Hugging Face's logo

Wanfq
/
fusechat_multi_teacher_ckpt

Text Generation
Transformers
Safetensors
mistral
conversational
text-generation-inference
Model card Files
xet
 Community
Wanfq commited on
Commit
4325d67
·
verified ·
1 Parent(s): 4af8da8

Upload folder using huggingface_hub

Browse files
Files changed (29) hide show
  1. added_tokens.json +4 -0
  2. checkpoint-1334/added_tokens.json +4 -0
  3. checkpoint-1334/config.json +25 -0
  4. checkpoint-1334/pytorch_model.bin +3 -0
  5. checkpoint-1334/special_tokens_map.json +28 -0
  6. checkpoint-1334/tokenizer.model +3 -0
  7. checkpoint-1334/tokenizer_config.json +63 -0
  8. checkpoint-1334/trainer_state.json +0 -0
  9. checkpoint-1334/training_args.bin +3 -0
  10. checkpoint-667/added_tokens.json +4 -0
  11. checkpoint-667/config.json +25 -0
  12. checkpoint-667/pytorch_model.bin +3 -0
  13. checkpoint-667/special_tokens_map.json +28 -0
  14. checkpoint-667/tokenizer.model +3 -0
  15. checkpoint-667/tokenizer_config.json +63 -0
  16. checkpoint-667/trainer_state.json +4021 -0
  17. checkpoint-667/training_args.bin +3 -0
  18. config.json +25 -0
  19. generation_config.json +9 -0
  20. model-00001-of-00003.safetensors +3 -0
  21. model-00002-of-00003.safetensors +3 -0
  22. model-00003-of-00003.safetensors +3 -0
  23. model.safetensors.index.json +298 -0
  24. special_tokens_map.json +27 -0
  25. tokenizer.json +0 -0
  26. tokenizer.model +3 -0
  27. tokenizer_config.json +62 -0
  28. trainer_state.json +0 -0
  29. training_args.bin +3 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|end_of_turn|>": 32000,
3
+ "<|pad_0|>": 32001
4
+ }
checkpoint-1334/added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|end_of_turn|>": 32000,
3
+ "<|pad_0|>": 32001
4
+ }
checkpoint-1334/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/apdcephfs/share_733425/timhuang/fanqiwan/PLMs/openchat-3.5",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 32000,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 14336,
12
+ "max_position_embeddings": 8192,
13
+ "model_type": "mistral",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 32,
16
+ "num_key_value_heads": 8,
17
+ "rms_norm_eps": 1e-05,
18
+ "rope_theta": 10000.0,
19
+ "sliding_window": 4096,
20
+ "tie_word_embeddings": false,
21
+ "torch_dtype": "bfloat16",
22
+ "transformers_version": "4.35.0",
23
+ "use_cache": false,
24
+ "vocab_size": 32002
25
+ }
checkpoint-1334/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f30d8b7257ce19e733725a062cd99ac79425ff74552342a85ff8ae3936821e22
3
+ size 14483644690
checkpoint-1334/special_tokens_map.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|end_of_turn|>",
4
+ "<|pad_0|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<s>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<|end_of_turn|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": "<unk>",
21
+ "unk_token": {
22
+ "content": "<unk>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ }
28
+ }
checkpoint-1334/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
checkpoint-1334/tokenizer_config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<|end_of_turn|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|pad_0|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ }
45
+ },
46
+ "additional_special_tokens": [
47
+ "<|end_of_turn|>",
48
+ "<|pad_0|>"
49
+ ],
50
+ "bos_token": "<s>",
51
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}",
52
+ "clean_up_tokenization_spaces": false,
53
+ "eos_token": "<|end_of_turn|>",
54
+ "legacy": true,
55
+ "model_max_length": 2048,
56
+ "pad_token": "<unk>",
57
+ "padding_side": "right",
58
+ "sp_model_kwargs": {},
59
+ "spaces_between_special_tokens": false,
60
+ "tokenizer_class": "LlamaTokenizer",
61
+ "unk_token": "<unk>",
62
+ "use_default_system_prompt": true
63
+ }
checkpoint-1334/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1334/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9990b0c49fc6deae3a2a406f23f161f0eefbeee820384d6cca7a1aca52d86279
3
+ size 6136
checkpoint-667/added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|end_of_turn|>": 32000,
3
+ "<|pad_0|>": 32001
4
+ }
checkpoint-667/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/apdcephfs/share_733425/timhuang/fanqiwan/PLMs/openchat-3.5",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 32000,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 14336,
12
+ "max_position_embeddings": 8192,
13
+ "model_type": "mistral",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 32,
16
+ "num_key_value_heads": 8,
17
+ "rms_norm_eps": 1e-05,
18
+ "rope_theta": 10000.0,
19
+ "sliding_window": 4096,
20
+ "tie_word_embeddings": false,
21
+ "torch_dtype": "bfloat16",
22
+ "transformers_version": "4.35.0",
23
+ "use_cache": false,
24
+ "vocab_size": 32002
25
+ }
checkpoint-667/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24231159015df86d6bddb1c29b2d24fe9e23b91fff12213b9847867984c61046
3
+ size 14483644690
checkpoint-667/special_tokens_map.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|end_of_turn|>",
4
+ "<|pad_0|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<s>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<|end_of_turn|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": "<unk>",
21
+ "unk_token": {
22
+ "content": "<unk>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ }
28
+ }
checkpoint-667/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
checkpoint-667/tokenizer_config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<|end_of_turn|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|pad_0|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ }
45
+ },
46
+ "additional_special_tokens": [
47
+ "<|end_of_turn|>",
48
+ "<|pad_0|>"
49
+ ],
50
+ "bos_token": "<s>",
51
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}",
52
+ "clean_up_tokenization_spaces": false,
53
+ "eos_token": "<|end_of_turn|>",
54
+ "legacy": true,
55
+ "model_max_length": 2048,
56
+ "pad_token": "<unk>",
57
+ "padding_side": "right",
58
+ "sp_model_kwargs": {},
59
+ "spaces_between_special_tokens": false,
60
+ "tokenizer_class": "LlamaTokenizer",
61
+ "unk_token": "<unk>",
62
+ "use_default_system_prompt": true
63
+ }
checkpoint-667/trainer_state.json ADDED
@@ -0,0 +1,4021 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9996253278381416,
5
+ "eval_steps": 500,
6
+ "global_step": 667,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 8.19672131147541e-08,
14
+ "loss": 0.7543,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "learning_rate": 1.639344262295082e-07,
20
+ "loss": 0.7901,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.0,
25
+ "learning_rate": 2.459016393442623e-07,
26
+ "loss": 0.6852,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.01,
31
+ "learning_rate": 3.278688524590164e-07,
32
+ "loss": 0.7048,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.01,
37
+ "learning_rate": 4.0983606557377047e-07,
38
+ "loss": 0.7231,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.01,
43
+ "learning_rate": 4.918032786885246e-07,
44
+ "loss": 0.7159,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.01,
49
+ "learning_rate": 5.737704918032787e-07,
50
+ "loss": 0.7806,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.01,
55
+ "learning_rate": 6.557377049180328e-07,
56
+ "loss": 0.6879,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.01,
61
+ "learning_rate": 7.377049180327869e-07,
62
+ "loss": 0.7071,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.01,
67
+ "learning_rate": 8.196721311475409e-07,
68
+ "loss": 0.7347,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.02,
73
+ "learning_rate": 9.016393442622952e-07,
74
+ "loss": 0.6785,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.02,
79
+ "learning_rate": 9.836065573770493e-07,
80
+ "loss": 0.7917,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.02,
85
+ "learning_rate": 1.0655737704918034e-06,
86
+ "loss": 0.7418,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.02,
91
+ "learning_rate": 1.1475409836065575e-06,
92
+ "loss": 0.6687,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.02,
97
+ "learning_rate": 1.2295081967213116e-06,
98
+ "loss": 0.6408,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.02,
103
+ "learning_rate": 1.3114754098360657e-06,
104
+ "loss": 0.6247,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.03,
109
+ "learning_rate": 1.3934426229508196e-06,
110
+ "loss": 0.6756,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.03,
115
+ "learning_rate": 1.4754098360655739e-06,
116
+ "loss": 0.7031,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.03,
121
+ "learning_rate": 1.557377049180328e-06,
122
+ "loss": 0.7049,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.03,
127
+ "learning_rate": 1.6393442622950819e-06,
128
+ "loss": 0.7581,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.03,
133
+ "learning_rate": 1.7213114754098362e-06,
134
+ "loss": 0.7167,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.03,
139
+ "learning_rate": 1.8032786885245903e-06,
140
+ "loss": 0.658,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.03,
145
+ "learning_rate": 1.8852459016393442e-06,
146
+ "loss": 0.7326,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.04,
151
+ "learning_rate": 1.9672131147540985e-06,
152
+ "loss": 0.6703,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.04,
157
+ "learning_rate": 2.0491803278688526e-06,
158
+ "loss": 0.6357,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.04,
163
+ "learning_rate": 2.1311475409836067e-06,
164
+ "loss": 0.7067,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.04,
169
+ "learning_rate": 2.213114754098361e-06,
170
+ "loss": 0.7178,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.04,
175
+ "learning_rate": 2.295081967213115e-06,
176
+ "loss": 0.6182,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.04,
181
+ "learning_rate": 2.377049180327869e-06,
182
+ "loss": 0.6385,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.04,
187
+ "learning_rate": 2.459016393442623e-06,
188
+ "loss": 0.7547,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.05,
193
+ "learning_rate": 2.5409836065573773e-06,
194
+ "loss": 0.6316,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.05,
199
+ "learning_rate": 2.6229508196721314e-06,
200
+ "loss": 0.7463,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.05,
205
+ "learning_rate": 2.704918032786886e-06,
206
+ "loss": 0.6611,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.05,
211
+ "learning_rate": 2.786885245901639e-06,
212
+ "loss": 0.6776,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.05,
217
+ "learning_rate": 2.8688524590163937e-06,
218
+ "loss": 0.6184,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.05,
223
+ "learning_rate": 2.9508196721311478e-06,
224
+ "loss": 0.6991,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.06,
229
+ "learning_rate": 3.032786885245902e-06,
230
+ "loss": 0.6379,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.06,
235
+ "learning_rate": 3.114754098360656e-06,
236
+ "loss": 0.6486,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.06,
241
+ "learning_rate": 3.1967213114754105e-06,
242
+ "loss": 0.6311,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.06,
247
+ "learning_rate": 3.2786885245901638e-06,
248
+ "loss": 0.665,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.06,
253
+ "learning_rate": 3.3606557377049183e-06,
254
+ "loss": 0.6492,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.06,
259
+ "learning_rate": 3.4426229508196724e-06,
260
+ "loss": 0.6686,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.06,
265
+ "learning_rate": 3.5245901639344265e-06,
266
+ "loss": 0.6756,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.07,
271
+ "learning_rate": 3.6065573770491806e-06,
272
+ "loss": 0.713,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.07,
277
+ "learning_rate": 3.6885245901639347e-06,
278
+ "loss": 0.6224,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.07,
283
+ "learning_rate": 3.7704918032786884e-06,
284
+ "loss": 0.6908,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.07,
289
+ "learning_rate": 3.852459016393443e-06,
290
+ "loss": 0.6866,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.07,
295
+ "learning_rate": 3.934426229508197e-06,
296
+ "loss": 0.6274,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.07,
301
+ "learning_rate": 4.016393442622951e-06,
302
+ "loss": 0.6272,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.07,
307
+ "learning_rate": 4.098360655737705e-06,
308
+ "loss": 0.7227,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.08,
313
+ "learning_rate": 4.180327868852459e-06,
314
+ "loss": 0.5906,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.08,
319
+ "learning_rate": 4.2622950819672135e-06,
320
+ "loss": 0.6846,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.08,
325
+ "learning_rate": 4.3442622950819676e-06,
326
+ "loss": 0.7143,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.08,
331
+ "learning_rate": 4.426229508196722e-06,
332
+ "loss": 0.6506,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.08,
337
+ "learning_rate": 4.508196721311476e-06,
338
+ "loss": 0.6546,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.08,
343
+ "learning_rate": 4.59016393442623e-06,
344
+ "loss": 0.6785,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.09,
349
+ "learning_rate": 4.672131147540984e-06,
350
+ "loss": 0.6212,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.09,
355
+ "learning_rate": 4.754098360655738e-06,
356
+ "loss": 0.642,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.09,
361
+ "learning_rate": 4.836065573770492e-06,
362
+ "loss": 0.6,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.09,
367
+ "learning_rate": 4.918032786885246e-06,
368
+ "loss": 0.7337,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.09,
373
+ "learning_rate": 5e-06,
374
+ "loss": 0.6778,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.09,
379
+ "learning_rate": 4.999996722020724e-06,
380
+ "loss": 0.6572,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.09,
385
+ "learning_rate": 4.99998688809149e-06,
386
+ "loss": 0.6596,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.1,
391
+ "learning_rate": 4.999970498238088e-06,
392
+ "loss": 0.6212,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.1,
397
+ "learning_rate": 4.9999475525034974e-06,
398
+ "loss": 0.7529,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.1,
403
+ "learning_rate": 4.999918050947891e-06,
404
+ "loss": 0.7086,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.1,
409
+ "learning_rate": 4.999881993648633e-06,
410
+ "loss": 0.7246,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.1,
415
+ "learning_rate": 4.999839380700281e-06,
416
+ "loss": 0.7175,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.1,
421
+ "learning_rate": 4.99979021221458e-06,
422
+ "loss": 0.6657,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.1,
427
+ "learning_rate": 4.99973448832047e-06,
428
+ "loss": 0.6624,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.11,
433
+ "learning_rate": 4.9996722091640805e-06,
434
+ "loss": 0.6993,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.11,
439
+ "learning_rate": 4.999603374908732e-06,
440
+ "loss": 0.6095,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.11,
445
+ "learning_rate": 4.999527985734932e-06,
446
+ "loss": 0.6477,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.11,
451
+ "learning_rate": 4.999446041840382e-06,
452
+ "loss": 0.6187,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.11,
457
+ "learning_rate": 4.999357543439969e-06,
458
+ "loss": 0.7445,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.11,
463
+ "learning_rate": 4.99926249076577e-06,
464
+ "loss": 0.6511,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.12,
469
+ "learning_rate": 4.999160884067051e-06,
470
+ "loss": 0.6273,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.12,
475
+ "learning_rate": 4.999052723610262e-06,
476
+ "loss": 0.5931,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.12,
481
+ "learning_rate": 4.9989380096790416e-06,
482
+ "loss": 0.6816,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.12,
487
+ "learning_rate": 4.998816742574214e-06,
488
+ "loss": 0.6552,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.12,
493
+ "learning_rate": 4.998688922613788e-06,
494
+ "loss": 0.6911,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.12,
499
+ "learning_rate": 4.998554550132956e-06,
500
+ "loss": 0.6581,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.12,
505
+ "learning_rate": 4.998413625484095e-06,
506
+ "loss": 0.6527,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.13,
511
+ "learning_rate": 4.998266149036763e-06,
512
+ "loss": 0.5868,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.13,
517
+ "learning_rate": 4.9981121211777e-06,
518
+ "loss": 0.6383,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.13,
523
+ "learning_rate": 4.9979515423108255e-06,
524
+ "loss": 0.6259,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.13,
529
+ "learning_rate": 4.997784412857239e-06,
530
+ "loss": 0.6554,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.13,
535
+ "learning_rate": 4.99761073325522e-06,
536
+ "loss": 0.6439,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.13,
541
+ "learning_rate": 4.99743050396022e-06,
542
+ "loss": 0.628,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.13,
547
+ "learning_rate": 4.9972437254448705e-06,
548
+ "loss": 0.597,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.14,
553
+ "learning_rate": 4.997050398198977e-06,
554
+ "loss": 0.6297,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.14,
559
+ "learning_rate": 4.9968505227295176e-06,
560
+ "loss": 0.6229,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.14,
565
+ "learning_rate": 4.9966440995606415e-06,
566
+ "loss": 0.5862,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.14,
571
+ "learning_rate": 4.99643112923367e-06,
572
+ "loss": 0.6609,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.14,
577
+ "learning_rate": 4.9962116123070925e-06,
578
+ "loss": 0.6339,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.14,
583
+ "learning_rate": 4.995985549356568e-06,
584
+ "loss": 0.6858,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.15,
589
+ "learning_rate": 4.9957529409749185e-06,
590
+ "loss": 0.6505,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.15,
595
+ "learning_rate": 4.995513787772132e-06,
596
+ "loss": 0.575,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.15,
601
+ "learning_rate": 4.995268090375362e-06,
602
+ "loss": 0.6286,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.15,
607
+ "learning_rate": 4.995015849428921e-06,
608
+ "loss": 0.7287,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.15,
613
+ "learning_rate": 4.99475706559428e-06,
614
+ "loss": 0.7023,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.15,
619
+ "learning_rate": 4.994491739550069e-06,
620
+ "loss": 0.5816,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.15,
625
+ "learning_rate": 4.994219871992077e-06,
626
+ "loss": 0.7043,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.16,
631
+ "learning_rate": 4.9939414636332434e-06,
632
+ "loss": 0.6513,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.16,
637
+ "learning_rate": 4.993656515203662e-06,
638
+ "loss": 0.623,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.16,
643
+ "learning_rate": 4.993365027450576e-06,
644
+ "loss": 0.7,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.16,
649
+ "learning_rate": 4.99306700113838e-06,
650
+ "loss": 0.6665,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.16,
655
+ "learning_rate": 4.992762437048612e-06,
656
+ "loss": 0.6505,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.16,
661
+ "learning_rate": 4.9924513359799555e-06,
662
+ "loss": 0.5958,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.16,
667
+ "learning_rate": 4.992133698748237e-06,
668
+ "loss": 0.6494,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.17,
673
+ "learning_rate": 4.991809526186424e-06,
674
+ "loss": 0.7549,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.17,
679
+ "learning_rate": 4.99147881914462e-06,
680
+ "loss": 0.6153,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.17,
685
+ "learning_rate": 4.991141578490066e-06,
686
+ "loss": 0.713,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.17,
691
+ "learning_rate": 4.990797805107138e-06,
692
+ "loss": 0.6281,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.17,
697
+ "learning_rate": 4.990447499897339e-06,
698
+ "loss": 0.661,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.17,
703
+ "learning_rate": 4.990090663779305e-06,
704
+ "loss": 0.6761,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.18,
709
+ "learning_rate": 4.989727297688797e-06,
710
+ "loss": 0.6165,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.18,
715
+ "learning_rate": 4.989357402578699e-06,
716
+ "loss": 0.6698,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.18,
721
+ "learning_rate": 4.98898097941902e-06,
722
+ "loss": 0.6527,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.18,
727
+ "learning_rate": 4.988598029196885e-06,
728
+ "loss": 0.5937,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.18,
733
+ "learning_rate": 4.988208552916535e-06,
734
+ "loss": 0.6261,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.18,
739
+ "learning_rate": 4.987812551599328e-06,
740
+ "loss": 0.6122,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.18,
745
+ "learning_rate": 4.98741002628373e-06,
746
+ "loss": 0.6458,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.19,
751
+ "learning_rate": 4.9870009780253185e-06,
752
+ "loss": 0.6206,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.19,
757
+ "learning_rate": 4.9865854078967715e-06,
758
+ "loss": 0.7455,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.19,
763
+ "learning_rate": 4.986163316987877e-06,
764
+ "loss": 0.6228,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.19,
769
+ "learning_rate": 4.985734706405516e-06,
770
+ "loss": 0.7177,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.19,
775
+ "learning_rate": 4.985299577273672e-06,
776
+ "loss": 0.6044,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.19,
781
+ "learning_rate": 4.9848579307334195e-06,
782
+ "loss": 0.564,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.19,
787
+ "learning_rate": 4.984409767942926e-06,
788
+ "loss": 0.6219,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.2,
793
+ "learning_rate": 4.983955090077445e-06,
794
+ "loss": 0.6838,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.2,
799
+ "learning_rate": 4.983493898329316e-06,
800
+ "loss": 0.6676,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.2,
805
+ "learning_rate": 4.983026193907962e-06,
806
+ "loss": 0.6298,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.2,
811
+ "learning_rate": 4.982551978039882e-06,
812
+ "loss": 0.6684,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.2,
817
+ "learning_rate": 4.982071251968653e-06,
818
+ "loss": 0.6423,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.2,
823
+ "learning_rate": 4.9815840169549216e-06,
824
+ "loss": 0.6123,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.21,
829
+ "learning_rate": 4.981090274276406e-06,
830
+ "loss": 0.6627,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.21,
835
+ "learning_rate": 4.980590025227888e-06,
836
+ "loss": 0.6561,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.21,
841
+ "learning_rate": 4.980083271121215e-06,
842
+ "loss": 0.6023,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.21,
847
+ "learning_rate": 4.979570013285286e-06,
848
+ "loss": 0.6557,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.21,
853
+ "learning_rate": 4.979050253066064e-06,
854
+ "loss": 0.7552,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.21,
859
+ "learning_rate": 4.978523991826556e-06,
860
+ "loss": 0.7153,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.21,
865
+ "learning_rate": 4.977991230946824e-06,
866
+ "loss": 0.7379,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.22,
871
+ "learning_rate": 4.97745197182397e-06,
872
+ "loss": 0.7123,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.22,
877
+ "learning_rate": 4.976906215872137e-06,
878
+ "loss": 0.621,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.22,
883
+ "learning_rate": 4.976353964522509e-06,
884
+ "loss": 0.5685,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.22,
889
+ "learning_rate": 4.975795219223299e-06,
890
+ "loss": 0.592,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.22,
895
+ "learning_rate": 4.97522998143975e-06,
896
+ "loss": 0.6185,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.22,
901
+ "learning_rate": 4.974658252654135e-06,
902
+ "loss": 0.6303,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.22,
907
+ "learning_rate": 4.974080034365746e-06,
908
+ "loss": 0.6045,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 0.23,
913
+ "learning_rate": 4.973495328090891e-06,
914
+ "loss": 0.6235,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 0.23,
919
+ "learning_rate": 4.972904135362895e-06,
920
+ "loss": 0.7236,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 0.23,
925
+ "learning_rate": 4.972306457732091e-06,
926
+ "loss": 0.5955,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 0.23,
931
+ "learning_rate": 4.971702296765821e-06,
932
+ "loss": 0.6259,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 0.23,
937
+ "learning_rate": 4.971091654048427e-06,
938
+ "loss": 0.6441,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 0.23,
943
+ "learning_rate": 4.970474531181245e-06,
944
+ "loss": 0.665,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 0.24,
949
+ "learning_rate": 4.96985092978261e-06,
950
+ "loss": 0.6792,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 0.24,
955
+ "learning_rate": 4.9692208514878445e-06,
956
+ "loss": 0.589,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 0.24,
961
+ "learning_rate": 4.968584297949255e-06,
962
+ "loss": 0.6726,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 0.24,
967
+ "learning_rate": 4.967941270836128e-06,
968
+ "loss": 0.6972,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 0.24,
973
+ "learning_rate": 4.967291771834727e-06,
974
+ "loss": 0.5856,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 0.24,
979
+ "learning_rate": 4.966635802648289e-06,
980
+ "loss": 0.652,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 0.24,
985
+ "learning_rate": 4.965973364997015e-06,
986
+ "loss": 0.656,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 0.25,
991
+ "learning_rate": 4.9653044606180725e-06,
992
+ "loss": 0.6783,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 0.25,
997
+ "learning_rate": 4.964629091265583e-06,
998
+ "loss": 0.5841,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 0.25,
1003
+ "learning_rate": 4.963947258710626e-06,
1004
+ "loss": 0.6502,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 0.25,
1009
+ "learning_rate": 4.963258964741227e-06,
1010
+ "loss": 0.6695,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 0.25,
1015
+ "learning_rate": 4.9625642111623555e-06,
1016
+ "loss": 0.67,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 0.25,
1021
+ "learning_rate": 4.961862999795923e-06,
1022
+ "loss": 0.6408,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 0.25,
1027
+ "learning_rate": 4.961155332480775e-06,
1028
+ "loss": 0.6179,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 0.26,
1033
+ "learning_rate": 4.960441211072686e-06,
1034
+ "loss": 0.6662,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 0.26,
1039
+ "learning_rate": 4.959720637444356e-06,
1040
+ "loss": 0.6425,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 0.26,
1045
+ "learning_rate": 4.958993613485406e-06,
1046
+ "loss": 0.5379,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 0.26,
1051
+ "learning_rate": 4.95826014110237e-06,
1052
+ "loss": 0.6582,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 0.26,
1057
+ "learning_rate": 4.957520222218695e-06,
1058
+ "loss": 0.7435,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 0.26,
1063
+ "learning_rate": 4.9567738587747314e-06,
1064
+ "loss": 0.6835,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 0.27,
1069
+ "learning_rate": 4.956021052727731e-06,
1070
+ "loss": 0.6002,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 0.27,
1075
+ "learning_rate": 4.9552618060518405e-06,
1076
+ "loss": 0.6838,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 0.27,
1081
+ "learning_rate": 4.954496120738094e-06,
1082
+ "loss": 0.5937,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 0.27,
1087
+ "learning_rate": 4.953723998794413e-06,
1088
+ "loss": 0.6657,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 0.27,
1093
+ "learning_rate": 4.952945442245598e-06,
1094
+ "loss": 0.7005,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 0.27,
1099
+ "learning_rate": 4.9521604531333215e-06,
1100
+ "loss": 0.6776,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 0.27,
1105
+ "learning_rate": 4.951369033516127e-06,
1106
+ "loss": 0.5453,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 0.28,
1111
+ "learning_rate": 4.9505711854694185e-06,
1112
+ "loss": 0.7262,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 0.28,
1117
+ "learning_rate": 4.949766911085461e-06,
1118
+ "loss": 0.6434,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 0.28,
1123
+ "learning_rate": 4.948956212473371e-06,
1124
+ "loss": 0.6317,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 0.28,
1129
+ "learning_rate": 4.948139091759108e-06,
1130
+ "loss": 0.5808,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 0.28,
1135
+ "learning_rate": 4.947315551085479e-06,
1136
+ "loss": 0.608,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 0.28,
1141
+ "learning_rate": 4.946485592612122e-06,
1142
+ "loss": 0.6725,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 0.28,
1147
+ "learning_rate": 4.945649218515507e-06,
1148
+ "loss": 0.6668,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 0.29,
1153
+ "learning_rate": 4.944806430988927e-06,
1154
+ "loss": 0.7065,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 0.29,
1159
+ "learning_rate": 4.943957232242494e-06,
1160
+ "loss": 0.6788,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 0.29,
1165
+ "learning_rate": 4.943101624503133e-06,
1166
+ "loss": 0.6993,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 0.29,
1171
+ "learning_rate": 4.942239610014575e-06,
1172
+ "loss": 0.6657,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 0.29,
1177
+ "learning_rate": 4.941371191037353e-06,
1178
+ "loss": 0.6167,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 0.29,
1183
+ "learning_rate": 4.940496369848795e-06,
1184
+ "loss": 0.6072,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 0.3,
1189
+ "learning_rate": 4.939615148743017e-06,
1190
+ "loss": 0.6639,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 0.3,
1195
+ "learning_rate": 4.938727530030919e-06,
1196
+ "loss": 0.656,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 0.3,
1201
+ "learning_rate": 4.937833516040177e-06,
1202
+ "loss": 0.6625,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 0.3,
1207
+ "learning_rate": 4.936933109115239e-06,
1208
+ "loss": 0.6165,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 0.3,
1213
+ "learning_rate": 4.936026311617316e-06,
1214
+ "loss": 0.586,
1215
+ "step": 201
1216
+ },
1217
+ {
1218
+ "epoch": 0.3,
1219
+ "learning_rate": 4.935113125924379e-06,
1220
+ "loss": 0.6245,
1221
+ "step": 202
1222
+ },
1223
+ {
1224
+ "epoch": 0.3,
1225
+ "learning_rate": 4.9341935544311536e-06,
1226
+ "loss": 0.6929,
1227
+ "step": 203
1228
+ },
1229
+ {
1230
+ "epoch": 0.31,
1231
+ "learning_rate": 4.933267599549106e-06,
1232
+ "loss": 0.7072,
1233
+ "step": 204
1234
+ },
1235
+ {
1236
+ "epoch": 0.31,
1237
+ "learning_rate": 4.932335263706446e-06,
1238
+ "loss": 0.7562,
1239
+ "step": 205
1240
+ },
1241
+ {
1242
+ "epoch": 0.31,
1243
+ "learning_rate": 4.931396549348115e-06,
1244
+ "loss": 0.6091,
1245
+ "step": 206
1246
+ },
1247
+ {
1248
+ "epoch": 0.31,
1249
+ "learning_rate": 4.930451458935783e-06,
1250
+ "loss": 0.6255,
1251
+ "step": 207
1252
+ },
1253
+ {
1254
+ "epoch": 0.31,
1255
+ "learning_rate": 4.929499994947839e-06,
1256
+ "loss": 0.6095,
1257
+ "step": 208
1258
+ },
1259
+ {
1260
+ "epoch": 0.31,
1261
+ "learning_rate": 4.928542159879386e-06,
1262
+ "loss": 0.6439,
1263
+ "step": 209
1264
+ },
1265
+ {
1266
+ "epoch": 0.31,
1267
+ "learning_rate": 4.9275779562422355e-06,
1268
+ "loss": 0.666,
1269
+ "step": 210
1270
+ },
1271
+ {
1272
+ "epoch": 0.32,
1273
+ "learning_rate": 4.926607386564898e-06,
1274
+ "loss": 0.722,
1275
+ "step": 211
1276
+ },
1277
+ {
1278
+ "epoch": 0.32,
1279
+ "learning_rate": 4.9256304533925804e-06,
1280
+ "loss": 0.7118,
1281
+ "step": 212
1282
+ },
1283
+ {
1284
+ "epoch": 0.32,
1285
+ "learning_rate": 4.924647159287176e-06,
1286
+ "loss": 0.647,
1287
+ "step": 213
1288
+ },
1289
+ {
1290
+ "epoch": 0.32,
1291
+ "learning_rate": 4.923657506827259e-06,
1292
+ "loss": 0.6128,
1293
+ "step": 214
1294
+ },
1295
+ {
1296
+ "epoch": 0.32,
1297
+ "learning_rate": 4.922661498608077e-06,
1298
+ "loss": 0.5735,
1299
+ "step": 215
1300
+ },
1301
+ {
1302
+ "epoch": 0.32,
1303
+ "learning_rate": 4.921659137241544e-06,
1304
+ "loss": 0.6629,
1305
+ "step": 216
1306
+ },
1307
+ {
1308
+ "epoch": 0.33,
1309
+ "learning_rate": 4.920650425356239e-06,
1310
+ "loss": 0.6016,
1311
+ "step": 217
1312
+ },
1313
+ {
1314
+ "epoch": 0.33,
1315
+ "learning_rate": 4.919635365597391e-06,
1316
+ "loss": 0.6508,
1317
+ "step": 218
1318
+ },
1319
+ {
1320
+ "epoch": 0.33,
1321
+ "learning_rate": 4.9186139606268735e-06,
1322
+ "loss": 0.689,
1323
+ "step": 219
1324
+ },
1325
+ {
1326
+ "epoch": 0.33,
1327
+ "learning_rate": 4.9175862131232035e-06,
1328
+ "loss": 0.6153,
1329
+ "step": 220
1330
+ },
1331
+ {
1332
+ "epoch": 0.33,
1333
+ "learning_rate": 4.916552125781529e-06,
1334
+ "loss": 0.728,
1335
+ "step": 221
1336
+ },
1337
+ {
1338
+ "epoch": 0.33,
1339
+ "learning_rate": 4.915511701313622e-06,
1340
+ "loss": 0.6765,
1341
+ "step": 222
1342
+ },
1343
+ {
1344
+ "epoch": 0.33,
1345
+ "learning_rate": 4.9144649424478765e-06,
1346
+ "loss": 0.6656,
1347
+ "step": 223
1348
+ },
1349
+ {
1350
+ "epoch": 0.34,
1351
+ "learning_rate": 4.913411851929295e-06,
1352
+ "loss": 0.6533,
1353
+ "step": 224
1354
+ },
1355
+ {
1356
+ "epoch": 0.34,
1357
+ "learning_rate": 4.912352432519484e-06,
1358
+ "loss": 0.6778,
1359
+ "step": 225
1360
+ },
1361
+ {
1362
+ "epoch": 0.34,
1363
+ "learning_rate": 4.911286686996648e-06,
1364
+ "loss": 0.652,
1365
+ "step": 226
1366
+ },
1367
+ {
1368
+ "epoch": 0.34,
1369
+ "learning_rate": 4.910214618155579e-06,
1370
+ "loss": 0.613,
1371
+ "step": 227
1372
+ },
1373
+ {
1374
+ "epoch": 0.34,
1375
+ "learning_rate": 4.909136228807655e-06,
1376
+ "loss": 0.628,
1377
+ "step": 228
1378
+ },
1379
+ {
1380
+ "epoch": 0.34,
1381
+ "learning_rate": 4.908051521780824e-06,
1382
+ "loss": 0.6609,
1383
+ "step": 229
1384
+ },
1385
+ {
1386
+ "epoch": 0.34,
1387
+ "learning_rate": 4.906960499919606e-06,
1388
+ "loss": 0.612,
1389
+ "step": 230
1390
+ },
1391
+ {
1392
+ "epoch": 0.35,
1393
+ "learning_rate": 4.905863166085076e-06,
1394
+ "loss": 0.6671,
1395
+ "step": 231
1396
+ },
1397
+ {
1398
+ "epoch": 0.35,
1399
+ "learning_rate": 4.904759523154866e-06,
1400
+ "loss": 0.6094,
1401
+ "step": 232
1402
+ },
1403
+ {
1404
+ "epoch": 0.35,
1405
+ "learning_rate": 4.903649574023151e-06,
1406
+ "loss": 0.6292,
1407
+ "step": 233
1408
+ },
1409
+ {
1410
+ "epoch": 0.35,
1411
+ "learning_rate": 4.902533321600641e-06,
1412
+ "loss": 0.5816,
1413
+ "step": 234
1414
+ },
1415
+ {
1416
+ "epoch": 0.35,
1417
+ "learning_rate": 4.901410768814581e-06,
1418
+ "loss": 0.6292,
1419
+ "step": 235
1420
+ },
1421
+ {
1422
+ "epoch": 0.35,
1423
+ "learning_rate": 4.900281918608732e-06,
1424
+ "loss": 0.6715,
1425
+ "step": 236
1426
+ },
1427
+ {
1428
+ "epoch": 0.36,
1429
+ "learning_rate": 4.899146773943374e-06,
1430
+ "loss": 0.6165,
1431
+ "step": 237
1432
+ },
1433
+ {
1434
+ "epoch": 0.36,
1435
+ "learning_rate": 4.898005337795291e-06,
1436
+ "loss": 0.6411,
1437
+ "step": 238
1438
+ },
1439
+ {
1440
+ "epoch": 0.36,
1441
+ "learning_rate": 4.896857613157765e-06,
1442
+ "loss": 0.6574,
1443
+ "step": 239
1444
+ },
1445
+ {
1446
+ "epoch": 0.36,
1447
+ "learning_rate": 4.895703603040572e-06,
1448
+ "loss": 0.6604,
1449
+ "step": 240
1450
+ },
1451
+ {
1452
+ "epoch": 0.36,
1453
+ "learning_rate": 4.894543310469968e-06,
1454
+ "loss": 0.733,
1455
+ "step": 241
1456
+ },
1457
+ {
1458
+ "epoch": 0.36,
1459
+ "learning_rate": 4.893376738488685e-06,
1460
+ "loss": 0.607,
1461
+ "step": 242
1462
+ },
1463
+ {
1464
+ "epoch": 0.36,
1465
+ "learning_rate": 4.8922038901559225e-06,
1466
+ "loss": 0.6022,
1467
+ "step": 243
1468
+ },
1469
+ {
1470
+ "epoch": 0.37,
1471
+ "learning_rate": 4.891024768547338e-06,
1472
+ "loss": 0.6306,
1473
+ "step": 244
1474
+ },
1475
+ {
1476
+ "epoch": 0.37,
1477
+ "learning_rate": 4.889839376755041e-06,
1478
+ "loss": 0.689,
1479
+ "step": 245
1480
+ },
1481
+ {
1482
+ "epoch": 0.37,
1483
+ "learning_rate": 4.888647717887582e-06,
1484
+ "loss": 0.6178,
1485
+ "step": 246
1486
+ },
1487
+ {
1488
+ "epoch": 0.37,
1489
+ "learning_rate": 4.887449795069948e-06,
1490
+ "loss": 0.656,
1491
+ "step": 247
1492
+ },
1493
+ {
1494
+ "epoch": 0.37,
1495
+ "learning_rate": 4.886245611443554e-06,
1496
+ "loss": 0.6352,
1497
+ "step": 248
1498
+ },
1499
+ {
1500
+ "epoch": 0.37,
1501
+ "learning_rate": 4.885035170166229e-06,
1502
+ "loss": 0.6416,
1503
+ "step": 249
1504
+ },
1505
+ {
1506
+ "epoch": 0.37,
1507
+ "learning_rate": 4.883818474412214e-06,
1508
+ "loss": 0.6109,
1509
+ "step": 250
1510
+ },
1511
+ {
1512
+ "epoch": 0.38,
1513
+ "learning_rate": 4.8825955273721524e-06,
1514
+ "loss": 0.6239,
1515
+ "step": 251
1516
+ },
1517
+ {
1518
+ "epoch": 0.38,
1519
+ "learning_rate": 4.8813663322530806e-06,
1520
+ "loss": 0.5663,
1521
+ "step": 252
1522
+ },
1523
+ {
1524
+ "epoch": 0.38,
1525
+ "learning_rate": 4.88013089227842e-06,
1526
+ "loss": 0.6967,
1527
+ "step": 253
1528
+ },
1529
+ {
1530
+ "epoch": 0.38,
1531
+ "learning_rate": 4.878889210687966e-06,
1532
+ "loss": 0.593,
1533
+ "step": 254
1534
+ },
1535
+ {
1536
+ "epoch": 0.38,
1537
+ "learning_rate": 4.8776412907378845e-06,
1538
+ "loss": 0.6723,
1539
+ "step": 255
1540
+ },
1541
+ {
1542
+ "epoch": 0.38,
1543
+ "learning_rate": 4.876387135700701e-06,
1544
+ "loss": 0.6897,
1545
+ "step": 256
1546
+ },
1547
+ {
1548
+ "epoch": 0.39,
1549
+ "learning_rate": 4.87512674886529e-06,
1550
+ "loss": 0.657,
1551
+ "step": 257
1552
+ },
1553
+ {
1554
+ "epoch": 0.39,
1555
+ "learning_rate": 4.87386013353687e-06,
1556
+ "loss": 0.5264,
1557
+ "step": 258
1558
+ },
1559
+ {
1560
+ "epoch": 0.39,
1561
+ "learning_rate": 4.872587293036991e-06,
1562
+ "loss": 0.6432,
1563
+ "step": 259
1564
+ },
1565
+ {
1566
+ "epoch": 0.39,
1567
+ "learning_rate": 4.871308230703529e-06,
1568
+ "loss": 0.6075,
1569
+ "step": 260
1570
+ },
1571
+ {
1572
+ "epoch": 0.39,
1573
+ "learning_rate": 4.870022949890676e-06,
1574
+ "loss": 0.6092,
1575
+ "step": 261
1576
+ },
1577
+ {
1578
+ "epoch": 0.39,
1579
+ "learning_rate": 4.868731453968932e-06,
1580
+ "loss": 0.6553,
1581
+ "step": 262
1582
+ },
1583
+ {
1584
+ "epoch": 0.39,
1585
+ "learning_rate": 4.867433746325093e-06,
1586
+ "loss": 0.7799,
1587
+ "step": 263
1588
+ },
1589
+ {
1590
+ "epoch": 0.4,
1591
+ "learning_rate": 4.866129830362247e-06,
1592
+ "loss": 0.65,
1593
+ "step": 264
1594
+ },
1595
+ {
1596
+ "epoch": 0.4,
1597
+ "learning_rate": 4.864819709499762e-06,
1598
+ "loss": 0.7294,
1599
+ "step": 265
1600
+ },
1601
+ {
1602
+ "epoch": 0.4,
1603
+ "learning_rate": 4.863503387173276e-06,
1604
+ "loss": 0.6032,
1605
+ "step": 266
1606
+ },
1607
+ {
1608
+ "epoch": 0.4,
1609
+ "learning_rate": 4.862180866834691e-06,
1610
+ "loss": 0.6481,
1611
+ "step": 267
1612
+ },
1613
+ {
1614
+ "epoch": 0.4,
1615
+ "learning_rate": 4.8608521519521625e-06,
1616
+ "loss": 0.6935,
1617
+ "step": 268
1618
+ },
1619
+ {
1620
+ "epoch": 0.4,
1621
+ "learning_rate": 4.8595172460100914e-06,
1622
+ "loss": 0.7026,
1623
+ "step": 269
1624
+ },
1625
+ {
1626
+ "epoch": 0.4,
1627
+ "learning_rate": 4.858176152509112e-06,
1628
+ "loss": 0.7004,
1629
+ "step": 270
1630
+ },
1631
+ {
1632
+ "epoch": 0.41,
1633
+ "learning_rate": 4.856828874966086e-06,
1634
+ "loss": 0.7371,
1635
+ "step": 271
1636
+ },
1637
+ {
1638
+ "epoch": 0.41,
1639
+ "learning_rate": 4.855475416914091e-06,
1640
+ "loss": 0.6234,
1641
+ "step": 272
1642
+ },
1643
+ {
1644
+ "epoch": 0.41,
1645
+ "learning_rate": 4.854115781902414e-06,
1646
+ "loss": 0.648,
1647
+ "step": 273
1648
+ },
1649
+ {
1650
+ "epoch": 0.41,
1651
+ "learning_rate": 4.852749973496539e-06,
1652
+ "loss": 0.7241,
1653
+ "step": 274
1654
+ },
1655
+ {
1656
+ "epoch": 0.41,
1657
+ "learning_rate": 4.851377995278138e-06,
1658
+ "loss": 0.5456,
1659
+ "step": 275
1660
+ },
1661
+ {
1662
+ "epoch": 0.41,
1663
+ "learning_rate": 4.849999850845066e-06,
1664
+ "loss": 0.6571,
1665
+ "step": 276
1666
+ },
1667
+ {
1668
+ "epoch": 0.42,
1669
+ "learning_rate": 4.8486155438113455e-06,
1670
+ "loss": 0.5847,
1671
+ "step": 277
1672
+ },
1673
+ {
1674
+ "epoch": 0.42,
1675
+ "learning_rate": 4.847225077807159e-06,
1676
+ "loss": 0.6271,
1677
+ "step": 278
1678
+ },
1679
+ {
1680
+ "epoch": 0.42,
1681
+ "learning_rate": 4.845828456478843e-06,
1682
+ "loss": 0.6662,
1683
+ "step": 279
1684
+ },
1685
+ {
1686
+ "epoch": 0.42,
1687
+ "learning_rate": 4.844425683488873e-06,
1688
+ "loss": 0.5785,
1689
+ "step": 280
1690
+ },
1691
+ {
1692
+ "epoch": 0.42,
1693
+ "learning_rate": 4.84301676251586e-06,
1694
+ "loss": 0.6561,
1695
+ "step": 281
1696
+ },
1697
+ {
1698
+ "epoch": 0.42,
1699
+ "learning_rate": 4.841601697254532e-06,
1700
+ "loss": 0.6676,
1701
+ "step": 282
1702
+ },
1703
+ {
1704
+ "epoch": 0.42,
1705
+ "learning_rate": 4.840180491415733e-06,
1706
+ "loss": 0.6267,
1707
+ "step": 283
1708
+ },
1709
+ {
1710
+ "epoch": 0.43,
1711
+ "learning_rate": 4.838753148726411e-06,
1712
+ "loss": 0.6603,
1713
+ "step": 284
1714
+ },
1715
+ {
1716
+ "epoch": 0.43,
1717
+ "learning_rate": 4.837319672929606e-06,
1718
+ "loss": 0.6696,
1719
+ "step": 285
1720
+ },
1721
+ {
1722
+ "epoch": 0.43,
1723
+ "learning_rate": 4.835880067784441e-06,
1724
+ "loss": 0.5933,
1725
+ "step": 286
1726
+ },
1727
+ {
1728
+ "epoch": 0.43,
1729
+ "learning_rate": 4.834434337066112e-06,
1730
+ "loss": 0.6347,
1731
+ "step": 287
1732
+ },
1733
+ {
1734
+ "epoch": 0.43,
1735
+ "learning_rate": 4.832982484565879e-06,
1736
+ "loss": 0.7012,
1737
+ "step": 288
1738
+ },
1739
+ {
1740
+ "epoch": 0.43,
1741
+ "learning_rate": 4.831524514091056e-06,
1742
+ "loss": 0.6537,
1743
+ "step": 289
1744
+ },
1745
+ {
1746
+ "epoch": 0.43,
1747
+ "learning_rate": 4.830060429465002e-06,
1748
+ "loss": 0.6495,
1749
+ "step": 290
1750
+ },
1751
+ {
1752
+ "epoch": 0.44,
1753
+ "learning_rate": 4.828590234527107e-06,
1754
+ "loss": 0.5948,
1755
+ "step": 291
1756
+ },
1757
+ {
1758
+ "epoch": 0.44,
1759
+ "learning_rate": 4.827113933132785e-06,
1760
+ "loss": 0.6396,
1761
+ "step": 292
1762
+ },
1763
+ {
1764
+ "epoch": 0.44,
1765
+ "learning_rate": 4.825631529153466e-06,
1766
+ "loss": 0.6895,
1767
+ "step": 293
1768
+ },
1769
+ {
1770
+ "epoch": 0.44,
1771
+ "learning_rate": 4.824143026476581e-06,
1772
+ "loss": 0.5879,
1773
+ "step": 294
1774
+ },
1775
+ {
1776
+ "epoch": 0.44,
1777
+ "learning_rate": 4.8226484290055544e-06,
1778
+ "loss": 0.5997,
1779
+ "step": 295
1780
+ },
1781
+ {
1782
+ "epoch": 0.44,
1783
+ "learning_rate": 4.821147740659795e-06,
1784
+ "loss": 0.6544,
1785
+ "step": 296
1786
+ },
1787
+ {
1788
+ "epoch": 0.45,
1789
+ "learning_rate": 4.8196409653746815e-06,
1790
+ "loss": 0.7022,
1791
+ "step": 297
1792
+ },
1793
+ {
1794
+ "epoch": 0.45,
1795
+ "learning_rate": 4.818128107101558e-06,
1796
+ "loss": 0.6618,
1797
+ "step": 298
1798
+ },
1799
+ {
1800
+ "epoch": 0.45,
1801
+ "learning_rate": 4.8166091698077165e-06,
1802
+ "loss": 0.6817,
1803
+ "step": 299
1804
+ },
1805
+ {
1806
+ "epoch": 0.45,
1807
+ "learning_rate": 4.815084157476395e-06,
1808
+ "loss": 0.6167,
1809
+ "step": 300
1810
+ },
1811
+ {
1812
+ "epoch": 0.45,
1813
+ "learning_rate": 4.813553074106761e-06,
1814
+ "loss": 0.7029,
1815
+ "step": 301
1816
+ },
1817
+ {
1818
+ "epoch": 0.45,
1819
+ "learning_rate": 4.812015923713901e-06,
1820
+ "loss": 0.6474,
1821
+ "step": 302
1822
+ },
1823
+ {
1824
+ "epoch": 0.45,
1825
+ "learning_rate": 4.8104727103288125e-06,
1826
+ "loss": 0.5441,
1827
+ "step": 303
1828
+ },
1829
+ {
1830
+ "epoch": 0.46,
1831
+ "learning_rate": 4.808923437998393e-06,
1832
+ "loss": 0.691,
1833
+ "step": 304
1834
+ },
1835
+ {
1836
+ "epoch": 0.46,
1837
+ "learning_rate": 4.80736811078543e-06,
1838
+ "loss": 0.563,
1839
+ "step": 305
1840
+ },
1841
+ {
1842
+ "epoch": 0.46,
1843
+ "learning_rate": 4.805806732768585e-06,
1844
+ "loss": 0.7345,
1845
+ "step": 306
1846
+ },
1847
+ {
1848
+ "epoch": 0.46,
1849
+ "learning_rate": 4.804239308042392e-06,
1850
+ "loss": 0.6248,
1851
+ "step": 307
1852
+ },
1853
+ {
1854
+ "epoch": 0.46,
1855
+ "learning_rate": 4.802665840717239e-06,
1856
+ "loss": 0.6877,
1857
+ "step": 308
1858
+ },
1859
+ {
1860
+ "epoch": 0.46,
1861
+ "learning_rate": 4.8010863349193605e-06,
1862
+ "loss": 0.5395,
1863
+ "step": 309
1864
+ },
1865
+ {
1866
+ "epoch": 0.46,
1867
+ "learning_rate": 4.799500794790827e-06,
1868
+ "loss": 0.6758,
1869
+ "step": 310
1870
+ },
1871
+ {
1872
+ "epoch": 0.47,
1873
+ "learning_rate": 4.797909224489531e-06,
1874
+ "loss": 0.6718,
1875
+ "step": 311
1876
+ },
1877
+ {
1878
+ "epoch": 0.47,
1879
+ "learning_rate": 4.796311628189182e-06,
1880
+ "loss": 0.7564,
1881
+ "step": 312
1882
+ },
1883
+ {
1884
+ "epoch": 0.47,
1885
+ "learning_rate": 4.794708010079288e-06,
1886
+ "loss": 0.6032,
1887
+ "step": 313
1888
+ },
1889
+ {
1890
+ "epoch": 0.47,
1891
+ "learning_rate": 4.793098374365153e-06,
1892
+ "loss": 0.6446,
1893
+ "step": 314
1894
+ },
1895
+ {
1896
+ "epoch": 0.47,
1897
+ "learning_rate": 4.791482725267858e-06,
1898
+ "loss": 0.6191,
1899
+ "step": 315
1900
+ },
1901
+ {
1902
+ "epoch": 0.47,
1903
+ "learning_rate": 4.789861067024253e-06,
1904
+ "loss": 0.6522,
1905
+ "step": 316
1906
+ },
1907
+ {
1908
+ "epoch": 0.48,
1909
+ "learning_rate": 4.78823340388695e-06,
1910
+ "loss": 0.5952,
1911
+ "step": 317
1912
+ },
1913
+ {
1914
+ "epoch": 0.48,
1915
+ "learning_rate": 4.786599740124303e-06,
1916
+ "loss": 0.5718,
1917
+ "step": 318
1918
+ },
1919
+ {
1920
+ "epoch": 0.48,
1921
+ "learning_rate": 4.7849600800204075e-06,
1922
+ "loss": 0.6754,
1923
+ "step": 319
1924
+ },
1925
+ {
1926
+ "epoch": 0.48,
1927
+ "learning_rate": 4.783314427875079e-06,
1928
+ "loss": 0.6304,
1929
+ "step": 320
1930
+ },
1931
+ {
1932
+ "epoch": 0.48,
1933
+ "learning_rate": 4.781662788003851e-06,
1934
+ "loss": 0.7108,
1935
+ "step": 321
1936
+ },
1937
+ {
1938
+ "epoch": 0.48,
1939
+ "learning_rate": 4.780005164737953e-06,
1940
+ "loss": 0.5482,
1941
+ "step": 322
1942
+ },
1943
+ {
1944
+ "epoch": 0.48,
1945
+ "learning_rate": 4.778341562424312e-06,
1946
+ "loss": 0.6221,
1947
+ "step": 323
1948
+ },
1949
+ {
1950
+ "epoch": 0.49,
1951
+ "learning_rate": 4.77667198542553e-06,
1952
+ "loss": 0.6402,
1953
+ "step": 324
1954
+ },
1955
+ {
1956
+ "epoch": 0.49,
1957
+ "learning_rate": 4.774996438119876e-06,
1958
+ "loss": 0.6815,
1959
+ "step": 325
1960
+ },
1961
+ {
1962
+ "epoch": 0.49,
1963
+ "learning_rate": 4.773314924901281e-06,
1964
+ "loss": 0.6012,
1965
+ "step": 326
1966
+ },
1967
+ {
1968
+ "epoch": 0.49,
1969
+ "learning_rate": 4.771627450179315e-06,
1970
+ "loss": 0.5947,
1971
+ "step": 327
1972
+ },
1973
+ {
1974
+ "epoch": 0.49,
1975
+ "learning_rate": 4.769934018379184e-06,
1976
+ "loss": 0.6487,
1977
+ "step": 328
1978
+ },
1979
+ {
1980
+ "epoch": 0.49,
1981
+ "learning_rate": 4.768234633941716e-06,
1982
+ "loss": 0.6514,
1983
+ "step": 329
1984
+ },
1985
+ {
1986
+ "epoch": 0.49,
1987
+ "learning_rate": 4.766529301323348e-06,
1988
+ "loss": 0.5795,
1989
+ "step": 330
1990
+ },
1991
+ {
1992
+ "epoch": 0.5,
1993
+ "learning_rate": 4.764818024996117e-06,
1994
+ "loss": 0.6174,
1995
+ "step": 331
1996
+ },
1997
+ {
1998
+ "epoch": 0.5,
1999
+ "learning_rate": 4.763100809447645e-06,
2000
+ "loss": 0.6777,
2001
+ "step": 332
2002
+ },
2003
+ {
2004
+ "epoch": 0.5,
2005
+ "learning_rate": 4.76137765918113e-06,
2006
+ "loss": 0.7552,
2007
+ "step": 333
2008
+ },
2009
+ {
2010
+ "epoch": 0.5,
2011
+ "learning_rate": 4.759648578715332e-06,
2012
+ "loss": 0.6257,
2013
+ "step": 334
2014
+ },
2015
+ {
2016
+ "epoch": 0.5,
2017
+ "learning_rate": 4.757913572584564e-06,
2018
+ "loss": 0.6385,
2019
+ "step": 335
2020
+ },
2021
+ {
2022
+ "epoch": 0.5,
2023
+ "learning_rate": 4.756172645338675e-06,
2024
+ "loss": 0.6018,
2025
+ "step": 336
2026
+ },
2027
+ {
2028
+ "epoch": 0.51,
2029
+ "learning_rate": 4.754425801543047e-06,
2030
+ "loss": 0.6403,
2031
+ "step": 337
2032
+ },
2033
+ {
2034
+ "epoch": 0.51,
2035
+ "learning_rate": 4.752673045778571e-06,
2036
+ "loss": 0.6967,
2037
+ "step": 338
2038
+ },
2039
+ {
2040
+ "epoch": 0.51,
2041
+ "learning_rate": 4.750914382641647e-06,
2042
+ "loss": 0.6542,
2043
+ "step": 339
2044
+ },
2045
+ {
2046
+ "epoch": 0.51,
2047
+ "learning_rate": 4.7491498167441645e-06,
2048
+ "loss": 0.6813,
2049
+ "step": 340
2050
+ },
2051
+ {
2052
+ "epoch": 0.51,
2053
+ "learning_rate": 4.747379352713489e-06,
2054
+ "loss": 0.6943,
2055
+ "step": 341
2056
+ },
2057
+ {
2058
+ "epoch": 0.51,
2059
+ "learning_rate": 4.745602995192458e-06,
2060
+ "loss": 0.5977,
2061
+ "step": 342
2062
+ },
2063
+ {
2064
+ "epoch": 0.51,
2065
+ "learning_rate": 4.743820748839362e-06,
2066
+ "loss": 0.6014,
2067
+ "step": 343
2068
+ },
2069
+ {
2070
+ "epoch": 0.52,
2071
+ "learning_rate": 4.742032618327933e-06,
2072
+ "loss": 0.7428,
2073
+ "step": 344
2074
+ },
2075
+ {
2076
+ "epoch": 0.52,
2077
+ "learning_rate": 4.740238608347337e-06,
2078
+ "loss": 0.5771,
2079
+ "step": 345
2080
+ },
2081
+ {
2082
+ "epoch": 0.52,
2083
+ "learning_rate": 4.738438723602154e-06,
2084
+ "loss": 0.622,
2085
+ "step": 346
2086
+ },
2087
+ {
2088
+ "epoch": 0.52,
2089
+ "learning_rate": 4.736632968812374e-06,
2090
+ "loss": 0.6699,
2091
+ "step": 347
2092
+ },
2093
+ {
2094
+ "epoch": 0.52,
2095
+ "learning_rate": 4.734821348713375e-06,
2096
+ "loss": 0.6372,
2097
+ "step": 348
2098
+ },
2099
+ {
2100
+ "epoch": 0.52,
2101
+ "learning_rate": 4.733003868055923e-06,
2102
+ "loss": 0.7212,
2103
+ "step": 349
2104
+ },
2105
+ {
2106
+ "epoch": 0.52,
2107
+ "learning_rate": 4.731180531606147e-06,
2108
+ "loss": 0.6755,
2109
+ "step": 350
2110
+ },
2111
+ {
2112
+ "epoch": 0.53,
2113
+ "learning_rate": 4.729351344145536e-06,
2114
+ "loss": 0.6487,
2115
+ "step": 351
2116
+ },
2117
+ {
2118
+ "epoch": 0.53,
2119
+ "learning_rate": 4.72751631047092e-06,
2120
+ "loss": 0.7057,
2121
+ "step": 352
2122
+ },
2123
+ {
2124
+ "epoch": 0.53,
2125
+ "learning_rate": 4.725675435394461e-06,
2126
+ "loss": 0.6158,
2127
+ "step": 353
2128
+ },
2129
+ {
2130
+ "epoch": 0.53,
2131
+ "learning_rate": 4.723828723743638e-06,
2132
+ "loss": 0.6,
2133
+ "step": 354
2134
+ },
2135
+ {
2136
+ "epoch": 0.53,
2137
+ "learning_rate": 4.721976180361239e-06,
2138
+ "loss": 0.6158,
2139
+ "step": 355
2140
+ },
2141
+ {
2142
+ "epoch": 0.53,
2143
+ "learning_rate": 4.720117810105341e-06,
2144
+ "loss": 0.5514,
2145
+ "step": 356
2146
+ },
2147
+ {
2148
+ "epoch": 0.54,
2149
+ "learning_rate": 4.718253617849306e-06,
2150
+ "loss": 0.6548,
2151
+ "step": 357
2152
+ },
2153
+ {
2154
+ "epoch": 0.54,
2155
+ "learning_rate": 4.7163836084817586e-06,
2156
+ "loss": 0.7832,
2157
+ "step": 358
2158
+ },
2159
+ {
2160
+ "epoch": 0.54,
2161
+ "learning_rate": 4.7145077869065815e-06,
2162
+ "loss": 0.6102,
2163
+ "step": 359
2164
+ },
2165
+ {
2166
+ "epoch": 0.54,
2167
+ "learning_rate": 4.712626158042898e-06,
2168
+ "loss": 0.6531,
2169
+ "step": 360
2170
+ },
2171
+ {
2172
+ "epoch": 0.54,
2173
+ "learning_rate": 4.710738726825059e-06,
2174
+ "loss": 0.5852,
2175
+ "step": 361
2176
+ },
2177
+ {
2178
+ "epoch": 0.54,
2179
+ "learning_rate": 4.708845498202635e-06,
2180
+ "loss": 0.6211,
2181
+ "step": 362
2182
+ },
2183
+ {
2184
+ "epoch": 0.54,
2185
+ "learning_rate": 4.706946477140396e-06,
2186
+ "loss": 0.6057,
2187
+ "step": 363
2188
+ },
2189
+ {
2190
+ "epoch": 0.55,
2191
+ "learning_rate": 4.705041668618304e-06,
2192
+ "loss": 0.6308,
2193
+ "step": 364
2194
+ },
2195
+ {
2196
+ "epoch": 0.55,
2197
+ "learning_rate": 4.703131077631498e-06,
2198
+ "loss": 0.6086,
2199
+ "step": 365
2200
+ },
2201
+ {
2202
+ "epoch": 0.55,
2203
+ "learning_rate": 4.701214709190277e-06,
2204
+ "loss": 0.6403,
2205
+ "step": 366
2206
+ },
2207
+ {
2208
+ "epoch": 0.55,
2209
+ "learning_rate": 4.699292568320097e-06,
2210
+ "loss": 0.5631,
2211
+ "step": 367
2212
+ },
2213
+ {
2214
+ "epoch": 0.55,
2215
+ "learning_rate": 4.697364660061548e-06,
2216
+ "loss": 0.6992,
2217
+ "step": 368
2218
+ },
2219
+ {
2220
+ "epoch": 0.55,
2221
+ "learning_rate": 4.6954309894703435e-06,
2222
+ "loss": 0.649,
2223
+ "step": 369
2224
+ },
2225
+ {
2226
+ "epoch": 0.55,
2227
+ "learning_rate": 4.693491561617309e-06,
2228
+ "loss": 0.6579,
2229
+ "step": 370
2230
+ },
2231
+ {
2232
+ "epoch": 0.56,
2233
+ "learning_rate": 4.69154638158837e-06,
2234
+ "loss": 0.6637,
2235
+ "step": 371
2236
+ },
2237
+ {
2238
+ "epoch": 0.56,
2239
+ "learning_rate": 4.689595454484531e-06,
2240
+ "loss": 0.6391,
2241
+ "step": 372
2242
+ },
2243
+ {
2244
+ "epoch": 0.56,
2245
+ "learning_rate": 4.687638785421875e-06,
2246
+ "loss": 0.6079,
2247
+ "step": 373
2248
+ },
2249
+ {
2250
+ "epoch": 0.56,
2251
+ "learning_rate": 4.685676379531535e-06,
2252
+ "loss": 0.6613,
2253
+ "step": 374
2254
+ },
2255
+ {
2256
+ "epoch": 0.56,
2257
+ "learning_rate": 4.683708241959694e-06,
2258
+ "loss": 0.6155,
2259
+ "step": 375
2260
+ },
2261
+ {
2262
+ "epoch": 0.56,
2263
+ "learning_rate": 4.681734377867562e-06,
2264
+ "loss": 0.5651,
2265
+ "step": 376
2266
+ },
2267
+ {
2268
+ "epoch": 0.57,
2269
+ "learning_rate": 4.679754792431368e-06,
2270
+ "loss": 0.6705,
2271
+ "step": 377
2272
+ },
2273
+ {
2274
+ "epoch": 0.57,
2275
+ "learning_rate": 4.677769490842344e-06,
2276
+ "loss": 0.7012,
2277
+ "step": 378
2278
+ },
2279
+ {
2280
+ "epoch": 0.57,
2281
+ "learning_rate": 4.675778478306712e-06,
2282
+ "loss": 0.5865,
2283
+ "step": 379
2284
+ },
2285
+ {
2286
+ "epoch": 0.57,
2287
+ "learning_rate": 4.673781760045669e-06,
2288
+ "loss": 0.6333,
2289
+ "step": 380
2290
+ },
2291
+ {
2292
+ "epoch": 0.57,
2293
+ "learning_rate": 4.671779341295378e-06,
2294
+ "loss": 0.5923,
2295
+ "step": 381
2296
+ },
2297
+ {
2298
+ "epoch": 0.57,
2299
+ "learning_rate": 4.6697712273069475e-06,
2300
+ "loss": 0.6173,
2301
+ "step": 382
2302
+ },
2303
+ {
2304
+ "epoch": 0.57,
2305
+ "learning_rate": 4.667757423346423e-06,
2306
+ "loss": 0.6453,
2307
+ "step": 383
2308
+ },
2309
+ {
2310
+ "epoch": 0.58,
2311
+ "learning_rate": 4.665737934694769e-06,
2312
+ "loss": 0.6044,
2313
+ "step": 384
2314
+ },
2315
+ {
2316
+ "epoch": 0.58,
2317
+ "learning_rate": 4.663712766647862e-06,
2318
+ "loss": 0.6679,
2319
+ "step": 385
2320
+ },
2321
+ {
2322
+ "epoch": 0.58,
2323
+ "learning_rate": 4.661681924516466e-06,
2324
+ "loss": 0.6285,
2325
+ "step": 386
2326
+ },
2327
+ {
2328
+ "epoch": 0.58,
2329
+ "learning_rate": 4.65964541362623e-06,
2330
+ "loss": 0.5703,
2331
+ "step": 387
2332
+ },
2333
+ {
2334
+ "epoch": 0.58,
2335
+ "learning_rate": 4.657603239317665e-06,
2336
+ "loss": 0.5869,
2337
+ "step": 388
2338
+ },
2339
+ {
2340
+ "epoch": 0.58,
2341
+ "learning_rate": 4.655555406946135e-06,
2342
+ "loss": 0.6306,
2343
+ "step": 389
2344
+ },
2345
+ {
2346
+ "epoch": 0.58,
2347
+ "learning_rate": 4.6535019218818435e-06,
2348
+ "loss": 0.6176,
2349
+ "step": 390
2350
+ },
2351
+ {
2352
+ "epoch": 0.59,
2353
+ "learning_rate": 4.651442789509813e-06,
2354
+ "loss": 0.6953,
2355
+ "step": 391
2356
+ },
2357
+ {
2358
+ "epoch": 0.59,
2359
+ "learning_rate": 4.649378015229881e-06,
2360
+ "loss": 0.7032,
2361
+ "step": 392
2362
+ },
2363
+ {
2364
+ "epoch": 0.59,
2365
+ "learning_rate": 4.647307604456675e-06,
2366
+ "loss": 0.6164,
2367
+ "step": 393
2368
+ },
2369
+ {
2370
+ "epoch": 0.59,
2371
+ "learning_rate": 4.645231562619606e-06,
2372
+ "loss": 0.6152,
2373
+ "step": 394
2374
+ },
2375
+ {
2376
+ "epoch": 0.59,
2377
+ "learning_rate": 4.643149895162854e-06,
2378
+ "loss": 0.7484,
2379
+ "step": 395
2380
+ },
2381
+ {
2382
+ "epoch": 0.59,
2383
+ "learning_rate": 4.641062607545347e-06,
2384
+ "loss": 0.6073,
2385
+ "step": 396
2386
+ },
2387
+ {
2388
+ "epoch": 0.59,
2389
+ "learning_rate": 4.6389697052407535e-06,
2390
+ "loss": 0.6597,
2391
+ "step": 397
2392
+ },
2393
+ {
2394
+ "epoch": 0.6,
2395
+ "learning_rate": 4.636871193737466e-06,
2396
+ "loss": 0.6376,
2397
+ "step": 398
2398
+ },
2399
+ {
2400
+ "epoch": 0.6,
2401
+ "learning_rate": 4.634767078538589e-06,
2402
+ "loss": 0.6549,
2403
+ "step": 399
2404
+ },
2405
+ {
2406
+ "epoch": 0.6,
2407
+ "learning_rate": 4.6326573651619145e-06,
2408
+ "loss": 0.6295,
2409
+ "step": 400
2410
+ },
2411
+ {
2412
+ "epoch": 0.6,
2413
+ "learning_rate": 4.630542059139923e-06,
2414
+ "loss": 0.6254,
2415
+ "step": 401
2416
+ },
2417
+ {
2418
+ "epoch": 0.6,
2419
+ "learning_rate": 4.628421166019758e-06,
2420
+ "loss": 0.6236,
2421
+ "step": 402
2422
+ },
2423
+ {
2424
+ "epoch": 0.6,
2425
+ "learning_rate": 4.626294691363213e-06,
2426
+ "loss": 0.6202,
2427
+ "step": 403
2428
+ },
2429
+ {
2430
+ "epoch": 0.61,
2431
+ "learning_rate": 4.624162640746722e-06,
2432
+ "loss": 0.7059,
2433
+ "step": 404
2434
+ },
2435
+ {
2436
+ "epoch": 0.61,
2437
+ "learning_rate": 4.622025019761336e-06,
2438
+ "loss": 0.694,
2439
+ "step": 405
2440
+ },
2441
+ {
2442
+ "epoch": 0.61,
2443
+ "learning_rate": 4.61988183401272e-06,
2444
+ "loss": 0.6582,
2445
+ "step": 406
2446
+ },
2447
+ {
2448
+ "epoch": 0.61,
2449
+ "learning_rate": 4.617733089121127e-06,
2450
+ "loss": 0.6624,
2451
+ "step": 407
2452
+ },
2453
+ {
2454
+ "epoch": 0.61,
2455
+ "learning_rate": 4.615578790721391e-06,
2456
+ "loss": 0.6266,
2457
+ "step": 408
2458
+ },
2459
+ {
2460
+ "epoch": 0.61,
2461
+ "learning_rate": 4.613418944462907e-06,
2462
+ "loss": 0.5788,
2463
+ "step": 409
2464
+ },
2465
+ {
2466
+ "epoch": 0.61,
2467
+ "learning_rate": 4.611253556009621e-06,
2468
+ "loss": 0.6341,
2469
+ "step": 410
2470
+ },
2471
+ {
2472
+ "epoch": 0.62,
2473
+ "learning_rate": 4.609082631040012e-06,
2474
+ "loss": 0.5473,
2475
+ "step": 411
2476
+ },
2477
+ {
2478
+ "epoch": 0.62,
2479
+ "learning_rate": 4.606906175247077e-06,
2480
+ "loss": 0.5308,
2481
+ "step": 412
2482
+ },
2483
+ {
2484
+ "epoch": 0.62,
2485
+ "learning_rate": 4.604724194338318e-06,
2486
+ "loss": 0.6084,
2487
+ "step": 413
2488
+ },
2489
+ {
2490
+ "epoch": 0.62,
2491
+ "learning_rate": 4.602536694035725e-06,
2492
+ "loss": 0.642,
2493
+ "step": 414
2494
+ },
2495
+ {
2496
+ "epoch": 0.62,
2497
+ "learning_rate": 4.600343680075764e-06,
2498
+ "loss": 0.6859,
2499
+ "step": 415
2500
+ },
2501
+ {
2502
+ "epoch": 0.62,
2503
+ "learning_rate": 4.598145158209356e-06,
2504
+ "loss": 0.5046,
2505
+ "step": 416
2506
+ },
2507
+ {
2508
+ "epoch": 0.62,
2509
+ "learning_rate": 4.5959411342018715e-06,
2510
+ "loss": 0.6213,
2511
+ "step": 417
2512
+ },
2513
+ {
2514
+ "epoch": 0.63,
2515
+ "learning_rate": 4.593731613833103e-06,
2516
+ "loss": 0.6038,
2517
+ "step": 418
2518
+ },
2519
+ {
2520
+ "epoch": 0.63,
2521
+ "learning_rate": 4.591516602897263e-06,
2522
+ "loss": 0.6423,
2523
+ "step": 419
2524
+ },
2525
+ {
2526
+ "epoch": 0.63,
2527
+ "learning_rate": 4.589296107202957e-06,
2528
+ "loss": 0.5456,
2529
+ "step": 420
2530
+ },
2531
+ {
2532
+ "epoch": 0.63,
2533
+ "learning_rate": 4.587070132573178e-06,
2534
+ "loss": 0.619,
2535
+ "step": 421
2536
+ },
2537
+ {
2538
+ "epoch": 0.63,
2539
+ "learning_rate": 4.5848386848452845e-06,
2540
+ "loss": 0.6434,
2541
+ "step": 422
2542
+ },
2543
+ {
2544
+ "epoch": 0.63,
2545
+ "learning_rate": 4.582601769870988e-06,
2546
+ "loss": 0.6322,
2547
+ "step": 423
2548
+ },
2549
+ {
2550
+ "epoch": 0.64,
2551
+ "learning_rate": 4.580359393516337e-06,
2552
+ "loss": 0.6349,
2553
+ "step": 424
2554
+ },
2555
+ {
2556
+ "epoch": 0.64,
2557
+ "learning_rate": 4.578111561661702e-06,
2558
+ "loss": 0.597,
2559
+ "step": 425
2560
+ },
2561
+ {
2562
+ "epoch": 0.64,
2563
+ "learning_rate": 4.575858280201761e-06,
2564
+ "loss": 0.5919,
2565
+ "step": 426
2566
+ },
2567
+ {
2568
+ "epoch": 0.64,
2569
+ "learning_rate": 4.57359955504548e-06,
2570
+ "loss": 0.6547,
2571
+ "step": 427
2572
+ },
2573
+ {
2574
+ "epoch": 0.64,
2575
+ "learning_rate": 4.571335392116104e-06,
2576
+ "loss": 0.7244,
2577
+ "step": 428
2578
+ },
2579
+ {
2580
+ "epoch": 0.64,
2581
+ "learning_rate": 4.569065797351135e-06,
2582
+ "loss": 0.6238,
2583
+ "step": 429
2584
+ },
2585
+ {
2586
+ "epoch": 0.64,
2587
+ "learning_rate": 4.566790776702322e-06,
2588
+ "loss": 0.5867,
2589
+ "step": 430
2590
+ },
2591
+ {
2592
+ "epoch": 0.65,
2593
+ "learning_rate": 4.564510336135642e-06,
2594
+ "loss": 0.6188,
2595
+ "step": 431
2596
+ },
2597
+ {
2598
+ "epoch": 0.65,
2599
+ "learning_rate": 4.562224481631282e-06,
2600
+ "loss": 0.6765,
2601
+ "step": 432
2602
+ },
2603
+ {
2604
+ "epoch": 0.65,
2605
+ "learning_rate": 4.559933219183631e-06,
2606
+ "loss": 0.5697,
2607
+ "step": 433
2608
+ },
2609
+ {
2610
+ "epoch": 0.65,
2611
+ "learning_rate": 4.557636554801258e-06,
2612
+ "loss": 0.5907,
2613
+ "step": 434
2614
+ },
2615
+ {
2616
+ "epoch": 0.65,
2617
+ "learning_rate": 4.555334494506895e-06,
2618
+ "loss": 0.5777,
2619
+ "step": 435
2620
+ },
2621
+ {
2622
+ "epoch": 0.65,
2623
+ "learning_rate": 4.5530270443374305e-06,
2624
+ "loss": 0.65,
2625
+ "step": 436
2626
+ },
2627
+ {
2628
+ "epoch": 0.65,
2629
+ "learning_rate": 4.550714210343879e-06,
2630
+ "loss": 0.7257,
2631
+ "step": 437
2632
+ },
2633
+ {
2634
+ "epoch": 0.66,
2635
+ "learning_rate": 4.548395998591383e-06,
2636
+ "loss": 0.645,
2637
+ "step": 438
2638
+ },
2639
+ {
2640
+ "epoch": 0.66,
2641
+ "learning_rate": 4.546072415159179e-06,
2642
+ "loss": 0.564,
2643
+ "step": 439
2644
+ },
2645
+ {
2646
+ "epoch": 0.66,
2647
+ "learning_rate": 4.543743466140595e-06,
2648
+ "loss": 0.6302,
2649
+ "step": 440
2650
+ },
2651
+ {
2652
+ "epoch": 0.66,
2653
+ "learning_rate": 4.541409157643027e-06,
2654
+ "loss": 0.6529,
2655
+ "step": 441
2656
+ },
2657
+ {
2658
+ "epoch": 0.66,
2659
+ "learning_rate": 4.53906949578793e-06,
2660
+ "loss": 0.6413,
2661
+ "step": 442
2662
+ },
2663
+ {
2664
+ "epoch": 0.66,
2665
+ "learning_rate": 4.5367244867107905e-06,
2666
+ "loss": 0.6605,
2667
+ "step": 443
2668
+ },
2669
+ {
2670
+ "epoch": 0.67,
2671
+ "learning_rate": 4.534374136561125e-06,
2672
+ "loss": 0.645,
2673
+ "step": 444
2674
+ },
2675
+ {
2676
+ "epoch": 0.67,
2677
+ "learning_rate": 4.53201845150245e-06,
2678
+ "loss": 0.6168,
2679
+ "step": 445
2680
+ },
2681
+ {
2682
+ "epoch": 0.67,
2683
+ "learning_rate": 4.5296574377122765e-06,
2684
+ "loss": 0.5961,
2685
+ "step": 446
2686
+ },
2687
+ {
2688
+ "epoch": 0.67,
2689
+ "learning_rate": 4.527291101382088e-06,
2690
+ "loss": 0.5908,
2691
+ "step": 447
2692
+ },
2693
+ {
2694
+ "epoch": 0.67,
2695
+ "learning_rate": 4.524919448717324e-06,
2696
+ "loss": 0.5936,
2697
+ "step": 448
2698
+ },
2699
+ {
2700
+ "epoch": 0.67,
2701
+ "learning_rate": 4.522542485937369e-06,
2702
+ "loss": 0.6486,
2703
+ "step": 449
2704
+ },
2705
+ {
2706
+ "epoch": 0.67,
2707
+ "learning_rate": 4.52016021927553e-06,
2708
+ "loss": 0.6342,
2709
+ "step": 450
2710
+ },
2711
+ {
2712
+ "epoch": 0.68,
2713
+ "learning_rate": 4.517772654979024e-06,
2714
+ "loss": 0.6082,
2715
+ "step": 451
2716
+ },
2717
+ {
2718
+ "epoch": 0.68,
2719
+ "learning_rate": 4.515379799308959e-06,
2720
+ "loss": 0.6672,
2721
+ "step": 452
2722
+ },
2723
+ {
2724
+ "epoch": 0.68,
2725
+ "learning_rate": 4.512981658540321e-06,
2726
+ "loss": 0.6411,
2727
+ "step": 453
2728
+ },
2729
+ {
2730
+ "epoch": 0.68,
2731
+ "learning_rate": 4.510578238961955e-06,
2732
+ "loss": 0.559,
2733
+ "step": 454
2734
+ },
2735
+ {
2736
+ "epoch": 0.68,
2737
+ "learning_rate": 4.508169546876547e-06,
2738
+ "loss": 0.6612,
2739
+ "step": 455
2740
+ },
2741
+ {
2742
+ "epoch": 0.68,
2743
+ "learning_rate": 4.505755588600613e-06,
2744
+ "loss": 0.6116,
2745
+ "step": 456
2746
+ },
2747
+ {
2748
+ "epoch": 0.68,
2749
+ "learning_rate": 4.503336370464476e-06,
2750
+ "loss": 0.5487,
2751
+ "step": 457
2752
+ },
2753
+ {
2754
+ "epoch": 0.69,
2755
+ "learning_rate": 4.500911898812254e-06,
2756
+ "loss": 0.546,
2757
+ "step": 458
2758
+ },
2759
+ {
2760
+ "epoch": 0.69,
2761
+ "learning_rate": 4.49848218000184e-06,
2762
+ "loss": 0.5619,
2763
+ "step": 459
2764
+ },
2765
+ {
2766
+ "epoch": 0.69,
2767
+ "learning_rate": 4.496047220404891e-06,
2768
+ "loss": 0.6467,
2769
+ "step": 460
2770
+ },
2771
+ {
2772
+ "epoch": 0.69,
2773
+ "learning_rate": 4.493607026406802e-06,
2774
+ "loss": 0.6351,
2775
+ "step": 461
2776
+ },
2777
+ {
2778
+ "epoch": 0.69,
2779
+ "learning_rate": 4.4911616044067e-06,
2780
+ "loss": 0.6049,
2781
+ "step": 462
2782
+ },
2783
+ {
2784
+ "epoch": 0.69,
2785
+ "learning_rate": 4.488710960817416e-06,
2786
+ "loss": 0.6946,
2787
+ "step": 463
2788
+ },
2789
+ {
2790
+ "epoch": 0.7,
2791
+ "learning_rate": 4.48625510206548e-06,
2792
+ "loss": 0.6271,
2793
+ "step": 464
2794
+ },
2795
+ {
2796
+ "epoch": 0.7,
2797
+ "learning_rate": 4.483794034591092e-06,
2798
+ "loss": 0.6869,
2799
+ "step": 465
2800
+ },
2801
+ {
2802
+ "epoch": 0.7,
2803
+ "learning_rate": 4.481327764848118e-06,
2804
+ "loss": 0.6117,
2805
+ "step": 466
2806
+ },
2807
+ {
2808
+ "epoch": 0.7,
2809
+ "learning_rate": 4.4788562993040615e-06,
2810
+ "loss": 0.6117,
2811
+ "step": 467
2812
+ },
2813
+ {
2814
+ "epoch": 0.7,
2815
+ "learning_rate": 4.476379644440052e-06,
2816
+ "loss": 0.5523,
2817
+ "step": 468
2818
+ },
2819
+ {
2820
+ "epoch": 0.7,
2821
+ "learning_rate": 4.473897806750829e-06,
2822
+ "loss": 0.5639,
2823
+ "step": 469
2824
+ },
2825
+ {
2826
+ "epoch": 0.7,
2827
+ "learning_rate": 4.471410792744723e-06,
2828
+ "loss": 0.6212,
2829
+ "step": 470
2830
+ },
2831
+ {
2832
+ "epoch": 0.71,
2833
+ "learning_rate": 4.4689186089436365e-06,
2834
+ "loss": 0.6071,
2835
+ "step": 471
2836
+ },
2837
+ {
2838
+ "epoch": 0.71,
2839
+ "learning_rate": 4.466421261883033e-06,
2840
+ "loss": 0.5548,
2841
+ "step": 472
2842
+ },
2843
+ {
2844
+ "epoch": 0.71,
2845
+ "learning_rate": 4.463918758111912e-06,
2846
+ "loss": 0.6171,
2847
+ "step": 473
2848
+ },
2849
+ {
2850
+ "epoch": 0.71,
2851
+ "learning_rate": 4.4614111041928e-06,
2852
+ "loss": 0.6367,
2853
+ "step": 474
2854
+ },
2855
+ {
2856
+ "epoch": 0.71,
2857
+ "learning_rate": 4.4588983067017255e-06,
2858
+ "loss": 0.5579,
2859
+ "step": 475
2860
+ },
2861
+ {
2862
+ "epoch": 0.71,
2863
+ "learning_rate": 4.456380372228208e-06,
2864
+ "loss": 0.5622,
2865
+ "step": 476
2866
+ },
2867
+ {
2868
+ "epoch": 0.71,
2869
+ "learning_rate": 4.4538573073752365e-06,
2870
+ "loss": 0.6741,
2871
+ "step": 477
2872
+ },
2873
+ {
2874
+ "epoch": 0.72,
2875
+ "learning_rate": 4.451329118759254e-06,
2876
+ "loss": 0.632,
2877
+ "step": 478
2878
+ },
2879
+ {
2880
+ "epoch": 0.72,
2881
+ "learning_rate": 4.448795813010142e-06,
2882
+ "loss": 0.6588,
2883
+ "step": 479
2884
+ },
2885
+ {
2886
+ "epoch": 0.72,
2887
+ "learning_rate": 4.446257396771198e-06,
2888
+ "loss": 0.6643,
2889
+ "step": 480
2890
+ },
2891
+ {
2892
+ "epoch": 0.72,
2893
+ "learning_rate": 4.443713876699124e-06,
2894
+ "loss": 0.5922,
2895
+ "step": 481
2896
+ },
2897
+ {
2898
+ "epoch": 0.72,
2899
+ "learning_rate": 4.441165259464003e-06,
2900
+ "loss": 0.5944,
2901
+ "step": 482
2902
+ },
2903
+ {
2904
+ "epoch": 0.72,
2905
+ "learning_rate": 4.438611551749288e-06,
2906
+ "loss": 0.6382,
2907
+ "step": 483
2908
+ },
2909
+ {
2910
+ "epoch": 0.73,
2911
+ "learning_rate": 4.43605276025178e-06,
2912
+ "loss": 0.6223,
2913
+ "step": 484
2914
+ },
2915
+ {
2916
+ "epoch": 0.73,
2917
+ "learning_rate": 4.4334888916816096e-06,
2918
+ "loss": 0.6029,
2919
+ "step": 485
2920
+ },
2921
+ {
2922
+ "epoch": 0.73,
2923
+ "learning_rate": 4.430919952762226e-06,
2924
+ "loss": 0.5906,
2925
+ "step": 486
2926
+ },
2927
+ {
2928
+ "epoch": 0.73,
2929
+ "learning_rate": 4.42834595023037e-06,
2930
+ "loss": 0.5783,
2931
+ "step": 487
2932
+ },
2933
+ {
2934
+ "epoch": 0.73,
2935
+ "learning_rate": 4.425766890836063e-06,
2936
+ "loss": 0.5963,
2937
+ "step": 488
2938
+ },
2939
+ {
2940
+ "epoch": 0.73,
2941
+ "learning_rate": 4.423182781342589e-06,
2942
+ "loss": 0.5772,
2943
+ "step": 489
2944
+ },
2945
+ {
2946
+ "epoch": 0.73,
2947
+ "learning_rate": 4.420593628526472e-06,
2948
+ "loss": 0.6569,
2949
+ "step": 490
2950
+ },
2951
+ {
2952
+ "epoch": 0.74,
2953
+ "learning_rate": 4.417999439177465e-06,
2954
+ "loss": 0.6363,
2955
+ "step": 491
2956
+ },
2957
+ {
2958
+ "epoch": 0.74,
2959
+ "learning_rate": 4.415400220098528e-06,
2960
+ "loss": 0.6453,
2961
+ "step": 492
2962
+ },
2963
+ {
2964
+ "epoch": 0.74,
2965
+ "learning_rate": 4.412795978105807e-06,
2966
+ "loss": 0.6129,
2967
+ "step": 493
2968
+ },
2969
+ {
2970
+ "epoch": 0.74,
2971
+ "learning_rate": 4.410186720028626e-06,
2972
+ "loss": 0.6464,
2973
+ "step": 494
2974
+ },
2975
+ {
2976
+ "epoch": 0.74,
2977
+ "learning_rate": 4.407572452709459e-06,
2978
+ "loss": 0.5378,
2979
+ "step": 495
2980
+ },
2981
+ {
2982
+ "epoch": 0.74,
2983
+ "learning_rate": 4.404953183003916e-06,
2984
+ "loss": 0.5863,
2985
+ "step": 496
2986
+ },
2987
+ {
2988
+ "epoch": 0.74,
2989
+ "learning_rate": 4.402328917780728e-06,
2990
+ "loss": 0.5855,
2991
+ "step": 497
2992
+ },
2993
+ {
2994
+ "epoch": 0.75,
2995
+ "learning_rate": 4.399699663921725e-06,
2996
+ "loss": 0.7054,
2997
+ "step": 498
2998
+ },
2999
+ {
3000
+ "epoch": 0.75,
3001
+ "learning_rate": 4.397065428321818e-06,
3002
+ "loss": 0.6431,
3003
+ "step": 499
3004
+ },
3005
+ {
3006
+ "epoch": 0.75,
3007
+ "learning_rate": 4.394426217888981e-06,
3008
+ "loss": 0.6492,
3009
+ "step": 500
3010
+ },
3011
+ {
3012
+ "epoch": 0.75,
3013
+ "learning_rate": 4.391782039544239e-06,
3014
+ "loss": 0.6399,
3015
+ "step": 501
3016
+ },
3017
+ {
3018
+ "epoch": 0.75,
3019
+ "learning_rate": 4.389132900221638e-06,
3020
+ "loss": 0.5969,
3021
+ "step": 502
3022
+ },
3023
+ {
3024
+ "epoch": 0.75,
3025
+ "learning_rate": 4.386478806868242e-06,
3026
+ "loss": 0.6215,
3027
+ "step": 503
3028
+ },
3029
+ {
3030
+ "epoch": 0.76,
3031
+ "learning_rate": 4.383819766444095e-06,
3032
+ "loss": 0.7034,
3033
+ "step": 504
3034
+ },
3035
+ {
3036
+ "epoch": 0.76,
3037
+ "learning_rate": 4.381155785922226e-06,
3038
+ "loss": 0.6588,
3039
+ "step": 505
3040
+ },
3041
+ {
3042
+ "epoch": 0.76,
3043
+ "learning_rate": 4.378486872288611e-06,
3044
+ "loss": 0.5721,
3045
+ "step": 506
3046
+ },
3047
+ {
3048
+ "epoch": 0.76,
3049
+ "learning_rate": 4.375813032542164e-06,
3050
+ "loss": 0.651,
3051
+ "step": 507
3052
+ },
3053
+ {
3054
+ "epoch": 0.76,
3055
+ "learning_rate": 4.37313427369472e-06,
3056
+ "loss": 0.5738,
3057
+ "step": 508
3058
+ },
3059
+ {
3060
+ "epoch": 0.76,
3061
+ "learning_rate": 4.37045060277101e-06,
3062
+ "loss": 0.6204,
3063
+ "step": 509
3064
+ },
3065
+ {
3066
+ "epoch": 0.76,
3067
+ "learning_rate": 4.36776202680865e-06,
3068
+ "loss": 0.6554,
3069
+ "step": 510
3070
+ },
3071
+ {
3072
+ "epoch": 0.77,
3073
+ "learning_rate": 4.365068552858116e-06,
3074
+ "loss": 0.5586,
3075
+ "step": 511
3076
+ },
3077
+ {
3078
+ "epoch": 0.77,
3079
+ "learning_rate": 4.362370187982729e-06,
3080
+ "loss": 0.5897,
3081
+ "step": 512
3082
+ },
3083
+ {
3084
+ "epoch": 0.77,
3085
+ "learning_rate": 4.359666939258637e-06,
3086
+ "loss": 0.6203,
3087
+ "step": 513
3088
+ },
3089
+ {
3090
+ "epoch": 0.77,
3091
+ "learning_rate": 4.356958813774793e-06,
3092
+ "loss": 0.5969,
3093
+ "step": 514
3094
+ },
3095
+ {
3096
+ "epoch": 0.77,
3097
+ "learning_rate": 4.354245818632944e-06,
3098
+ "loss": 0.6867,
3099
+ "step": 515
3100
+ },
3101
+ {
3102
+ "epoch": 0.77,
3103
+ "learning_rate": 4.3515279609476e-06,
3104
+ "loss": 0.6195,
3105
+ "step": 516
3106
+ },
3107
+ {
3108
+ "epoch": 0.77,
3109
+ "learning_rate": 4.348805247846027e-06,
3110
+ "loss": 0.6594,
3111
+ "step": 517
3112
+ },
3113
+ {
3114
+ "epoch": 0.78,
3115
+ "learning_rate": 4.346077686468224e-06,
3116
+ "loss": 0.6124,
3117
+ "step": 518
3118
+ },
3119
+ {
3120
+ "epoch": 0.78,
3121
+ "learning_rate": 4.343345283966901e-06,
3122
+ "loss": 0.6588,
3123
+ "step": 519
3124
+ },
3125
+ {
3126
+ "epoch": 0.78,
3127
+ "learning_rate": 4.3406080475074656e-06,
3128
+ "loss": 0.6637,
3129
+ "step": 520
3130
+ },
3131
+ {
3132
+ "epoch": 0.78,
3133
+ "learning_rate": 4.337865984268002e-06,
3134
+ "loss": 0.5828,
3135
+ "step": 521
3136
+ },
3137
+ {
3138
+ "epoch": 0.78,
3139
+ "learning_rate": 4.33511910143925e-06,
3140
+ "loss": 0.7009,
3141
+ "step": 522
3142
+ },
3143
+ {
3144
+ "epoch": 0.78,
3145
+ "learning_rate": 4.33236740622459e-06,
3146
+ "loss": 0.624,
3147
+ "step": 523
3148
+ },
3149
+ {
3150
+ "epoch": 0.79,
3151
+ "learning_rate": 4.329610905840023e-06,
3152
+ "loss": 0.6571,
3153
+ "step": 524
3154
+ },
3155
+ {
3156
+ "epoch": 0.79,
3157
+ "learning_rate": 4.326849607514149e-06,
3158
+ "loss": 0.6266,
3159
+ "step": 525
3160
+ },
3161
+ {
3162
+ "epoch": 0.79,
3163
+ "learning_rate": 4.324083518488151e-06,
3164
+ "loss": 0.7098,
3165
+ "step": 526
3166
+ },
3167
+ {
3168
+ "epoch": 0.79,
3169
+ "learning_rate": 4.321312646015775e-06,
3170
+ "loss": 0.6321,
3171
+ "step": 527
3172
+ },
3173
+ {
3174
+ "epoch": 0.79,
3175
+ "learning_rate": 4.318536997363312e-06,
3176
+ "loss": 0.6138,
3177
+ "step": 528
3178
+ },
3179
+ {
3180
+ "epoch": 0.79,
3181
+ "learning_rate": 4.315756579809575e-06,
3182
+ "loss": 0.6123,
3183
+ "step": 529
3184
+ },
3185
+ {
3186
+ "epoch": 0.79,
3187
+ "learning_rate": 4.312971400645887e-06,
3188
+ "loss": 0.6007,
3189
+ "step": 530
3190
+ },
3191
+ {
3192
+ "epoch": 0.8,
3193
+ "learning_rate": 4.3101814671760546e-06,
3194
+ "loss": 0.6429,
3195
+ "step": 531
3196
+ },
3197
+ {
3198
+ "epoch": 0.8,
3199
+ "learning_rate": 4.3073867867163525e-06,
3200
+ "loss": 0.6036,
3201
+ "step": 532
3202
+ },
3203
+ {
3204
+ "epoch": 0.8,
3205
+ "learning_rate": 4.304587366595506e-06,
3206
+ "loss": 0.6273,
3207
+ "step": 533
3208
+ },
3209
+ {
3210
+ "epoch": 0.8,
3211
+ "learning_rate": 4.301783214154667e-06,
3212
+ "loss": 0.6696,
3213
+ "step": 534
3214
+ },
3215
+ {
3216
+ "epoch": 0.8,
3217
+ "learning_rate": 4.298974336747397e-06,
3218
+ "loss": 0.6604,
3219
+ "step": 535
3220
+ },
3221
+ {
3222
+ "epoch": 0.8,
3223
+ "learning_rate": 4.296160741739652e-06,
3224
+ "loss": 0.6608,
3225
+ "step": 536
3226
+ },
3227
+ {
3228
+ "epoch": 0.8,
3229
+ "learning_rate": 4.2933424365097565e-06,
3230
+ "loss": 0.6118,
3231
+ "step": 537
3232
+ },
3233
+ {
3234
+ "epoch": 0.81,
3235
+ "learning_rate": 4.290519428448387e-06,
3236
+ "loss": 0.5697,
3237
+ "step": 538
3238
+ },
3239
+ {
3240
+ "epoch": 0.81,
3241
+ "learning_rate": 4.287691724958551e-06,
3242
+ "loss": 0.6265,
3243
+ "step": 539
3244
+ },
3245
+ {
3246
+ "epoch": 0.81,
3247
+ "learning_rate": 4.284859333455576e-06,
3248
+ "loss": 0.6065,
3249
+ "step": 540
3250
+ },
3251
+ {
3252
+ "epoch": 0.81,
3253
+ "learning_rate": 4.282022261367074e-06,
3254
+ "loss": 0.5639,
3255
+ "step": 541
3256
+ },
3257
+ {
3258
+ "epoch": 0.81,
3259
+ "learning_rate": 4.279180516132937e-06,
3260
+ "loss": 0.5614,
3261
+ "step": 542
3262
+ },
3263
+ {
3264
+ "epoch": 0.81,
3265
+ "learning_rate": 4.276334105205312e-06,
3266
+ "loss": 0.6428,
3267
+ "step": 543
3268
+ },
3269
+ {
3270
+ "epoch": 0.82,
3271
+ "learning_rate": 4.273483036048578e-06,
3272
+ "loss": 0.5957,
3273
+ "step": 544
3274
+ },
3275
+ {
3276
+ "epoch": 0.82,
3277
+ "learning_rate": 4.270627316139333e-06,
3278
+ "loss": 0.73,
3279
+ "step": 545
3280
+ },
3281
+ {
3282
+ "epoch": 0.82,
3283
+ "learning_rate": 4.267766952966369e-06,
3284
+ "loss": 0.6634,
3285
+ "step": 546
3286
+ },
3287
+ {
3288
+ "epoch": 0.82,
3289
+ "learning_rate": 4.264901954030655e-06,
3290
+ "loss": 0.7099,
3291
+ "step": 547
3292
+ },
3293
+ {
3294
+ "epoch": 0.82,
3295
+ "learning_rate": 4.262032326845317e-06,
3296
+ "loss": 0.6907,
3297
+ "step": 548
3298
+ },
3299
+ {
3300
+ "epoch": 0.82,
3301
+ "learning_rate": 4.259158078935616e-06,
3302
+ "loss": 0.603,
3303
+ "step": 549
3304
+ },
3305
+ {
3306
+ "epoch": 0.82,
3307
+ "learning_rate": 4.256279217838934e-06,
3308
+ "loss": 0.5936,
3309
+ "step": 550
3310
+ },
3311
+ {
3312
+ "epoch": 0.83,
3313
+ "learning_rate": 4.2533957511047485e-06,
3314
+ "loss": 0.6128,
3315
+ "step": 551
3316
+ },
3317
+ {
3318
+ "epoch": 0.83,
3319
+ "learning_rate": 4.250507686294614e-06,
3320
+ "loss": 0.7054,
3321
+ "step": 552
3322
+ },
3323
+ {
3324
+ "epoch": 0.83,
3325
+ "learning_rate": 4.247615030982144e-06,
3326
+ "loss": 0.6089,
3327
+ "step": 553
3328
+ },
3329
+ {
3330
+ "epoch": 0.83,
3331
+ "learning_rate": 4.244717792752991e-06,
3332
+ "loss": 0.5982,
3333
+ "step": 554
3334
+ },
3335
+ {
3336
+ "epoch": 0.83,
3337
+ "learning_rate": 4.241815979204822e-06,
3338
+ "loss": 0.6014,
3339
+ "step": 555
3340
+ },
3341
+ {
3342
+ "epoch": 0.83,
3343
+ "learning_rate": 4.238909597947307e-06,
3344
+ "loss": 0.6479,
3345
+ "step": 556
3346
+ },
3347
+ {
3348
+ "epoch": 0.83,
3349
+ "learning_rate": 4.235998656602091e-06,
3350
+ "loss": 0.6547,
3351
+ "step": 557
3352
+ },
3353
+ {
3354
+ "epoch": 0.84,
3355
+ "learning_rate": 4.233083162802779e-06,
3356
+ "loss": 0.6948,
3357
+ "step": 558
3358
+ },
3359
+ {
3360
+ "epoch": 0.84,
3361
+ "learning_rate": 4.230163124194913e-06,
3362
+ "loss": 0.6328,
3363
+ "step": 559
3364
+ },
3365
+ {
3366
+ "epoch": 0.84,
3367
+ "learning_rate": 4.227238548435954e-06,
3368
+ "loss": 0.5896,
3369
+ "step": 560
3370
+ },
3371
+ {
3372
+ "epoch": 0.84,
3373
+ "learning_rate": 4.224309443195261e-06,
3374
+ "loss": 0.6059,
3375
+ "step": 561
3376
+ },
3377
+ {
3378
+ "epoch": 0.84,
3379
+ "learning_rate": 4.2213758161540705e-06,
3380
+ "loss": 0.6595,
3381
+ "step": 562
3382
+ },
3383
+ {
3384
+ "epoch": 0.84,
3385
+ "learning_rate": 4.218437675005479e-06,
3386
+ "loss": 0.6203,
3387
+ "step": 563
3388
+ },
3389
+ {
3390
+ "epoch": 0.85,
3391
+ "learning_rate": 4.2154950274544175e-06,
3392
+ "loss": 0.6904,
3393
+ "step": 564
3394
+ },
3395
+ {
3396
+ "epoch": 0.85,
3397
+ "learning_rate": 4.212547881217637e-06,
3398
+ "loss": 0.591,
3399
+ "step": 565
3400
+ },
3401
+ {
3402
+ "epoch": 0.85,
3403
+ "learning_rate": 4.2095962440236846e-06,
3404
+ "loss": 0.6067,
3405
+ "step": 566
3406
+ },
3407
+ {
3408
+ "epoch": 0.85,
3409
+ "learning_rate": 4.206640123612885e-06,
3410
+ "loss": 0.5781,
3411
+ "step": 567
3412
+ },
3413
+ {
3414
+ "epoch": 0.85,
3415
+ "learning_rate": 4.2036795277373185e-06,
3416
+ "loss": 0.5979,
3417
+ "step": 568
3418
+ },
3419
+ {
3420
+ "epoch": 0.85,
3421
+ "learning_rate": 4.2007144641608035e-06,
3422
+ "loss": 0.5517,
3423
+ "step": 569
3424
+ },
3425
+ {
3426
+ "epoch": 0.85,
3427
+ "learning_rate": 4.197744940658874e-06,
3428
+ "loss": 0.6426,
3429
+ "step": 570
3430
+ },
3431
+ {
3432
+ "epoch": 0.86,
3433
+ "learning_rate": 4.194770965018758e-06,
3434
+ "loss": 0.6511,
3435
+ "step": 571
3436
+ },
3437
+ {
3438
+ "epoch": 0.86,
3439
+ "learning_rate": 4.1917925450393606e-06,
3440
+ "loss": 0.6538,
3441
+ "step": 572
3442
+ },
3443
+ {
3444
+ "epoch": 0.86,
3445
+ "learning_rate": 4.188809688531241e-06,
3446
+ "loss": 0.697,
3447
+ "step": 573
3448
+ },
3449
+ {
3450
+ "epoch": 0.86,
3451
+ "learning_rate": 4.185822403316593e-06,
3452
+ "loss": 0.6005,
3453
+ "step": 574
3454
+ },
3455
+ {
3456
+ "epoch": 0.86,
3457
+ "learning_rate": 4.182830697229223e-06,
3458
+ "loss": 0.6262,
3459
+ "step": 575
3460
+ },
3461
+ {
3462
+ "epoch": 0.86,
3463
+ "learning_rate": 4.179834578114531e-06,
3464
+ "loss": 0.6722,
3465
+ "step": 576
3466
+ },
3467
+ {
3468
+ "epoch": 0.86,
3469
+ "learning_rate": 4.176834053829492e-06,
3470
+ "loss": 0.5372,
3471
+ "step": 577
3472
+ },
3473
+ {
3474
+ "epoch": 0.87,
3475
+ "learning_rate": 4.173829132242629e-06,
3476
+ "loss": 0.6606,
3477
+ "step": 578
3478
+ },
3479
+ {
3480
+ "epoch": 0.87,
3481
+ "learning_rate": 4.170819821234001e-06,
3482
+ "loss": 0.5827,
3483
+ "step": 579
3484
+ },
3485
+ {
3486
+ "epoch": 0.87,
3487
+ "learning_rate": 4.167806128695173e-06,
3488
+ "loss": 0.568,
3489
+ "step": 580
3490
+ },
3491
+ {
3492
+ "epoch": 0.87,
3493
+ "learning_rate": 4.164788062529203e-06,
3494
+ "loss": 0.6232,
3495
+ "step": 581
3496
+ },
3497
+ {
3498
+ "epoch": 0.87,
3499
+ "learning_rate": 4.1617656306506185e-06,
3500
+ "loss": 0.6385,
3501
+ "step": 582
3502
+ },
3503
+ {
3504
+ "epoch": 0.87,
3505
+ "learning_rate": 4.158738840985393e-06,
3506
+ "loss": 0.6554,
3507
+ "step": 583
3508
+ },
3509
+ {
3510
+ "epoch": 0.88,
3511
+ "learning_rate": 4.155707701470932e-06,
3512
+ "loss": 0.6399,
3513
+ "step": 584
3514
+ },
3515
+ {
3516
+ "epoch": 0.88,
3517
+ "learning_rate": 4.1526722200560445e-06,
3518
+ "loss": 0.6664,
3519
+ "step": 585
3520
+ },
3521
+ {
3522
+ "epoch": 0.88,
3523
+ "learning_rate": 4.149632404700925e-06,
3524
+ "loss": 0.5615,
3525
+ "step": 586
3526
+ },
3527
+ {
3528
+ "epoch": 0.88,
3529
+ "learning_rate": 4.146588263377137e-06,
3530
+ "loss": 0.5989,
3531
+ "step": 587
3532
+ },
3533
+ {
3534
+ "epoch": 0.88,
3535
+ "learning_rate": 4.143539804067585e-06,
3536
+ "loss": 0.6342,
3537
+ "step": 588
3538
+ },
3539
+ {
3540
+ "epoch": 0.88,
3541
+ "learning_rate": 4.140487034766499e-06,
3542
+ "loss": 0.6588,
3543
+ "step": 589
3544
+ },
3545
+ {
3546
+ "epoch": 0.88,
3547
+ "learning_rate": 4.13742996347941e-06,
3548
+ "loss": 0.6167,
3549
+ "step": 590
3550
+ },
3551
+ {
3552
+ "epoch": 0.89,
3553
+ "learning_rate": 4.134368598223132e-06,
3554
+ "loss": 0.6365,
3555
+ "step": 591
3556
+ },
3557
+ {
3558
+ "epoch": 0.89,
3559
+ "learning_rate": 4.131302947025737e-06,
3560
+ "loss": 0.6306,
3561
+ "step": 592
3562
+ },
3563
+ {
3564
+ "epoch": 0.89,
3565
+ "learning_rate": 4.128233017926538e-06,
3566
+ "loss": 0.6245,
3567
+ "step": 593
3568
+ },
3569
+ {
3570
+ "epoch": 0.89,
3571
+ "learning_rate": 4.1251588189760685e-06,
3572
+ "loss": 0.7224,
3573
+ "step": 594
3574
+ },
3575
+ {
3576
+ "epoch": 0.89,
3577
+ "learning_rate": 4.1220803582360545e-06,
3578
+ "loss": 0.6377,
3579
+ "step": 595
3580
+ },
3581
+ {
3582
+ "epoch": 0.89,
3583
+ "learning_rate": 4.118997643779401e-06,
3584
+ "loss": 0.601,
3585
+ "step": 596
3586
+ },
3587
+ {
3588
+ "epoch": 0.89,
3589
+ "learning_rate": 4.115910683690167e-06,
3590
+ "loss": 0.6312,
3591
+ "step": 597
3592
+ },
3593
+ {
3594
+ "epoch": 0.9,
3595
+ "learning_rate": 4.1128194860635465e-06,
3596
+ "loss": 0.6931,
3597
+ "step": 598
3598
+ },
3599
+ {
3600
+ "epoch": 0.9,
3601
+ "learning_rate": 4.109724059005844e-06,
3602
+ "loss": 0.71,
3603
+ "step": 599
3604
+ },
3605
+ {
3606
+ "epoch": 0.9,
3607
+ "learning_rate": 4.1066244106344565e-06,
3608
+ "loss": 0.5844,
3609
+ "step": 600
3610
+ },
3611
+ {
3612
+ "epoch": 0.9,
3613
+ "learning_rate": 4.1035205490778505e-06,
3614
+ "loss": 0.6208,
3615
+ "step": 601
3616
+ },
3617
+ {
3618
+ "epoch": 0.9,
3619
+ "learning_rate": 4.10041248247554e-06,
3620
+ "loss": 0.5465,
3621
+ "step": 602
3622
+ },
3623
+ {
3624
+ "epoch": 0.9,
3625
+ "learning_rate": 4.09730021897807e-06,
3626
+ "loss": 0.6247,
3627
+ "step": 603
3628
+ },
3629
+ {
3630
+ "epoch": 0.91,
3631
+ "learning_rate": 4.094183766746985e-06,
3632
+ "loss": 0.7047,
3633
+ "step": 604
3634
+ },
3635
+ {
3636
+ "epoch": 0.91,
3637
+ "learning_rate": 4.091063133954821e-06,
3638
+ "loss": 0.6232,
3639
+ "step": 605
3640
+ },
3641
+ {
3642
+ "epoch": 0.91,
3643
+ "learning_rate": 4.087938328785071e-06,
3644
+ "loss": 0.7008,
3645
+ "step": 606
3646
+ },
3647
+ {
3648
+ "epoch": 0.91,
3649
+ "learning_rate": 4.084809359432175e-06,
3650
+ "loss": 0.6428,
3651
+ "step": 607
3652
+ },
3653
+ {
3654
+ "epoch": 0.91,
3655
+ "learning_rate": 4.081676234101488e-06,
3656
+ "loss": 0.614,
3657
+ "step": 608
3658
+ },
3659
+ {
3660
+ "epoch": 0.91,
3661
+ "learning_rate": 4.0785389610092684e-06,
3662
+ "loss": 0.6007,
3663
+ "step": 609
3664
+ },
3665
+ {
3666
+ "epoch": 0.91,
3667
+ "learning_rate": 4.075397548382646e-06,
3668
+ "loss": 0.5722,
3669
+ "step": 610
3670
+ },
3671
+ {
3672
+ "epoch": 0.92,
3673
+ "learning_rate": 4.072252004459612e-06,
3674
+ "loss": 0.6575,
3675
+ "step": 611
3676
+ },
3677
+ {
3678
+ "epoch": 0.92,
3679
+ "learning_rate": 4.069102337488986e-06,
3680
+ "loss": 0.6093,
3681
+ "step": 612
3682
+ },
3683
+ {
3684
+ "epoch": 0.92,
3685
+ "learning_rate": 4.065948555730405e-06,
3686
+ "loss": 0.6852,
3687
+ "step": 613
3688
+ },
3689
+ {
3690
+ "epoch": 0.92,
3691
+ "learning_rate": 4.062790667454293e-06,
3692
+ "loss": 0.6932,
3693
+ "step": 614
3694
+ },
3695
+ {
3696
+ "epoch": 0.92,
3697
+ "learning_rate": 4.059628680941843e-06,
3698
+ "loss": 0.5603,
3699
+ "step": 615
3700
+ },
3701
+ {
3702
+ "epoch": 0.92,
3703
+ "learning_rate": 4.056462604484998e-06,
3704
+ "loss": 0.6945,
3705
+ "step": 616
3706
+ },
3707
+ {
3708
+ "epoch": 0.92,
3709
+ "learning_rate": 4.053292446386422e-06,
3710
+ "loss": 0.5946,
3711
+ "step": 617
3712
+ },
3713
+ {
3714
+ "epoch": 0.93,
3715
+ "learning_rate": 4.0501182149594865e-06,
3716
+ "loss": 0.652,
3717
+ "step": 618
3718
+ },
3719
+ {
3720
+ "epoch": 0.93,
3721
+ "learning_rate": 4.046939918528243e-06,
3722
+ "loss": 0.584,
3723
+ "step": 619
3724
+ },
3725
+ {
3726
+ "epoch": 0.93,
3727
+ "learning_rate": 4.043757565427404e-06,
3728
+ "loss": 0.6483,
3729
+ "step": 620
3730
+ },
3731
+ {
3732
+ "epoch": 0.93,
3733
+ "learning_rate": 4.040571164002319e-06,
3734
+ "loss": 0.6778,
3735
+ "step": 621
3736
+ },
3737
+ {
3738
+ "epoch": 0.93,
3739
+ "learning_rate": 4.037380722608954e-06,
3740
+ "loss": 0.7376,
3741
+ "step": 622
3742
+ },
3743
+ {
3744
+ "epoch": 0.93,
3745
+ "learning_rate": 4.034186249613869e-06,
3746
+ "loss": 0.63,
3747
+ "step": 623
3748
+ },
3749
+ {
3750
+ "epoch": 0.94,
3751
+ "learning_rate": 4.030987753394199e-06,
3752
+ "loss": 0.5927,
3753
+ "step": 624
3754
+ },
3755
+ {
3756
+ "epoch": 0.94,
3757
+ "learning_rate": 4.027785242337626e-06,
3758
+ "loss": 0.6163,
3759
+ "step": 625
3760
+ },
3761
+ {
3762
+ "epoch": 0.94,
3763
+ "learning_rate": 4.0245787248423614e-06,
3764
+ "loss": 0.7246,
3765
+ "step": 626
3766
+ },
3767
+ {
3768
+ "epoch": 0.94,
3769
+ "learning_rate": 4.021368209317126e-06,
3770
+ "loss": 0.6698,
3771
+ "step": 627
3772
+ },
3773
+ {
3774
+ "epoch": 0.94,
3775
+ "learning_rate": 4.01815370418112e-06,
3776
+ "loss": 0.6764,
3777
+ "step": 628
3778
+ },
3779
+ {
3780
+ "epoch": 0.94,
3781
+ "learning_rate": 4.014935217864009e-06,
3782
+ "loss": 0.6704,
3783
+ "step": 629
3784
+ },
3785
+ {
3786
+ "epoch": 0.94,
3787
+ "learning_rate": 4.0117127588058985e-06,
3788
+ "loss": 0.5537,
3789
+ "step": 630
3790
+ },
3791
+ {
3792
+ "epoch": 0.95,
3793
+ "learning_rate": 4.008486335457312e-06,
3794
+ "loss": 0.6097,
3795
+ "step": 631
3796
+ },
3797
+ {
3798
+ "epoch": 0.95,
3799
+ "learning_rate": 4.005255956279168e-06,
3800
+ "loss": 0.5991,
3801
+ "step": 632
3802
+ },
3803
+ {
3804
+ "epoch": 0.95,
3805
+ "learning_rate": 4.002021629742759e-06,
3806
+ "loss": 0.5868,
3807
+ "step": 633
3808
+ },
3809
+ {
3810
+ "epoch": 0.95,
3811
+ "learning_rate": 3.99878336432973e-06,
3812
+ "loss": 0.6474,
3813
+ "step": 634
3814
+ },
3815
+ {
3816
+ "epoch": 0.95,
3817
+ "learning_rate": 3.995541168532055e-06,
3818
+ "loss": 0.5777,
3819
+ "step": 635
3820
+ },
3821
+ {
3822
+ "epoch": 0.95,
3823
+ "learning_rate": 3.992295050852013e-06,
3824
+ "loss": 0.6073,
3825
+ "step": 636
3826
+ },
3827
+ {
3828
+ "epoch": 0.95,
3829
+ "learning_rate": 3.989045019802171e-06,
3830
+ "loss": 0.6732,
3831
+ "step": 637
3832
+ },
3833
+ {
3834
+ "epoch": 0.96,
3835
+ "learning_rate": 3.9857910839053545e-06,
3836
+ "loss": 0.6782,
3837
+ "step": 638
3838
+ },
3839
+ {
3840
+ "epoch": 0.96,
3841
+ "learning_rate": 3.982533251694632e-06,
3842
+ "loss": 0.6001,
3843
+ "step": 639
3844
+ },
3845
+ {
3846
+ "epoch": 0.96,
3847
+ "learning_rate": 3.97927153171329e-06,
3848
+ "loss": 0.6456,
3849
+ "step": 640
3850
+ },
3851
+ {
3852
+ "epoch": 0.96,
3853
+ "learning_rate": 3.976005932514807e-06,
3854
+ "loss": 0.6279,
3855
+ "step": 641
3856
+ },
3857
+ {
3858
+ "epoch": 0.96,
3859
+ "learning_rate": 3.972736462662837e-06,
3860
+ "loss": 0.6467,
3861
+ "step": 642
3862
+ },
3863
+ {
3864
+ "epoch": 0.96,
3865
+ "learning_rate": 3.969463130731183e-06,
3866
+ "loss": 0.6515,
3867
+ "step": 643
3868
+ },
3869
+ {
3870
+ "epoch": 0.97,
3871
+ "learning_rate": 3.966185945303778e-06,
3872
+ "loss": 0.6443,
3873
+ "step": 644
3874
+ },
3875
+ {
3876
+ "epoch": 0.97,
3877
+ "learning_rate": 3.962904914974656e-06,
3878
+ "loss": 0.5741,
3879
+ "step": 645
3880
+ },
3881
+ {
3882
+ "epoch": 0.97,
3883
+ "learning_rate": 3.959620048347938e-06,
3884
+ "loss": 0.7084,
3885
+ "step": 646
3886
+ },
3887
+ {
3888
+ "epoch": 0.97,
3889
+ "learning_rate": 3.956331354037805e-06,
3890
+ "loss": 0.693,
3891
+ "step": 647
3892
+ },
3893
+ {
3894
+ "epoch": 0.97,
3895
+ "learning_rate": 3.953038840668474e-06,
3896
+ "loss": 0.597,
3897
+ "step": 648
3898
+ },
3899
+ {
3900
+ "epoch": 0.97,
3901
+ "learning_rate": 3.949742516874175e-06,
3902
+ "loss": 0.5629,
3903
+ "step": 649
3904
+ },
3905
+ {
3906
+ "epoch": 0.97,
3907
+ "learning_rate": 3.946442391299136e-06,
3908
+ "loss": 0.6512,
3909
+ "step": 650
3910
+ },
3911
+ {
3912
+ "epoch": 0.98,
3913
+ "learning_rate": 3.943138472597549e-06,
3914
+ "loss": 0.6829,
3915
+ "step": 651
3916
+ },
3917
+ {
3918
+ "epoch": 0.98,
3919
+ "learning_rate": 3.939830769433558e-06,
3920
+ "loss": 0.6253,
3921
+ "step": 652
3922
+ },
3923
+ {
3924
+ "epoch": 0.98,
3925
+ "learning_rate": 3.936519290481226e-06,
3926
+ "loss": 0.6549,
3927
+ "step": 653
3928
+ },
3929
+ {
3930
+ "epoch": 0.98,
3931
+ "learning_rate": 3.933204044424524e-06,
3932
+ "loss": 0.6451,
3933
+ "step": 654
3934
+ },
3935
+ {
3936
+ "epoch": 0.98,
3937
+ "learning_rate": 3.929885039957296e-06,
3938
+ "loss": 0.6289,
3939
+ "step": 655
3940
+ },
3941
+ {
3942
+ "epoch": 0.98,
3943
+ "learning_rate": 3.9265622857832455e-06,
3944
+ "loss": 0.588,
3945
+ "step": 656
3946
+ },
3947
+ {
3948
+ "epoch": 0.98,
3949
+ "learning_rate": 3.923235790615907e-06,
3950
+ "loss": 0.5371,
3951
+ "step": 657
3952
+ },
3953
+ {
3954
+ "epoch": 0.99,
3955
+ "learning_rate": 3.919905563178627e-06,
3956
+ "loss": 0.6327,
3957
+ "step": 658
3958
+ },
3959
+ {
3960
+ "epoch": 0.99,
3961
+ "learning_rate": 3.916571612204538e-06,
3962
+ "loss": 0.6298,
3963
+ "step": 659
3964
+ },
3965
+ {
3966
+ "epoch": 0.99,
3967
+ "learning_rate": 3.913233946436537e-06,
3968
+ "loss": 0.677,
3969
+ "step": 660
3970
+ },
3971
+ {
3972
+ "epoch": 0.99,
3973
+ "learning_rate": 3.909892574627267e-06,
3974
+ "loss": 0.6158,
3975
+ "step": 661
3976
+ },
3977
+ {
3978
+ "epoch": 0.99,
3979
+ "learning_rate": 3.906547505539082e-06,
3980
+ "loss": 0.6354,
3981
+ "step": 662
3982
+ },
3983
+ {
3984
+ "epoch": 0.99,
3985
+ "learning_rate": 3.903198747944037e-06,
3986
+ "loss": 0.6414,
3987
+ "step": 663
3988
+ },
3989
+ {
3990
+ "epoch": 1.0,
3991
+ "learning_rate": 3.899846310623859e-06,
3992
+ "loss": 0.6448,
3993
+ "step": 664
3994
+ },
3995
+ {
3996
+ "epoch": 1.0,
3997
+ "learning_rate": 3.896490202369924e-06,
3998
+ "loss": 0.6596,
3999
+ "step": 665
4000
+ },
4001
+ {
4002
+ "epoch": 1.0,
4003
+ "learning_rate": 3.893130431983234e-06,
4004
+ "loss": 0.5931,
4005
+ "step": 666
4006
+ },
4007
+ {
4008
+ "epoch": 1.0,
4009
+ "learning_rate": 3.889767008274396e-06,
4010
+ "loss": 0.6544,
4011
+ "step": 667
4012
+ }
4013
+ ],
4014
+ "logging_steps": 1.0,
4015
+ "max_steps": 2001,
4016
+ "num_train_epochs": 3,
4017
+ "save_steps": 10000.0,
4018
+ "total_flos": 9.500209984202342e+17,
4019
+ "trial_name": null,
4020
+ "trial_params": null
4021
+ }
checkpoint-667/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9990b0c49fc6deae3a2a406f23f161f0eefbeee820384d6cca7a1aca52d86279
3
+ size 6136
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "imone/Mistral_7B_with_EOT_token",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 32000,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 14336,
12
+ "max_position_embeddings": 8192,
13
+ "model_type": "mistral",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 32,
16
+ "num_key_value_heads": 8,
17
+ "rms_norm_eps": 1e-05,
18
+ "rope_theta": 10000.0,
19
+ "sliding_window": 4096,
20
+ "tie_word_embeddings": false,
21
+ "torch_dtype": "bfloat16",
22
+ "transformers_version": "4.34.1",
23
+ "use_cache": true,
24
+ "vocab_size": 32002
25
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 32000,
5
+ "max_length": 8192,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.5,
8
+ "transformers_version": "4.34.1"
9
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae1deb16910641ceb9e892a0fbb7c348175144f9449f9f089a19f2e7d950fe74
3
+ size 4943178720
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26bdffff8092d28662893b25206c2d01c7ce4c5eaa260ac3f5d65b51a8d35904
3
+ size 4999819336
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db72146723c6ce3675206fff15dda519b601e2ac1b0f2c6185481efbbdbcd18c
3
+ size 4540532728
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14483496960
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
296
+ "model.norm.weight": "model-00003-of-00003.safetensors"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|end_of_turn|>",
4
+ "<|pad_0|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<s>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "</s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "unk_token": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ }
27
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<|end_of_turn|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|pad_0|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ }
45
+ },
46
+ "additional_special_tokens": [
47
+ "<|end_of_turn|>",
48
+ "<|pad_0|>"
49
+ ],
50
+ "bos_token": "<s>",
51
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}",
52
+ "clean_up_tokenization_spaces": false,
53
+ "eos_token": "<|end_of_turn|>",
54
+ "legacy": true,
55
+ "model_max_length": 1000000000000000019884624838656,
56
+ "pad_token": null,
57
+ "sp_model_kwargs": {},
58
+ "spaces_between_special_tokens": false,
59
+ "tokenizer_class": "LlamaTokenizer",
60
+ "unk_token": "<unk>",
61
+ "use_default_system_prompt": true
62
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9990b0c49fc6deae3a2a406f23f161f0eefbeee820384d6cca7a1aca52d86279
3
+ size 6136