Hugging Face's logo

Wanfq
/
fusechat_v1_solar_teacher_woref_ckpt

Text Generation
Transformers
Safetensors
mistral
conversational
text-generation-inference
Model card Files Community
Wanfq commited on
Commit
3ff89e6
·
verified ·
1 Parent(s): 8d3437e

Upload folder using huggingface_hub

Browse files
Files changed (29) hide show
  1. added_tokens.json +4 -0
  2. checkpoint-1484/added_tokens.json +4 -0
  3. checkpoint-1484/config.json +25 -0
  4. checkpoint-1484/pytorch_model.bin +3 -0
  5. checkpoint-1484/special_tokens_map.json +28 -0
  6. checkpoint-1484/tokenizer.model +3 -0
  7. checkpoint-1484/tokenizer_config.json +63 -0
  8. checkpoint-1484/trainer_state.json +0 -0
  9. checkpoint-1484/training_args.bin +3 -0
  10. checkpoint-742/added_tokens.json +4 -0
  11. checkpoint-742/config.json +25 -0
  12. checkpoint-742/pytorch_model.bin +3 -0
  13. checkpoint-742/special_tokens_map.json +28 -0
  14. checkpoint-742/tokenizer.model +3 -0
  15. checkpoint-742/tokenizer_config.json +63 -0
  16. checkpoint-742/trainer_state.json +4471 -0
  17. checkpoint-742/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-1484/added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|end_of_turn|>": 32000,
3
+ "<|pad_0|>": 32001
4
+ }
checkpoint-1484/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-1484/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8b40ee3c57bb214d0029fb8f3eb932279dbe3d259e53c14592c9d9c6df094a3
3
+ size 14483644690
checkpoint-1484/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-1484/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
checkpoint-1484/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-1484/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1484/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df645e38e090e9d2cbe1630ed71ba09aabda63d992b28e342963cada2d5af430
3
+ size 6136
checkpoint-742/added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|end_of_turn|>": 32000,
3
+ "<|pad_0|>": 32001
4
+ }
checkpoint-742/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-742/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c3bf877aa46489d9ab272da7e4f5b408276ce68f4b15396b18650da7c18b797
3
+ size 14483644690
checkpoint-742/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-742/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
checkpoint-742/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-742/trainer_state.json ADDED
@@ -0,0 +1,4471 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 742,
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": 7.462686567164179e-08,
14
+ "loss": 0.6423,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "learning_rate": 1.4925373134328358e-07,
20
+ "loss": 0.6177,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.0,
25
+ "learning_rate": 2.2388059701492537e-07,
26
+ "loss": 0.5907,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.01,
31
+ "learning_rate": 2.9850746268656716e-07,
32
+ "loss": 0.6307,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.01,
37
+ "learning_rate": 3.7313432835820895e-07,
38
+ "loss": 0.721,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.01,
43
+ "learning_rate": 4.4776119402985074e-07,
44
+ "loss": 0.6646,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.01,
49
+ "learning_rate": 5.223880597014925e-07,
50
+ "loss": 0.66,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.01,
55
+ "learning_rate": 5.970149253731343e-07,
56
+ "loss": 0.6376,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.01,
61
+ "learning_rate": 6.716417910447762e-07,
62
+ "loss": 0.6132,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.01,
67
+ "learning_rate": 7.462686567164179e-07,
68
+ "loss": 0.633,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.01,
73
+ "learning_rate": 8.208955223880598e-07,
74
+ "loss": 0.6168,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.02,
79
+ "learning_rate": 8.955223880597015e-07,
80
+ "loss": 0.5818,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.02,
85
+ "learning_rate": 9.701492537313434e-07,
86
+ "loss": 0.724,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.02,
91
+ "learning_rate": 1.044776119402985e-06,
92
+ "loss": 0.5968,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.02,
97
+ "learning_rate": 1.119402985074627e-06,
98
+ "loss": 0.5895,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.02,
103
+ "learning_rate": 1.1940298507462686e-06,
104
+ "loss": 0.5987,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.02,
109
+ "learning_rate": 1.2686567164179105e-06,
110
+ "loss": 0.6585,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.02,
115
+ "learning_rate": 1.3432835820895524e-06,
116
+ "loss": 0.5707,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.03,
121
+ "learning_rate": 1.417910447761194e-06,
122
+ "loss": 0.5809,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.03,
127
+ "learning_rate": 1.4925373134328358e-06,
128
+ "loss": 0.6062,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.03,
133
+ "learning_rate": 1.5671641791044779e-06,
134
+ "loss": 0.6142,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.03,
139
+ "learning_rate": 1.6417910447761196e-06,
140
+ "loss": 0.581,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.03,
145
+ "learning_rate": 1.7164179104477613e-06,
146
+ "loss": 0.6735,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.03,
151
+ "learning_rate": 1.791044776119403e-06,
152
+ "loss": 0.6011,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.03,
157
+ "learning_rate": 1.865671641791045e-06,
158
+ "loss": 0.5916,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.04,
163
+ "learning_rate": 1.9402985074626867e-06,
164
+ "loss": 0.6114,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.04,
169
+ "learning_rate": 2.0149253731343284e-06,
170
+ "loss": 0.5439,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.04,
175
+ "learning_rate": 2.08955223880597e-06,
176
+ "loss": 0.6002,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.04,
181
+ "learning_rate": 2.1641791044776118e-06,
182
+ "loss": 0.6543,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.04,
187
+ "learning_rate": 2.238805970149254e-06,
188
+ "loss": 0.668,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.04,
193
+ "learning_rate": 2.3134328358208956e-06,
194
+ "loss": 0.5723,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.04,
199
+ "learning_rate": 2.3880597014925373e-06,
200
+ "loss": 0.6427,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.04,
205
+ "learning_rate": 2.4626865671641794e-06,
206
+ "loss": 0.6142,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.05,
211
+ "learning_rate": 2.537313432835821e-06,
212
+ "loss": 0.5646,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.05,
217
+ "learning_rate": 2.6119402985074627e-06,
218
+ "loss": 0.5973,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.05,
223
+ "learning_rate": 2.686567164179105e-06,
224
+ "loss": 0.5616,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.05,
229
+ "learning_rate": 2.7611940298507465e-06,
230
+ "loss": 0.5881,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.05,
235
+ "learning_rate": 2.835820895522388e-06,
236
+ "loss": 0.576,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.05,
241
+ "learning_rate": 2.9104477611940303e-06,
242
+ "loss": 0.679,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.05,
247
+ "learning_rate": 2.9850746268656716e-06,
248
+ "loss": 0.5761,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.06,
253
+ "learning_rate": 3.0597014925373137e-06,
254
+ "loss": 0.6966,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.06,
259
+ "learning_rate": 3.1343283582089558e-06,
260
+ "loss": 0.58,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.06,
265
+ "learning_rate": 3.208955223880597e-06,
266
+ "loss": 0.5924,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.06,
271
+ "learning_rate": 3.283582089552239e-06,
272
+ "loss": 0.5976,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.06,
277
+ "learning_rate": 3.3582089552238813e-06,
278
+ "loss": 0.6475,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.06,
283
+ "learning_rate": 3.4328358208955225e-06,
284
+ "loss": 0.56,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.06,
289
+ "learning_rate": 3.5074626865671646e-06,
290
+ "loss": 0.6735,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.06,
295
+ "learning_rate": 3.582089552238806e-06,
296
+ "loss": 0.5665,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.07,
301
+ "learning_rate": 3.656716417910448e-06,
302
+ "loss": 0.6151,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.07,
307
+ "learning_rate": 3.73134328358209e-06,
308
+ "loss": 0.5687,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.07,
313
+ "learning_rate": 3.8059701492537314e-06,
314
+ "loss": 0.5896,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.07,
319
+ "learning_rate": 3.8805970149253735e-06,
320
+ "loss": 0.5482,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.07,
325
+ "learning_rate": 3.955223880597015e-06,
326
+ "loss": 0.5854,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.07,
331
+ "learning_rate": 4.029850746268657e-06,
332
+ "loss": 0.543,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.07,
337
+ "learning_rate": 4.104477611940299e-06,
338
+ "loss": 0.5193,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.08,
343
+ "learning_rate": 4.17910447761194e-06,
344
+ "loss": 0.5576,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.08,
349
+ "learning_rate": 4.253731343283583e-06,
350
+ "loss": 0.6328,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.08,
355
+ "learning_rate": 4.3283582089552236e-06,
356
+ "loss": 0.543,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.08,
361
+ "learning_rate": 4.402985074626866e-06,
362
+ "loss": 0.5874,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.08,
367
+ "learning_rate": 4.477611940298508e-06,
368
+ "loss": 0.6383,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.08,
373
+ "learning_rate": 4.5522388059701495e-06,
374
+ "loss": 0.5593,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.08,
379
+ "learning_rate": 4.626865671641791e-06,
380
+ "loss": 0.6524,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.08,
385
+ "learning_rate": 4.701492537313434e-06,
386
+ "loss": 0.614,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.09,
391
+ "learning_rate": 4.7761194029850745e-06,
392
+ "loss": 0.5952,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.09,
397
+ "learning_rate": 4.850746268656717e-06,
398
+ "loss": 0.5631,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.09,
403
+ "learning_rate": 4.925373134328359e-06,
404
+ "loss": 0.6144,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.09,
409
+ "learning_rate": 5e-06,
410
+ "loss": 0.634,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.09,
415
+ "learning_rate": 4.999997353301952e-06,
416
+ "loss": 0.5947,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.09,
421
+ "learning_rate": 4.999989413213412e-06,
422
+ "loss": 0.6104,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.09,
427
+ "learning_rate": 4.999976179751192e-06,
428
+ "loss": 0.5968,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.1,
433
+ "learning_rate": 4.999957652943311e-06,
434
+ "loss": 0.6113,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.1,
439
+ "learning_rate": 4.999933832828997e-06,
440
+ "loss": 0.6135,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.1,
445
+ "learning_rate": 4.999904719458687e-06,
446
+ "loss": 0.6171,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.1,
451
+ "learning_rate": 4.999870312894024e-06,
452
+ "loss": 0.5515,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.1,
457
+ "learning_rate": 4.9998306132078584e-06,
458
+ "loss": 0.6273,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.1,
463
+ "learning_rate": 4.999785620484249e-06,
464
+ "loss": 0.6061,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.1,
469
+ "learning_rate": 4.999735334818462e-06,
470
+ "loss": 0.5914,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.11,
475
+ "learning_rate": 4.9996797563169695e-06,
476
+ "loss": 0.606,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.11,
481
+ "learning_rate": 4.999618885097451e-06,
482
+ "loss": 0.5641,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.11,
487
+ "learning_rate": 4.999552721288794e-06,
488
+ "loss": 0.5109,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.11,
493
+ "learning_rate": 4.99948126503109e-06,
494
+ "loss": 0.5312,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.11,
499
+ "learning_rate": 4.999404516475637e-06,
500
+ "loss": 0.6127,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.11,
505
+ "learning_rate": 4.99932247578494e-06,
506
+ "loss": 0.5973,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.11,
511
+ "learning_rate": 4.999235143132708e-06,
512
+ "loss": 0.6037,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.11,
517
+ "learning_rate": 4.999142518703857e-06,
518
+ "loss": 0.576,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.12,
523
+ "learning_rate": 4.999044602694504e-06,
524
+ "loss": 0.5563,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.12,
529
+ "learning_rate": 4.998941395311973e-06,
530
+ "loss": 0.6013,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.12,
535
+ "learning_rate": 4.998832896774791e-06,
536
+ "loss": 0.5999,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.12,
541
+ "learning_rate": 4.99871910731269e-06,
542
+ "loss": 0.5908,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.12,
547
+ "learning_rate": 4.998600027166601e-06,
548
+ "loss": 0.6267,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.12,
553
+ "learning_rate": 4.99847565658866e-06,
554
+ "loss": 0.5976,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.12,
559
+ "learning_rate": 4.998345995842204e-06,
560
+ "loss": 0.5706,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.13,
565
+ "learning_rate": 4.998211045201771e-06,
566
+ "loss": 0.5906,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.13,
571
+ "learning_rate": 4.998070804953101e-06,
572
+ "loss": 0.5676,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.13,
577
+ "learning_rate": 4.997925275393132e-06,
578
+ "loss": 0.5702,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.13,
583
+ "learning_rate": 4.997774456830002e-06,
584
+ "loss": 0.5529,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.13,
589
+ "learning_rate": 4.997618349583049e-06,
590
+ "loss": 0.5694,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.13,
595
+ "learning_rate": 4.9974569539828064e-06,
596
+ "loss": 0.5443,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.13,
601
+ "learning_rate": 4.997290270371008e-06,
602
+ "loss": 0.5213,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.13,
607
+ "learning_rate": 4.997118299100582e-06,
608
+ "loss": 0.5883,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.14,
613
+ "learning_rate": 4.996941040535654e-06,
614
+ "loss": 0.5835,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.14,
619
+ "learning_rate": 4.996758495051542e-06,
620
+ "loss": 0.5756,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.14,
625
+ "learning_rate": 4.996570663034764e-06,
626
+ "loss": 0.5719,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.14,
631
+ "learning_rate": 4.9963775448830225e-06,
632
+ "loss": 0.6012,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.14,
637
+ "learning_rate": 4.996179141005222e-06,
638
+ "loss": 0.6051,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.14,
643
+ "learning_rate": 4.9959754518214535e-06,
644
+ "loss": 0.5905,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.14,
649
+ "learning_rate": 4.995766477762999e-06,
650
+ "loss": 0.5492,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.15,
655
+ "learning_rate": 4.995552219272333e-06,
656
+ "loss": 0.6055,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.15,
661
+ "learning_rate": 4.995332676803117e-06,
662
+ "loss": 0.5788,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.15,
667
+ "learning_rate": 4.995107850820199e-06,
668
+ "loss": 0.5784,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.15,
673
+ "learning_rate": 4.994877741799619e-06,
674
+ "loss": 0.6152,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.15,
679
+ "learning_rate": 4.994642350228601e-06,
680
+ "loss": 0.6223,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.15,
685
+ "learning_rate": 4.99440167660555e-06,
686
+ "loss": 0.478,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.15,
691
+ "learning_rate": 4.99415572144006e-06,
692
+ "loss": 0.5487,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.15,
697
+ "learning_rate": 4.993904485252907e-06,
698
+ "loss": 0.6073,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.16,
703
+ "learning_rate": 4.993647968576047e-06,
704
+ "loss": 0.6092,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.16,
709
+ "learning_rate": 4.9933861719526176e-06,
710
+ "loss": 0.5703,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.16,
715
+ "learning_rate": 4.993119095936937e-06,
716
+ "loss": 0.6088,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.16,
721
+ "learning_rate": 4.9928467410945e-06,
722
+ "loss": 0.5716,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.16,
727
+ "learning_rate": 4.992569108001981e-06,
728
+ "loss": 0.5494,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.16,
733
+ "learning_rate": 4.9922861972472255e-06,
734
+ "loss": 0.5917,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.16,
739
+ "learning_rate": 4.991998009429261e-06,
740
+ "loss": 0.6129,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.17,
745
+ "learning_rate": 4.9917045451582815e-06,
746
+ "loss": 0.593,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.17,
751
+ "learning_rate": 4.991405805055658e-06,
752
+ "loss": 0.5571,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.17,
757
+ "learning_rate": 4.991101789753928e-06,
758
+ "loss": 0.5656,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.17,
763
+ "learning_rate": 4.9907924998968035e-06,
764
+ "loss": 0.5481,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.17,
769
+ "learning_rate": 4.990477936139159e-06,
770
+ "loss": 0.6061,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.17,
775
+ "learning_rate": 4.990158099147043e-06,
776
+ "loss": 0.5552,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.17,
781
+ "learning_rate": 4.989832989597661e-06,
782
+ "loss": 0.5966,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.18,
787
+ "learning_rate": 4.9895026081793884e-06,
788
+ "loss": 0.5445,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.18,
793
+ "learning_rate": 4.98916695559176e-06,
794
+ "loss": 0.5757,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.18,
799
+ "learning_rate": 4.988826032545474e-06,
800
+ "loss": 0.5566,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.18,
805
+ "learning_rate": 4.9884798397623856e-06,
806
+ "loss": 0.5119,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.18,
811
+ "learning_rate": 4.98812837797551e-06,
812
+ "loss": 0.5603,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.18,
817
+ "learning_rate": 4.987771647929017e-06,
818
+ "loss": 0.5771,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.18,
823
+ "learning_rate": 4.987409650378232e-06,
824
+ "loss": 0.6126,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.18,
829
+ "learning_rate": 4.987042386089633e-06,
830
+ "loss": 0.5963,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.19,
835
+ "learning_rate": 4.986669855840852e-06,
836
+ "loss": 0.5413,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.19,
841
+ "learning_rate": 4.9862920604206675e-06,
842
+ "loss": 0.5406,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.19,
847
+ "learning_rate": 4.985909000629009e-06,
848
+ "loss": 0.6792,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.19,
853
+ "learning_rate": 4.98552067727695e-06,
854
+ "loss": 0.5665,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.19,
859
+ "learning_rate": 4.98512709118671e-06,
860
+ "loss": 0.5529,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.19,
865
+ "learning_rate": 4.984728243191653e-06,
866
+ "loss": 0.5199,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.19,
871
+ "learning_rate": 4.984324134136284e-06,
872
+ "loss": 0.5718,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.2,
877
+ "learning_rate": 4.983914764876245e-06,
878
+ "loss": 0.5387,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.2,
883
+ "learning_rate": 4.9835001362783175e-06,
884
+ "loss": 0.6141,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.2,
889
+ "learning_rate": 4.98308024922042e-06,
890
+ "loss": 0.5685,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.2,
895
+ "learning_rate": 4.982655104591604e-06,
896
+ "loss": 0.5851,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.2,
901
+ "learning_rate": 4.982224703292051e-06,
902
+ "loss": 0.5623,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.2,
907
+ "learning_rate": 4.981789046233076e-06,
908
+ "loss": 0.5067,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 0.2,
913
+ "learning_rate": 4.981348134337123e-06,
914
+ "loss": 0.6005,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 0.2,
919
+ "learning_rate": 4.980901968537758e-06,
920
+ "loss": 0.6434,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 0.21,
925
+ "learning_rate": 4.980450549779675e-06,
926
+ "loss": 0.659,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 0.21,
931
+ "learning_rate": 4.979993879018688e-06,
932
+ "loss": 0.5762,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 0.21,
937
+ "learning_rate": 4.9795319572217356e-06,
938
+ "loss": 0.5527,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 0.21,
943
+ "learning_rate": 4.9790647853668686e-06,
944
+ "loss": 0.5685,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 0.21,
949
+ "learning_rate": 4.978592364443259e-06,
950
+ "loss": 0.6348,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 0.21,
955
+ "learning_rate": 4.978114695451192e-06,
956
+ "loss": 0.6047,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 0.21,
961
+ "learning_rate": 4.977631779402061e-06,
962
+ "loss": 0.6143,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 0.22,
967
+ "learning_rate": 4.977143617318376e-06,
968
+ "loss": 0.6329,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 0.22,
973
+ "learning_rate": 4.976650210233749e-06,
974
+ "loss": 0.581,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 0.22,
979
+ "learning_rate": 4.9761515591929e-06,
980
+ "loss": 0.5456,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 0.22,
985
+ "learning_rate": 4.975647665251652e-06,
986
+ "loss": 0.518,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 0.22,
991
+ "learning_rate": 4.975138529476929e-06,
992
+ "loss": 0.5648,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 0.22,
997
+ "learning_rate": 4.974624152946755e-06,
998
+ "loss": 0.5921,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 0.22,
1003
+ "learning_rate": 4.9741045367502475e-06,
1004
+ "loss": 0.5568,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 0.23,
1009
+ "learning_rate": 4.973579681987622e-06,
1010
+ "loss": 0.4872,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 0.23,
1015
+ "learning_rate": 4.973049589770183e-06,
1016
+ "loss": 0.6711,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 0.23,
1021
+ "learning_rate": 4.972514261220327e-06,
1022
+ "loss": 0.6142,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 0.23,
1027
+ "learning_rate": 4.971973697471535e-06,
1028
+ "loss": 0.6344,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 0.23,
1033
+ "learning_rate": 4.971427899668376e-06,
1034
+ "loss": 0.6002,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 0.23,
1039
+ "learning_rate": 4.970876868966497e-06,
1040
+ "loss": 0.5672,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 0.23,
1045
+ "learning_rate": 4.97032060653263e-06,
1046
+ "loss": 0.6347,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 0.23,
1051
+ "learning_rate": 4.969759113544581e-06,
1052
+ "loss": 0.5874,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 0.24,
1057
+ "learning_rate": 4.969192391191231e-06,
1058
+ "loss": 0.501,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 0.24,
1063
+ "learning_rate": 4.9686204406725355e-06,
1064
+ "loss": 0.5753,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 0.24,
1069
+ "learning_rate": 4.968043263199518e-06,
1070
+ "loss": 0.5443,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 0.24,
1075
+ "learning_rate": 4.967460859994272e-06,
1076
+ "loss": 0.5693,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 0.24,
1081
+ "learning_rate": 4.966873232289951e-06,
1082
+ "loss": 0.5469,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 0.24,
1087
+ "learning_rate": 4.966280381330775e-06,
1088
+ "loss": 0.5876,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 0.24,
1093
+ "learning_rate": 4.965682308372022e-06,
1094
+ "loss": 0.5709,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 0.25,
1099
+ "learning_rate": 4.965079014680027e-06,
1100
+ "loss": 0.5215,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 0.25,
1105
+ "learning_rate": 4.964470501532179e-06,
1106
+ "loss": 0.5841,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 0.25,
1111
+ "learning_rate": 4.963856770216917e-06,
1112
+ "loss": 0.6485,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 0.25,
1117
+ "learning_rate": 4.963237822033733e-06,
1118
+ "loss": 0.6201,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 0.25,
1123
+ "learning_rate": 4.962613658293158e-06,
1124
+ "loss": 0.5295,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 0.25,
1129
+ "learning_rate": 4.961984280316775e-06,
1130
+ "loss": 0.6078,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 0.25,
1135
+ "learning_rate": 4.961349689437199e-06,
1136
+ "loss": 0.6665,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 0.25,
1141
+ "learning_rate": 4.96070988699809e-06,
1142
+ "loss": 0.5529,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 0.26,
1147
+ "learning_rate": 4.960064874354136e-06,
1148
+ "loss": 0.5783,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 0.26,
1153
+ "learning_rate": 4.9594146528710596e-06,
1154
+ "loss": 0.5181,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 0.26,
1159
+ "learning_rate": 4.9587592239256154e-06,
1160
+ "loss": 0.5941,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 0.26,
1165
+ "learning_rate": 4.95809858890558e-06,
1166
+ "loss": 0.5932,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 0.26,
1171
+ "learning_rate": 4.957432749209755e-06,
1172
+ "loss": 0.601,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 0.26,
1177
+ "learning_rate": 4.956761706247961e-06,
1178
+ "loss": 0.6308,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 0.26,
1183
+ "learning_rate": 4.956085461441037e-06,
1184
+ "loss": 0.5827,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 0.27,
1189
+ "learning_rate": 4.955404016220835e-06,
1190
+ "loss": 0.5602,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 0.27,
1195
+ "learning_rate": 4.95471737203022e-06,
1196
+ "loss": 0.5478,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 0.27,
1201
+ "learning_rate": 4.954025530323063e-06,
1202
+ "loss": 0.5433,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 0.27,
1207
+ "learning_rate": 4.953328492564241e-06,
1208
+ "loss": 0.5952,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 0.27,
1213
+ "learning_rate": 4.952626260229633e-06,
1214
+ "loss": 0.6151,
1215
+ "step": 201
1216
+ },
1217
+ {
1218
+ "epoch": 0.27,
1219
+ "learning_rate": 4.951918834806116e-06,
1220
+ "loss": 0.5552,
1221
+ "step": 202
1222
+ },
1223
+ {
1224
+ "epoch": 0.27,
1225
+ "learning_rate": 4.9512062177915634e-06,
1226
+ "loss": 0.5577,
1227
+ "step": 203
1228
+ },
1229
+ {
1230
+ "epoch": 0.27,
1231
+ "learning_rate": 4.950488410694842e-06,
1232
+ "loss": 0.6224,
1233
+ "step": 204
1234
+ },
1235
+ {
1236
+ "epoch": 0.28,
1237
+ "learning_rate": 4.949765415035805e-06,
1238
+ "loss": 0.5383,
1239
+ "step": 205
1240
+ },
1241
+ {
1242
+ "epoch": 0.28,
1243
+ "learning_rate": 4.949037232345294e-06,
1244
+ "loss": 0.6319,
1245
+ "step": 206
1246
+ },
1247
+ {
1248
+ "epoch": 0.28,
1249
+ "learning_rate": 4.948303864165133e-06,
1250
+ "loss": 0.6086,
1251
+ "step": 207
1252
+ },
1253
+ {
1254
+ "epoch": 0.28,
1255
+ "learning_rate": 4.947565312048125e-06,
1256
+ "loss": 0.5733,
1257
+ "step": 208
1258
+ },
1259
+ {
1260
+ "epoch": 0.28,
1261
+ "learning_rate": 4.94682157755805e-06,
1262
+ "loss": 0.5885,
1263
+ "step": 209
1264
+ },
1265
+ {
1266
+ "epoch": 0.28,
1267
+ "learning_rate": 4.946072662269661e-06,
1268
+ "loss": 0.5965,
1269
+ "step": 210
1270
+ },
1271
+ {
1272
+ "epoch": 0.28,
1273
+ "learning_rate": 4.945318567768677e-06,
1274
+ "loss": 0.5688,
1275
+ "step": 211
1276
+ },
1277
+ {
1278
+ "epoch": 0.29,
1279
+ "learning_rate": 4.9445592956517905e-06,
1280
+ "loss": 0.6098,
1281
+ "step": 212
1282
+ },
1283
+ {
1284
+ "epoch": 0.29,
1285
+ "learning_rate": 4.943794847526651e-06,
1286
+ "loss": 0.6059,
1287
+ "step": 213
1288
+ },
1289
+ {
1290
+ "epoch": 0.29,
1291
+ "learning_rate": 4.943025225011869e-06,
1292
+ "loss": 0.5723,
1293
+ "step": 214
1294
+ },
1295
+ {
1296
+ "epoch": 0.29,
1297
+ "learning_rate": 4.942250429737011e-06,
1298
+ "loss": 0.6188,
1299
+ "step": 215
1300
+ },
1301
+ {
1302
+ "epoch": 0.29,
1303
+ "learning_rate": 4.941470463342596e-06,
1304
+ "loss": 0.5953,
1305
+ "step": 216
1306
+ },
1307
+ {
1308
+ "epoch": 0.29,
1309
+ "learning_rate": 4.940685327480094e-06,
1310
+ "loss": 0.5418,
1311
+ "step": 217
1312
+ },
1313
+ {
1314
+ "epoch": 0.29,
1315
+ "learning_rate": 4.939895023811918e-06,
1316
+ "loss": 0.5664,
1317
+ "step": 218
1318
+ },
1319
+ {
1320
+ "epoch": 0.3,
1321
+ "learning_rate": 4.939099554011424e-06,
1322
+ "loss": 0.6042,
1323
+ "step": 219
1324
+ },
1325
+ {
1326
+ "epoch": 0.3,
1327
+ "learning_rate": 4.938298919762907e-06,
1328
+ "loss": 0.5681,
1329
+ "step": 220
1330
+ },
1331
+ {
1332
+ "epoch": 0.3,
1333
+ "learning_rate": 4.937493122761596e-06,
1334
+ "loss": 0.5376,
1335
+ "step": 221
1336
+ },
1337
+ {
1338
+ "epoch": 0.3,
1339
+ "learning_rate": 4.936682164713654e-06,
1340
+ "loss": 0.5843,
1341
+ "step": 222
1342
+ },
1343
+ {
1344
+ "epoch": 0.3,
1345
+ "learning_rate": 4.935866047336168e-06,
1346
+ "loss": 0.6206,
1347
+ "step": 223
1348
+ },
1349
+ {
1350
+ "epoch": 0.3,
1351
+ "learning_rate": 4.935044772357152e-06,
1352
+ "loss": 0.5741,
1353
+ "step": 224
1354
+ },
1355
+ {
1356
+ "epoch": 0.3,
1357
+ "learning_rate": 4.934218341515538e-06,
1358
+ "loss": 0.6445,
1359
+ "step": 225
1360
+ },
1361
+ {
1362
+ "epoch": 0.3,
1363
+ "learning_rate": 4.933386756561178e-06,
1364
+ "loss": 0.5918,
1365
+ "step": 226
1366
+ },
1367
+ {
1368
+ "epoch": 0.31,
1369
+ "learning_rate": 4.932550019254835e-06,
1370
+ "loss": 0.5168,
1371
+ "step": 227
1372
+ },
1373
+ {
1374
+ "epoch": 0.31,
1375
+ "learning_rate": 4.931708131368181e-06,
1376
+ "loss": 0.5812,
1377
+ "step": 228
1378
+ },
1379
+ {
1380
+ "epoch": 0.31,
1381
+ "learning_rate": 4.9308610946837955e-06,
1382
+ "loss": 0.6094,
1383
+ "step": 229
1384
+ },
1385
+ {
1386
+ "epoch": 0.31,
1387
+ "learning_rate": 4.930008910995158e-06,
1388
+ "loss": 0.5939,
1389
+ "step": 230
1390
+ },
1391
+ {
1392
+ "epoch": 0.31,
1393
+ "learning_rate": 4.9291515821066475e-06,
1394
+ "loss": 0.5721,
1395
+ "step": 231
1396
+ },
1397
+ {
1398
+ "epoch": 0.31,
1399
+ "learning_rate": 4.928289109833536e-06,
1400
+ "loss": 0.5902,
1401
+ "step": 232
1402
+ },
1403
+ {
1404
+ "epoch": 0.31,
1405
+ "learning_rate": 4.927421496001988e-06,
1406
+ "loss": 0.545,
1407
+ "step": 233
1408
+ },
1409
+ {
1410
+ "epoch": 0.32,
1411
+ "learning_rate": 4.92654874244905e-06,
1412
+ "loss": 0.5317,
1413
+ "step": 234
1414
+ },
1415
+ {
1416
+ "epoch": 0.32,
1417
+ "learning_rate": 4.925670851022656e-06,
1418
+ "loss": 0.5704,
1419
+ "step": 235
1420
+ },
1421
+ {
1422
+ "epoch": 0.32,
1423
+ "learning_rate": 4.924787823581616e-06,
1424
+ "loss": 0.5337,
1425
+ "step": 236
1426
+ },
1427
+ {
1428
+ "epoch": 0.32,
1429
+ "learning_rate": 4.923899661995617e-06,
1430
+ "loss": 0.6223,
1431
+ "step": 237
1432
+ },
1433
+ {
1434
+ "epoch": 0.32,
1435
+ "learning_rate": 4.923006368145215e-06,
1436
+ "loss": 0.6146,
1437
+ "step": 238
1438
+ },
1439
+ {
1440
+ "epoch": 0.32,
1441
+ "learning_rate": 4.9221079439218314e-06,
1442
+ "loss": 0.6047,
1443
+ "step": 239
1444
+ },
1445
+ {
1446
+ "epoch": 0.32,
1447
+ "learning_rate": 4.921204391227754e-06,
1448
+ "loss": 0.5593,
1449
+ "step": 240
1450
+ },
1451
+ {
1452
+ "epoch": 0.32,
1453
+ "learning_rate": 4.920295711976129e-06,
1454
+ "loss": 0.5095,
1455
+ "step": 241
1456
+ },
1457
+ {
1458
+ "epoch": 0.33,
1459
+ "learning_rate": 4.9193819080909534e-06,
1460
+ "loss": 0.582,
1461
+ "step": 242
1462
+ },
1463
+ {
1464
+ "epoch": 0.33,
1465
+ "learning_rate": 4.918462981507079e-06,
1466
+ "loss": 0.6257,
1467
+ "step": 243
1468
+ },
1469
+ {
1470
+ "epoch": 0.33,
1471
+ "learning_rate": 4.917538934170202e-06,
1472
+ "loss": 0.6386,
1473
+ "step": 244
1474
+ },
1475
+ {
1476
+ "epoch": 0.33,
1477
+ "learning_rate": 4.9166097680368615e-06,
1478
+ "loss": 0.6566,
1479
+ "step": 245
1480
+ },
1481
+ {
1482
+ "epoch": 0.33,
1483
+ "learning_rate": 4.915675485074438e-06,
1484
+ "loss": 0.4939,
1485
+ "step": 246
1486
+ },
1487
+ {
1488
+ "epoch": 0.33,
1489
+ "learning_rate": 4.91473608726114e-06,
1490
+ "loss": 0.5267,
1491
+ "step": 247
1492
+ },
1493
+ {
1494
+ "epoch": 0.33,
1495
+ "learning_rate": 4.913791576586012e-06,
1496
+ "loss": 0.5606,
1497
+ "step": 248
1498
+ },
1499
+ {
1500
+ "epoch": 0.34,
1501
+ "learning_rate": 4.91284195504892e-06,
1502
+ "loss": 0.6032,
1503
+ "step": 249
1504
+ },
1505
+ {
1506
+ "epoch": 0.34,
1507
+ "learning_rate": 4.911887224660553e-06,
1508
+ "loss": 0.6338,
1509
+ "step": 250
1510
+ },
1511
+ {
1512
+ "epoch": 0.34,
1513
+ "learning_rate": 4.91092738744242e-06,
1514
+ "loss": 0.5635,
1515
+ "step": 251
1516
+ },
1517
+ {
1518
+ "epoch": 0.34,
1519
+ "learning_rate": 4.9099624454268365e-06,
1520
+ "loss": 0.6003,
1521
+ "step": 252
1522
+ },
1523
+ {
1524
+ "epoch": 0.34,
1525
+ "learning_rate": 4.908992400656934e-06,
1526
+ "loss": 0.5308,
1527
+ "step": 253
1528
+ },
1529
+ {
1530
+ "epoch": 0.34,
1531
+ "learning_rate": 4.908017255186644e-06,
1532
+ "loss": 0.5695,
1533
+ "step": 254
1534
+ },
1535
+ {
1536
+ "epoch": 0.34,
1537
+ "learning_rate": 4.907037011080697e-06,
1538
+ "loss": 0.5377,
1539
+ "step": 255
1540
+ },
1541
+ {
1542
+ "epoch": 0.35,
1543
+ "learning_rate": 4.906051670414623e-06,
1544
+ "loss": 0.4869,
1545
+ "step": 256
1546
+ },
1547
+ {
1548
+ "epoch": 0.35,
1549
+ "learning_rate": 4.905061235274743e-06,
1550
+ "loss": 0.6222,
1551
+ "step": 257
1552
+ },
1553
+ {
1554
+ "epoch": 0.35,
1555
+ "learning_rate": 4.904065707758159e-06,
1556
+ "loss": 0.545,
1557
+ "step": 258
1558
+ },
1559
+ {
1560
+ "epoch": 0.35,
1561
+ "learning_rate": 4.9030650899727636e-06,
1562
+ "loss": 0.6023,
1563
+ "step": 259
1564
+ },
1565
+ {
1566
+ "epoch": 0.35,
1567
+ "learning_rate": 4.902059384037221e-06,
1568
+ "loss": 0.6098,
1569
+ "step": 260
1570
+ },
1571
+ {
1572
+ "epoch": 0.35,
1573
+ "learning_rate": 4.9010485920809715e-06,
1574
+ "loss": 0.6025,
1575
+ "step": 261
1576
+ },
1577
+ {
1578
+ "epoch": 0.35,
1579
+ "learning_rate": 4.900032716244225e-06,
1580
+ "loss": 0.5454,
1581
+ "step": 262
1582
+ },
1583
+ {
1584
+ "epoch": 0.35,
1585
+ "learning_rate": 4.899011758677954e-06,
1586
+ "loss": 0.5883,
1587
+ "step": 263
1588
+ },
1589
+ {
1590
+ "epoch": 0.36,
1591
+ "learning_rate": 4.897985721543891e-06,
1592
+ "loss": 0.5959,
1593
+ "step": 264
1594
+ },
1595
+ {
1596
+ "epoch": 0.36,
1597
+ "learning_rate": 4.896954607014526e-06,
1598
+ "loss": 0.5522,
1599
+ "step": 265
1600
+ },
1601
+ {
1602
+ "epoch": 0.36,
1603
+ "learning_rate": 4.8959184172730955e-06,
1604
+ "loss": 0.5334,
1605
+ "step": 266
1606
+ },
1607
+ {
1608
+ "epoch": 0.36,
1609
+ "learning_rate": 4.894877154513588e-06,
1610
+ "loss": 0.6167,
1611
+ "step": 267
1612
+ },
1613
+ {
1614
+ "epoch": 0.36,
1615
+ "learning_rate": 4.893830820940727e-06,
1616
+ "loss": 0.537,
1617
+ "step": 268
1618
+ },
1619
+ {
1620
+ "epoch": 0.36,
1621
+ "learning_rate": 4.892779418769977e-06,
1622
+ "loss": 0.6554,
1623
+ "step": 269
1624
+ },
1625
+ {
1626
+ "epoch": 0.36,
1627
+ "learning_rate": 4.891722950227534e-06,
1628
+ "loss": 0.5863,
1629
+ "step": 270
1630
+ },
1631
+ {
1632
+ "epoch": 0.37,
1633
+ "learning_rate": 4.8906614175503196e-06,
1634
+ "loss": 0.57,
1635
+ "step": 271
1636
+ },
1637
+ {
1638
+ "epoch": 0.37,
1639
+ "learning_rate": 4.889594822985978e-06,
1640
+ "loss": 0.5661,
1641
+ "step": 272
1642
+ },
1643
+ {
1644
+ "epoch": 0.37,
1645
+ "learning_rate": 4.8885231687928746e-06,
1646
+ "loss": 0.6108,
1647
+ "step": 273
1648
+ },
1649
+ {
1650
+ "epoch": 0.37,
1651
+ "learning_rate": 4.887446457240083e-06,
1652
+ "loss": 0.5673,
1653
+ "step": 274
1654
+ },
1655
+ {
1656
+ "epoch": 0.37,
1657
+ "learning_rate": 4.8863646906073895e-06,
1658
+ "loss": 0.5654,
1659
+ "step": 275
1660
+ },
1661
+ {
1662
+ "epoch": 0.37,
1663
+ "learning_rate": 4.885277871185281e-06,
1664
+ "loss": 0.5476,
1665
+ "step": 276
1666
+ },
1667
+ {
1668
+ "epoch": 0.37,
1669
+ "learning_rate": 4.884186001274944e-06,
1670
+ "loss": 0.5836,
1671
+ "step": 277
1672
+ },
1673
+ {
1674
+ "epoch": 0.37,
1675
+ "learning_rate": 4.8830890831882575e-06,
1676
+ "loss": 0.5896,
1677
+ "step": 278
1678
+ },
1679
+ {
1680
+ "epoch": 0.38,
1681
+ "learning_rate": 4.881987119247791e-06,
1682
+ "loss": 0.5937,
1683
+ "step": 279
1684
+ },
1685
+ {
1686
+ "epoch": 0.38,
1687
+ "learning_rate": 4.8808801117867976e-06,
1688
+ "loss": 0.5862,
1689
+ "step": 280
1690
+ },
1691
+ {
1692
+ "epoch": 0.38,
1693
+ "learning_rate": 4.879768063149208e-06,
1694
+ "loss": 0.574,
1695
+ "step": 281
1696
+ },
1697
+ {
1698
+ "epoch": 0.38,
1699
+ "learning_rate": 4.878650975689628e-06,
1700
+ "loss": 0.5378,
1701
+ "step": 282
1702
+ },
1703
+ {
1704
+ "epoch": 0.38,
1705
+ "learning_rate": 4.8775288517733335e-06,
1706
+ "loss": 0.5579,
1707
+ "step": 283
1708
+ },
1709
+ {
1710
+ "epoch": 0.38,
1711
+ "learning_rate": 4.876401693776261e-06,
1712
+ "loss": 0.5522,
1713
+ "step": 284
1714
+ },
1715
+ {
1716
+ "epoch": 0.38,
1717
+ "learning_rate": 4.875269504085009e-06,
1718
+ "loss": 0.5588,
1719
+ "step": 285
1720
+ },
1721
+ {
1722
+ "epoch": 0.39,
1723
+ "learning_rate": 4.874132285096828e-06,
1724
+ "loss": 0.5635,
1725
+ "step": 286
1726
+ },
1727
+ {
1728
+ "epoch": 0.39,
1729
+ "learning_rate": 4.87299003921962e-06,
1730
+ "loss": 0.571,
1731
+ "step": 287
1732
+ },
1733
+ {
1734
+ "epoch": 0.39,
1735
+ "learning_rate": 4.871842768871928e-06,
1736
+ "loss": 0.5763,
1737
+ "step": 288
1738
+ },
1739
+ {
1740
+ "epoch": 0.39,
1741
+ "learning_rate": 4.8706904764829345e-06,
1742
+ "loss": 0.5428,
1743
+ "step": 289
1744
+ },
1745
+ {
1746
+ "epoch": 0.39,
1747
+ "learning_rate": 4.869533164492456e-06,
1748
+ "loss": 0.6225,
1749
+ "step": 290
1750
+ },
1751
+ {
1752
+ "epoch": 0.39,
1753
+ "learning_rate": 4.868370835350935e-06,
1754
+ "loss": 0.6056,
1755
+ "step": 291
1756
+ },
1757
+ {
1758
+ "epoch": 0.39,
1759
+ "learning_rate": 4.867203491519441e-06,
1760
+ "loss": 0.6129,
1761
+ "step": 292
1762
+ },
1763
+ {
1764
+ "epoch": 0.39,
1765
+ "learning_rate": 4.866031135469657e-06,
1766
+ "loss": 0.5854,
1767
+ "step": 293
1768
+ },
1769
+ {
1770
+ "epoch": 0.4,
1771
+ "learning_rate": 4.864853769683885e-06,
1772
+ "loss": 0.556,
1773
+ "step": 294
1774
+ },
1775
+ {
1776
+ "epoch": 0.4,
1777
+ "learning_rate": 4.863671396655026e-06,
1778
+ "loss": 0.571,
1779
+ "step": 295
1780
+ },
1781
+ {
1782
+ "epoch": 0.4,
1783
+ "learning_rate": 4.862484018886591e-06,
1784
+ "loss": 0.5766,
1785
+ "step": 296
1786
+ },
1787
+ {
1788
+ "epoch": 0.4,
1789
+ "learning_rate": 4.861291638892682e-06,
1790
+ "loss": 0.5975,
1791
+ "step": 297
1792
+ },
1793
+ {
1794
+ "epoch": 0.4,
1795
+ "learning_rate": 4.8600942591979955e-06,
1796
+ "loss": 0.5632,
1797
+ "step": 298
1798
+ },
1799
+ {
1800
+ "epoch": 0.4,
1801
+ "learning_rate": 4.858891882337814e-06,
1802
+ "loss": 0.5562,
1803
+ "step": 299
1804
+ },
1805
+ {
1806
+ "epoch": 0.4,
1807
+ "learning_rate": 4.8576845108579995e-06,
1808
+ "loss": 0.5462,
1809
+ "step": 300
1810
+ },
1811
+ {
1812
+ "epoch": 0.41,
1813
+ "learning_rate": 4.85647214731499e-06,
1814
+ "loss": 0.5241,
1815
+ "step": 301
1816
+ },
1817
+ {
1818
+ "epoch": 0.41,
1819
+ "learning_rate": 4.855254794275796e-06,
1820
+ "loss": 0.5706,
1821
+ "step": 302
1822
+ },
1823
+ {
1824
+ "epoch": 0.41,
1825
+ "learning_rate": 4.854032454317987e-06,
1826
+ "loss": 0.5534,
1827
+ "step": 303
1828
+ },
1829
+ {
1830
+ "epoch": 0.41,
1831
+ "learning_rate": 4.852805130029696e-06,
1832
+ "loss": 0.5394,
1833
+ "step": 304
1834
+ },
1835
+ {
1836
+ "epoch": 0.41,
1837
+ "learning_rate": 4.85157282400961e-06,
1838
+ "loss": 0.5586,
1839
+ "step": 305
1840
+ },
1841
+ {
1842
+ "epoch": 0.41,
1843
+ "learning_rate": 4.850335538866961e-06,
1844
+ "loss": 0.5726,
1845
+ "step": 306
1846
+ },
1847
+ {
1848
+ "epoch": 0.41,
1849
+ "learning_rate": 4.849093277221525e-06,
1850
+ "loss": 0.5541,
1851
+ "step": 307
1852
+ },
1853
+ {
1854
+ "epoch": 0.42,
1855
+ "learning_rate": 4.847846041703616e-06,
1856
+ "loss": 0.5826,
1857
+ "step": 308
1858
+ },
1859
+ {
1860
+ "epoch": 0.42,
1861
+ "learning_rate": 4.846593834954078e-06,
1862
+ "loss": 0.5864,
1863
+ "step": 309
1864
+ },
1865
+ {
1866
+ "epoch": 0.42,
1867
+ "learning_rate": 4.845336659624282e-06,
1868
+ "loss": 0.544,
1869
+ "step": 310
1870
+ },
1871
+ {
1872
+ "epoch": 0.42,
1873
+ "learning_rate": 4.844074518376118e-06,
1874
+ "loss": 0.5671,
1875
+ "step": 311
1876
+ },
1877
+ {
1878
+ "epoch": 0.42,
1879
+ "learning_rate": 4.842807413881993e-06,
1880
+ "loss": 0.5405,
1881
+ "step": 312
1882
+ },
1883
+ {
1884
+ "epoch": 0.42,
1885
+ "learning_rate": 4.84153534882482e-06,
1886
+ "loss": 0.6019,
1887
+ "step": 313
1888
+ },
1889
+ {
1890
+ "epoch": 0.42,
1891
+ "learning_rate": 4.840258325898017e-06,
1892
+ "loss": 0.5412,
1893
+ "step": 314
1894
+ },
1895
+ {
1896
+ "epoch": 0.42,
1897
+ "learning_rate": 4.8389763478055e-06,
1898
+ "loss": 0.5927,
1899
+ "step": 315
1900
+ },
1901
+ {
1902
+ "epoch": 0.43,
1903
+ "learning_rate": 4.837689417261674e-06,
1904
+ "loss": 0.6319,
1905
+ "step": 316
1906
+ },
1907
+ {
1908
+ "epoch": 0.43,
1909
+ "learning_rate": 4.8363975369914355e-06,
1910
+ "loss": 0.5956,
1911
+ "step": 317
1912
+ },
1913
+ {
1914
+ "epoch": 0.43,
1915
+ "learning_rate": 4.835100709730155e-06,
1916
+ "loss": 0.613,
1917
+ "step": 318
1918
+ },
1919
+ {
1920
+ "epoch": 0.43,
1921
+ "learning_rate": 4.833798938223682e-06,
1922
+ "loss": 0.6687,
1923
+ "step": 319
1924
+ },
1925
+ {
1926
+ "epoch": 0.43,
1927
+ "learning_rate": 4.832492225228334e-06,
1928
+ "loss": 0.6312,
1929
+ "step": 320
1930
+ },
1931
+ {
1932
+ "epoch": 0.43,
1933
+ "learning_rate": 4.83118057351089e-06,
1934
+ "loss": 0.5668,
1935
+ "step": 321
1936
+ },
1937
+ {
1938
+ "epoch": 0.43,
1939
+ "learning_rate": 4.829863985848587e-06,
1940
+ "loss": 0.5697,
1941
+ "step": 322
1942
+ },
1943
+ {
1944
+ "epoch": 0.44,
1945
+ "learning_rate": 4.828542465029112e-06,
1946
+ "loss": 0.5391,
1947
+ "step": 323
1948
+ },
1949
+ {
1950
+ "epoch": 0.44,
1951
+ "learning_rate": 4.827216013850601e-06,
1952
+ "loss": 0.6234,
1953
+ "step": 324
1954
+ },
1955
+ {
1956
+ "epoch": 0.44,
1957
+ "learning_rate": 4.825884635121624e-06,
1958
+ "loss": 0.5776,
1959
+ "step": 325
1960
+ },
1961
+ {
1962
+ "epoch": 0.44,
1963
+ "learning_rate": 4.824548331661187e-06,
1964
+ "loss": 0.6005,
1965
+ "step": 326
1966
+ },
1967
+ {
1968
+ "epoch": 0.44,
1969
+ "learning_rate": 4.823207106298725e-06,
1970
+ "loss": 0.5165,
1971
+ "step": 327
1972
+ },
1973
+ {
1974
+ "epoch": 0.44,
1975
+ "learning_rate": 4.821860961874093e-06,
1976
+ "loss": 0.5904,
1977
+ "step": 328
1978
+ },
1979
+ {
1980
+ "epoch": 0.44,
1981
+ "learning_rate": 4.820509901237559e-06,
1982
+ "loss": 0.6053,
1983
+ "step": 329
1984
+ },
1985
+ {
1986
+ "epoch": 0.44,
1987
+ "learning_rate": 4.819153927249804e-06,
1988
+ "loss": 0.6007,
1989
+ "step": 330
1990
+ },
1991
+ {
1992
+ "epoch": 0.45,
1993
+ "learning_rate": 4.817793042781911e-06,
1994
+ "loss": 0.6506,
1995
+ "step": 331
1996
+ },
1997
+ {
1998
+ "epoch": 0.45,
1999
+ "learning_rate": 4.8164272507153605e-06,
2000
+ "loss": 0.5246,
2001
+ "step": 332
2002
+ },
2003
+ {
2004
+ "epoch": 0.45,
2005
+ "learning_rate": 4.815056553942024e-06,
2006
+ "loss": 0.5676,
2007
+ "step": 333
2008
+ },
2009
+ {
2010
+ "epoch": 0.45,
2011
+ "learning_rate": 4.813680955364156e-06,
2012
+ "loss": 0.5418,
2013
+ "step": 334
2014
+ },
2015
+ {
2016
+ "epoch": 0.45,
2017
+ "learning_rate": 4.812300457894395e-06,
2018
+ "loss": 0.531,
2019
+ "step": 335
2020
+ },
2021
+ {
2022
+ "epoch": 0.45,
2023
+ "learning_rate": 4.810915064455746e-06,
2024
+ "loss": 0.5959,
2025
+ "step": 336
2026
+ },
2027
+ {
2028
+ "epoch": 0.45,
2029
+ "learning_rate": 4.809524777981584e-06,
2030
+ "loss": 0.5781,
2031
+ "step": 337
2032
+ },
2033
+ {
2034
+ "epoch": 0.46,
2035
+ "learning_rate": 4.808129601415645e-06,
2036
+ "loss": 0.5337,
2037
+ "step": 338
2038
+ },
2039
+ {
2040
+ "epoch": 0.46,
2041
+ "learning_rate": 4.806729537712017e-06,
2042
+ "loss": 0.6285,
2043
+ "step": 339
2044
+ },
2045
+ {
2046
+ "epoch": 0.46,
2047
+ "learning_rate": 4.805324589835138e-06,
2048
+ "loss": 0.6457,
2049
+ "step": 340
2050
+ },
2051
+ {
2052
+ "epoch": 0.46,
2053
+ "learning_rate": 4.8039147607597835e-06,
2054
+ "loss": 0.5889,
2055
+ "step": 341
2056
+ },
2057
+ {
2058
+ "epoch": 0.46,
2059
+ "learning_rate": 4.80250005347107e-06,
2060
+ "loss": 0.6054,
2061
+ "step": 342
2062
+ },
2063
+ {
2064
+ "epoch": 0.46,
2065
+ "learning_rate": 4.801080470964438e-06,
2066
+ "loss": 0.5838,
2067
+ "step": 343
2068
+ },
2069
+ {
2070
+ "epoch": 0.46,
2071
+ "learning_rate": 4.799656016245653e-06,
2072
+ "loss": 0.5877,
2073
+ "step": 344
2074
+ },
2075
+ {
2076
+ "epoch": 0.46,
2077
+ "learning_rate": 4.798226692330797e-06,
2078
+ "loss": 0.6596,
2079
+ "step": 345
2080
+ },
2081
+ {
2082
+ "epoch": 0.47,
2083
+ "learning_rate": 4.79679250224626e-06,
2084
+ "loss": 0.6457,
2085
+ "step": 346
2086
+ },
2087
+ {
2088
+ "epoch": 0.47,
2089
+ "learning_rate": 4.795353449028737e-06,
2090
+ "loss": 0.6714,
2091
+ "step": 347
2092
+ },
2093
+ {
2094
+ "epoch": 0.47,
2095
+ "learning_rate": 4.793909535725219e-06,
2096
+ "loss": 0.5839,
2097
+ "step": 348
2098
+ },
2099
+ {
2100
+ "epoch": 0.47,
2101
+ "learning_rate": 4.792460765392989e-06,
2102
+ "loss": 0.4988,
2103
+ "step": 349
2104
+ },
2105
+ {
2106
+ "epoch": 0.47,
2107
+ "learning_rate": 4.791007141099611e-06,
2108
+ "loss": 0.5687,
2109
+ "step": 350
2110
+ },
2111
+ {
2112
+ "epoch": 0.47,
2113
+ "learning_rate": 4.789548665922932e-06,
2114
+ "loss": 0.5333,
2115
+ "step": 351
2116
+ },
2117
+ {
2118
+ "epoch": 0.47,
2119
+ "learning_rate": 4.788085342951063e-06,
2120
+ "loss": 0.4989,
2121
+ "step": 352
2122
+ },
2123
+ {
2124
+ "epoch": 0.48,
2125
+ "learning_rate": 4.786617175282387e-06,
2126
+ "loss": 0.6209,
2127
+ "step": 353
2128
+ },
2129
+ {
2130
+ "epoch": 0.48,
2131
+ "learning_rate": 4.785144166025537e-06,
2132
+ "loss": 0.6196,
2133
+ "step": 354
2134
+ },
2135
+ {
2136
+ "epoch": 0.48,
2137
+ "learning_rate": 4.7836663182994054e-06,
2138
+ "loss": 0.5705,
2139
+ "step": 355
2140
+ },
2141
+ {
2142
+ "epoch": 0.48,
2143
+ "learning_rate": 4.7821836352331235e-06,
2144
+ "loss": 0.6934,
2145
+ "step": 356
2146
+ },
2147
+ {
2148
+ "epoch": 0.48,
2149
+ "learning_rate": 4.780696119966064e-06,
2150
+ "loss": 0.5832,
2151
+ "step": 357
2152
+ },
2153
+ {
2154
+ "epoch": 0.48,
2155
+ "learning_rate": 4.779203775647828e-06,
2156
+ "loss": 0.5212,
2157
+ "step": 358
2158
+ },
2159
+ {
2160
+ "epoch": 0.48,
2161
+ "learning_rate": 4.777706605438246e-06,
2162
+ "loss": 0.5548,
2163
+ "step": 359
2164
+ },
2165
+ {
2166
+ "epoch": 0.49,
2167
+ "learning_rate": 4.776204612507361e-06,
2168
+ "loss": 0.5626,
2169
+ "step": 360
2170
+ },
2171
+ {
2172
+ "epoch": 0.49,
2173
+ "learning_rate": 4.774697800035433e-06,
2174
+ "loss": 0.585,
2175
+ "step": 361
2176
+ },
2177
+ {
2178
+ "epoch": 0.49,
2179
+ "learning_rate": 4.773186171212922e-06,
2180
+ "loss": 0.6399,
2181
+ "step": 362
2182
+ },
2183
+ {
2184
+ "epoch": 0.49,
2185
+ "learning_rate": 4.77166972924049e-06,
2186
+ "loss": 0.5562,
2187
+ "step": 363
2188
+ },
2189
+ {
2190
+ "epoch": 0.49,
2191
+ "learning_rate": 4.7701484773289874e-06,
2192
+ "loss": 0.5208,
2193
+ "step": 364
2194
+ },
2195
+ {
2196
+ "epoch": 0.49,
2197
+ "learning_rate": 4.768622418699449e-06,
2198
+ "loss": 0.5369,
2199
+ "step": 365
2200
+ },
2201
+ {
2202
+ "epoch": 0.49,
2203
+ "learning_rate": 4.767091556583089e-06,
2204
+ "loss": 0.5876,
2205
+ "step": 366
2206
+ },
2207
+ {
2208
+ "epoch": 0.49,
2209
+ "learning_rate": 4.765555894221291e-06,
2210
+ "loss": 0.6237,
2211
+ "step": 367
2212
+ },
2213
+ {
2214
+ "epoch": 0.5,
2215
+ "learning_rate": 4.764015434865601e-06,
2216
+ "loss": 0.6593,
2217
+ "step": 368
2218
+ },
2219
+ {
2220
+ "epoch": 0.5,
2221
+ "learning_rate": 4.762470181777726e-06,
2222
+ "loss": 0.5541,
2223
+ "step": 369
2224
+ },
2225
+ {
2226
+ "epoch": 0.5,
2227
+ "learning_rate": 4.76092013822952e-06,
2228
+ "loss": 0.578,
2229
+ "step": 370
2230
+ },
2231
+ {
2232
+ "epoch": 0.5,
2233
+ "learning_rate": 4.759365307502981e-06,
2234
+ "loss": 0.5523,
2235
+ "step": 371
2236
+ },
2237
+ {
2238
+ "epoch": 0.5,
2239
+ "learning_rate": 4.757805692890241e-06,
2240
+ "loss": 0.5682,
2241
+ "step": 372
2242
+ },
2243
+ {
2244
+ "epoch": 0.5,
2245
+ "learning_rate": 4.7562412976935655e-06,
2246
+ "loss": 0.5599,
2247
+ "step": 373
2248
+ },
2249
+ {
2250
+ "epoch": 0.5,
2251
+ "learning_rate": 4.7546721252253395e-06,
2252
+ "loss": 0.5949,
2253
+ "step": 374
2254
+ },
2255
+ {
2256
+ "epoch": 0.51,
2257
+ "learning_rate": 4.753098178808063e-06,
2258
+ "loss": 0.4994,
2259
+ "step": 375
2260
+ },
2261
+ {
2262
+ "epoch": 0.51,
2263
+ "learning_rate": 4.751519461774344e-06,
2264
+ "loss": 0.6295,
2265
+ "step": 376
2266
+ },
2267
+ {
2268
+ "epoch": 0.51,
2269
+ "learning_rate": 4.7499359774668935e-06,
2270
+ "loss": 0.5813,
2271
+ "step": 377
2272
+ },
2273
+ {
2274
+ "epoch": 0.51,
2275
+ "learning_rate": 4.748347729238515e-06,
2276
+ "loss": 0.5691,
2277
+ "step": 378
2278
+ },
2279
+ {
2280
+ "epoch": 0.51,
2281
+ "learning_rate": 4.746754720452099e-06,
2282
+ "loss": 0.5352,
2283
+ "step": 379
2284
+ },
2285
+ {
2286
+ "epoch": 0.51,
2287
+ "learning_rate": 4.745156954480617e-06,
2288
+ "loss": 0.5713,
2289
+ "step": 380
2290
+ },
2291
+ {
2292
+ "epoch": 0.51,
2293
+ "learning_rate": 4.743554434707111e-06,
2294
+ "loss": 0.5313,
2295
+ "step": 381
2296
+ },
2297
+ {
2298
+ "epoch": 0.51,
2299
+ "learning_rate": 4.741947164524691e-06,
2300
+ "loss": 0.5207,
2301
+ "step": 382
2302
+ },
2303
+ {
2304
+ "epoch": 0.52,
2305
+ "learning_rate": 4.7403351473365235e-06,
2306
+ "loss": 0.6032,
2307
+ "step": 383
2308
+ },
2309
+ {
2310
+ "epoch": 0.52,
2311
+ "learning_rate": 4.738718386555826e-06,
2312
+ "loss": 0.5859,
2313
+ "step": 384
2314
+ },
2315
+ {
2316
+ "epoch": 0.52,
2317
+ "learning_rate": 4.737096885605862e-06,
2318
+ "loss": 0.5978,
2319
+ "step": 385
2320
+ },
2321
+ {
2322
+ "epoch": 0.52,
2323
+ "learning_rate": 4.735470647919928e-06,
2324
+ "loss": 0.5586,
2325
+ "step": 386
2326
+ },
2327
+ {
2328
+ "epoch": 0.52,
2329
+ "learning_rate": 4.733839676941355e-06,
2330
+ "loss": 0.5008,
2331
+ "step": 387
2332
+ },
2333
+ {
2334
+ "epoch": 0.52,
2335
+ "learning_rate": 4.732203976123492e-06,
2336
+ "loss": 0.6217,
2337
+ "step": 388
2338
+ },
2339
+ {
2340
+ "epoch": 0.52,
2341
+ "learning_rate": 4.730563548929703e-06,
2342
+ "loss": 0.5872,
2343
+ "step": 389
2344
+ },
2345
+ {
2346
+ "epoch": 0.53,
2347
+ "learning_rate": 4.728918398833361e-06,
2348
+ "loss": 0.5123,
2349
+ "step": 390
2350
+ },
2351
+ {
2352
+ "epoch": 0.53,
2353
+ "learning_rate": 4.727268529317839e-06,
2354
+ "loss": 0.5139,
2355
+ "step": 391
2356
+ },
2357
+ {
2358
+ "epoch": 0.53,
2359
+ "learning_rate": 4.725613943876502e-06,
2360
+ "loss": 0.6775,
2361
+ "step": 392
2362
+ },
2363
+ {
2364
+ "epoch": 0.53,
2365
+ "learning_rate": 4.723954646012699e-06,
2366
+ "loss": 0.6362,
2367
+ "step": 393
2368
+ },
2369
+ {
2370
+ "epoch": 0.53,
2371
+ "learning_rate": 4.7222906392397596e-06,
2372
+ "loss": 0.6033,
2373
+ "step": 394
2374
+ },
2375
+ {
2376
+ "epoch": 0.53,
2377
+ "learning_rate": 4.720621927080982e-06,
2378
+ "loss": 0.574,
2379
+ "step": 395
2380
+ },
2381
+ {
2382
+ "epoch": 0.53,
2383
+ "learning_rate": 4.718948513069629e-06,
2384
+ "loss": 0.5384,
2385
+ "step": 396
2386
+ },
2387
+ {
2388
+ "epoch": 0.54,
2389
+ "learning_rate": 4.717270400748917e-06,
2390
+ "loss": 0.5976,
2391
+ "step": 397
2392
+ },
2393
+ {
2394
+ "epoch": 0.54,
2395
+ "learning_rate": 4.715587593672012e-06,
2396
+ "loss": 0.6397,
2397
+ "step": 398
2398
+ },
2399
+ {
2400
+ "epoch": 0.54,
2401
+ "learning_rate": 4.713900095402019e-06,
2402
+ "loss": 0.5382,
2403
+ "step": 399
2404
+ },
2405
+ {
2406
+ "epoch": 0.54,
2407
+ "learning_rate": 4.7122079095119765e-06,
2408
+ "loss": 0.6114,
2409
+ "step": 400
2410
+ },
2411
+ {
2412
+ "epoch": 0.54,
2413
+ "learning_rate": 4.710511039584849e-06,
2414
+ "loss": 0.5958,
2415
+ "step": 401
2416
+ },
2417
+ {
2418
+ "epoch": 0.54,
2419
+ "learning_rate": 4.708809489213519e-06,
2420
+ "loss": 0.6055,
2421
+ "step": 402
2422
+ },
2423
+ {
2424
+ "epoch": 0.54,
2425
+ "learning_rate": 4.707103262000778e-06,
2426
+ "loss": 0.5728,
2427
+ "step": 403
2428
+ },
2429
+ {
2430
+ "epoch": 0.54,
2431
+ "learning_rate": 4.70539236155932e-06,
2432
+ "loss": 0.5638,
2433
+ "step": 404
2434
+ },
2435
+ {
2436
+ "epoch": 0.55,
2437
+ "learning_rate": 4.7036767915117355e-06,
2438
+ "loss": 0.5813,
2439
+ "step": 405
2440
+ },
2441
+ {
2442
+ "epoch": 0.55,
2443
+ "learning_rate": 4.7019565554905e-06,
2444
+ "loss": 0.5263,
2445
+ "step": 406
2446
+ },
2447
+ {
2448
+ "epoch": 0.55,
2449
+ "learning_rate": 4.700231657137971e-06,
2450
+ "loss": 0.6219,
2451
+ "step": 407
2452
+ },
2453
+ {
2454
+ "epoch": 0.55,
2455
+ "learning_rate": 4.698502100106376e-06,
2456
+ "loss": 0.5896,
2457
+ "step": 408
2458
+ },
2459
+ {
2460
+ "epoch": 0.55,
2461
+ "learning_rate": 4.6967678880578075e-06,
2462
+ "loss": 0.5986,
2463
+ "step": 409
2464
+ },
2465
+ {
2466
+ "epoch": 0.55,
2467
+ "learning_rate": 4.695029024664214e-06,
2468
+ "loss": 0.5573,
2469
+ "step": 410
2470
+ },
2471
+ {
2472
+ "epoch": 0.55,
2473
+ "learning_rate": 4.693285513607392e-06,
2474
+ "loss": 0.6516,
2475
+ "step": 411
2476
+ },
2477
+ {
2478
+ "epoch": 0.56,
2479
+ "learning_rate": 4.691537358578979e-06,
2480
+ "loss": 0.6078,
2481
+ "step": 412
2482
+ },
2483
+ {
2484
+ "epoch": 0.56,
2485
+ "learning_rate": 4.689784563280447e-06,
2486
+ "loss": 0.5442,
2487
+ "step": 413
2488
+ },
2489
+ {
2490
+ "epoch": 0.56,
2491
+ "learning_rate": 4.688027131423092e-06,
2492
+ "loss": 0.5692,
2493
+ "step": 414
2494
+ },
2495
+ {
2496
+ "epoch": 0.56,
2497
+ "learning_rate": 4.686265066728026e-06,
2498
+ "loss": 0.6515,
2499
+ "step": 415
2500
+ },
2501
+ {
2502
+ "epoch": 0.56,
2503
+ "learning_rate": 4.684498372926172e-06,
2504
+ "loss": 0.5343,
2505
+ "step": 416
2506
+ },
2507
+ {
2508
+ "epoch": 0.56,
2509
+ "learning_rate": 4.6827270537582544e-06,
2510
+ "loss": 0.5115,
2511
+ "step": 417
2512
+ },
2513
+ {
2514
+ "epoch": 0.56,
2515
+ "learning_rate": 4.680951112974791e-06,
2516
+ "loss": 0.643,
2517
+ "step": 418
2518
+ },
2519
+ {
2520
+ "epoch": 0.56,
2521
+ "learning_rate": 4.679170554336085e-06,
2522
+ "loss": 0.5451,
2523
+ "step": 419
2524
+ },
2525
+ {
2526
+ "epoch": 0.57,
2527
+ "learning_rate": 4.677385381612215e-06,
2528
+ "loss": 0.5823,
2529
+ "step": 420
2530
+ },
2531
+ {
2532
+ "epoch": 0.57,
2533
+ "learning_rate": 4.675595598583035e-06,
2534
+ "loss": 0.5244,
2535
+ "step": 421
2536
+ },
2537
+ {
2538
+ "epoch": 0.57,
2539
+ "learning_rate": 4.673801209038154e-06,
2540
+ "loss": 0.5801,
2541
+ "step": 422
2542
+ },
2543
+ {
2544
+ "epoch": 0.57,
2545
+ "learning_rate": 4.672002216776941e-06,
2546
+ "loss": 0.5131,
2547
+ "step": 423
2548
+ },
2549
+ {
2550
+ "epoch": 0.57,
2551
+ "learning_rate": 4.670198625608504e-06,
2552
+ "loss": 0.6185,
2553
+ "step": 424
2554
+ },
2555
+ {
2556
+ "epoch": 0.57,
2557
+ "learning_rate": 4.6683904393516955e-06,
2558
+ "loss": 0.5772,
2559
+ "step": 425
2560
+ },
2561
+ {
2562
+ "epoch": 0.57,
2563
+ "learning_rate": 4.666577661835092e-06,
2564
+ "loss": 0.5883,
2565
+ "step": 426
2566
+ },
2567
+ {
2568
+ "epoch": 0.58,
2569
+ "learning_rate": 4.664760296896993e-06,
2570
+ "loss": 0.528,
2571
+ "step": 427
2572
+ },
2573
+ {
2574
+ "epoch": 0.58,
2575
+ "learning_rate": 4.6629383483854115e-06,
2576
+ "loss": 0.6697,
2577
+ "step": 428
2578
+ },
2579
+ {
2580
+ "epoch": 0.58,
2581
+ "learning_rate": 4.661111820158068e-06,
2582
+ "loss": 0.4754,
2583
+ "step": 429
2584
+ },
2585
+ {
2586
+ "epoch": 0.58,
2587
+ "learning_rate": 4.6592807160823735e-06,
2588
+ "loss": 0.6839,
2589
+ "step": 430
2590
+ },
2591
+ {
2592
+ "epoch": 0.58,
2593
+ "learning_rate": 4.657445040035434e-06,
2594
+ "loss": 0.6277,
2595
+ "step": 431
2596
+ },
2597
+ {
2598
+ "epoch": 0.58,
2599
+ "learning_rate": 4.655604795904034e-06,
2600
+ "loss": 0.5867,
2601
+ "step": 432
2602
+ },
2603
+ {
2604
+ "epoch": 0.58,
2605
+ "learning_rate": 4.65375998758463e-06,
2606
+ "loss": 0.5332,
2607
+ "step": 433
2608
+ },
2609
+ {
2610
+ "epoch": 0.58,
2611
+ "learning_rate": 4.6519106189833405e-06,
2612
+ "loss": 0.6095,
2613
+ "step": 434
2614
+ },
2615
+ {
2616
+ "epoch": 0.59,
2617
+ "learning_rate": 4.650056694015943e-06,
2618
+ "loss": 0.532,
2619
+ "step": 435
2620
+ },
2621
+ {
2622
+ "epoch": 0.59,
2623
+ "learning_rate": 4.6481982166078615e-06,
2624
+ "loss": 0.5194,
2625
+ "step": 436
2626
+ },
2627
+ {
2628
+ "epoch": 0.59,
2629
+ "learning_rate": 4.646335190694159e-06,
2630
+ "loss": 0.5159,
2631
+ "step": 437
2632
+ },
2633
+ {
2634
+ "epoch": 0.59,
2635
+ "learning_rate": 4.644467620219527e-06,
2636
+ "loss": 0.6093,
2637
+ "step": 438
2638
+ },
2639
+ {
2640
+ "epoch": 0.59,
2641
+ "learning_rate": 4.642595509138285e-06,
2642
+ "loss": 0.6159,
2643
+ "step": 439
2644
+ },
2645
+ {
2646
+ "epoch": 0.59,
2647
+ "learning_rate": 4.640718861414361e-06,
2648
+ "loss": 0.5613,
2649
+ "step": 440
2650
+ },
2651
+ {
2652
+ "epoch": 0.59,
2653
+ "learning_rate": 4.63883768102129e-06,
2654
+ "loss": 0.528,
2655
+ "step": 441
2656
+ },
2657
+ {
2658
+ "epoch": 0.6,
2659
+ "learning_rate": 4.6369519719422075e-06,
2660
+ "loss": 0.5926,
2661
+ "step": 442
2662
+ },
2663
+ {
2664
+ "epoch": 0.6,
2665
+ "learning_rate": 4.635061738169835e-06,
2666
+ "loss": 0.6028,
2667
+ "step": 443
2668
+ },
2669
+ {
2670
+ "epoch": 0.6,
2671
+ "learning_rate": 4.633166983706474e-06,
2672
+ "loss": 0.6421,
2673
+ "step": 444
2674
+ },
2675
+ {
2676
+ "epoch": 0.6,
2677
+ "learning_rate": 4.631267712563998e-06,
2678
+ "loss": 0.5765,
2679
+ "step": 445
2680
+ },
2681
+ {
2682
+ "epoch": 0.6,
2683
+ "learning_rate": 4.629363928763848e-06,
2684
+ "loss": 0.5149,
2685
+ "step": 446
2686
+ },
2687
+ {
2688
+ "epoch": 0.6,
2689
+ "learning_rate": 4.627455636337014e-06,
2690
+ "loss": 0.5851,
2691
+ "step": 447
2692
+ },
2693
+ {
2694
+ "epoch": 0.6,
2695
+ "learning_rate": 4.625542839324036e-06,
2696
+ "loss": 0.5438,
2697
+ "step": 448
2698
+ },
2699
+ {
2700
+ "epoch": 0.61,
2701
+ "learning_rate": 4.6236255417749906e-06,
2702
+ "loss": 0.5618,
2703
+ "step": 449
2704
+ },
2705
+ {
2706
+ "epoch": 0.61,
2707
+ "learning_rate": 4.621703747749484e-06,
2708
+ "loss": 0.6441,
2709
+ "step": 450
2710
+ },
2711
+ {
2712
+ "epoch": 0.61,
2713
+ "learning_rate": 4.619777461316643e-06,
2714
+ "loss": 0.6496,
2715
+ "step": 451
2716
+ },
2717
+ {
2718
+ "epoch": 0.61,
2719
+ "learning_rate": 4.617846686555107e-06,
2720
+ "loss": 0.598,
2721
+ "step": 452
2722
+ },
2723
+ {
2724
+ "epoch": 0.61,
2725
+ "learning_rate": 4.615911427553017e-06,
2726
+ "loss": 0.6012,
2727
+ "step": 453
2728
+ },
2729
+ {
2730
+ "epoch": 0.61,
2731
+ "learning_rate": 4.613971688408011e-06,
2732
+ "loss": 0.5478,
2733
+ "step": 454
2734
+ },
2735
+ {
2736
+ "epoch": 0.61,
2737
+ "learning_rate": 4.612027473227212e-06,
2738
+ "loss": 0.6098,
2739
+ "step": 455
2740
+ },
2741
+ {
2742
+ "epoch": 0.61,
2743
+ "learning_rate": 4.61007878612722e-06,
2744
+ "loss": 0.6157,
2745
+ "step": 456
2746
+ },
2747
+ {
2748
+ "epoch": 0.62,
2749
+ "learning_rate": 4.608125631234104e-06,
2750
+ "loss": 0.5677,
2751
+ "step": 457
2752
+ },
2753
+ {
2754
+ "epoch": 0.62,
2755
+ "learning_rate": 4.606168012683394e-06,
2756
+ "loss": 0.582,
2757
+ "step": 458
2758
+ },
2759
+ {
2760
+ "epoch": 0.62,
2761
+ "learning_rate": 4.604205934620069e-06,
2762
+ "loss": 0.598,
2763
+ "step": 459
2764
+ },
2765
+ {
2766
+ "epoch": 0.62,
2767
+ "learning_rate": 4.602239401198552e-06,
2768
+ "loss": 0.5248,
2769
+ "step": 460
2770
+ },
2771
+ {
2772
+ "epoch": 0.62,
2773
+ "learning_rate": 4.6002684165827e-06,
2774
+ "loss": 0.5587,
2775
+ "step": 461
2776
+ },
2777
+ {
2778
+ "epoch": 0.62,
2779
+ "learning_rate": 4.5982929849457915e-06,
2780
+ "loss": 0.5792,
2781
+ "step": 462
2782
+ },
2783
+ {
2784
+ "epoch": 0.62,
2785
+ "learning_rate": 4.596313110470525e-06,
2786
+ "loss": 0.5679,
2787
+ "step": 463
2788
+ },
2789
+ {
2790
+ "epoch": 0.63,
2791
+ "learning_rate": 4.594328797349005e-06,
2792
+ "loss": 0.5206,
2793
+ "step": 464
2794
+ },
2795
+ {
2796
+ "epoch": 0.63,
2797
+ "learning_rate": 4.592340049782732e-06,
2798
+ "loss": 0.5738,
2799
+ "step": 465
2800
+ },
2801
+ {
2802
+ "epoch": 0.63,
2803
+ "learning_rate": 4.590346871982599e-06,
2804
+ "loss": 0.6298,
2805
+ "step": 466
2806
+ },
2807
+ {
2808
+ "epoch": 0.63,
2809
+ "learning_rate": 4.588349268168878e-06,
2810
+ "loss": 0.5276,
2811
+ "step": 467
2812
+ },
2813
+ {
2814
+ "epoch": 0.63,
2815
+ "learning_rate": 4.58634724257121e-06,
2816
+ "loss": 0.6081,
2817
+ "step": 468
2818
+ },
2819
+ {
2820
+ "epoch": 0.63,
2821
+ "learning_rate": 4.5843407994286035e-06,
2822
+ "loss": 0.5262,
2823
+ "step": 469
2824
+ },
2825
+ {
2826
+ "epoch": 0.63,
2827
+ "learning_rate": 4.5823299429894155e-06,
2828
+ "loss": 0.519,
2829
+ "step": 470
2830
+ },
2831
+ {
2832
+ "epoch": 0.63,
2833
+ "learning_rate": 4.580314677511352e-06,
2834
+ "loss": 0.5797,
2835
+ "step": 471
2836
+ },
2837
+ {
2838
+ "epoch": 0.64,
2839
+ "learning_rate": 4.57829500726145e-06,
2840
+ "loss": 0.6002,
2841
+ "step": 472
2842
+ },
2843
+ {
2844
+ "epoch": 0.64,
2845
+ "learning_rate": 4.576270936516078e-06,
2846
+ "loss": 0.5263,
2847
+ "step": 473
2848
+ },
2849
+ {
2850
+ "epoch": 0.64,
2851
+ "learning_rate": 4.574242469560917e-06,
2852
+ "loss": 0.5529,
2853
+ "step": 474
2854
+ },
2855
+ {
2856
+ "epoch": 0.64,
2857
+ "learning_rate": 4.5722096106909595e-06,
2858
+ "loss": 0.5836,
2859
+ "step": 475
2860
+ },
2861
+ {
2862
+ "epoch": 0.64,
2863
+ "learning_rate": 4.570172364210497e-06,
2864
+ "loss": 0.5576,
2865
+ "step": 476
2866
+ },
2867
+ {
2868
+ "epoch": 0.64,
2869
+ "learning_rate": 4.56813073443311e-06,
2870
+ "loss": 0.5774,
2871
+ "step": 477
2872
+ },
2873
+ {
2874
+ "epoch": 0.64,
2875
+ "learning_rate": 4.5660847256816605e-06,
2876
+ "loss": 0.6327,
2877
+ "step": 478
2878
+ },
2879
+ {
2880
+ "epoch": 0.65,
2881
+ "learning_rate": 4.564034342288282e-06,
2882
+ "loss": 0.5737,
2883
+ "step": 479
2884
+ },
2885
+ {
2886
+ "epoch": 0.65,
2887
+ "learning_rate": 4.561979588594372e-06,
2888
+ "loss": 0.5601,
2889
+ "step": 480
2890
+ },
2891
+ {
2892
+ "epoch": 0.65,
2893
+ "learning_rate": 4.55992046895058e-06,
2894
+ "loss": 0.5353,
2895
+ "step": 481
2896
+ },
2897
+ {
2898
+ "epoch": 0.65,
2899
+ "learning_rate": 4.5578569877168e-06,
2900
+ "loss": 0.6106,
2901
+ "step": 482
2902
+ },
2903
+ {
2904
+ "epoch": 0.65,
2905
+ "learning_rate": 4.555789149262162e-06,
2906
+ "loss": 0.619,
2907
+ "step": 483
2908
+ },
2909
+ {
2910
+ "epoch": 0.65,
2911
+ "learning_rate": 4.553716957965021e-06,
2912
+ "loss": 0.544,
2913
+ "step": 484
2914
+ },
2915
+ {
2916
+ "epoch": 0.65,
2917
+ "learning_rate": 4.551640418212948e-06,
2918
+ "loss": 0.5549,
2919
+ "step": 485
2920
+ },
2921
+ {
2922
+ "epoch": 0.65,
2923
+ "learning_rate": 4.549559534402723e-06,
2924
+ "loss": 0.5328,
2925
+ "step": 486
2926
+ },
2927
+ {
2928
+ "epoch": 0.66,
2929
+ "learning_rate": 4.547474310940324e-06,
2930
+ "loss": 0.5771,
2931
+ "step": 487
2932
+ },
2933
+ {
2934
+ "epoch": 0.66,
2935
+ "learning_rate": 4.545384752240913e-06,
2936
+ "loss": 0.517,
2937
+ "step": 488
2938
+ },
2939
+ {
2940
+ "epoch": 0.66,
2941
+ "learning_rate": 4.543290862728838e-06,
2942
+ "loss": 0.6366,
2943
+ "step": 489
2944
+ },
2945
+ {
2946
+ "epoch": 0.66,
2947
+ "learning_rate": 4.541192646837613e-06,
2948
+ "loss": 0.6169,
2949
+ "step": 490
2950
+ },
2951
+ {
2952
+ "epoch": 0.66,
2953
+ "learning_rate": 4.539090109009912e-06,
2954
+ "loss": 0.5425,
2955
+ "step": 491
2956
+ },
2957
+ {
2958
+ "epoch": 0.66,
2959
+ "learning_rate": 4.536983253697561e-06,
2960
+ "loss": 0.61,
2961
+ "step": 492
2962
+ },
2963
+ {
2964
+ "epoch": 0.66,
2965
+ "learning_rate": 4.5348720853615304e-06,
2966
+ "loss": 0.6311,
2967
+ "step": 493
2968
+ },
2969
+ {
2970
+ "epoch": 0.67,
2971
+ "learning_rate": 4.532756608471917e-06,
2972
+ "loss": 0.5941,
2973
+ "step": 494
2974
+ },
2975
+ {
2976
+ "epoch": 0.67,
2977
+ "learning_rate": 4.530636827507946e-06,
2978
+ "loss": 0.4866,
2979
+ "step": 495
2980
+ },
2981
+ {
2982
+ "epoch": 0.67,
2983
+ "learning_rate": 4.528512746957953e-06,
2984
+ "loss": 0.5785,
2985
+ "step": 496
2986
+ },
2987
+ {
2988
+ "epoch": 0.67,
2989
+ "learning_rate": 4.526384371319377e-06,
2990
+ "loss": 0.5574,
2991
+ "step": 497
2992
+ },
2993
+ {
2994
+ "epoch": 0.67,
2995
+ "learning_rate": 4.524251705098752e-06,
2996
+ "loss": 0.5019,
2997
+ "step": 498
2998
+ },
2999
+ {
3000
+ "epoch": 0.67,
3001
+ "learning_rate": 4.5221147528116986e-06,
3002
+ "loss": 0.5514,
3003
+ "step": 499
3004
+ },
3005
+ {
3006
+ "epoch": 0.67,
3007
+ "learning_rate": 4.5199735189829095e-06,
3008
+ "loss": 0.5541,
3009
+ "step": 500
3010
+ },
3011
+ {
3012
+ "epoch": 0.68,
3013
+ "learning_rate": 4.517828008146145e-06,
3014
+ "loss": 0.5179,
3015
+ "step": 501
3016
+ },
3017
+ {
3018
+ "epoch": 0.68,
3019
+ "learning_rate": 4.515678224844219e-06,
3020
+ "loss": 0.5544,
3021
+ "step": 502
3022
+ },
3023
+ {
3024
+ "epoch": 0.68,
3025
+ "learning_rate": 4.513524173628994e-06,
3026
+ "loss": 0.5268,
3027
+ "step": 503
3028
+ },
3029
+ {
3030
+ "epoch": 0.68,
3031
+ "learning_rate": 4.51136585906137e-06,
3032
+ "loss": 0.5486,
3033
+ "step": 504
3034
+ },
3035
+ {
3036
+ "epoch": 0.68,
3037
+ "learning_rate": 4.50920328571127e-06,
3038
+ "loss": 0.599,
3039
+ "step": 505
3040
+ },
3041
+ {
3042
+ "epoch": 0.68,
3043
+ "learning_rate": 4.50703645815764e-06,
3044
+ "loss": 0.5492,
3045
+ "step": 506
3046
+ },
3047
+ {
3048
+ "epoch": 0.68,
3049
+ "learning_rate": 4.504865380988428e-06,
3050
+ "loss": 0.5157,
3051
+ "step": 507
3052
+ },
3053
+ {
3054
+ "epoch": 0.68,
3055
+ "learning_rate": 4.502690058800583e-06,
3056
+ "loss": 0.5522,
3057
+ "step": 508
3058
+ },
3059
+ {
3060
+ "epoch": 0.69,
3061
+ "learning_rate": 4.500510496200043e-06,
3062
+ "loss": 0.6046,
3063
+ "step": 509
3064
+ },
3065
+ {
3066
+ "epoch": 0.69,
3067
+ "learning_rate": 4.498326697801723e-06,
3068
+ "loss": 0.6006,
3069
+ "step": 510
3070
+ },
3071
+ {
3072
+ "epoch": 0.69,
3073
+ "learning_rate": 4.4961386682295045e-06,
3074
+ "loss": 0.5056,
3075
+ "step": 511
3076
+ },
3077
+ {
3078
+ "epoch": 0.69,
3079
+ "learning_rate": 4.493946412116235e-06,
3080
+ "loss": 0.5967,
3081
+ "step": 512
3082
+ },
3083
+ {
3084
+ "epoch": 0.69,
3085
+ "learning_rate": 4.491749934103702e-06,
3086
+ "loss": 0.5706,
3087
+ "step": 513
3088
+ },
3089
+ {
3090
+ "epoch": 0.69,
3091
+ "learning_rate": 4.4895492388426394e-06,
3092
+ "loss": 0.5597,
3093
+ "step": 514
3094
+ },
3095
+ {
3096
+ "epoch": 0.69,
3097
+ "learning_rate": 4.487344330992706e-06,
3098
+ "loss": 0.5553,
3099
+ "step": 515
3100
+ },
3101
+ {
3102
+ "epoch": 0.7,
3103
+ "learning_rate": 4.485135215222485e-06,
3104
+ "loss": 0.6106,
3105
+ "step": 516
3106
+ },
3107
+ {
3108
+ "epoch": 0.7,
3109
+ "learning_rate": 4.482921896209463e-06,
3110
+ "loss": 0.5479,
3111
+ "step": 517
3112
+ },
3113
+ {
3114
+ "epoch": 0.7,
3115
+ "learning_rate": 4.480704378640031e-06,
3116
+ "loss": 0.5321,
3117
+ "step": 518
3118
+ },
3119
+ {
3120
+ "epoch": 0.7,
3121
+ "learning_rate": 4.478482667209471e-06,
3122
+ "loss": 0.5633,
3123
+ "step": 519
3124
+ },
3125
+ {
3126
+ "epoch": 0.7,
3127
+ "learning_rate": 4.476256766621937e-06,
3128
+ "loss": 0.5842,
3129
+ "step": 520
3130
+ },
3131
+ {
3132
+ "epoch": 0.7,
3133
+ "learning_rate": 4.474026681590464e-06,
3134
+ "loss": 0.5064,
3135
+ "step": 521
3136
+ },
3137
+ {
3138
+ "epoch": 0.7,
3139
+ "learning_rate": 4.471792416836938e-06,
3140
+ "loss": 0.6332,
3141
+ "step": 522
3142
+ },
3143
+ {
3144
+ "epoch": 0.7,
3145
+ "learning_rate": 4.4695539770920985e-06,
3146
+ "loss": 0.5234,
3147
+ "step": 523
3148
+ },
3149
+ {
3150
+ "epoch": 0.71,
3151
+ "learning_rate": 4.467311367095526e-06,
3152
+ "loss": 0.5326,
3153
+ "step": 524
3154
+ },
3155
+ {
3156
+ "epoch": 0.71,
3157
+ "learning_rate": 4.465064591595629e-06,
3158
+ "loss": 0.614,
3159
+ "step": 525
3160
+ },
3161
+ {
3162
+ "epoch": 0.71,
3163
+ "learning_rate": 4.462813655349637e-06,
3164
+ "loss": 0.5514,
3165
+ "step": 526
3166
+ },
3167
+ {
3168
+ "epoch": 0.71,
3169
+ "learning_rate": 4.4605585631235896e-06,
3170
+ "loss": 0.5385,
3171
+ "step": 527
3172
+ },
3173
+ {
3174
+ "epoch": 0.71,
3175
+ "learning_rate": 4.458299319692323e-06,
3176
+ "loss": 0.586,
3177
+ "step": 528
3178
+ },
3179
+ {
3180
+ "epoch": 0.71,
3181
+ "learning_rate": 4.456035929839468e-06,
3182
+ "loss": 0.5621,
3183
+ "step": 529
3184
+ },
3185
+ {
3186
+ "epoch": 0.71,
3187
+ "learning_rate": 4.45376839835743e-06,
3188
+ "loss": 0.6015,
3189
+ "step": 530
3190
+ },
3191
+ {
3192
+ "epoch": 0.72,
3193
+ "learning_rate": 4.451496730047387e-06,
3194
+ "loss": 0.5595,
3195
+ "step": 531
3196
+ },
3197
+ {
3198
+ "epoch": 0.72,
3199
+ "learning_rate": 4.449220929719274e-06,
3200
+ "loss": 0.5407,
3201
+ "step": 532
3202
+ },
3203
+ {
3204
+ "epoch": 0.72,
3205
+ "learning_rate": 4.4469410021917784e-06,
3206
+ "loss": 0.4871,
3207
+ "step": 533
3208
+ },
3209
+ {
3210
+ "epoch": 0.72,
3211
+ "learning_rate": 4.444656952292321e-06,
3212
+ "loss": 0.5569,
3213
+ "step": 534
3214
+ },
3215
+ {
3216
+ "epoch": 0.72,
3217
+ "learning_rate": 4.442368784857057e-06,
3218
+ "loss": 0.668,
3219
+ "step": 535
3220
+ },
3221
+ {
3222
+ "epoch": 0.72,
3223
+ "learning_rate": 4.440076504730855e-06,
3224
+ "loss": 0.5083,
3225
+ "step": 536
3226
+ },
3227
+ {
3228
+ "epoch": 0.72,
3229
+ "learning_rate": 4.4377801167672945e-06,
3230
+ "loss": 0.5741,
3231
+ "step": 537
3232
+ },
3233
+ {
3234
+ "epoch": 0.73,
3235
+ "learning_rate": 4.435479625828652e-06,
3236
+ "loss": 0.5866,
3237
+ "step": 538
3238
+ },
3239
+ {
3240
+ "epoch": 0.73,
3241
+ "learning_rate": 4.4331750367858906e-06,
3242
+ "loss": 0.5299,
3243
+ "step": 539
3244
+ },
3245
+ {
3246
+ "epoch": 0.73,
3247
+ "learning_rate": 4.430866354518653e-06,
3248
+ "loss": 0.525,
3249
+ "step": 540
3250
+ },
3251
+ {
3252
+ "epoch": 0.73,
3253
+ "learning_rate": 4.428553583915245e-06,
3254
+ "loss": 0.5077,
3255
+ "step": 541
3256
+ },
3257
+ {
3258
+ "epoch": 0.73,
3259
+ "learning_rate": 4.426236729872633e-06,
3260
+ "loss": 0.5841,
3261
+ "step": 542
3262
+ },
3263
+ {
3264
+ "epoch": 0.73,
3265
+ "learning_rate": 4.423915797296426e-06,
3266
+ "loss": 0.5103,
3267
+ "step": 543
3268
+ },
3269
+ {
3270
+ "epoch": 0.73,
3271
+ "learning_rate": 4.421590791100869e-06,
3272
+ "loss": 0.55,
3273
+ "step": 544
3274
+ },
3275
+ {
3276
+ "epoch": 0.73,
3277
+ "learning_rate": 4.419261716208837e-06,
3278
+ "loss": 0.5814,
3279
+ "step": 545
3280
+ },
3281
+ {
3282
+ "epoch": 0.74,
3283
+ "learning_rate": 4.416928577551813e-06,
3284
+ "loss": 0.6587,
3285
+ "step": 546
3286
+ },
3287
+ {
3288
+ "epoch": 0.74,
3289
+ "learning_rate": 4.414591380069892e-06,
3290
+ "loss": 0.6303,
3291
+ "step": 547
3292
+ },
3293
+ {
3294
+ "epoch": 0.74,
3295
+ "learning_rate": 4.412250128711754e-06,
3296
+ "loss": 0.5439,
3297
+ "step": 548
3298
+ },
3299
+ {
3300
+ "epoch": 0.74,
3301
+ "learning_rate": 4.409904828434669e-06,
3302
+ "loss": 0.5464,
3303
+ "step": 549
3304
+ },
3305
+ {
3306
+ "epoch": 0.74,
3307
+ "learning_rate": 4.4075554842044795e-06,
3308
+ "loss": 0.5362,
3309
+ "step": 550
3310
+ },
3311
+ {
3312
+ "epoch": 0.74,
3313
+ "learning_rate": 4.405202100995588e-06,
3314
+ "loss": 0.592,
3315
+ "step": 551
3316
+ },
3317
+ {
3318
+ "epoch": 0.74,
3319
+ "learning_rate": 4.402844683790953e-06,
3320
+ "loss": 0.5624,
3321
+ "step": 552
3322
+ },
3323
+ {
3324
+ "epoch": 0.75,
3325
+ "learning_rate": 4.400483237582067e-06,
3326
+ "loss": 0.5854,
3327
+ "step": 553
3328
+ },
3329
+ {
3330
+ "epoch": 0.75,
3331
+ "learning_rate": 4.3981177673689625e-06,
3332
+ "loss": 0.5768,
3333
+ "step": 554
3334
+ },
3335
+ {
3336
+ "epoch": 0.75,
3337
+ "learning_rate": 4.395748278160184e-06,
3338
+ "loss": 0.5695,
3339
+ "step": 555
3340
+ },
3341
+ {
3342
+ "epoch": 0.75,
3343
+ "learning_rate": 4.393374774972793e-06,
3344
+ "loss": 0.5952,
3345
+ "step": 556
3346
+ },
3347
+ {
3348
+ "epoch": 0.75,
3349
+ "learning_rate": 4.390997262832345e-06,
3350
+ "loss": 0.6261,
3351
+ "step": 557
3352
+ },
3353
+ {
3354
+ "epoch": 0.75,
3355
+ "learning_rate": 4.3886157467728845e-06,
3356
+ "loss": 0.6034,
3357
+ "step": 558
3358
+ },
3359
+ {
3360
+ "epoch": 0.75,
3361
+ "learning_rate": 4.386230231836936e-06,
3362
+ "loss": 0.5326,
3363
+ "step": 559
3364
+ },
3365
+ {
3366
+ "epoch": 0.75,
3367
+ "learning_rate": 4.383840723075488e-06,
3368
+ "loss": 0.5507,
3369
+ "step": 560
3370
+ },
3371
+ {
3372
+ "epoch": 0.76,
3373
+ "learning_rate": 4.38144722554799e-06,
3374
+ "loss": 0.5612,
3375
+ "step": 561
3376
+ },
3377
+ {
3378
+ "epoch": 0.76,
3379
+ "learning_rate": 4.3790497443223316e-06,
3380
+ "loss": 0.5735,
3381
+ "step": 562
3382
+ },
3383
+ {
3384
+ "epoch": 0.76,
3385
+ "learning_rate": 4.376648284474841e-06,
3386
+ "loss": 0.5491,
3387
+ "step": 563
3388
+ },
3389
+ {
3390
+ "epoch": 0.76,
3391
+ "learning_rate": 4.374242851090269e-06,
3392
+ "loss": 0.5162,
3393
+ "step": 564
3394
+ },
3395
+ {
3396
+ "epoch": 0.76,
3397
+ "learning_rate": 4.37183344926178e-06,
3398
+ "loss": 0.5451,
3399
+ "step": 565
3400
+ },
3401
+ {
3402
+ "epoch": 0.76,
3403
+ "learning_rate": 4.369420084090942e-06,
3404
+ "loss": 0.6291,
3405
+ "step": 566
3406
+ },
3407
+ {
3408
+ "epoch": 0.76,
3409
+ "learning_rate": 4.367002760687713e-06,
3410
+ "loss": 0.5922,
3411
+ "step": 567
3412
+ },
3413
+ {
3414
+ "epoch": 0.77,
3415
+ "learning_rate": 4.364581484170435e-06,
3416
+ "loss": 0.6281,
3417
+ "step": 568
3418
+ },
3419
+ {
3420
+ "epoch": 0.77,
3421
+ "learning_rate": 4.362156259665817e-06,
3422
+ "loss": 0.6049,
3423
+ "step": 569
3424
+ },
3425
+ {
3426
+ "epoch": 0.77,
3427
+ "learning_rate": 4.3597270923089286e-06,
3428
+ "loss": 0.4983,
3429
+ "step": 570
3430
+ },
3431
+ {
3432
+ "epoch": 0.77,
3433
+ "learning_rate": 4.357293987243188e-06,
3434
+ "loss": 0.6074,
3435
+ "step": 571
3436
+ },
3437
+ {
3438
+ "epoch": 0.77,
3439
+ "learning_rate": 4.354856949620351e-06,
3440
+ "loss": 0.5515,
3441
+ "step": 572
3442
+ },
3443
+ {
3444
+ "epoch": 0.77,
3445
+ "learning_rate": 4.3524159846004985e-06,
3446
+ "loss": 0.5663,
3447
+ "step": 573
3448
+ },
3449
+ {
3450
+ "epoch": 0.77,
3451
+ "learning_rate": 4.349971097352031e-06,
3452
+ "loss": 0.5298,
3453
+ "step": 574
3454
+ },
3455
+ {
3456
+ "epoch": 0.77,
3457
+ "learning_rate": 4.3475222930516484e-06,
3458
+ "loss": 0.5779,
3459
+ "step": 575
3460
+ },
3461
+ {
3462
+ "epoch": 0.78,
3463
+ "learning_rate": 4.345069576884348e-06,
3464
+ "loss": 0.6118,
3465
+ "step": 576
3466
+ },
3467
+ {
3468
+ "epoch": 0.78,
3469
+ "learning_rate": 4.34261295404341e-06,
3470
+ "loss": 0.5585,
3471
+ "step": 577
3472
+ },
3473
+ {
3474
+ "epoch": 0.78,
3475
+ "learning_rate": 4.340152429730384e-06,
3476
+ "loss": 0.6217,
3477
+ "step": 578
3478
+ },
3479
+ {
3480
+ "epoch": 0.78,
3481
+ "learning_rate": 4.337688009155084e-06,
3482
+ "loss": 0.5257,
3483
+ "step": 579
3484
+ },
3485
+ {
3486
+ "epoch": 0.78,
3487
+ "learning_rate": 4.33521969753557e-06,
3488
+ "loss": 0.5539,
3489
+ "step": 580
3490
+ },
3491
+ {
3492
+ "epoch": 0.78,
3493
+ "learning_rate": 4.332747500098143e-06,
3494
+ "loss": 0.5334,
3495
+ "step": 581
3496
+ },
3497
+ {
3498
+ "epoch": 0.78,
3499
+ "learning_rate": 4.3302714220773305e-06,
3500
+ "loss": 0.5239,
3501
+ "step": 582
3502
+ },
3503
+ {
3504
+ "epoch": 0.79,
3505
+ "learning_rate": 4.327791468715878e-06,
3506
+ "loss": 0.6228,
3507
+ "step": 583
3508
+ },
3509
+ {
3510
+ "epoch": 0.79,
3511
+ "learning_rate": 4.3253076452647355e-06,
3512
+ "loss": 0.5515,
3513
+ "step": 584
3514
+ },
3515
+ {
3516
+ "epoch": 0.79,
3517
+ "learning_rate": 4.322819956983047e-06,
3518
+ "loss": 0.5151,
3519
+ "step": 585
3520
+ },
3521
+ {
3522
+ "epoch": 0.79,
3523
+ "learning_rate": 4.320328409138141e-06,
3524
+ "loss": 0.5831,
3525
+ "step": 586
3526
+ },
3527
+ {
3528
+ "epoch": 0.79,
3529
+ "learning_rate": 4.317833007005517e-06,
3530
+ "loss": 0.5766,
3531
+ "step": 587
3532
+ },
3533
+ {
3534
+ "epoch": 0.79,
3535
+ "learning_rate": 4.315333755868836e-06,
3536
+ "loss": 0.5509,
3537
+ "step": 588
3538
+ },
3539
+ {
3540
+ "epoch": 0.79,
3541
+ "learning_rate": 4.3128306610199076e-06,
3542
+ "loss": 0.617,
3543
+ "step": 589
3544
+ },
3545
+ {
3546
+ "epoch": 0.8,
3547
+ "learning_rate": 4.310323727758682e-06,
3548
+ "loss": 0.521,
3549
+ "step": 590
3550
+ },
3551
+ {
3552
+ "epoch": 0.8,
3553
+ "learning_rate": 4.3078129613932354e-06,
3554
+ "loss": 0.5317,
3555
+ "step": 591
3556
+ },
3557
+ {
3558
+ "epoch": 0.8,
3559
+ "learning_rate": 4.305298367239758e-06,
3560
+ "loss": 0.5576,
3561
+ "step": 592
3562
+ },
3563
+ {
3564
+ "epoch": 0.8,
3565
+ "learning_rate": 4.302779950622551e-06,
3566
+ "loss": 0.579,
3567
+ "step": 593
3568
+ },
3569
+ {
3570
+ "epoch": 0.8,
3571
+ "learning_rate": 4.300257716874001e-06,
3572
+ "loss": 0.5904,
3573
+ "step": 594
3574
+ },
3575
+ {
3576
+ "epoch": 0.8,
3577
+ "learning_rate": 4.297731671334584e-06,
3578
+ "loss": 0.5276,
3579
+ "step": 595
3580
+ },
3581
+ {
3582
+ "epoch": 0.8,
3583
+ "learning_rate": 4.2952018193528425e-06,
3584
+ "loss": 0.5281,
3585
+ "step": 596
3586
+ },
3587
+ {
3588
+ "epoch": 0.8,
3589
+ "learning_rate": 4.2926681662853785e-06,
3590
+ "loss": 0.5217,
3591
+ "step": 597
3592
+ },
3593
+ {
3594
+ "epoch": 0.81,
3595
+ "learning_rate": 4.290130717496847e-06,
3596
+ "loss": 0.5252,
3597
+ "step": 598
3598
+ },
3599
+ {
3600
+ "epoch": 0.81,
3601
+ "learning_rate": 4.2875894783599335e-06,
3602
+ "loss": 0.522,
3603
+ "step": 599
3604
+ },
3605
+ {
3606
+ "epoch": 0.81,
3607
+ "learning_rate": 4.2850444542553535e-06,
3608
+ "loss": 0.5978,
3609
+ "step": 600
3610
+ },
3611
+ {
3612
+ "epoch": 0.81,
3613
+ "learning_rate": 4.2824956505718355e-06,
3614
+ "loss": 0.5406,
3615
+ "step": 601
3616
+ },
3617
+ {
3618
+ "epoch": 0.81,
3619
+ "learning_rate": 4.279943072706109e-06,
3620
+ "loss": 0.6198,
3621
+ "step": 602
3622
+ },
3623
+ {
3624
+ "epoch": 0.81,
3625
+ "learning_rate": 4.2773867260629e-06,
3626
+ "loss": 0.5042,
3627
+ "step": 603
3628
+ },
3629
+ {
3630
+ "epoch": 0.81,
3631
+ "learning_rate": 4.274826616054906e-06,
3632
+ "loss": 0.5485,
3633
+ "step": 604
3634
+ },
3635
+ {
3636
+ "epoch": 0.82,
3637
+ "learning_rate": 4.2722627481028e-06,
3638
+ "loss": 0.5828,
3639
+ "step": 605
3640
+ },
3641
+ {
3642
+ "epoch": 0.82,
3643
+ "learning_rate": 4.269695127635209e-06,
3644
+ "loss": 0.5614,
3645
+ "step": 606
3646
+ },
3647
+ {
3648
+ "epoch": 0.82,
3649
+ "learning_rate": 4.267123760088706e-06,
3650
+ "loss": 0.6055,
3651
+ "step": 607
3652
+ },
3653
+ {
3654
+ "epoch": 0.82,
3655
+ "learning_rate": 4.264548650907798e-06,
3656
+ "loss": 0.5284,
3657
+ "step": 608
3658
+ },
3659
+ {
3660
+ "epoch": 0.82,
3661
+ "learning_rate": 4.261969805544914e-06,
3662
+ "loss": 0.5217,
3663
+ "step": 609
3664
+ },
3665
+ {
3666
+ "epoch": 0.82,
3667
+ "learning_rate": 4.259387229460393e-06,
3668
+ "loss": 0.5893,
3669
+ "step": 610
3670
+ },
3671
+ {
3672
+ "epoch": 0.82,
3673
+ "learning_rate": 4.2568009281224755e-06,
3674
+ "loss": 0.5702,
3675
+ "step": 611
3676
+ },
3677
+ {
3678
+ "epoch": 0.82,
3679
+ "learning_rate": 4.2542109070072884e-06,
3680
+ "loss": 0.5206,
3681
+ "step": 612
3682
+ },
3683
+ {
3684
+ "epoch": 0.83,
3685
+ "learning_rate": 4.251617171598834e-06,
3686
+ "loss": 0.486,
3687
+ "step": 613
3688
+ },
3689
+ {
3690
+ "epoch": 0.83,
3691
+ "learning_rate": 4.24901972738898e-06,
3692
+ "loss": 0.5843,
3693
+ "step": 614
3694
+ },
3695
+ {
3696
+ "epoch": 0.83,
3697
+ "learning_rate": 4.2464185798774485e-06,
3698
+ "loss": 0.5801,
3699
+ "step": 615
3700
+ },
3701
+ {
3702
+ "epoch": 0.83,
3703
+ "learning_rate": 4.243813734571798e-06,
3704
+ "loss": 0.5293,
3705
+ "step": 616
3706
+ },
3707
+ {
3708
+ "epoch": 0.83,
3709
+ "learning_rate": 4.241205196987422e-06,
3710
+ "loss": 0.5644,
3711
+ "step": 617
3712
+ },
3713
+ {
3714
+ "epoch": 0.83,
3715
+ "learning_rate": 4.2385929726475295e-06,
3716
+ "loss": 0.6096,
3717
+ "step": 618
3718
+ },
3719
+ {
3720
+ "epoch": 0.83,
3721
+ "learning_rate": 4.235977067083134e-06,
3722
+ "loss": 0.5863,
3723
+ "step": 619
3724
+ },
3725
+ {
3726
+ "epoch": 0.84,
3727
+ "learning_rate": 4.233357485833048e-06,
3728
+ "loss": 0.5464,
3729
+ "step": 620
3730
+ },
3731
+ {
3732
+ "epoch": 0.84,
3733
+ "learning_rate": 4.230734234443861e-06,
3734
+ "loss": 0.5871,
3735
+ "step": 621
3736
+ },
3737
+ {
3738
+ "epoch": 0.84,
3739
+ "learning_rate": 4.228107318469938e-06,
3740
+ "loss": 0.5036,
3741
+ "step": 622
3742
+ },
3743
+ {
3744
+ "epoch": 0.84,
3745
+ "learning_rate": 4.225476743473403e-06,
3746
+ "loss": 0.5659,
3747
+ "step": 623
3748
+ },
3749
+ {
3750
+ "epoch": 0.84,
3751
+ "learning_rate": 4.222842515024123e-06,
3752
+ "loss": 0.6611,
3753
+ "step": 624
3754
+ },
3755
+ {
3756
+ "epoch": 0.84,
3757
+ "learning_rate": 4.220204638699707e-06,
3758
+ "loss": 0.5194,
3759
+ "step": 625
3760
+ },
3761
+ {
3762
+ "epoch": 0.84,
3763
+ "learning_rate": 4.217563120085483e-06,
3764
+ "loss": 0.5512,
3765
+ "step": 626
3766
+ },
3767
+ {
3768
+ "epoch": 0.85,
3769
+ "learning_rate": 4.214917964774493e-06,
3770
+ "loss": 0.6293,
3771
+ "step": 627
3772
+ },
3773
+ {
3774
+ "epoch": 0.85,
3775
+ "learning_rate": 4.2122691783674786e-06,
3776
+ "loss": 0.6099,
3777
+ "step": 628
3778
+ },
3779
+ {
3780
+ "epoch": 0.85,
3781
+ "learning_rate": 4.209616766472869e-06,
3782
+ "loss": 0.5465,
3783
+ "step": 629
3784
+ },
3785
+ {
3786
+ "epoch": 0.85,
3787
+ "learning_rate": 4.206960734706774e-06,
3788
+ "loss": 0.5462,
3789
+ "step": 630
3790
+ },
3791
+ {
3792
+ "epoch": 0.85,
3793
+ "learning_rate": 4.204301088692964e-06,
3794
+ "loss": 0.5083,
3795
+ "step": 631
3796
+ },
3797
+ {
3798
+ "epoch": 0.85,
3799
+ "learning_rate": 4.20163783406286e-06,
3800
+ "loss": 0.5827,
3801
+ "step": 632
3802
+ },
3803
+ {
3804
+ "epoch": 0.85,
3805
+ "learning_rate": 4.19897097645553e-06,
3806
+ "loss": 0.5706,
3807
+ "step": 633
3808
+ },
3809
+ {
3810
+ "epoch": 0.85,
3811
+ "learning_rate": 4.1963005215176655e-06,
3812
+ "loss": 0.5946,
3813
+ "step": 634
3814
+ },
3815
+ {
3816
+ "epoch": 0.86,
3817
+ "learning_rate": 4.193626474903578e-06,
3818
+ "loss": 0.5746,
3819
+ "step": 635
3820
+ },
3821
+ {
3822
+ "epoch": 0.86,
3823
+ "learning_rate": 4.190948842275182e-06,
3824
+ "loss": 0.6247,
3825
+ "step": 636
3826
+ },
3827
+ {
3828
+ "epoch": 0.86,
3829
+ "learning_rate": 4.188267629301986e-06,
3830
+ "loss": 0.6076,
3831
+ "step": 637
3832
+ },
3833
+ {
3834
+ "epoch": 0.86,
3835
+ "learning_rate": 4.185582841661079e-06,
3836
+ "loss": 0.528,
3837
+ "step": 638
3838
+ },
3839
+ {
3840
+ "epoch": 0.86,
3841
+ "learning_rate": 4.182894485037117e-06,
3842
+ "loss": 0.5771,
3843
+ "step": 639
3844
+ },
3845
+ {
3846
+ "epoch": 0.86,
3847
+ "learning_rate": 4.180202565122318e-06,
3848
+ "loss": 0.4491,
3849
+ "step": 640
3850
+ },
3851
+ {
3852
+ "epoch": 0.86,
3853
+ "learning_rate": 4.177507087616438e-06,
3854
+ "loss": 0.5962,
3855
+ "step": 641
3856
+ },
3857
+ {
3858
+ "epoch": 0.87,
3859
+ "learning_rate": 4.174808058226771e-06,
3860
+ "loss": 0.5363,
3861
+ "step": 642
3862
+ },
3863
+ {
3864
+ "epoch": 0.87,
3865
+ "learning_rate": 4.172105482668127e-06,
3866
+ "loss": 0.5633,
3867
+ "step": 643
3868
+ },
3869
+ {
3870
+ "epoch": 0.87,
3871
+ "learning_rate": 4.169399366662831e-06,
3872
+ "loss": 0.5211,
3873
+ "step": 644
3874
+ },
3875
+ {
3876
+ "epoch": 0.87,
3877
+ "learning_rate": 4.166689715940699e-06,
3878
+ "loss": 0.5,
3879
+ "step": 645
3880
+ },
3881
+ {
3882
+ "epoch": 0.87,
3883
+ "learning_rate": 4.163976536239032e-06,
3884
+ "loss": 0.5578,
3885
+ "step": 646
3886
+ },
3887
+ {
3888
+ "epoch": 0.87,
3889
+ "learning_rate": 4.161259833302605e-06,
3890
+ "loss": 0.5856,
3891
+ "step": 647
3892
+ },
3893
+ {
3894
+ "epoch": 0.87,
3895
+ "learning_rate": 4.15853961288365e-06,
3896
+ "loss": 0.5503,
3897
+ "step": 648
3898
+ },
3899
+ {
3900
+ "epoch": 0.87,
3901
+ "learning_rate": 4.155815880741851e-06,
3902
+ "loss": 0.5569,
3903
+ "step": 649
3904
+ },
3905
+ {
3906
+ "epoch": 0.88,
3907
+ "learning_rate": 4.153088642644325e-06,
3908
+ "loss": 0.5067,
3909
+ "step": 650
3910
+ },
3911
+ {
3912
+ "epoch": 0.88,
3913
+ "learning_rate": 4.150357904365611e-06,
3914
+ "loss": 0.5913,
3915
+ "step": 651
3916
+ },
3917
+ {
3918
+ "epoch": 0.88,
3919
+ "learning_rate": 4.147623671687662e-06,
3920
+ "loss": 0.7278,
3921
+ "step": 652
3922
+ },
3923
+ {
3924
+ "epoch": 0.88,
3925
+ "learning_rate": 4.1448859503998275e-06,
3926
+ "loss": 0.5854,
3927
+ "step": 653
3928
+ },
3929
+ {
3930
+ "epoch": 0.88,
3931
+ "learning_rate": 4.142144746298846e-06,
3932
+ "loss": 0.5993,
3933
+ "step": 654
3934
+ },
3935
+ {
3936
+ "epoch": 0.88,
3937
+ "learning_rate": 4.1394000651888285e-06,
3938
+ "loss": 0.5394,
3939
+ "step": 655
3940
+ },
3941
+ {
3942
+ "epoch": 0.88,
3943
+ "learning_rate": 4.13665191288125e-06,
3944
+ "loss": 0.6006,
3945
+ "step": 656
3946
+ },
3947
+ {
3948
+ "epoch": 0.89,
3949
+ "learning_rate": 4.133900295194931e-06,
3950
+ "loss": 0.6133,
3951
+ "step": 657
3952
+ },
3953
+ {
3954
+ "epoch": 0.89,
3955
+ "learning_rate": 4.131145217956036e-06,
3956
+ "loss": 0.5946,
3957
+ "step": 658
3958
+ },
3959
+ {
3960
+ "epoch": 0.89,
3961
+ "learning_rate": 4.128386686998048e-06,
3962
+ "loss": 0.5552,
3963
+ "step": 659
3964
+ },
3965
+ {
3966
+ "epoch": 0.89,
3967
+ "learning_rate": 4.125624708161768e-06,
3968
+ "loss": 0.5654,
3969
+ "step": 660
3970
+ },
3971
+ {
3972
+ "epoch": 0.89,
3973
+ "learning_rate": 4.122859287295294e-06,
3974
+ "loss": 0.568,
3975
+ "step": 661
3976
+ },
3977
+ {
3978
+ "epoch": 0.89,
3979
+ "learning_rate": 4.120090430254013e-06,
3980
+ "loss": 0.568,
3981
+ "step": 662
3982
+ },
3983
+ {
3984
+ "epoch": 0.89,
3985
+ "learning_rate": 4.1173181429005895e-06,
3986
+ "loss": 0.5896,
3987
+ "step": 663
3988
+ },
3989
+ {
3990
+ "epoch": 0.89,
3991
+ "learning_rate": 4.114542431104948e-06,
3992
+ "loss": 0.6089,
3993
+ "step": 664
3994
+ },
3995
+ {
3996
+ "epoch": 0.9,
3997
+ "learning_rate": 4.111763300744265e-06,
3998
+ "loss": 0.5207,
3999
+ "step": 665
4000
+ },
4001
+ {
4002
+ "epoch": 0.9,
4003
+ "learning_rate": 4.108980757702956e-06,
4004
+ "loss": 0.5555,
4005
+ "step": 666
4006
+ },
4007
+ {
4008
+ "epoch": 0.9,
4009
+ "learning_rate": 4.106194807872663e-06,
4010
+ "loss": 0.6308,
4011
+ "step": 667
4012
+ },
4013
+ {
4014
+ "epoch": 0.9,
4015
+ "learning_rate": 4.10340545715224e-06,
4016
+ "loss": 0.6148,
4017
+ "step": 668
4018
+ },
4019
+ {
4020
+ "epoch": 0.9,
4021
+ "learning_rate": 4.100612711447741e-06,
4022
+ "loss": 0.5744,
4023
+ "step": 669
4024
+ },
4025
+ {
4026
+ "epoch": 0.9,
4027
+ "learning_rate": 4.097816576672412e-06,
4028
+ "loss": 0.5493,
4029
+ "step": 670
4030
+ },
4031
+ {
4032
+ "epoch": 0.9,
4033
+ "learning_rate": 4.09501705874667e-06,
4034
+ "loss": 0.5823,
4035
+ "step": 671
4036
+ },
4037
+ {
4038
+ "epoch": 0.91,
4039
+ "learning_rate": 4.0922141635981e-06,
4040
+ "loss": 0.5568,
4041
+ "step": 672
4042
+ },
4043
+ {
4044
+ "epoch": 0.91,
4045
+ "learning_rate": 4.089407897161434e-06,
4046
+ "loss": 0.5935,
4047
+ "step": 673
4048
+ },
4049
+ {
4050
+ "epoch": 0.91,
4051
+ "learning_rate": 4.086598265378545e-06,
4052
+ "loss": 0.5386,
4053
+ "step": 674
4054
+ },
4055
+ {
4056
+ "epoch": 0.91,
4057
+ "learning_rate": 4.0837852741984305e-06,
4058
+ "loss": 0.5596,
4059
+ "step": 675
4060
+ },
4061
+ {
4062
+ "epoch": 0.91,
4063
+ "learning_rate": 4.0809689295772e-06,
4064
+ "loss": 0.5187,
4065
+ "step": 676
4066
+ },
4067
+ {
4068
+ "epoch": 0.91,
4069
+ "learning_rate": 4.078149237478066e-06,
4070
+ "loss": 0.5811,
4071
+ "step": 677
4072
+ },
4073
+ {
4074
+ "epoch": 0.91,
4075
+ "learning_rate": 4.075326203871327e-06,
4076
+ "loss": 0.5738,
4077
+ "step": 678
4078
+ },
4079
+ {
4080
+ "epoch": 0.92,
4081
+ "learning_rate": 4.072499834734357e-06,
4082
+ "loss": 0.5527,
4083
+ "step": 679
4084
+ },
4085
+ {
4086
+ "epoch": 0.92,
4087
+ "learning_rate": 4.069670136051591e-06,
4088
+ "loss": 0.5897,
4089
+ "step": 680
4090
+ },
4091
+ {
4092
+ "epoch": 0.92,
4093
+ "learning_rate": 4.066837113814518e-06,
4094
+ "loss": 0.5307,
4095
+ "step": 681
4096
+ },
4097
+ {
4098
+ "epoch": 0.92,
4099
+ "learning_rate": 4.06400077402166e-06,
4100
+ "loss": 0.5536,
4101
+ "step": 682
4102
+ },
4103
+ {
4104
+ "epoch": 0.92,
4105
+ "learning_rate": 4.061161122678566e-06,
4106
+ "loss": 0.606,
4107
+ "step": 683
4108
+ },
4109
+ {
4110
+ "epoch": 0.92,
4111
+ "learning_rate": 4.058318165797794e-06,
4112
+ "loss": 0.5559,
4113
+ "step": 684
4114
+ },
4115
+ {
4116
+ "epoch": 0.92,
4117
+ "learning_rate": 4.055471909398904e-06,
4118
+ "loss": 0.6132,
4119
+ "step": 685
4120
+ },
4121
+ {
4122
+ "epoch": 0.92,
4123
+ "learning_rate": 4.052622359508441e-06,
4124
+ "loss": 0.5803,
4125
+ "step": 686
4126
+ },
4127
+ {
4128
+ "epoch": 0.93,
4129
+ "learning_rate": 4.049769522159923e-06,
4130
+ "loss": 0.5899,
4131
+ "step": 687
4132
+ },
4133
+ {
4134
+ "epoch": 0.93,
4135
+ "learning_rate": 4.04691340339383e-06,
4136
+ "loss": 0.5873,
4137
+ "step": 688
4138
+ },
4139
+ {
4140
+ "epoch": 0.93,
4141
+ "learning_rate": 4.044054009257588e-06,
4142
+ "loss": 0.6187,
4143
+ "step": 689
4144
+ },
4145
+ {
4146
+ "epoch": 0.93,
4147
+ "learning_rate": 4.04119134580556e-06,
4148
+ "loss": 0.5386,
4149
+ "step": 690
4150
+ },
4151
+ {
4152
+ "epoch": 0.93,
4153
+ "learning_rate": 4.038325419099032e-06,
4154
+ "loss": 0.6336,
4155
+ "step": 691
4156
+ },
4157
+ {
4158
+ "epoch": 0.93,
4159
+ "learning_rate": 4.035456235206195e-06,
4160
+ "loss": 0.4896,
4161
+ "step": 692
4162
+ },
4163
+ {
4164
+ "epoch": 0.93,
4165
+ "learning_rate": 4.0325838002021425e-06,
4166
+ "loss": 0.6069,
4167
+ "step": 693
4168
+ },
4169
+ {
4170
+ "epoch": 0.94,
4171
+ "learning_rate": 4.029708120168847e-06,
4172
+ "loss": 0.6055,
4173
+ "step": 694
4174
+ },
4175
+ {
4176
+ "epoch": 0.94,
4177
+ "learning_rate": 4.026829201195155e-06,
4178
+ "loss": 0.5544,
4179
+ "step": 695
4180
+ },
4181
+ {
4182
+ "epoch": 0.94,
4183
+ "learning_rate": 4.02394704937677e-06,
4184
+ "loss": 0.5978,
4185
+ "step": 696
4186
+ },
4187
+ {
4188
+ "epoch": 0.94,
4189
+ "learning_rate": 4.0210616708162395e-06,
4190
+ "loss": 0.5601,
4191
+ "step": 697
4192
+ },
4193
+ {
4194
+ "epoch": 0.94,
4195
+ "learning_rate": 4.018173071622946e-06,
4196
+ "loss": 0.5842,
4197
+ "step": 698
4198
+ },
4199
+ {
4200
+ "epoch": 0.94,
4201
+ "learning_rate": 4.0152812579130875e-06,
4202
+ "loss": 0.5686,
4203
+ "step": 699
4204
+ },
4205
+ {
4206
+ "epoch": 0.94,
4207
+ "learning_rate": 4.012386235809671e-06,
4208
+ "loss": 0.5164,
4209
+ "step": 700
4210
+ },
4211
+ {
4212
+ "epoch": 0.94,
4213
+ "learning_rate": 4.009488011442495e-06,
4214
+ "loss": 0.4864,
4215
+ "step": 701
4216
+ },
4217
+ {
4218
+ "epoch": 0.95,
4219
+ "learning_rate": 4.006586590948141e-06,
4220
+ "loss": 0.5935,
4221
+ "step": 702
4222
+ },
4223
+ {
4224
+ "epoch": 0.95,
4225
+ "learning_rate": 4.003681980469956e-06,
4226
+ "loss": 0.5334,
4227
+ "step": 703
4228
+ },
4229
+ {
4230
+ "epoch": 0.95,
4231
+ "learning_rate": 4.0007741861580395e-06,
4232
+ "loss": 0.5446,
4233
+ "step": 704
4234
+ },
4235
+ {
4236
+ "epoch": 0.95,
4237
+ "learning_rate": 3.9978632141692355e-06,
4238
+ "loss": 0.518,
4239
+ "step": 705
4240
+ },
4241
+ {
4242
+ "epoch": 0.95,
4243
+ "learning_rate": 3.994949070667116e-06,
4244
+ "loss": 0.5973,
4245
+ "step": 706
4246
+ },
4247
+ {
4248
+ "epoch": 0.95,
4249
+ "learning_rate": 3.992031761821967e-06,
4250
+ "loss": 0.5407,
4251
+ "step": 707
4252
+ },
4253
+ {
4254
+ "epoch": 0.95,
4255
+ "learning_rate": 3.9891112938107755e-06,
4256
+ "loss": 0.5739,
4257
+ "step": 708
4258
+ },
4259
+ {
4260
+ "epoch": 0.96,
4261
+ "learning_rate": 3.98618767281722e-06,
4262
+ "loss": 0.5854,
4263
+ "step": 709
4264
+ },
4265
+ {
4266
+ "epoch": 0.96,
4267
+ "learning_rate": 3.983260905031656e-06,
4268
+ "loss": 0.6069,
4269
+ "step": 710
4270
+ },
4271
+ {
4272
+ "epoch": 0.96,
4273
+ "learning_rate": 3.980330996651097e-06,
4274
+ "loss": 0.6012,
4275
+ "step": 711
4276
+ },
4277
+ {
4278
+ "epoch": 0.96,
4279
+ "learning_rate": 3.977397953879211e-06,
4280
+ "loss": 0.5287,
4281
+ "step": 712
4282
+ },
4283
+ {
4284
+ "epoch": 0.96,
4285
+ "learning_rate": 3.974461782926299e-06,
4286
+ "loss": 0.5626,
4287
+ "step": 713
4288
+ },
4289
+ {
4290
+ "epoch": 0.96,
4291
+ "learning_rate": 3.9715224900092895e-06,
4292
+ "loss": 0.5879,
4293
+ "step": 714
4294
+ },
4295
+ {
4296
+ "epoch": 0.96,
4297
+ "learning_rate": 3.968580081351718e-06,
4298
+ "loss": 0.5241,
4299
+ "step": 715
4300
+ },
4301
+ {
4302
+ "epoch": 0.96,
4303
+ "learning_rate": 3.96563456318372e-06,
4304
+ "loss": 0.6111,
4305
+ "step": 716
4306
+ },
4307
+ {
4308
+ "epoch": 0.97,
4309
+ "learning_rate": 3.96268594174201e-06,
4310
+ "loss": 0.5267,
4311
+ "step": 717
4312
+ },
4313
+ {
4314
+ "epoch": 0.97,
4315
+ "learning_rate": 3.959734223269879e-06,
4316
+ "loss": 0.553,
4317
+ "step": 718
4318
+ },
4319
+ {
4320
+ "epoch": 0.97,
4321
+ "learning_rate": 3.956779414017173e-06,
4322
+ "loss": 0.5159,
4323
+ "step": 719
4324
+ },
4325
+ {
4326
+ "epoch": 0.97,
4327
+ "learning_rate": 3.953821520240281e-06,
4328
+ "loss": 0.4857,
4329
+ "step": 720
4330
+ },
4331
+ {
4332
+ "epoch": 0.97,
4333
+ "learning_rate": 3.950860548202125e-06,
4334
+ "loss": 0.5817,
4335
+ "step": 721
4336
+ },
4337
+ {
4338
+ "epoch": 0.97,
4339
+ "learning_rate": 3.947896504172144e-06,
4340
+ "loss": 0.5664,
4341
+ "step": 722
4342
+ },
4343
+ {
4344
+ "epoch": 0.97,
4345
+ "learning_rate": 3.944929394426283e-06,
4346
+ "loss": 0.5236,
4347
+ "step": 723
4348
+ },
4349
+ {
4350
+ "epoch": 0.98,
4351
+ "learning_rate": 3.941959225246975e-06,
4352
+ "loss": 0.5555,
4353
+ "step": 724
4354
+ },
4355
+ {
4356
+ "epoch": 0.98,
4357
+ "learning_rate": 3.938986002923133e-06,
4358
+ "loss": 0.5173,
4359
+ "step": 725
4360
+ },
4361
+ {
4362
+ "epoch": 0.98,
4363
+ "learning_rate": 3.9360097337501355e-06,
4364
+ "loss": 0.5483,
4365
+ "step": 726
4366
+ },
4367
+ {
4368
+ "epoch": 0.98,
4369
+ "learning_rate": 3.93303042402981e-06,
4370
+ "loss": 0.6349,
4371
+ "step": 727
4372
+ },
4373
+ {
4374
+ "epoch": 0.98,
4375
+ "learning_rate": 3.930048080070424e-06,
4376
+ "loss": 0.6136,
4377
+ "step": 728
4378
+ },
4379
+ {
4380
+ "epoch": 0.98,
4381
+ "learning_rate": 3.927062708186667e-06,
4382
+ "loss": 0.517,
4383
+ "step": 729
4384
+ },
4385
+ {
4386
+ "epoch": 0.98,
4387
+ "learning_rate": 3.924074314699643e-06,
4388
+ "loss": 0.5116,
4389
+ "step": 730
4390
+ },
4391
+ {
4392
+ "epoch": 0.99,
4393
+ "learning_rate": 3.921082905936852e-06,
4394
+ "loss": 0.63,
4395
+ "step": 731
4396
+ },
4397
+ {
4398
+ "epoch": 0.99,
4399
+ "learning_rate": 3.918088488232178e-06,
4400
+ "loss": 0.5495,
4401
+ "step": 732
4402
+ },
4403
+ {
4404
+ "epoch": 0.99,
4405
+ "learning_rate": 3.915091067925878e-06,
4406
+ "loss": 0.5947,
4407
+ "step": 733
4408
+ },
4409
+ {
4410
+ "epoch": 0.99,
4411
+ "learning_rate": 3.912090651364563e-06,
4412
+ "loss": 0.6379,
4413
+ "step": 734
4414
+ },
4415
+ {
4416
+ "epoch": 0.99,
4417
+ "learning_rate": 3.909087244901192e-06,
4418
+ "loss": 0.5514,
4419
+ "step": 735
4420
+ },
4421
+ {
4422
+ "epoch": 0.99,
4423
+ "learning_rate": 3.906080854895051e-06,
4424
+ "loss": 0.5258,
4425
+ "step": 736
4426
+ },
4427
+ {
4428
+ "epoch": 0.99,
4429
+ "learning_rate": 3.903071487711748e-06,
4430
+ "loss": 0.4872,
4431
+ "step": 737
4432
+ },
4433
+ {
4434
+ "epoch": 0.99,
4435
+ "learning_rate": 3.90005914972319e-06,
4436
+ "loss": 0.5287,
4437
+ "step": 738
4438
+ },
4439
+ {
4440
+ "epoch": 1.0,
4441
+ "learning_rate": 3.897043847307578e-06,
4442
+ "loss": 0.5857,
4443
+ "step": 739
4444
+ },
4445
+ {
4446
+ "epoch": 1.0,
4447
+ "learning_rate": 3.894025586849386e-06,
4448
+ "loss": 0.5029,
4449
+ "step": 740
4450
+ },
4451
+ {
4452
+ "epoch": 1.0,
4453
+ "learning_rate": 3.891004374739354e-06,
4454
+ "loss": 0.5309,
4455
+ "step": 741
4456
+ },
4457
+ {
4458
+ "epoch": 1.0,
4459
+ "learning_rate": 3.887980217374472e-06,
4460
+ "loss": 0.6516,
4461
+ "step": 742
4462
+ }
4463
+ ],
4464
+ "logging_steps": 1.0,
4465
+ "max_steps": 2226,
4466
+ "num_train_epochs": 3,
4467
+ "save_steps": 10000.0,
4468
+ "total_flos": 1.0564489783856333e+18,
4469
+ "trial_name": null,
4470
+ "trial_params": null
4471
+ }
checkpoint-742/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df645e38e090e9d2cbe1630ed71ba09aabda63d992b28e342963cada2d5af430
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 sha256:666b96c921529e6799651f603d7ccfdccc64c3d9774326d2c28f17f9568ea2a6
3
+ size 4943178720
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cb23ec5ddc8a9c373ff07dadc5072a7593c3b70753e21d7a6319d04f2a55c17
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:beeb0b33def2727d1a7ae801b88ffd5cb6163e060963fc037aa5865ae7bf0e0d
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 sha256:00c9eb21f95ad754d7628a792e16f27b01d0a4fa7992398c01d7eb12eea01d05
3
+ size 6136