Hugging Face's logo

HydraLM
/
mistralic-expert-28

Model card Files Community
pharaouk commited on
Commit
40af4ca
•
1 Parent(s): 6da5046

Training in progress, step 200, checkpoint

Browse files
Files changed (15) hide show
  1. checkpoint-200/README.md +21 -0
  2. checkpoint-200/adapter_config.json +26 -0
  3. checkpoint-200/adapter_model.bin +3 -0
  4. checkpoint-200/adapter_model/adapter_model/README.md +21 -0
  5. checkpoint-200/adapter_model/adapter_model/adapter_config.json +26 -0
  6. checkpoint-200/adapter_model/adapter_model/adapter_model.bin +3 -0
  7. checkpoint-200/added_tokens.json +8 -0
  8. checkpoint-200/optimizer.pt +3 -0
  9. checkpoint-200/rng_state.pth +3 -0
  10. checkpoint-200/scheduler.pt +3 -0
  11. checkpoint-200/special_tokens_map.json +11 -0
  12. checkpoint-200/tokenizer.model +3 -0
  13. checkpoint-200/tokenizer_config.json +74 -0
  14. checkpoint-200/trainer_state.json +1290 -0
  15. checkpoint-200/training_args.bin +3 -0
checkpoint-200/README.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: True
17
+ - bnb_4bit_compute_dtype: bfloat16
18
+ ### Framework versions
19
+
20
+
21
+ - PEFT 0.4.0
checkpoint-200/adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "SkunkworksAI/Mistralic-7B-1",
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": 16.0,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "k_proj",
18
+ "q_proj",
19
+ "up_proj",
20
+ "down_proj",
21
+ "o_proj",
22
+ "v_proj",
23
+ "gate_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
checkpoint-200/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f80f743d19326f65fe3851d20236f07fccdf49592617be62a77f74d875322cfb
3
+ size 335706314
checkpoint-200/adapter_model/adapter_model/README.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: True
17
+ - bnb_4bit_compute_dtype: bfloat16
18
+ ### Framework versions
19
+
20
+
21
+ - PEFT 0.4.0
checkpoint-200/adapter_model/adapter_model/adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "SkunkworksAI/Mistralic-7B-1",
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": 16.0,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "k_proj",
18
+ "q_proj",
19
+ "up_proj",
20
+ "down_proj",
21
+ "o_proj",
22
+ "v_proj",
23
+ "gate_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
checkpoint-200/adapter_model/adapter_model/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f80f743d19326f65fe3851d20236f07fccdf49592617be62a77f74d875322cfb
3
+ size 335706314
checkpoint-200/added_tokens.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<s>": 1,
4
+ "<unk>": 0,
5
+ "<|im_end|>": 32000,
6
+ "<|im_start|>": 32001,
7
+ "[PAD]": 32002
8
+ }
checkpoint-200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a66461c9d547616a0a493ca5f29e536694df5d7963dac9dddc4fca55313ac8cf
3
+ size 1342452986
checkpoint-200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1781af2d51cebf6fd8b23cf17ab450897aa6ada74f3384ad511b66212f7c7484
3
+ size 14180
checkpoint-200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:859ff0676471245c9481ca25d6d6778d1c7963c39b7877af46bb8ca30a9ead21
3
+ size 1064
checkpoint-200/special_tokens_map.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": "<s>",
8
+ "eos_token": "</s>",
9
+ "pad_token": "[PAD]",
10
+ "unk_token": "<unk>"
11
+ }
checkpoint-200/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
checkpoint-200/tokenizer_config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": true,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": true,
16
+ "normalized": false,
17
+ "rstrip": true,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": true,
24
+ "normalized": false,
25
+ "rstrip": true,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<|im_end|>",
31
+ "lstrip": true,
32
+ "normalized": true,
33
+ "rstrip": true,
34
+ "single_word": false,
35
+ "special": false
36
+ },
37
+ "32001": {
38
+ "content": "<|im_start|>",
39
+ "lstrip": true,
40
+ "normalized": true,
41
+ "rstrip": true,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "32002": {
46
+ "content": "[PAD]",
47
+ "lstrip": true,
48
+ "normalized": false,
49
+ "rstrip": true,
50
+ "single_word": false,
51
+ "special": true
52
+ }
53
+ },
54
+ "additional_special_tokens": [
55
+ "<unk>",
56
+ "<s>",
57
+ "</s>"
58
+ ],
59
+ "bos_token": "<s>",
60
+ "clean_up_tokenization_spaces": false,
61
+ "eos_token": "</s>",
62
+ "legacy": true,
63
+ "model_max_length": 1000000000000000019884624838656,
64
+ "pad_token": "[PAD]",
65
+ "padding_side": "right",
66
+ "sp_model_kwargs": {},
67
+ "spaces_between_special_tokens": false,
68
+ "tokenizer_class": "LlamaTokenizer",
69
+ "tokenizer_file": null,
70
+ "trust_remote_code": false,
71
+ "unk_token": "<unk>",
72
+ "use_default_system_prompt": true,
73
+ "use_fast": true
74
+ }
checkpoint-200/trainer_state.json ADDED
@@ -0,0 +1,1290 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.918748676776886,
3
+ "best_model_checkpoint": "experts/mistralic-expert-28/checkpoint-200",
4
+ "epoch": 0.034666551111496295,
5
+ "eval_steps": 200,
6
+ "global_step": 200,
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": 0.9153,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "learning_rate": 0.0002,
20
+ "loss": 1.1126,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.0,
25
+ "learning_rate": 0.0002,
26
+ "loss": 0.9623,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.0,
31
+ "learning_rate": 0.0002,
32
+ "loss": 1.0142,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.0,
37
+ "learning_rate": 0.0002,
38
+ "loss": 1.0401,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.0,
43
+ "learning_rate": 0.0002,
44
+ "loss": 0.7844,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.0,
49
+ "learning_rate": 0.0002,
50
+ "loss": 1.014,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.0,
55
+ "learning_rate": 0.0002,
56
+ "loss": 0.8062,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.0,
61
+ "learning_rate": 0.0002,
62
+ "loss": 0.7818,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.0,
67
+ "learning_rate": 0.0002,
68
+ "loss": 0.9638,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.0,
73
+ "learning_rate": 0.0002,
74
+ "loss": 0.7674,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.0,
79
+ "learning_rate": 0.0002,
80
+ "loss": 1.1185,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.0,
85
+ "learning_rate": 0.0002,
86
+ "loss": 0.8292,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.0,
91
+ "learning_rate": 0.0002,
92
+ "loss": 0.6469,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.0,
97
+ "learning_rate": 0.0002,
98
+ "loss": 0.9843,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.0,
103
+ "learning_rate": 0.0002,
104
+ "loss": 1.1966,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.0,
109
+ "learning_rate": 0.0002,
110
+ "loss": 1.0369,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.0,
115
+ "learning_rate": 0.0002,
116
+ "loss": 1.0368,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.0,
121
+ "learning_rate": 0.0002,
122
+ "loss": 0.9693,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.0,
127
+ "learning_rate": 0.0002,
128
+ "loss": 0.8299,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.0,
133
+ "learning_rate": 0.0002,
134
+ "loss": 0.9227,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.0,
139
+ "learning_rate": 0.0002,
140
+ "loss": 0.7564,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.0,
145
+ "learning_rate": 0.0002,
146
+ "loss": 0.8868,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.0,
151
+ "learning_rate": 0.0002,
152
+ "loss": 1.1065,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.0,
157
+ "learning_rate": 0.0002,
158
+ "loss": 0.8981,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.0,
163
+ "learning_rate": 0.0002,
164
+ "loss": 0.9463,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.0,
169
+ "learning_rate": 0.0002,
170
+ "loss": 0.756,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.0,
175
+ "learning_rate": 0.0002,
176
+ "loss": 0.8951,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.01,
181
+ "learning_rate": 0.0002,
182
+ "loss": 0.8101,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.01,
187
+ "learning_rate": 0.0002,
188
+ "loss": 0.8278,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.01,
193
+ "learning_rate": 0.0002,
194
+ "loss": 0.9454,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.01,
199
+ "learning_rate": 0.0002,
200
+ "loss": 0.9271,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.01,
205
+ "learning_rate": 0.0002,
206
+ "loss": 0.6077,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.01,
211
+ "learning_rate": 0.0002,
212
+ "loss": 1.0646,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.01,
217
+ "learning_rate": 0.0002,
218
+ "loss": 0.6949,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.01,
223
+ "learning_rate": 0.0002,
224
+ "loss": 0.9631,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.01,
229
+ "learning_rate": 0.0002,
230
+ "loss": 0.9045,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.01,
235
+ "learning_rate": 0.0002,
236
+ "loss": 0.9562,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.01,
241
+ "learning_rate": 0.0002,
242
+ "loss": 0.9692,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.01,
247
+ "learning_rate": 0.0002,
248
+ "loss": 0.9586,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.01,
253
+ "learning_rate": 0.0002,
254
+ "loss": 0.9513,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.01,
259
+ "learning_rate": 0.0002,
260
+ "loss": 1.0374,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.01,
265
+ "learning_rate": 0.0002,
266
+ "loss": 0.9099,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.01,
271
+ "learning_rate": 0.0002,
272
+ "loss": 0.9617,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.01,
277
+ "learning_rate": 0.0002,
278
+ "loss": 1.0033,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.01,
283
+ "learning_rate": 0.0002,
284
+ "loss": 1.0036,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.01,
289
+ "learning_rate": 0.0002,
290
+ "loss": 0.9478,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.01,
295
+ "learning_rate": 0.0002,
296
+ "loss": 0.6875,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.01,
301
+ "learning_rate": 0.0002,
302
+ "loss": 0.893,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.01,
307
+ "learning_rate": 0.0002,
308
+ "loss": 0.9539,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.01,
313
+ "learning_rate": 0.0002,
314
+ "loss": 0.8106,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.01,
319
+ "learning_rate": 0.0002,
320
+ "loss": 0.8526,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.01,
325
+ "learning_rate": 0.0002,
326
+ "loss": 1.0052,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.01,
331
+ "learning_rate": 0.0002,
332
+ "loss": 0.9359,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.01,
337
+ "learning_rate": 0.0002,
338
+ "loss": 0.8657,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.01,
343
+ "learning_rate": 0.0002,
344
+ "loss": 0.9159,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.01,
349
+ "learning_rate": 0.0002,
350
+ "loss": 0.7594,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.01,
355
+ "learning_rate": 0.0002,
356
+ "loss": 0.9969,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.01,
361
+ "learning_rate": 0.0002,
362
+ "loss": 0.9412,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.01,
367
+ "learning_rate": 0.0002,
368
+ "loss": 0.8695,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.01,
373
+ "learning_rate": 0.0002,
374
+ "loss": 0.9306,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.01,
379
+ "learning_rate": 0.0002,
380
+ "loss": 1.1756,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.01,
385
+ "learning_rate": 0.0002,
386
+ "loss": 0.8805,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.01,
391
+ "learning_rate": 0.0002,
392
+ "loss": 1.0183,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.01,
397
+ "learning_rate": 0.0002,
398
+ "loss": 0.9008,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.01,
403
+ "learning_rate": 0.0002,
404
+ "loss": 0.787,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.01,
409
+ "learning_rate": 0.0002,
410
+ "loss": 0.8999,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.01,
415
+ "learning_rate": 0.0002,
416
+ "loss": 0.8642,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.01,
421
+ "learning_rate": 0.0002,
422
+ "loss": 0.8307,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.01,
427
+ "learning_rate": 0.0002,
428
+ "loss": 1.0866,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.01,
433
+ "learning_rate": 0.0002,
434
+ "loss": 0.8396,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.01,
439
+ "learning_rate": 0.0002,
440
+ "loss": 1.3022,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.01,
445
+ "learning_rate": 0.0002,
446
+ "loss": 0.9115,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.01,
451
+ "learning_rate": 0.0002,
452
+ "loss": 1.0308,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.01,
457
+ "learning_rate": 0.0002,
458
+ "loss": 0.9449,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.01,
463
+ "learning_rate": 0.0002,
464
+ "loss": 0.835,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.01,
469
+ "learning_rate": 0.0002,
470
+ "loss": 1.0277,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.01,
475
+ "learning_rate": 0.0002,
476
+ "loss": 1.0807,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.01,
481
+ "learning_rate": 0.0002,
482
+ "loss": 0.9567,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.01,
487
+ "learning_rate": 0.0002,
488
+ "loss": 0.9698,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.01,
493
+ "learning_rate": 0.0002,
494
+ "loss": 0.9644,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.01,
499
+ "learning_rate": 0.0002,
500
+ "loss": 0.7428,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.01,
505
+ "learning_rate": 0.0002,
506
+ "loss": 0.9928,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.01,
511
+ "learning_rate": 0.0002,
512
+ "loss": 1.0731,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.01,
517
+ "learning_rate": 0.0002,
518
+ "loss": 0.8638,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.01,
523
+ "learning_rate": 0.0002,
524
+ "loss": 0.9244,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.02,
529
+ "learning_rate": 0.0002,
530
+ "loss": 0.6978,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.02,
535
+ "learning_rate": 0.0002,
536
+ "loss": 1.0289,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.02,
541
+ "learning_rate": 0.0002,
542
+ "loss": 0.7879,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.02,
547
+ "learning_rate": 0.0002,
548
+ "loss": 1.0854,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.02,
553
+ "learning_rate": 0.0002,
554
+ "loss": 0.8177,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.02,
559
+ "learning_rate": 0.0002,
560
+ "loss": 1.0794,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.02,
565
+ "learning_rate": 0.0002,
566
+ "loss": 1.3084,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.02,
571
+ "learning_rate": 0.0002,
572
+ "loss": 0.8073,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.02,
577
+ "learning_rate": 0.0002,
578
+ "loss": 0.9544,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.02,
583
+ "learning_rate": 0.0002,
584
+ "loss": 0.8831,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.02,
589
+ "learning_rate": 0.0002,
590
+ "loss": 0.8451,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.02,
595
+ "learning_rate": 0.0002,
596
+ "loss": 0.9125,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.02,
601
+ "learning_rate": 0.0002,
602
+ "loss": 0.7928,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.02,
607
+ "learning_rate": 0.0002,
608
+ "loss": 0.8143,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.02,
613
+ "learning_rate": 0.0002,
614
+ "loss": 1.0305,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.02,
619
+ "learning_rate": 0.0002,
620
+ "loss": 1.1199,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.02,
625
+ "learning_rate": 0.0002,
626
+ "loss": 0.9476,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.02,
631
+ "learning_rate": 0.0002,
632
+ "loss": 0.9556,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.02,
637
+ "learning_rate": 0.0002,
638
+ "loss": 0.9603,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.02,
643
+ "learning_rate": 0.0002,
644
+ "loss": 1.1322,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.02,
649
+ "learning_rate": 0.0002,
650
+ "loss": 1.0186,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.02,
655
+ "learning_rate": 0.0002,
656
+ "loss": 1.0976,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.02,
661
+ "learning_rate": 0.0002,
662
+ "loss": 0.6639,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.02,
667
+ "learning_rate": 0.0002,
668
+ "loss": 0.7569,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.02,
673
+ "learning_rate": 0.0002,
674
+ "loss": 0.8701,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.02,
679
+ "learning_rate": 0.0002,
680
+ "loss": 1.0863,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.02,
685
+ "learning_rate": 0.0002,
686
+ "loss": 0.9724,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.02,
691
+ "learning_rate": 0.0002,
692
+ "loss": 0.8466,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.02,
697
+ "learning_rate": 0.0002,
698
+ "loss": 0.7405,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.02,
703
+ "learning_rate": 0.0002,
704
+ "loss": 1.0396,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.02,
709
+ "learning_rate": 0.0002,
710
+ "loss": 1.0059,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.02,
715
+ "learning_rate": 0.0002,
716
+ "loss": 0.8913,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.02,
721
+ "learning_rate": 0.0002,
722
+ "loss": 1.1489,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.02,
727
+ "learning_rate": 0.0002,
728
+ "loss": 0.8515,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.02,
733
+ "learning_rate": 0.0002,
734
+ "loss": 0.9792,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.02,
739
+ "learning_rate": 0.0002,
740
+ "loss": 1.1725,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.02,
745
+ "learning_rate": 0.0002,
746
+ "loss": 0.8935,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.02,
751
+ "learning_rate": 0.0002,
752
+ "loss": 0.9956,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.02,
757
+ "learning_rate": 0.0002,
758
+ "loss": 0.9844,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.02,
763
+ "learning_rate": 0.0002,
764
+ "loss": 0.9799,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.02,
769
+ "learning_rate": 0.0002,
770
+ "loss": 0.6775,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.02,
775
+ "learning_rate": 0.0002,
776
+ "loss": 0.7439,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.02,
781
+ "learning_rate": 0.0002,
782
+ "loss": 0.9888,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.02,
787
+ "learning_rate": 0.0002,
788
+ "loss": 0.9094,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.02,
793
+ "learning_rate": 0.0002,
794
+ "loss": 0.9001,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.02,
799
+ "learning_rate": 0.0002,
800
+ "loss": 0.6952,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.02,
805
+ "learning_rate": 0.0002,
806
+ "loss": 0.8925,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.02,
811
+ "learning_rate": 0.0002,
812
+ "loss": 0.9453,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.02,
817
+ "learning_rate": 0.0002,
818
+ "loss": 1.0495,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.02,
823
+ "learning_rate": 0.0002,
824
+ "loss": 0.5741,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.02,
829
+ "learning_rate": 0.0002,
830
+ "loss": 1.1232,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.02,
835
+ "learning_rate": 0.0002,
836
+ "loss": 0.9066,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.02,
841
+ "learning_rate": 0.0002,
842
+ "loss": 1.0007,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.02,
847
+ "learning_rate": 0.0002,
848
+ "loss": 0.7621,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.02,
853
+ "learning_rate": 0.0002,
854
+ "loss": 0.8324,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.02,
859
+ "learning_rate": 0.0002,
860
+ "loss": 0.9299,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.02,
865
+ "learning_rate": 0.0002,
866
+ "loss": 0.8145,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.02,
871
+ "learning_rate": 0.0002,
872
+ "loss": 0.6945,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.03,
877
+ "learning_rate": 0.0002,
878
+ "loss": 0.9305,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.03,
883
+ "learning_rate": 0.0002,
884
+ "loss": 1.0048,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.03,
889
+ "learning_rate": 0.0002,
890
+ "loss": 0.7729,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.03,
895
+ "learning_rate": 0.0002,
896
+ "loss": 1.0078,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.03,
901
+ "learning_rate": 0.0002,
902
+ "loss": 0.7944,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.03,
907
+ "learning_rate": 0.0002,
908
+ "loss": 0.7829,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 0.03,
913
+ "learning_rate": 0.0002,
914
+ "loss": 1.0636,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 0.03,
919
+ "learning_rate": 0.0002,
920
+ "loss": 1.02,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 0.03,
925
+ "learning_rate": 0.0002,
926
+ "loss": 0.8744,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 0.03,
931
+ "learning_rate": 0.0002,
932
+ "loss": 0.9944,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 0.03,
937
+ "learning_rate": 0.0002,
938
+ "loss": 1.0413,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 0.03,
943
+ "learning_rate": 0.0002,
944
+ "loss": 0.9772,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 0.03,
949
+ "learning_rate": 0.0002,
950
+ "loss": 1.0797,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 0.03,
955
+ "learning_rate": 0.0002,
956
+ "loss": 0.8422,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 0.03,
961
+ "learning_rate": 0.0002,
962
+ "loss": 0.9591,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 0.03,
967
+ "learning_rate": 0.0002,
968
+ "loss": 0.8085,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 0.03,
973
+ "learning_rate": 0.0002,
974
+ "loss": 0.6908,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 0.03,
979
+ "learning_rate": 0.0002,
980
+ "loss": 1.0377,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 0.03,
985
+ "learning_rate": 0.0002,
986
+ "loss": 0.9779,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 0.03,
991
+ "learning_rate": 0.0002,
992
+ "loss": 0.8234,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 0.03,
997
+ "learning_rate": 0.0002,
998
+ "loss": 0.8714,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 0.03,
1003
+ "learning_rate": 0.0002,
1004
+ "loss": 1.1599,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 0.03,
1009
+ "learning_rate": 0.0002,
1010
+ "loss": 0.8281,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 0.03,
1015
+ "learning_rate": 0.0002,
1016
+ "loss": 0.9024,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 0.03,
1021
+ "learning_rate": 0.0002,
1022
+ "loss": 0.9552,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 0.03,
1027
+ "learning_rate": 0.0002,
1028
+ "loss": 0.9298,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 0.03,
1033
+ "learning_rate": 0.0002,
1034
+ "loss": 0.8903,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 0.03,
1039
+ "learning_rate": 0.0002,
1040
+ "loss": 0.9371,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 0.03,
1045
+ "learning_rate": 0.0002,
1046
+ "loss": 0.8271,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 0.03,
1051
+ "learning_rate": 0.0002,
1052
+ "loss": 1.0959,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 0.03,
1057
+ "learning_rate": 0.0002,
1058
+ "loss": 0.9753,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 0.03,
1063
+ "learning_rate": 0.0002,
1064
+ "loss": 0.9881,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 0.03,
1069
+ "learning_rate": 0.0002,
1070
+ "loss": 0.955,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 0.03,
1075
+ "learning_rate": 0.0002,
1076
+ "loss": 0.8817,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 0.03,
1081
+ "learning_rate": 0.0002,
1082
+ "loss": 0.8931,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 0.03,
1087
+ "learning_rate": 0.0002,
1088
+ "loss": 0.8116,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 0.03,
1093
+ "learning_rate": 0.0002,
1094
+ "loss": 0.8405,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 0.03,
1099
+ "learning_rate": 0.0002,
1100
+ "loss": 1.0196,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 0.03,
1105
+ "learning_rate": 0.0002,
1106
+ "loss": 1.0874,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 0.03,
1111
+ "learning_rate": 0.0002,
1112
+ "loss": 0.8415,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 0.03,
1117
+ "learning_rate": 0.0002,
1118
+ "loss": 0.8357,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 0.03,
1123
+ "learning_rate": 0.0002,
1124
+ "loss": 0.8063,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 0.03,
1129
+ "learning_rate": 0.0002,
1130
+ "loss": 0.9091,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 0.03,
1135
+ "learning_rate": 0.0002,
1136
+ "loss": 0.8249,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 0.03,
1141
+ "learning_rate": 0.0002,
1142
+ "loss": 0.9477,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 0.03,
1147
+ "learning_rate": 0.0002,
1148
+ "loss": 0.9192,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 0.03,
1153
+ "learning_rate": 0.0002,
1154
+ "loss": 1.1802,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 0.03,
1159
+ "learning_rate": 0.0002,
1160
+ "loss": 1.1188,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 0.03,
1165
+ "learning_rate": 0.0002,
1166
+ "loss": 0.7995,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 0.03,
1171
+ "learning_rate": 0.0002,
1172
+ "loss": 1.2284,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 0.03,
1177
+ "learning_rate": 0.0002,
1178
+ "loss": 0.9915,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 0.03,
1183
+ "learning_rate": 0.0002,
1184
+ "loss": 1.0516,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 0.03,
1189
+ "learning_rate": 0.0002,
1190
+ "loss": 0.8023,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 0.03,
1195
+ "learning_rate": 0.0002,
1196
+ "loss": 0.8398,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 0.03,
1201
+ "learning_rate": 0.0002,
1202
+ "loss": 1.0297,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 0.03,
1207
+ "learning_rate": 0.0002,
1208
+ "loss": 0.9599,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 0.03,
1213
+ "eval_loss": 0.918748676776886,
1214
+ "eval_runtime": 110.4336,
1215
+ "eval_samples_per_second": 9.055,
1216
+ "eval_steps_per_second": 4.528,
1217
+ "step": 200
1218
+ },
1219
+ {
1220
+ "epoch": 0.03,
1221
+ "mmlu_eval_accuracy": 0.5936350541565827,
1222
+ "mmlu_eval_accuracy_abstract_algebra": 0.2727272727272727,
1223
+ "mmlu_eval_accuracy_anatomy": 0.5714285714285714,
1224
+ "mmlu_eval_accuracy_astronomy": 0.8125,
1225
+ "mmlu_eval_accuracy_business_ethics": 0.6363636363636364,
1226
+ "mmlu_eval_accuracy_clinical_knowledge": 0.5862068965517241,
1227
+ "mmlu_eval_accuracy_college_biology": 0.625,
1228
+ "mmlu_eval_accuracy_college_chemistry": 0.25,
1229
+ "mmlu_eval_accuracy_college_computer_science": 0.45454545454545453,
1230
+ "mmlu_eval_accuracy_college_mathematics": 0.6363636363636364,
1231
+ "mmlu_eval_accuracy_college_medicine": 0.6363636363636364,
1232
+ "mmlu_eval_accuracy_college_physics": 0.45454545454545453,
1233
+ "mmlu_eval_accuracy_computer_security": 0.5454545454545454,
1234
+ "mmlu_eval_accuracy_conceptual_physics": 0.5384615384615384,
1235
+ "mmlu_eval_accuracy_econometrics": 0.5833333333333334,
1236
+ "mmlu_eval_accuracy_electrical_engineering": 0.625,
1237
+ "mmlu_eval_accuracy_elementary_mathematics": 0.4146341463414634,
1238
+ "mmlu_eval_accuracy_formal_logic": 0.2857142857142857,
1239
+ "mmlu_eval_accuracy_global_facts": 0.3,
1240
+ "mmlu_eval_accuracy_high_school_biology": 0.59375,
1241
+ "mmlu_eval_accuracy_high_school_chemistry": 0.3181818181818182,
1242
+ "mmlu_eval_accuracy_high_school_computer_science": 0.6666666666666666,
1243
+ "mmlu_eval_accuracy_high_school_european_history": 0.7777777777777778,
1244
+ "mmlu_eval_accuracy_high_school_geography": 0.8636363636363636,
1245
+ "mmlu_eval_accuracy_high_school_government_and_politics": 0.7142857142857143,
1246
+ "mmlu_eval_accuracy_high_school_macroeconomics": 0.627906976744186,
1247
+ "mmlu_eval_accuracy_high_school_mathematics": 0.2413793103448276,
1248
+ "mmlu_eval_accuracy_high_school_microeconomics": 0.5769230769230769,
1249
+ "mmlu_eval_accuracy_high_school_physics": 0.17647058823529413,
1250
+ "mmlu_eval_accuracy_high_school_psychology": 0.8333333333333334,
1251
+ "mmlu_eval_accuracy_high_school_statistics": 0.34782608695652173,
1252
+ "mmlu_eval_accuracy_high_school_us_history": 0.7272727272727273,
1253
+ "mmlu_eval_accuracy_high_school_world_history": 0.6153846153846154,
1254
+ "mmlu_eval_accuracy_human_aging": 0.7391304347826086,
1255
+ "mmlu_eval_accuracy_human_sexuality": 0.5,
1256
+ "mmlu_eval_accuracy_international_law": 0.8461538461538461,
1257
+ "mmlu_eval_accuracy_jurisprudence": 0.5454545454545454,
1258
+ "mmlu_eval_accuracy_logical_fallacies": 0.6666666666666666,
1259
+ "mmlu_eval_accuracy_machine_learning": 0.5454545454545454,
1260
+ "mmlu_eval_accuracy_management": 0.9090909090909091,
1261
+ "mmlu_eval_accuracy_marketing": 0.92,
1262
+ "mmlu_eval_accuracy_medical_genetics": 0.9090909090909091,
1263
+ "mmlu_eval_accuracy_miscellaneous": 0.7441860465116279,
1264
+ "mmlu_eval_accuracy_moral_disputes": 0.5789473684210527,
1265
+ "mmlu_eval_accuracy_moral_scenarios": 0.36,
1266
+ "mmlu_eval_accuracy_nutrition": 0.696969696969697,
1267
+ "mmlu_eval_accuracy_philosophy": 0.7352941176470589,
1268
+ "mmlu_eval_accuracy_prehistory": 0.5428571428571428,
1269
+ "mmlu_eval_accuracy_professional_accounting": 0.4838709677419355,
1270
+ "mmlu_eval_accuracy_professional_law": 0.4117647058823529,
1271
+ "mmlu_eval_accuracy_professional_medicine": 0.6129032258064516,
1272
+ "mmlu_eval_accuracy_professional_psychology": 0.6086956521739131,
1273
+ "mmlu_eval_accuracy_public_relations": 0.4166666666666667,
1274
+ "mmlu_eval_accuracy_security_studies": 0.6296296296296297,
1275
+ "mmlu_eval_accuracy_sociology": 0.9090909090909091,
1276
+ "mmlu_eval_accuracy_us_foreign_policy": 0.8181818181818182,
1277
+ "mmlu_eval_accuracy_virology": 0.5555555555555556,
1278
+ "mmlu_eval_accuracy_world_religions": 0.8421052631578947,
1279
+ "mmlu_loss": 1.3518375517805314,
1280
+ "step": 200
1281
+ }
1282
+ ],
1283
+ "logging_steps": 1,
1284
+ "max_steps": 17307,
1285
+ "num_train_epochs": 3,
1286
+ "save_steps": 200,
1287
+ "total_flos": 2.997379918331904e+16,
1288
+ "trial_name": null,
1289
+ "trial_params": null
1290
+ }
checkpoint-200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1e61b61a92b9e31188d58dccd610cb4e55b2d9bc4be1080644d99a4209588a6
3
+ size 6392