583521394054e-06,
|
481 |
+
"loss": 0.7949,
|
482 |
+
"step": 79
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 1.7,
|
486 |
+
"learning_rate": 8.49314287750517e-06,
|
487 |
+
"loss": 0.8062,
|
488 |
+
"step": 80
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 1.72,
|
492 |
+
"learning_rate": 8.263518223330698e-06,
|
493 |
+
"loss": 0.7783,
|
494 |
+
"step": 81
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 1.74,
|
498 |
+
"learning_rate": 8.034833904671698e-06,
|
499 |
+
"loss": 0.8071,
|
500 |
+
"step": 82
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 1.77,
|
504 |
+
"learning_rate": 7.807213758120965e-06,
|
505 |
+
"loss": 0.7817,
|
506 |
+
"step": 83
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 1.79,
|
510 |
+
"learning_rate": 7.580781044003324e-06,
|
511 |
+
"loss": 0.7847,
|
512 |
+
"step": 84
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 1.81,
|
516 |
+
"learning_rate": 7.355658379627981e-06,
|
517 |
+
"loss": 0.7837,
|
518 |
+
"step": 85
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 1.83,
|
522 |
+
"learning_rate": 7.131967672889101e-06,
|
523 |
+
"loss": 0.749,
|
524 |
+
"step": 86
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 1.85,
|
528 |
+
"learning_rate": 6.909830056250527e-06,
|
529 |
+
"loss": 0.7754,
|
530 |
+
"step": 87
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 1.87,
|
534 |
+
"learning_rate": 6.689365821150421e-06,
|
535 |
+
"loss": 0.771,
|
536 |
+
"step": 88
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 1.89,
|
540 |
+
"learning_rate": 6.4706943528613135e-06,
|
541 |
+
"loss": 0.7705,
|
542 |
+
"step": 89
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 1.91,
|
546 |
+
"learning_rate": 6.25393406584088e-06,
|
547 |
+
"loss": 0.7881,
|
548 |
+
"step": 90
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 1.94,
|
552 |
+
"learning_rate": 6.039202339608432e-06,
|
553 |
+
"loss": 0.7603,
|
554 |
+
"step": 91
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 1.96,
|
558 |
+
"learning_rate": 5.8266154551818225e-06,
|
559 |
+
"loss": 0.7773,
|
560 |
+
"step": 92
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 1.98,
|
564 |
+
"learning_rate": 5.616288532109225e-06,
|
565 |
+
"loss": 0.7349,
|
566 |
+
"step": 93
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 2.0,
|
570 |
+
"learning_rate": 5.4083354661298816e-06,
|
571 |
+
"loss": 0.77,
|
572 |
+
"step": 94
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 2.02,
|
576 |
+
"learning_rate": 5.202868867497542e-06,
|
577 |
+
"loss": 0.584,
|
578 |
+
"step": 95
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 2.04,
|
582 |
+
"learning_rate": 5.000000000000003e-06,
|
583 |
+
"loss": 0.5554,
|
584 |
+
"step": 96
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 2.06,
|
588 |
+
"learning_rate": 4.799838720707847e-06,
|
589 |
+
"loss": 0.6069,
|
590 |
+
"step": 97
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 2.09,
|
594 |
+
"learning_rate": 4.6024934204848745e-06,
|
595 |
+
"loss": 0.6045,
|
596 |
+
"step": 98
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 2.11,
|
600 |
+
"learning_rate": 4.408070965292534e-06,
|
601 |
+
"loss": 0.6035,
|
602 |
+
"step": 99
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 2.13,
|
606 |
+
"learning_rate": 4.216676638320135e-06,
|
607 |
+
"loss": 0.5938,
|
608 |
+
"step": 100
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 2.15,
|
612 |
+
"learning_rate": 4.028414082972141e-06,
|
613 |
+
"loss": 0.5562,
|
614 |
+
"step": 101
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 2.17,
|
618 |
+
"learning_rate": 3.8433852467434175e-06,
|
619 |
+
"loss": 0.5879,
|
620 |
+
"step": 102
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 2.19,
|
624 |
+
"learning_rate": 3.661690326012897e-06,
|
625 |
+
"loss": 0.5493,
|
626 |
+
"step": 103
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 2.21,
|
630 |
+
"learning_rate": 3.483427711785449e-06,
|
631 |
+
"loss": 0.5342,
|
632 |
+
"step": 104
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 2.23,
|
636 |
+
"learning_rate": 3.308693936411421e-06,
|
637 |
+
"loss": 0.5178,
|
638 |
+
"step": 105
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 2.26,
|
642 |
+
"learning_rate": 3.1375836213126653e-06,
|
643 |
+
"loss": 0.5571,
|
644 |
+
"step": 106
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 2.28,
|
648 |
+
"learning_rate": 2.970189425743383e-06,
|
649 |
+
"loss": 0.5796,
|
650 |
+
"step": 107
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 2.3,
|
654 |
+
"learning_rate": 2.8066019966134907e-06,
|
655 |
+
"loss": 0.5642,
|
656 |
+
"step": 108
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 2.32,
|
660 |
+
"learning_rate": 2.6469099194017144e-06,
|
661 |
+
"loss": 0.5537,
|
662 |
+
"step": 109
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 2.34,
|
666 |
+
"learning_rate": 2.4911996701850083e-06,
|
667 |
+
"loss": 0.5374,
|
668 |
+
"step": 110
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 2.36,
|
672 |
+
"learning_rate": 2.339555568810221e-06,
|
673 |
+
"loss": 0.5552,
|
674 |
+
"step": 111
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 2.38,
|
678 |
+
"learning_rate": 2.192059733233408e-06,
|
679 |
+
"loss": 0.5544,
|
680 |
+
"step": 112
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 2.4,
|
684 |
+
"learning_rate": 2.048792035051521e-06,
|
685 |
+
"loss": 0.5889,
|
686 |
+
"step": 113
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 2.43,
|
690 |
+
"learning_rate": 1.9098300562505266e-06,
|
691 |
+
"loss": 0.5674,
|
692 |
+
"step": 114
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 2.45,
|
696 |
+
"learning_rate": 1.7752490471933769e-06,
|
697 |
+
"loss": 0.5664,
|
698 |
+
"step": 115
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 2.47,
|
702 |
+
"learning_rate": 1.6451218858706374e-06,
|
703 |
+
"loss": 0.5508,
|
704 |
+
"step": 116
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 2.49,
|
708 |
+
"learning_rate": 1.5195190384357405e-06,
|
709 |
+
"loss": 0.532,
|
710 |
+
"step": 117
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 2.51,
|
714 |
+
"learning_rate": 1.3985085210463479e-06,
|
715 |
+
"loss": 0.5378,
|
716 |
+
"step": 118
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 2.53,
|
720 |
+
"learning_rate": 1.282155863032377e-06,
|
721 |
+
"loss": 0.5535,
|
722 |
+
"step": 119
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 2.55,
|
726 |
+
"learning_rate": 1.1705240714107301e-06,
|
727 |
+
"loss": 0.5469,
|
728 |
+
"step": 120
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 2.57,
|
732 |
+
"learning_rate": 1.0636735967658785e-06,
|
733 |
+
"loss": 0.5659,
|
734 |
+
"step": 121
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 2.6,
|
738 |
+
"learning_rate": 9.616623005147952e-07,
|
739 |
+
"loss": 0.5435,
|
740 |
+
"step": 122
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 2.62,
|
744 |
+
"learning_rate": 8.645454235739903e-07,
|
745 |
+
"loss": 0.5513,
|
746 |
+
"step": 123
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 2.64,
|
750 |
+
"learning_rate": 7.723755564455771e-07,
|
751 |
+
"loss": 0.5437,
|
752 |
+
"step": 124
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 2.66,
|
756 |
+
"learning_rate": 6.852026107385756e-07,
|
757 |
+
"loss": 0.5422,
|
758 |
+
"step": 125
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 2.68,
|
762 |
+
"learning_rate": 6.030737921409169e-07,
|
763 |
+
"loss": 0.5461,
|
764 |
+
"step": 126
|
765 |
+
},
|
766 |
+
{
|
767 |
+
"epoch": 2.7,
|
768 |
+
"learning_rate": 5.26033574856708e-07,
|
769 |
+
"loss": 0.5347,
|
770 |
+
"step": 127
|
771 |
+
},
|
772 |
+
{
|
773 |
+
"epoch": 2.72,
|
774 |
+
"learning_rate": 4.5412367752268094e-07,
|
775 |
+
"loss": 0.5576,
|
776 |
+
"step": 128
|
777 |
+
},
|
778 |
+
{
|
779 |
+
"epoch": 2.74,
|
780 |
+
"learning_rate": 3.8738304061681107e-07,
|
781 |
+
"loss": 0.5261,
|
782 |
+
"step": 129
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 2.77,
|
786 |
+
"learning_rate": 3.2584780537136206e-07,
|
787 |
+
"loss": 0.5452,
|
788 |
+
"step": 130
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 2.79,
|
792 |
+
"learning_rate": 2.6955129420176193e-07,
|
793 |
+
"loss": 0.5811,
|
794 |
+
"step": 131
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 2.81,
|
798 |
+
"learning_rate": 2.1852399266194312e-07,
|
799 |
+
"loss": 0.5334,
|
800 |
+
"step": 132
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 2.83,
|
804 |
+
"learning_rate": 1.7279353293586765e-07,
|
805 |
+
"loss": 0.5542,
|
806 |
+
"step": 133
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 2.85,
|
810 |
+
"learning_rate": 1.323846788742078e-07,
|
811 |
+
"loss": 0.5732,
|
812 |
+
"step": 134
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 2.87,
|
816 |
+
"learning_rate": 9.731931258429638e-08,
|
817 |
+
"loss": 0.5583,
|
818 |
+
"step": 135
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 2.89,
|
822 |
+
"learning_rate": 6.761642258056977e-08,
|
823 |
+
"loss": 0.5696,
|
824 |
+
"step": 136
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 2.91,
|
828 |
+
"learning_rate": 4.329209350195651e-08,
|
829 |
+
"loss": 0.5571,
|
830 |
+
"step": 137
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 2.94,
|
834 |
+
"learning_rate": 2.4359497401758026e-08,
|
835 |
+
"loss": 0.5334,
|
836 |
+
"step": 138
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 2.96,
|
840 |
+
"learning_rate": 1.0828886614754342e-08,
|
841 |
+
"loss": 0.5129,
|
842 |
+
"step": 139
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 2.98,
|
846 |
+
"learning_rate": 2.7075882053828605e-09,
|
847 |
+
"loss": 0.5488,
|
848 |
+
"step": 140
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"epoch": 3.0,
|
852 |
+
"learning_rate": 0.0,
|
853 |
+
"loss": 0.5657,
|
854 |
+
"step": 141
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 3.0,
|
858 |
+
"step": 141,
|
859 |
+
"total_flos": 176790366584832.0,
|
860 |
+
"train_loss": 0.80621640902039,
|
861 |
+
"train_runtime": 20653.5724,
|
862 |
+
"train_samples_per_second": 0.868,
|
863 |
+
"train_steps_per_second": 0.007
|
864 |
+
}
|
865 |
+
],
|
866 |
+
"max_steps": 141,
|
867 |
+
"num_train_epochs": 3,
|
868 |
+
"total_flos": 176790366584832.0,
|
869 |
+
"trial_name": null,
|
870 |
+
"trial_params": null
|
871 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f40ede75a4fdf8597c96992604bfcd9e11e274604f25bd5757c327729f62e393
|
3 |
+
size 4795
|