Hugging Face's logo

wesley7137
/
MetaMath-CodeLlama-Python-7B-V1-lora

PEFT
Safetensors
Model card Files
xet
Community
wesley7137 commited on
Commit
9947c3a
·
1 Parent(s): 883e245

Upload 14 files

Browse files
Files changed (14) hide show
  1. README.md +34 -0
  2. adapter_config.json +21 -0
  3. adapter_model.bin +3 -0
  4. adapter_model.safetensors +3 -0
  5. added_tokens.json +6 -0
  6. optimizer.pt +3 -0
  7. rng_state.pth +3 -0
  8. scheduler.pt +3 -0
  9. special_tokens_map.json +30 -0
  10. tokenizer.json +0 -0
  11. tokenizer.model +3 -0
  12. tokenizer_config.json +83 -0
  13. trainer_state.json +1821 -0
  14. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: False
10
+ - load_in_4bit: True
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: nf4
16
+ - bnb_4bit_use_double_quant: False
17
+ - bnb_4bit_compute_dtype: float16
18
+
19
+ The following `bitsandbytes` quantization config was used during training:
20
+ - quant_method: bitsandbytes
21
+ - load_in_8bit: False
22
+ - load_in_4bit: True
23
+ - llm_int8_threshold: 6.0
24
+ - llm_int8_skip_modules: None
25
+ - llm_int8_enable_fp32_cpu_offload: False
26
+ - llm_int8_has_fp16_weight: False
27
+ - bnb_4bit_quant_type: nf4
28
+ - bnb_4bit_use_double_quant: False
29
+ - bnb_4bit_compute_dtype: float16
30
+ ### Framework versions
31
+
32
+ - PEFT 0.4.0
33
+
34
+ - PEFT 0.4.0
adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "codellama/CodeLlama-7b-Python-hf",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 16,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:735bb6d68d99613e202c4b05d8c26301901cc146bf950b9c29bb4342f22de131
3
+ size 134263757
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf8ca798c3827b6a534c0e4b1fa4c4027be75a6b8212b7ae1951a91b5521e9ae
3
+ size 134235048
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "▁<EOT>": 32003,
3
+ "▁<MID>": 32001,
4
+ "▁<PRE>": 32000,
5
+ "▁<SUF>": 32002
6
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbb8fa3b14ea9ca6cfe9e23890ee9982e0a40305436ee590f980d55bb24afd0e
3
+ size 268514565
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffaeedca22948b7fc77e859b2ec937650fb10a508455f9d6069ddbc5adefad13
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3e02e4b8a74e841ee5a1ce8c453a9becb15f5be6cbcdd100b814e93235dab36
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "▁<PRE>",
4
+ "▁<MID>",
5
+ "▁<SUF>",
6
+ "▁<EOT>"
7
+ ],
8
+ "bos_token": {
9
+ "content": "<s>",
10
+ "lstrip": false,
11
+ "normalized": false,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "eos_token": {
16
+ "content": "</s>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "pad_token": "</s>",
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "▁<PRE>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "▁<MID>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "▁<SUF>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32003": {
54
+ "content": "▁<EOT>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ }
61
+ },
62
+ "additional_special_tokens": [
63
+ "▁<PRE>",
64
+ "▁<MID>",
65
+ "▁<SUF>",
66
+ "▁<EOT>"
67
+ ],
68
+ "bos_token": "<s>",
69
+ "clean_up_tokenization_spaces": false,
70
+ "eos_token": "</s>",
71
+ "eot_token": "▁<EOT>",
72
+ "fill_token": "<FILL_ME>",
73
+ "legacy": null,
74
+ "middle_token": "▁<MID>",
75
+ "model_max_length": 1000000000000000019884624838656,
76
+ "pad_token": "</s>",
77
+ "prefix_token": "▁<PRE>",
78
+ "sp_model_kwargs": {},
79
+ "suffix_token": "▁<SUF>",
80
+ "tokenizer_class": "CodeLlamaTokenizer",
81
+ "unk_token": "<unk>",
82
+ "use_default_system_prompt": false
83
+ }
trainer_state.json ADDED
@@ -0,0 +1,1821 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.0060759493670886075,
5
+ "eval_steps": 500,
6
+ "global_step": 300,
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": 0.0002,
14
+ "loss": 1.0959,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "learning_rate": 0.0002,
20
+ "loss": 1.1546,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.0,
25
+ "learning_rate": 0.0002,
26
+ "loss": 1.3479,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.0,
31
+ "learning_rate": 0.0002,
32
+ "loss": 1.2503,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.0,
37
+ "learning_rate": 0.0002,
38
+ "loss": 1.3416,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.0,
43
+ "learning_rate": 0.0002,
44
+ "loss": 1.3484,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.0,
49
+ "learning_rate": 0.0002,
50
+ "loss": 1.3347,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.0,
55
+ "learning_rate": 0.0002,
56
+ "loss": 1.2724,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.0,
61
+ "learning_rate": 0.0002,
62
+ "loss": 1.2079,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.0,
67
+ "learning_rate": 0.0002,
68
+ "loss": 1.2547,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.0,
73
+ "learning_rate": 0.0002,
74
+ "loss": 1.2018,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.0,
79
+ "learning_rate": 0.0002,
80
+ "loss": 1.2583,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.0,
85
+ "learning_rate": 0.0002,
86
+ "loss": 1.284,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.0,
91
+ "learning_rate": 0.0002,
92
+ "loss": 1.0542,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.0,
97
+ "learning_rate": 0.0002,
98
+ "loss": 1.1568,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.0,
103
+ "learning_rate": 0.0002,
104
+ "loss": 1.017,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.0,
109
+ "learning_rate": 0.0002,
110
+ "loss": 1.0164,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.0,
115
+ "learning_rate": 0.0002,
116
+ "loss": 0.9156,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.0,
121
+ "learning_rate": 0.0002,
122
+ "loss": 0.9252,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.0,
127
+ "learning_rate": 0.0002,
128
+ "loss": 0.7876,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.0,
133
+ "learning_rate": 0.0002,
134
+ "loss": 0.7165,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.0,
139
+ "learning_rate": 0.0002,
140
+ "loss": 0.6807,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.0,
145
+ "learning_rate": 0.0002,
146
+ "loss": 0.6941,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.0,
151
+ "learning_rate": 0.0002,
152
+ "loss": 0.6218,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.0,
157
+ "learning_rate": 0.0002,
158
+ "loss": 0.6979,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.0,
163
+ "learning_rate": 0.0002,
164
+ "loss": 0.6974,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.0,
169
+ "learning_rate": 0.0002,
170
+ "loss": 0.6624,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.0,
175
+ "learning_rate": 0.0002,
176
+ "loss": 0.6455,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.0,
181
+ "learning_rate": 0.0002,
182
+ "loss": 0.701,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.0,
187
+ "learning_rate": 0.0002,
188
+ "loss": 0.6802,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.0,
193
+ "learning_rate": 0.0002,
194
+ "loss": 0.6353,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.0,
199
+ "learning_rate": 0.0002,
200
+ "loss": 0.5297,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.0,
205
+ "learning_rate": 0.0002,
206
+ "loss": 0.5491,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.0,
211
+ "learning_rate": 0.0002,
212
+ "loss": 0.6545,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.0,
217
+ "learning_rate": 0.0002,
218
+ "loss": 0.6168,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.0,
223
+ "learning_rate": 0.0002,
224
+ "loss": 0.6217,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.0,
229
+ "learning_rate": 0.0002,
230
+ "loss": 0.6234,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.0,
235
+ "learning_rate": 0.0002,
236
+ "loss": 0.5422,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.0,
241
+ "learning_rate": 0.0002,
242
+ "loss": 0.7242,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.0,
247
+ "learning_rate": 0.0002,
248
+ "loss": 0.6204,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.0,
253
+ "learning_rate": 0.0002,
254
+ "loss": 0.5836,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.0,
259
+ "learning_rate": 0.0002,
260
+ "loss": 0.5765,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.0,
265
+ "learning_rate": 0.0002,
266
+ "loss": 0.5622,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.0,
271
+ "learning_rate": 0.0002,
272
+ "loss": 0.5649,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.0,
277
+ "learning_rate": 0.0002,
278
+ "loss": 0.6327,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.0,
283
+ "learning_rate": 0.0002,
284
+ "loss": 0.488,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.0,
289
+ "learning_rate": 0.0002,
290
+ "loss": 0.5458,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.0,
295
+ "learning_rate": 0.0002,
296
+ "loss": 0.5693,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.0,
301
+ "learning_rate": 0.0002,
302
+ "loss": 0.5141,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.0,
307
+ "learning_rate": 0.0002,
308
+ "loss": 0.5334,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.0,
313
+ "learning_rate": 0.0002,
314
+ "loss": 0.5639,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.0,
319
+ "learning_rate": 0.0002,
320
+ "loss": 0.6323,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.0,
325
+ "learning_rate": 0.0002,
326
+ "loss": 0.6546,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.0,
331
+ "learning_rate": 0.0002,
332
+ "loss": 0.6939,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.0,
337
+ "learning_rate": 0.0002,
338
+ "loss": 0.6168,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.0,
343
+ "learning_rate": 0.0002,
344
+ "loss": 0.544,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.0,
349
+ "learning_rate": 0.0002,
350
+ "loss": 0.5988,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.0,
355
+ "learning_rate": 0.0002,
356
+ "loss": 0.5091,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.0,
361
+ "learning_rate": 0.0002,
362
+ "loss": 0.5366,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.0,
367
+ "learning_rate": 0.0002,
368
+ "loss": 0.5133,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.0,
373
+ "learning_rate": 0.0002,
374
+ "loss": 0.5831,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.0,
379
+ "learning_rate": 0.0002,
380
+ "loss": 0.6005,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.0,
385
+ "learning_rate": 0.0002,
386
+ "loss": 0.5529,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.0,
391
+ "learning_rate": 0.0002,
392
+ "loss": 0.5784,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.0,
397
+ "learning_rate": 0.0002,
398
+ "loss": 0.5777,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.0,
403
+ "learning_rate": 0.0002,
404
+ "loss": 0.5436,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.0,
409
+ "learning_rate": 0.0002,
410
+ "loss": 0.5509,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.0,
415
+ "learning_rate": 0.0002,
416
+ "loss": 0.6578,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.0,
421
+ "learning_rate": 0.0002,
422
+ "loss": 0.5672,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.0,
427
+ "learning_rate": 0.0002,
428
+ "loss": 0.507,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.0,
433
+ "learning_rate": 0.0002,
434
+ "loss": 0.6225,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.0,
439
+ "learning_rate": 0.0002,
440
+ "loss": 0.6094,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.0,
445
+ "learning_rate": 0.0002,
446
+ "loss": 0.5362,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.0,
451
+ "learning_rate": 0.0002,
452
+ "loss": 0.5388,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.0,
457
+ "learning_rate": 0.0002,
458
+ "loss": 0.5537,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.0,
463
+ "learning_rate": 0.0002,
464
+ "loss": 0.5853,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.0,
469
+ "learning_rate": 0.0002,
470
+ "loss": 0.4963,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.0,
475
+ "learning_rate": 0.0002,
476
+ "loss": 0.55,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.0,
481
+ "learning_rate": 0.0002,
482
+ "loss": 0.5461,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.0,
487
+ "learning_rate": 0.0002,
488
+ "loss": 0.541,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.0,
493
+ "learning_rate": 0.0002,
494
+ "loss": 0.622,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.0,
499
+ "learning_rate": 0.0002,
500
+ "loss": 0.5707,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.0,
505
+ "learning_rate": 0.0002,
506
+ "loss": 0.5854,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.0,
511
+ "learning_rate": 0.0002,
512
+ "loss": 0.5205,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.0,
517
+ "learning_rate": 0.0002,
518
+ "loss": 0.4645,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.0,
523
+ "learning_rate": 0.0002,
524
+ "loss": 0.5519,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.0,
529
+ "learning_rate": 0.0002,
530
+ "loss": 0.5284,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.0,
535
+ "learning_rate": 0.0002,
536
+ "loss": 0.4823,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.0,
541
+ "learning_rate": 0.0002,
542
+ "loss": 0.5102,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.0,
547
+ "learning_rate": 0.0002,
548
+ "loss": 0.5052,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.0,
553
+ "learning_rate": 0.0002,
554
+ "loss": 0.5103,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.0,
559
+ "learning_rate": 0.0002,
560
+ "loss": 0.4865,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.0,
565
+ "learning_rate": 0.0002,
566
+ "loss": 0.5144,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.0,
571
+ "learning_rate": 0.0002,
572
+ "loss": 0.4552,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.0,
577
+ "learning_rate": 0.0002,
578
+ "loss": 0.502,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.0,
583
+ "learning_rate": 0.0002,
584
+ "loss": 0.4691,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.0,
589
+ "learning_rate": 0.0002,
590
+ "loss": 0.4939,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.0,
595
+ "learning_rate": 0.0002,
596
+ "loss": 0.5012,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.0,
601
+ "learning_rate": 0.0002,
602
+ "loss": 0.4274,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.0,
607
+ "learning_rate": 0.0002,
608
+ "loss": 0.4208,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.0,
613
+ "learning_rate": 0.0002,
614
+ "loss": 0.5306,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.0,
619
+ "learning_rate": 0.0002,
620
+ "loss": 0.5154,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.0,
625
+ "learning_rate": 0.0002,
626
+ "loss": 0.6008,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.0,
631
+ "learning_rate": 0.0002,
632
+ "loss": 0.5512,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.0,
637
+ "learning_rate": 0.0002,
638
+ "loss": 0.4762,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.0,
643
+ "learning_rate": 0.0002,
644
+ "loss": 0.6241,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.0,
649
+ "learning_rate": 0.0002,
650
+ "loss": 0.5532,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.0,
655
+ "learning_rate": 0.0002,
656
+ "loss": 0.4581,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.0,
661
+ "learning_rate": 0.0002,
662
+ "loss": 0.5168,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.0,
667
+ "learning_rate": 0.0002,
668
+ "loss": 0.5216,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.0,
673
+ "learning_rate": 0.0002,
674
+ "loss": 0.4855,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.0,
679
+ "learning_rate": 0.0002,
680
+ "loss": 0.4711,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.0,
685
+ "learning_rate": 0.0002,
686
+ "loss": 0.4754,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.0,
691
+ "learning_rate": 0.0002,
692
+ "loss": 0.4509,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.0,
697
+ "learning_rate": 0.0002,
698
+ "loss": 0.4848,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.0,
703
+ "learning_rate": 0.0002,
704
+ "loss": 0.513,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.0,
709
+ "learning_rate": 0.0002,
710
+ "loss": 0.5992,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.0,
715
+ "learning_rate": 0.0002,
716
+ "loss": 0.5308,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.0,
721
+ "learning_rate": 0.0002,
722
+ "loss": 0.582,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.0,
727
+ "learning_rate": 0.0002,
728
+ "loss": 0.5188,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.0,
733
+ "learning_rate": 0.0002,
734
+ "loss": 0.5254,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.0,
739
+ "learning_rate": 0.0002,
740
+ "loss": 0.498,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.0,
745
+ "learning_rate": 0.0002,
746
+ "loss": 0.5578,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.0,
751
+ "learning_rate": 0.0002,
752
+ "loss": 0.4419,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.0,
757
+ "learning_rate": 0.0002,
758
+ "loss": 0.5088,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.0,
763
+ "learning_rate": 0.0002,
764
+ "loss": 0.4544,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.0,
769
+ "learning_rate": 0.0002,
770
+ "loss": 0.5729,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.0,
775
+ "learning_rate": 0.0002,
776
+ "loss": 0.5504,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.0,
781
+ "learning_rate": 0.0002,
782
+ "loss": 0.5765,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.0,
787
+ "learning_rate": 0.0002,
788
+ "loss": 0.4918,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.0,
793
+ "learning_rate": 0.0002,
794
+ "loss": 0.4546,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.0,
799
+ "learning_rate": 0.0002,
800
+ "loss": 0.4365,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.0,
805
+ "learning_rate": 0.0002,
806
+ "loss": 0.4332,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.0,
811
+ "learning_rate": 0.0002,
812
+ "loss": 0.4494,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.0,
817
+ "learning_rate": 0.0002,
818
+ "loss": 0.5548,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.0,
823
+ "learning_rate": 0.0002,
824
+ "loss": 0.5012,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.0,
829
+ "learning_rate": 0.0002,
830
+ "loss": 0.5329,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.0,
835
+ "learning_rate": 0.0002,
836
+ "loss": 0.4324,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.0,
841
+ "learning_rate": 0.0002,
842
+ "loss": 0.5084,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.0,
847
+ "learning_rate": 0.0002,
848
+ "loss": 0.551,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.0,
853
+ "learning_rate": 0.0002,
854
+ "loss": 0.4932,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.0,
859
+ "learning_rate": 0.0002,
860
+ "loss": 0.4554,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.0,
865
+ "learning_rate": 0.0002,
866
+ "loss": 0.4614,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.0,
871
+ "learning_rate": 0.0002,
872
+ "loss": 0.494,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.0,
877
+ "learning_rate": 0.0002,
878
+ "loss": 0.4955,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.0,
883
+ "learning_rate": 0.0002,
884
+ "loss": 0.5002,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.0,
889
+ "learning_rate": 0.0002,
890
+ "loss": 0.4597,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.0,
895
+ "learning_rate": 0.0002,
896
+ "loss": 0.5241,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.0,
901
+ "learning_rate": 0.0002,
902
+ "loss": 0.3929,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.0,
907
+ "learning_rate": 0.0002,
908
+ "loss": 0.3445,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 0.0,
913
+ "learning_rate": 0.0002,
914
+ "loss": 0.58,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 0.0,
919
+ "learning_rate": 0.0002,
920
+ "loss": 0.5182,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 0.0,
925
+ "learning_rate": 0.0002,
926
+ "loss": 0.5274,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 0.0,
931
+ "learning_rate": 0.0002,
932
+ "loss": 0.5099,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 0.0,
937
+ "learning_rate": 0.0002,
938
+ "loss": 0.5458,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 0.0,
943
+ "learning_rate": 0.0002,
944
+ "loss": 0.474,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 0.0,
949
+ "learning_rate": 0.0002,
950
+ "loss": 0.4769,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 0.0,
955
+ "learning_rate": 0.0002,
956
+ "loss": 0.4472,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 0.0,
961
+ "learning_rate": 0.0002,
962
+ "loss": 0.514,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 0.0,
967
+ "learning_rate": 0.0002,
968
+ "loss": 0.4605,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 0.0,
973
+ "learning_rate": 0.0002,
974
+ "loss": 0.4921,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 0.0,
979
+ "learning_rate": 0.0002,
980
+ "loss": 0.5079,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 0.0,
985
+ "learning_rate": 0.0002,
986
+ "loss": 0.5588,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 0.0,
991
+ "learning_rate": 0.0002,
992
+ "loss": 0.4637,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 0.0,
997
+ "learning_rate": 0.0002,
998
+ "loss": 0.4842,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 0.0,
1003
+ "learning_rate": 0.0002,
1004
+ "loss": 0.4781,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 0.0,
1009
+ "learning_rate": 0.0002,
1010
+ "loss": 0.5443,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 0.0,
1015
+ "learning_rate": 0.0002,
1016
+ "loss": 0.5679,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 0.0,
1021
+ "learning_rate": 0.0002,
1022
+ "loss": 0.523,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 0.0,
1027
+ "learning_rate": 0.0002,
1028
+ "loss": 0.5176,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 0.0,
1033
+ "learning_rate": 0.0002,
1034
+ "loss": 0.4599,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 0.0,
1039
+ "learning_rate": 0.0002,
1040
+ "loss": 0.5255,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 0.0,
1045
+ "learning_rate": 0.0002,
1046
+ "loss": 0.5217,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 0.0,
1051
+ "learning_rate": 0.0002,
1052
+ "loss": 0.4861,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 0.0,
1057
+ "learning_rate": 0.0002,
1058
+ "loss": 0.5303,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 0.0,
1063
+ "learning_rate": 0.0002,
1064
+ "loss": 0.5442,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 0.0,
1069
+ "learning_rate": 0.0002,
1070
+ "loss": 0.4619,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 0.0,
1075
+ "learning_rate": 0.0002,
1076
+ "loss": 0.4551,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 0.0,
1081
+ "learning_rate": 0.0002,
1082
+ "loss": 0.5021,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 0.0,
1087
+ "learning_rate": 0.0002,
1088
+ "loss": 0.4832,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 0.0,
1093
+ "learning_rate": 0.0002,
1094
+ "loss": 0.5725,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 0.0,
1099
+ "learning_rate": 0.0002,
1100
+ "loss": 0.4902,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 0.0,
1105
+ "learning_rate": 0.0002,
1106
+ "loss": 0.506,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 0.0,
1111
+ "learning_rate": 0.0002,
1112
+ "loss": 0.5055,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 0.0,
1117
+ "learning_rate": 0.0002,
1118
+ "loss": 0.5262,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 0.0,
1123
+ "learning_rate": 0.0002,
1124
+ "loss": 0.5572,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 0.0,
1129
+ "learning_rate": 0.0002,
1130
+ "loss": 0.4542,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 0.0,
1135
+ "learning_rate": 0.0002,
1136
+ "loss": 0.5356,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 0.0,
1141
+ "learning_rate": 0.0002,
1142
+ "loss": 0.493,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 0.0,
1147
+ "learning_rate": 0.0002,
1148
+ "loss": 0.4752,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 0.0,
1153
+ "learning_rate": 0.0002,
1154
+ "loss": 0.4753,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 0.0,
1159
+ "learning_rate": 0.0002,
1160
+ "loss": 0.4706,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 0.0,
1165
+ "learning_rate": 0.0002,
1166
+ "loss": 0.4993,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 0.0,
1171
+ "learning_rate": 0.0002,
1172
+ "loss": 0.4781,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 0.0,
1177
+ "learning_rate": 0.0002,
1178
+ "loss": 0.4874,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 0.0,
1183
+ "learning_rate": 0.0002,
1184
+ "loss": 0.549,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 0.0,
1189
+ "learning_rate": 0.0002,
1190
+ "loss": 0.4599,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 0.0,
1195
+ "learning_rate": 0.0002,
1196
+ "loss": 0.3982,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 0.0,
1201
+ "learning_rate": 0.0002,
1202
+ "loss": 0.36,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 0.0,
1207
+ "learning_rate": 0.0002,
1208
+ "loss": 0.3572,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 0.0,
1213
+ "learning_rate": 0.0002,
1214
+ "loss": 0.4734,
1215
+ "step": 201
1216
+ },
1217
+ {
1218
+ "epoch": 0.0,
1219
+ "learning_rate": 0.0002,
1220
+ "loss": 0.5174,
1221
+ "step": 202
1222
+ },
1223
+ {
1224
+ "epoch": 0.0,
1225
+ "learning_rate": 0.0002,
1226
+ "loss": 0.5445,
1227
+ "step": 203
1228
+ },
1229
+ {
1230
+ "epoch": 0.0,
1231
+ "learning_rate": 0.0002,
1232
+ "loss": 0.5521,
1233
+ "step": 204
1234
+ },
1235
+ {
1236
+ "epoch": 0.0,
1237
+ "learning_rate": 0.0002,
1238
+ "loss": 0.4273,
1239
+ "step": 205
1240
+ },
1241
+ {
1242
+ "epoch": 0.0,
1243
+ "learning_rate": 0.0002,
1244
+ "loss": 0.4393,
1245
+ "step": 206
1246
+ },
1247
+ {
1248
+ "epoch": 0.0,
1249
+ "learning_rate": 0.0002,
1250
+ "loss": 0.4361,
1251
+ "step": 207
1252
+ },
1253
+ {
1254
+ "epoch": 0.0,
1255
+ "learning_rate": 0.0002,
1256
+ "loss": 0.4453,
1257
+ "step": 208
1258
+ },
1259
+ {
1260
+ "epoch": 0.0,
1261
+ "learning_rate": 0.0002,
1262
+ "loss": 0.4597,
1263
+ "step": 209
1264
+ },
1265
+ {
1266
+ "epoch": 0.0,
1267
+ "learning_rate": 0.0002,
1268
+ "loss": 0.5559,
1269
+ "step": 210
1270
+ },
1271
+ {
1272
+ "epoch": 0.0,
1273
+ "learning_rate": 0.0002,
1274
+ "loss": 0.5015,
1275
+ "step": 211
1276
+ },
1277
+ {
1278
+ "epoch": 0.0,
1279
+ "learning_rate": 0.0002,
1280
+ "loss": 0.6537,
1281
+ "step": 212
1282
+ },
1283
+ {
1284
+ "epoch": 0.0,
1285
+ "learning_rate": 0.0002,
1286
+ "loss": 0.5598,
1287
+ "step": 213
1288
+ },
1289
+ {
1290
+ "epoch": 0.0,
1291
+ "learning_rate": 0.0002,
1292
+ "loss": 0.4147,
1293
+ "step": 214
1294
+ },
1295
+ {
1296
+ "epoch": 0.0,
1297
+ "learning_rate": 0.0002,
1298
+ "loss": 0.4752,
1299
+ "step": 215
1300
+ },
1301
+ {
1302
+ "epoch": 0.0,
1303
+ "learning_rate": 0.0002,
1304
+ "loss": 0.5194,
1305
+ "step": 216
1306
+ },
1307
+ {
1308
+ "epoch": 0.0,
1309
+ "learning_rate": 0.0002,
1310
+ "loss": 0.4395,
1311
+ "step": 217
1312
+ },
1313
+ {
1314
+ "epoch": 0.0,
1315
+ "learning_rate": 0.0002,
1316
+ "loss": 0.5379,
1317
+ "step": 218
1318
+ },
1319
+ {
1320
+ "epoch": 0.0,
1321
+ "learning_rate": 0.0002,
1322
+ "loss": 0.4989,
1323
+ "step": 219
1324
+ },
1325
+ {
1326
+ "epoch": 0.0,
1327
+ "learning_rate": 0.0002,
1328
+ "loss": 0.4861,
1329
+ "step": 220
1330
+ },
1331
+ {
1332
+ "epoch": 0.0,
1333
+ "learning_rate": 0.0002,
1334
+ "loss": 0.4913,
1335
+ "step": 221
1336
+ },
1337
+ {
1338
+ "epoch": 0.0,
1339
+ "learning_rate": 0.0002,
1340
+ "loss": 0.5293,
1341
+ "step": 222
1342
+ },
1343
+ {
1344
+ "epoch": 0.0,
1345
+ "learning_rate": 0.0002,
1346
+ "loss": 0.5284,
1347
+ "step": 223
1348
+ },
1349
+ {
1350
+ "epoch": 0.0,
1351
+ "learning_rate": 0.0002,
1352
+ "loss": 0.5284,
1353
+ "step": 224
1354
+ },
1355
+ {
1356
+ "epoch": 0.0,
1357
+ "learning_rate": 0.0002,
1358
+ "loss": 0.4723,
1359
+ "step": 225
1360
+ },
1361
+ {
1362
+ "epoch": 0.0,
1363
+ "learning_rate": 0.0002,
1364
+ "loss": 0.4811,
1365
+ "step": 226
1366
+ },
1367
+ {
1368
+ "epoch": 0.0,
1369
+ "learning_rate": 0.0002,
1370
+ "loss": 0.4969,
1371
+ "step": 227
1372
+ },
1373
+ {
1374
+ "epoch": 0.0,
1375
+ "learning_rate": 0.0002,
1376
+ "loss": 0.632,
1377
+ "step": 228
1378
+ },
1379
+ {
1380
+ "epoch": 0.0,
1381
+ "learning_rate": 0.0002,
1382
+ "loss": 0.507,
1383
+ "step": 229
1384
+ },
1385
+ {
1386
+ "epoch": 0.0,
1387
+ "learning_rate": 0.0002,
1388
+ "loss": 0.5252,
1389
+ "step": 230
1390
+ },
1391
+ {
1392
+ "epoch": 0.0,
1393
+ "learning_rate": 0.0002,
1394
+ "loss": 0.5073,
1395
+ "step": 231
1396
+ },
1397
+ {
1398
+ "epoch": 0.0,
1399
+ "learning_rate": 0.0002,
1400
+ "loss": 0.5142,
1401
+ "step": 232
1402
+ },
1403
+ {
1404
+ "epoch": 0.0,
1405
+ "learning_rate": 0.0002,
1406
+ "loss": 0.472,
1407
+ "step": 233
1408
+ },
1409
+ {
1410
+ "epoch": 0.0,
1411
+ "learning_rate": 0.0002,
1412
+ "loss": 0.5791,
1413
+ "step": 234
1414
+ },
1415
+ {
1416
+ "epoch": 0.0,
1417
+ "learning_rate": 0.0002,
1418
+ "loss": 0.5082,
1419
+ "step": 235
1420
+ },
1421
+ {
1422
+ "epoch": 0.0,
1423
+ "learning_rate": 0.0002,
1424
+ "loss": 0.4911,
1425
+ "step": 236
1426
+ },
1427
+ {
1428
+ "epoch": 0.0,
1429
+ "learning_rate": 0.0002,
1430
+ "loss": 0.4799,
1431
+ "step": 237
1432
+ },
1433
+ {
1434
+ "epoch": 0.0,
1435
+ "learning_rate": 0.0002,
1436
+ "loss": 0.4584,
1437
+ "step": 238
1438
+ },
1439
+ {
1440
+ "epoch": 0.0,
1441
+ "learning_rate": 0.0002,
1442
+ "loss": 0.5571,
1443
+ "step": 239
1444
+ },
1445
+ {
1446
+ "epoch": 0.0,
1447
+ "learning_rate": 0.0002,
1448
+ "loss": 0.4438,
1449
+ "step": 240
1450
+ },
1451
+ {
1452
+ "epoch": 0.0,
1453
+ "learning_rate": 0.0002,
1454
+ "loss": 0.491,
1455
+ "step": 241
1456
+ },
1457
+ {
1458
+ "epoch": 0.0,
1459
+ "learning_rate": 0.0002,
1460
+ "loss": 0.4601,
1461
+ "step": 242
1462
+ },
1463
+ {
1464
+ "epoch": 0.0,
1465
+ "learning_rate": 0.0002,
1466
+ "loss": 0.442,
1467
+ "step": 243
1468
+ },
1469
+ {
1470
+ "epoch": 0.0,
1471
+ "learning_rate": 0.0002,
1472
+ "loss": 0.4082,
1473
+ "step": 244
1474
+ },
1475
+ {
1476
+ "epoch": 0.0,
1477
+ "learning_rate": 0.0002,
1478
+ "loss": 0.4723,
1479
+ "step": 245
1480
+ },
1481
+ {
1482
+ "epoch": 0.0,
1483
+ "learning_rate": 0.0002,
1484
+ "loss": 0.4398,
1485
+ "step": 246
1486
+ },
1487
+ {
1488
+ "epoch": 0.01,
1489
+ "learning_rate": 0.0002,
1490
+ "loss": 0.4463,
1491
+ "step": 247
1492
+ },
1493
+ {
1494
+ "epoch": 0.01,
1495
+ "learning_rate": 0.0002,
1496
+ "loss": 0.3909,
1497
+ "step": 248
1498
+ },
1499
+ {
1500
+ "epoch": 0.01,
1501
+ "learning_rate": 0.0002,
1502
+ "loss": 0.4419,
1503
+ "step": 249
1504
+ },
1505
+ {
1506
+ "epoch": 0.01,
1507
+ "learning_rate": 0.0002,
1508
+ "loss": 0.3694,
1509
+ "step": 250
1510
+ },
1511
+ {
1512
+ "epoch": 0.01,
1513
+ "learning_rate": 0.0002,
1514
+ "loss": 0.5897,
1515
+ "step": 251
1516
+ },
1517
+ {
1518
+ "epoch": 0.01,
1519
+ "learning_rate": 0.0002,
1520
+ "loss": 0.5437,
1521
+ "step": 252
1522
+ },
1523
+ {
1524
+ "epoch": 0.01,
1525
+ "learning_rate": 0.0002,
1526
+ "loss": 0.4756,
1527
+ "step": 253
1528
+ },
1529
+ {
1530
+ "epoch": 0.01,
1531
+ "learning_rate": 0.0002,
1532
+ "loss": 0.4621,
1533
+ "step": 254
1534
+ },
1535
+ {
1536
+ "epoch": 0.01,
1537
+ "learning_rate": 0.0002,
1538
+ "loss": 0.4806,
1539
+ "step": 255
1540
+ },
1541
+ {
1542
+ "epoch": 0.01,
1543
+ "learning_rate": 0.0002,
1544
+ "loss": 0.4978,
1545
+ "step": 256
1546
+ },
1547
+ {
1548
+ "epoch": 0.01,
1549
+ "learning_rate": 0.0002,
1550
+ "loss": 0.3948,
1551
+ "step": 257
1552
+ },
1553
+ {
1554
+ "epoch": 0.01,
1555
+ "learning_rate": 0.0002,
1556
+ "loss": 0.4398,
1557
+ "step": 258
1558
+ },
1559
+ {
1560
+ "epoch": 0.01,
1561
+ "learning_rate": 0.0002,
1562
+ "loss": 0.4413,
1563
+ "step": 259
1564
+ },
1565
+ {
1566
+ "epoch": 0.01,
1567
+ "learning_rate": 0.0002,
1568
+ "loss": 0.4838,
1569
+ "step": 260
1570
+ },
1571
+ {
1572
+ "epoch": 0.01,
1573
+ "learning_rate": 0.0002,
1574
+ "loss": 0.4948,
1575
+ "step": 261
1576
+ },
1577
+ {
1578
+ "epoch": 0.01,
1579
+ "learning_rate": 0.0002,
1580
+ "loss": 0.4863,
1581
+ "step": 262
1582
+ },
1583
+ {
1584
+ "epoch": 0.01,
1585
+ "learning_rate": 0.0002,
1586
+ "loss": 0.5742,
1587
+ "step": 263
1588
+ },
1589
+ {
1590
+ "epoch": 0.01,
1591
+ "learning_rate": 0.0002,
1592
+ "loss": 0.4775,
1593
+ "step": 264
1594
+ },
1595
+ {
1596
+ "epoch": 0.01,
1597
+ "learning_rate": 0.0002,
1598
+ "loss": 0.4741,
1599
+ "step": 265
1600
+ },
1601
+ {
1602
+ "epoch": 0.01,
1603
+ "learning_rate": 0.0002,
1604
+ "loss": 0.4886,
1605
+ "step": 266
1606
+ },
1607
+ {
1608
+ "epoch": 0.01,
1609
+ "learning_rate": 0.0002,
1610
+ "loss": 0.5147,
1611
+ "step": 267
1612
+ },
1613
+ {
1614
+ "epoch": 0.01,
1615
+ "learning_rate": 0.0002,
1616
+ "loss": 0.4474,
1617
+ "step": 268
1618
+ },
1619
+ {
1620
+ "epoch": 0.01,
1621
+ "learning_rate": 0.0002,
1622
+ "loss": 0.4613,
1623
+ "step": 269
1624
+ },
1625
+ {
1626
+ "epoch": 0.01,
1627
+ "learning_rate": 0.0002,
1628
+ "loss": 0.4768,
1629
+ "step": 270
1630
+ },
1631
+ {
1632
+ "epoch": 0.01,
1633
+ "learning_rate": 0.0002,
1634
+ "loss": 0.5597,
1635
+ "step": 271
1636
+ },
1637
+ {
1638
+ "epoch": 0.01,
1639
+ "learning_rate": 0.0002,
1640
+ "loss": 0.5458,
1641
+ "step": 272
1642
+ },
1643
+ {
1644
+ "epoch": 0.01,
1645
+ "learning_rate": 0.0002,
1646
+ "loss": 0.5718,
1647
+ "step": 273
1648
+ },
1649
+ {
1650
+ "epoch": 0.01,
1651
+ "learning_rate": 0.0002,
1652
+ "loss": 0.4413,
1653
+ "step": 274
1654
+ },
1655
+ {
1656
+ "epoch": 0.01,
1657
+ "learning_rate": 0.0002,
1658
+ "loss": 0.4806,
1659
+ "step": 275
1660
+ },
1661
+ {
1662
+ "epoch": 0.01,
1663
+ "learning_rate": 0.0002,
1664
+ "loss": 0.5187,
1665
+ "step": 276
1666
+ },
1667
+ {
1668
+ "epoch": 0.01,
1669
+ "learning_rate": 0.0002,
1670
+ "loss": 0.5801,
1671
+ "step": 277
1672
+ },
1673
+ {
1674
+ "epoch": 0.01,
1675
+ "learning_rate": 0.0002,
1676
+ "loss": 0.4721,
1677
+ "step": 278
1678
+ },
1679
+ {
1680
+ "epoch": 0.01,
1681
+ "learning_rate": 0.0002,
1682
+ "loss": 0.5101,
1683
+ "step": 279
1684
+ },
1685
+ {
1686
+ "epoch": 0.01,
1687
+ "learning_rate": 0.0002,
1688
+ "loss": 0.4714,
1689
+ "step": 280
1690
+ },
1691
+ {
1692
+ "epoch": 0.01,
1693
+ "learning_rate": 0.0002,
1694
+ "loss": 0.4709,
1695
+ "step": 281
1696
+ },
1697
+ {
1698
+ "epoch": 0.01,
1699
+ "learning_rate": 0.0002,
1700
+ "loss": 0.5251,
1701
+ "step": 282
1702
+ },
1703
+ {
1704
+ "epoch": 0.01,
1705
+ "learning_rate": 0.0002,
1706
+ "loss": 0.4749,
1707
+ "step": 283
1708
+ },
1709
+ {
1710
+ "epoch": 0.01,
1711
+ "learning_rate": 0.0002,
1712
+ "loss": 0.4328,
1713
+ "step": 284
1714
+ },
1715
+ {
1716
+ "epoch": 0.01,
1717
+ "learning_rate": 0.0002,
1718
+ "loss": 0.516,
1719
+ "step": 285
1720
+ },
1721
+ {
1722
+ "epoch": 0.01,
1723
+ "learning_rate": 0.0002,
1724
+ "loss": 0.4037,
1725
+ "step": 286
1726
+ },
1727
+ {
1728
+ "epoch": 0.01,
1729
+ "learning_rate": 0.0002,
1730
+ "loss": 0.4403,
1731
+ "step": 287
1732
+ },
1733
+ {
1734
+ "epoch": 0.01,
1735
+ "learning_rate": 0.0002,
1736
+ "loss": 0.4025,
1737
+ "step": 288
1738
+ },
1739
+ {
1740
+ "epoch": 0.01,
1741
+ "learning_rate": 0.0002,
1742
+ "loss": 0.482,
1743
+ "step": 289
1744
+ },
1745
+ {
1746
+ "epoch": 0.01,
1747
+ "learning_rate": 0.0002,
1748
+ "loss": 0.4305,
1749
+ "step": 290
1750
+ },
1751
+ {
1752
+ "epoch": 0.01,
1753
+ "learning_rate": 0.0002,
1754
+ "loss": 0.4409,
1755
+ "step": 291
1756
+ },
1757
+ {
1758
+ "epoch": 0.01,
1759
+ "learning_rate": 0.0002,
1760
+ "loss": 0.4818,
1761
+ "step": 292
1762
+ },
1763
+ {
1764
+ "epoch": 0.01,
1765
+ "learning_rate": 0.0002,
1766
+ "loss": 0.4425,
1767
+ "step": 293
1768
+ },
1769
+ {
1770
+ "epoch": 0.01,
1771
+ "learning_rate": 0.0002,
1772
+ "loss": 0.472,
1773
+ "step": 294
1774
+ },
1775
+ {
1776
+ "epoch": 0.01,
1777
+ "learning_rate": 0.0002,
1778
+ "loss": 0.5274,
1779
+ "step": 295
1780
+ },
1781
+ {
1782
+ "epoch": 0.01,
1783
+ "learning_rate": 0.0002,
1784
+ "loss": 0.4769,
1785
+ "step": 296
1786
+ },
1787
+ {
1788
+ "epoch": 0.01,
1789
+ "learning_rate": 0.0002,
1790
+ "loss": 0.4344,
1791
+ "step": 297
1792
+ },
1793
+ {
1794
+ "epoch": 0.01,
1795
+ "learning_rate": 0.0002,
1796
+ "loss": 0.4103,
1797
+ "step": 298
1798
+ },
1799
+ {
1800
+ "epoch": 0.01,
1801
+ "learning_rate": 0.0002,
1802
+ "loss": 0.4382,
1803
+ "step": 299
1804
+ },
1805
+ {
1806
+ "epoch": 0.01,
1807
+ "learning_rate": 0.0002,
1808
+ "loss": 0.3984,
1809
+ "step": 300
1810
+ }
1811
+ ],
1812
+ "logging_steps": 1,
1813
+ "max_steps": 10000,
1814
+ "num_input_tokens_seen": 0,
1815
+ "num_train_epochs": 1,
1816
+ "save_steps": 50,
1817
+ "total_flos": 3.3099085906182144e+16,
1818
+ "train_batch_size": 4,
1819
+ "trial_name": null,
1820
+ "trial_params": null
1821
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:638850a602f7e52a5f1fadbe7e1bc65b1b987db455af3f016236fd25b1595481
3
+ size 4283