Hugging Face's logo

pharaouk
/
unnatural_codellama_34B

Model card Files Community
2
pharaouk commited on
Commit
87f10a5
•
1 Parent(s): d0bde34

checkpoint

Browse files
Files changed (22) hide show
  1. adapter_config.json +26 -0
  2. adapter_model.bin +3 -0
  3. added_tokens.json +3 -0
  4. checkpoint-200/README.md +20 -0
  5. checkpoint-200/adapter_config.json +26 -0
  6. checkpoint-200/adapter_model.bin +3 -0
  7. checkpoint-200/adapter_model/adapter_model/README.md +20 -0
  8. checkpoint-200/adapter_model/adapter_model/adapter_config.json +26 -0
  9. checkpoint-200/adapter_model/adapter_model/adapter_model.bin +3 -0
  10. checkpoint-200/added_tokens.json +3 -0
  11. checkpoint-200/optimizer.pt +3 -0
  12. checkpoint-200/rng_state.pth +3 -0
  13. checkpoint-200/scheduler.pt +3 -0
  14. checkpoint-200/special_tokens_map.json +6 -0
  15. checkpoint-200/tokenizer.model +3 -0
  16. checkpoint-200/tokenizer_config.json +37 -0
  17. checkpoint-200/trainer_state.json +1287 -0
  18. checkpoint-200/training_args.bin +3 -0
  19. special_tokens_map.json +6 -0
  20. tokenizer.model +3 -0
  21. tokenizer_config.json +37 -0
  22. training_args.bin +3 -0
adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "alpindale/CodeLlama-34B-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": 16.0,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "v_proj",
18
+ "up_proj",
19
+ "gate_proj",
20
+ "down_proj",
21
+ "q_proj",
22
+ "o_proj",
23
+ "k_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:160a60dd1cd3974d6547f7ec7bccbdd179da028231e05e345a2477823ba13476
3
+ size 871609293
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 32000
3
+ }
checkpoint-200/README.md ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: True
16
+ - bnb_4bit_compute_dtype: bfloat16
17
+ ### Framework versions
18
+
19
+
20
+ - 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": "alpindale/CodeLlama-34B-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": 16.0,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "v_proj",
18
+ "up_proj",
19
+ "gate_proj",
20
+ "down_proj",
21
+ "q_proj",
22
+ "o_proj",
23
+ "k_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 sha256:160a60dd1cd3974d6547f7ec7bccbdd179da028231e05e345a2477823ba13476
3
+ size 871609293
checkpoint-200/adapter_model/adapter_model/README.md ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: True
16
+ - bnb_4bit_compute_dtype: bfloat16
17
+ ### Framework versions
18
+
19
+
20
+ - 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": "alpindale/CodeLlama-34B-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": 16.0,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "v_proj",
18
+ "up_proj",
19
+ "gate_proj",
20
+ "down_proj",
21
+ "q_proj",
22
+ "o_proj",
23
+ "k_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 sha256:160a60dd1cd3974d6547f7ec7bccbdd179da028231e05e345a2477823ba13476
3
+ size 871609293
checkpoint-200/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 32000
3
+ }
checkpoint-200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28664f723821987f28653721f3c3e5831cf63de5de35a89366da708f0f7196fc
3
+ size 3485880477
checkpoint-200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41a5175571e28bc9e49814ab269d17e197cb3c5f958226d58cf87c3326589d83
3
+ size 14511
checkpoint-200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
3
+ size 627
checkpoint-200/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "<unk>"
6
+ }
checkpoint-200/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-200/tokenizer_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": null,
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "pad_token": null,
24
+ "padding_side": "right",
25
+ "sp_model_kwargs": {},
26
+ "spaces_between_special_tokens": false,
27
+ "tokenizer_class": "LlamaTokenizer",
28
+ "unk_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "use_default_system_prompt": true
37
+ }
checkpoint-200/trainer_state.json ADDED
@@ -0,0 +1,1287 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3453182876110077,
3
+ "best_model_checkpoint": "./output_v2/34bCodellama_CodeLlama-34B-hf_unnatural-instructions_standardized/checkpoint-200",
4
+ "epoch": 0.012222137346268428,
5
+ "global_step": 200,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 0.0002,
13
+ "loss": 1.9735,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.0,
18
+ "learning_rate": 0.0002,
19
+ "loss": 2.7155,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 0.0,
24
+ "learning_rate": 0.0002,
25
+ "loss": 3.1137,
26
+ "step": 3
27
+ },
28
+ {
29
+ "epoch": 0.0,
30
+ "learning_rate": 0.0002,
31
+ "loss": 1.6054,
32
+ "step": 4
33
+ },
34
+ {
35
+ "epoch": 0.0,
36
+ "learning_rate": 0.0002,
37
+ "loss": 1.0381,
38
+ "step": 5
39
+ },
40
+ {
41
+ "epoch": 0.0,
42
+ "learning_rate": 0.0002,
43
+ "loss": 0.9959,
44
+ "step": 6
45
+ },
46
+ {
47
+ "epoch": 0.0,
48
+ "learning_rate": 0.0002,
49
+ "loss": 0.7395,
50
+ "step": 7
51
+ },
52
+ {
53
+ "epoch": 0.0,
54
+ "learning_rate": 0.0002,
55
+ "loss": 0.3255,
56
+ "step": 8
57
+ },
58
+ {
59
+ "epoch": 0.0,
60
+ "learning_rate": 0.0002,
61
+ "loss": 0.8252,
62
+ "step": 9
63
+ },
64
+ {
65
+ "epoch": 0.0,
66
+ "learning_rate": 0.0002,
67
+ "loss": 0.5362,
68
+ "step": 10
69
+ },
70
+ {
71
+ "epoch": 0.0,
72
+ "learning_rate": 0.0002,
73
+ "loss": 1.404,
74
+ "step": 11
75
+ },
76
+ {
77
+ "epoch": 0.0,
78
+ "learning_rate": 0.0002,
79
+ "loss": 0.6234,
80
+ "step": 12
81
+ },
82
+ {
83
+ "epoch": 0.0,
84
+ "learning_rate": 0.0002,
85
+ "loss": 1.0263,
86
+ "step": 13
87
+ },
88
+ {
89
+ "epoch": 0.0,
90
+ "learning_rate": 0.0002,
91
+ "loss": 0.2622,
92
+ "step": 14
93
+ },
94
+ {
95
+ "epoch": 0.0,
96
+ "learning_rate": 0.0002,
97
+ "loss": 0.2692,
98
+ "step": 15
99
+ },
100
+ {
101
+ "epoch": 0.0,
102
+ "learning_rate": 0.0002,
103
+ "loss": 0.2624,
104
+ "step": 16
105
+ },
106
+ {
107
+ "epoch": 0.0,
108
+ "learning_rate": 0.0002,
109
+ "loss": 0.4385,
110
+ "step": 17
111
+ },
112
+ {
113
+ "epoch": 0.0,
114
+ "learning_rate": 0.0002,
115
+ "loss": 0.3265,
116
+ "step": 18
117
+ },
118
+ {
119
+ "epoch": 0.0,
120
+ "learning_rate": 0.0002,
121
+ "loss": 0.2191,
122
+ "step": 19
123
+ },
124
+ {
125
+ "epoch": 0.0,
126
+ "learning_rate": 0.0002,
127
+ "loss": 1.0049,
128
+ "step": 20
129
+ },
130
+ {
131
+ "epoch": 0.0,
132
+ "learning_rate": 0.0002,
133
+ "loss": 0.6586,
134
+ "step": 21
135
+ },
136
+ {
137
+ "epoch": 0.0,
138
+ "learning_rate": 0.0002,
139
+ "loss": 0.3471,
140
+ "step": 22
141
+ },
142
+ {
143
+ "epoch": 0.0,
144
+ "learning_rate": 0.0002,
145
+ "loss": 0.7134,
146
+ "step": 23
147
+ },
148
+ {
149
+ "epoch": 0.0,
150
+ "learning_rate": 0.0002,
151
+ "loss": 1.01,
152
+ "step": 24
153
+ },
154
+ {
155
+ "epoch": 0.0,
156
+ "learning_rate": 0.0002,
157
+ "loss": 0.2802,
158
+ "step": 25
159
+ },
160
+ {
161
+ "epoch": 0.0,
162
+ "learning_rate": 0.0002,
163
+ "loss": 0.4205,
164
+ "step": 26
165
+ },
166
+ {
167
+ "epoch": 0.0,
168
+ "learning_rate": 0.0002,
169
+ "loss": 0.7682,
170
+ "step": 27
171
+ },
172
+ {
173
+ "epoch": 0.0,
174
+ "learning_rate": 0.0002,
175
+ "loss": 0.2002,
176
+ "step": 28
177
+ },
178
+ {
179
+ "epoch": 0.0,
180
+ "learning_rate": 0.0002,
181
+ "loss": 0.2132,
182
+ "step": 29
183
+ },
184
+ {
185
+ "epoch": 0.0,
186
+ "learning_rate": 0.0002,
187
+ "loss": 1.0622,
188
+ "step": 30
189
+ },
190
+ {
191
+ "epoch": 0.0,
192
+ "learning_rate": 0.0002,
193
+ "loss": 0.212,
194
+ "step": 31
195
+ },
196
+ {
197
+ "epoch": 0.0,
198
+ "learning_rate": 0.0002,
199
+ "loss": 0.3738,
200
+ "step": 32
201
+ },
202
+ {
203
+ "epoch": 0.0,
204
+ "learning_rate": 0.0002,
205
+ "loss": 0.3594,
206
+ "step": 33
207
+ },
208
+ {
209
+ "epoch": 0.0,
210
+ "learning_rate": 0.0002,
211
+ "loss": 0.8766,
212
+ "step": 34
213
+ },
214
+ {
215
+ "epoch": 0.0,
216
+ "learning_rate": 0.0002,
217
+ "loss": 0.3108,
218
+ "step": 35
219
+ },
220
+ {
221
+ "epoch": 0.0,
222
+ "learning_rate": 0.0002,
223
+ "loss": 0.2127,
224
+ "step": 36
225
+ },
226
+ {
227
+ "epoch": 0.0,
228
+ "learning_rate": 0.0002,
229
+ "loss": 0.5968,
230
+ "step": 37
231
+ },
232
+ {
233
+ "epoch": 0.0,
234
+ "learning_rate": 0.0002,
235
+ "loss": 0.8806,
236
+ "step": 38
237
+ },
238
+ {
239
+ "epoch": 0.0,
240
+ "learning_rate": 0.0002,
241
+ "loss": 0.0633,
242
+ "step": 39
243
+ },
244
+ {
245
+ "epoch": 0.0,
246
+ "learning_rate": 0.0002,
247
+ "loss": 0.5851,
248
+ "step": 40
249
+ },
250
+ {
251
+ "epoch": 0.0,
252
+ "learning_rate": 0.0002,
253
+ "loss": 0.2376,
254
+ "step": 41
255
+ },
256
+ {
257
+ "epoch": 0.0,
258
+ "learning_rate": 0.0002,
259
+ "loss": 0.2293,
260
+ "step": 42
261
+ },
262
+ {
263
+ "epoch": 0.0,
264
+ "learning_rate": 0.0002,
265
+ "loss": 0.428,
266
+ "step": 43
267
+ },
268
+ {
269
+ "epoch": 0.0,
270
+ "learning_rate": 0.0002,
271
+ "loss": 0.131,
272
+ "step": 44
273
+ },
274
+ {
275
+ "epoch": 0.0,
276
+ "learning_rate": 0.0002,
277
+ "loss": 0.3724,
278
+ "step": 45
279
+ },
280
+ {
281
+ "epoch": 0.0,
282
+ "learning_rate": 0.0002,
283
+ "loss": 0.5031,
284
+ "step": 46
285
+ },
286
+ {
287
+ "epoch": 0.0,
288
+ "learning_rate": 0.0002,
289
+ "loss": 0.4934,
290
+ "step": 47
291
+ },
292
+ {
293
+ "epoch": 0.0,
294
+ "learning_rate": 0.0002,
295
+ "loss": 0.8127,
296
+ "step": 48
297
+ },
298
+ {
299
+ "epoch": 0.0,
300
+ "learning_rate": 0.0002,
301
+ "loss": 0.4573,
302
+ "step": 49
303
+ },
304
+ {
305
+ "epoch": 0.0,
306
+ "learning_rate": 0.0002,
307
+ "loss": 0.5568,
308
+ "step": 50
309
+ },
310
+ {
311
+ "epoch": 0.0,
312
+ "learning_rate": 0.0002,
313
+ "loss": 0.5411,
314
+ "step": 51
315
+ },
316
+ {
317
+ "epoch": 0.0,
318
+ "learning_rate": 0.0002,
319
+ "loss": 0.4448,
320
+ "step": 52
321
+ },
322
+ {
323
+ "epoch": 0.0,
324
+ "learning_rate": 0.0002,
325
+ "loss": 0.3774,
326
+ "step": 53
327
+ },
328
+ {
329
+ "epoch": 0.0,
330
+ "learning_rate": 0.0002,
331
+ "loss": 0.1825,
332
+ "step": 54
333
+ },
334
+ {
335
+ "epoch": 0.0,
336
+ "learning_rate": 0.0002,
337
+ "loss": 0.2356,
338
+ "step": 55
339
+ },
340
+ {
341
+ "epoch": 0.0,
342
+ "learning_rate": 0.0002,
343
+ "loss": 0.0236,
344
+ "step": 56
345
+ },
346
+ {
347
+ "epoch": 0.0,
348
+ "learning_rate": 0.0002,
349
+ "loss": 0.4344,
350
+ "step": 57
351
+ },
352
+ {
353
+ "epoch": 0.0,
354
+ "learning_rate": 0.0002,
355
+ "loss": 0.4589,
356
+ "step": 58
357
+ },
358
+ {
359
+ "epoch": 0.0,
360
+ "learning_rate": 0.0002,
361
+ "loss": 0.3766,
362
+ "step": 59
363
+ },
364
+ {
365
+ "epoch": 0.0,
366
+ "learning_rate": 0.0002,
367
+ "loss": 0.6034,
368
+ "step": 60
369
+ },
370
+ {
371
+ "epoch": 0.0,
372
+ "learning_rate": 0.0002,
373
+ "loss": 0.7632,
374
+ "step": 61
375
+ },
376
+ {
377
+ "epoch": 0.0,
378
+ "learning_rate": 0.0002,
379
+ "loss": 0.0612,
380
+ "step": 62
381
+ },
382
+ {
383
+ "epoch": 0.0,
384
+ "learning_rate": 0.0002,
385
+ "loss": 0.6783,
386
+ "step": 63
387
+ },
388
+ {
389
+ "epoch": 0.0,
390
+ "learning_rate": 0.0002,
391
+ "loss": 0.2845,
392
+ "step": 64
393
+ },
394
+ {
395
+ "epoch": 0.0,
396
+ "learning_rate": 0.0002,
397
+ "loss": 0.395,
398
+ "step": 65
399
+ },
400
+ {
401
+ "epoch": 0.0,
402
+ "learning_rate": 0.0002,
403
+ "loss": 0.8106,
404
+ "step": 66
405
+ },
406
+ {
407
+ "epoch": 0.0,
408
+ "learning_rate": 0.0002,
409
+ "loss": 0.1468,
410
+ "step": 67
411
+ },
412
+ {
413
+ "epoch": 0.0,
414
+ "learning_rate": 0.0002,
415
+ "loss": 0.0537,
416
+ "step": 68
417
+ },
418
+ {
419
+ "epoch": 0.0,
420
+ "learning_rate": 0.0002,
421
+ "loss": 0.4816,
422
+ "step": 69
423
+ },
424
+ {
425
+ "epoch": 0.0,
426
+ "learning_rate": 0.0002,
427
+ "loss": 0.6052,
428
+ "step": 70
429
+ },
430
+ {
431
+ "epoch": 0.0,
432
+ "learning_rate": 0.0002,
433
+ "loss": 0.2805,
434
+ "step": 71
435
+ },
436
+ {
437
+ "epoch": 0.0,
438
+ "learning_rate": 0.0002,
439
+ "loss": 0.8279,
440
+ "step": 72
441
+ },
442
+ {
443
+ "epoch": 0.0,
444
+ "learning_rate": 0.0002,
445
+ "loss": 0.6954,
446
+ "step": 73
447
+ },
448
+ {
449
+ "epoch": 0.0,
450
+ "learning_rate": 0.0002,
451
+ "loss": 0.0635,
452
+ "step": 74
453
+ },
454
+ {
455
+ "epoch": 0.0,
456
+ "learning_rate": 0.0002,
457
+ "loss": 0.2866,
458
+ "step": 75
459
+ },
460
+ {
461
+ "epoch": 0.0,
462
+ "learning_rate": 0.0002,
463
+ "loss": 0.9656,
464
+ "step": 76
465
+ },
466
+ {
467
+ "epoch": 0.0,
468
+ "learning_rate": 0.0002,
469
+ "loss": 0.1113,
470
+ "step": 77
471
+ },
472
+ {
473
+ "epoch": 0.0,
474
+ "learning_rate": 0.0002,
475
+ "loss": 0.4063,
476
+ "step": 78
477
+ },
478
+ {
479
+ "epoch": 0.0,
480
+ "learning_rate": 0.0002,
481
+ "loss": 0.3245,
482
+ "step": 79
483
+ },
484
+ {
485
+ "epoch": 0.0,
486
+ "learning_rate": 0.0002,
487
+ "loss": 0.3966,
488
+ "step": 80
489
+ },
490
+ {
491
+ "epoch": 0.0,
492
+ "learning_rate": 0.0002,
493
+ "loss": 0.4809,
494
+ "step": 81
495
+ },
496
+ {
497
+ "epoch": 0.01,
498
+ "learning_rate": 0.0002,
499
+ "loss": 0.3844,
500
+ "step": 82
501
+ },
502
+ {
503
+ "epoch": 0.01,
504
+ "learning_rate": 0.0002,
505
+ "loss": 0.1501,
506
+ "step": 83
507
+ },
508
+ {
509
+ "epoch": 0.01,
510
+ "learning_rate": 0.0002,
511
+ "loss": 0.5504,
512
+ "step": 84
513
+ },
514
+ {
515
+ "epoch": 0.01,
516
+ "learning_rate": 0.0002,
517
+ "loss": 0.2332,
518
+ "step": 85
519
+ },
520
+ {
521
+ "epoch": 0.01,
522
+ "learning_rate": 0.0002,
523
+ "loss": 0.0049,
524
+ "step": 86
525
+ },
526
+ {
527
+ "epoch": 0.01,
528
+ "learning_rate": 0.0002,
529
+ "loss": 0.2585,
530
+ "step": 87
531
+ },
532
+ {
533
+ "epoch": 0.01,
534
+ "learning_rate": 0.0002,
535
+ "loss": 0.2012,
536
+ "step": 88
537
+ },
538
+ {
539
+ "epoch": 0.01,
540
+ "learning_rate": 0.0002,
541
+ "loss": 0.0386,
542
+ "step": 89
543
+ },
544
+ {
545
+ "epoch": 0.01,
546
+ "learning_rate": 0.0002,
547
+ "loss": 0.5818,
548
+ "step": 90
549
+ },
550
+ {
551
+ "epoch": 0.01,
552
+ "learning_rate": 0.0002,
553
+ "loss": 0.2827,
554
+ "step": 91
555
+ },
556
+ {
557
+ "epoch": 0.01,
558
+ "learning_rate": 0.0002,
559
+ "loss": 0.3877,
560
+ "step": 92
561
+ },
562
+ {
563
+ "epoch": 0.01,
564
+ "learning_rate": 0.0002,
565
+ "loss": 0.3117,
566
+ "step": 93
567
+ },
568
+ {
569
+ "epoch": 0.01,
570
+ "learning_rate": 0.0002,
571
+ "loss": 0.9205,
572
+ "step": 94
573
+ },
574
+ {
575
+ "epoch": 0.01,
576
+ "learning_rate": 0.0002,
577
+ "loss": 0.4653,
578
+ "step": 95
579
+ },
580
+ {
581
+ "epoch": 0.01,
582
+ "learning_rate": 0.0002,
583
+ "loss": 0.3412,
584
+ "step": 96
585
+ },
586
+ {
587
+ "epoch": 0.01,
588
+ "learning_rate": 0.0002,
589
+ "loss": 0.3367,
590
+ "step": 97
591
+ },
592
+ {
593
+ "epoch": 0.01,
594
+ "learning_rate": 0.0002,
595
+ "loss": 0.1755,
596
+ "step": 98
597
+ },
598
+ {
599
+ "epoch": 0.01,
600
+ "learning_rate": 0.0002,
601
+ "loss": 0.3586,
602
+ "step": 99
603
+ },
604
+ {
605
+ "epoch": 0.01,
606
+ "learning_rate": 0.0002,
607
+ "loss": 0.5682,
608
+ "step": 100
609
+ },
610
+ {
611
+ "epoch": 0.01,
612
+ "learning_rate": 0.0002,
613
+ "loss": 0.4869,
614
+ "step": 101
615
+ },
616
+ {
617
+ "epoch": 0.01,
618
+ "learning_rate": 0.0002,
619
+ "loss": 0.7614,
620
+ "step": 102
621
+ },
622
+ {
623
+ "epoch": 0.01,
624
+ "learning_rate": 0.0002,
625
+ "loss": 0.4366,
626
+ "step": 103
627
+ },
628
+ {
629
+ "epoch": 0.01,
630
+ "learning_rate": 0.0002,
631
+ "loss": 0.5307,
632
+ "step": 104
633
+ },
634
+ {
635
+ "epoch": 0.01,
636
+ "learning_rate": 0.0002,
637
+ "loss": 0.3974,
638
+ "step": 105
639
+ },
640
+ {
641
+ "epoch": 0.01,
642
+ "learning_rate": 0.0002,
643
+ "loss": 0.5255,
644
+ "step": 106
645
+ },
646
+ {
647
+ "epoch": 0.01,
648
+ "learning_rate": 0.0002,
649
+ "loss": 0.2682,
650
+ "step": 107
651
+ },
652
+ {
653
+ "epoch": 0.01,
654
+ "learning_rate": 0.0002,
655
+ "loss": 0.4884,
656
+ "step": 108
657
+ },
658
+ {
659
+ "epoch": 0.01,
660
+ "learning_rate": 0.0002,
661
+ "loss": 0.0414,
662
+ "step": 109
663
+ },
664
+ {
665
+ "epoch": 0.01,
666
+ "learning_rate": 0.0002,
667
+ "loss": 0.5094,
668
+ "step": 110
669
+ },
670
+ {
671
+ "epoch": 0.01,
672
+ "learning_rate": 0.0002,
673
+ "loss": 0.298,
674
+ "step": 111
675
+ },
676
+ {
677
+ "epoch": 0.01,
678
+ "learning_rate": 0.0002,
679
+ "loss": 0.2147,
680
+ "step": 112
681
+ },
682
+ {
683
+ "epoch": 0.01,
684
+ "learning_rate": 0.0002,
685
+ "loss": 0.2712,
686
+ "step": 113
687
+ },
688
+ {
689
+ "epoch": 0.01,
690
+ "learning_rate": 0.0002,
691
+ "loss": 0.5713,
692
+ "step": 114
693
+ },
694
+ {
695
+ "epoch": 0.01,
696
+ "learning_rate": 0.0002,
697
+ "loss": 0.2979,
698
+ "step": 115
699
+ },
700
+ {
701
+ "epoch": 0.01,
702
+ "learning_rate": 0.0002,
703
+ "loss": 0.2424,
704
+ "step": 116
705
+ },
706
+ {
707
+ "epoch": 0.01,
708
+ "learning_rate": 0.0002,
709
+ "loss": 0.1412,
710
+ "step": 117
711
+ },
712
+ {
713
+ "epoch": 0.01,
714
+ "learning_rate": 0.0002,
715
+ "loss": 0.3252,
716
+ "step": 118
717
+ },
718
+ {
719
+ "epoch": 0.01,
720
+ "learning_rate": 0.0002,
721
+ "loss": 0.4267,
722
+ "step": 119
723
+ },
724
+ {
725
+ "epoch": 0.01,
726
+ "learning_rate": 0.0002,
727
+ "loss": 0.2139,
728
+ "step": 120
729
+ },
730
+ {
731
+ "epoch": 0.01,
732
+ "learning_rate": 0.0002,
733
+ "loss": 0.4214,
734
+ "step": 121
735
+ },
736
+ {
737
+ "epoch": 0.01,
738
+ "learning_rate": 0.0002,
739
+ "loss": 0.2338,
740
+ "step": 122
741
+ },
742
+ {
743
+ "epoch": 0.01,
744
+ "learning_rate": 0.0002,
745
+ "loss": 0.5877,
746
+ "step": 123
747
+ },
748
+ {
749
+ "epoch": 0.01,
750
+ "learning_rate": 0.0002,
751
+ "loss": 0.2574,
752
+ "step": 124
753
+ },
754
+ {
755
+ "epoch": 0.01,
756
+ "learning_rate": 0.0002,
757
+ "loss": 0.0011,
758
+ "step": 125
759
+ },
760
+ {
761
+ "epoch": 0.01,
762
+ "learning_rate": 0.0002,
763
+ "loss": 0.6156,
764
+ "step": 126
765
+ },
766
+ {
767
+ "epoch": 0.01,
768
+ "learning_rate": 0.0002,
769
+ "loss": 0.0888,
770
+ "step": 127
771
+ },
772
+ {
773
+ "epoch": 0.01,
774
+ "learning_rate": 0.0002,
775
+ "loss": 0.3159,
776
+ "step": 128
777
+ },
778
+ {
779
+ "epoch": 0.01,
780
+ "learning_rate": 0.0002,
781
+ "loss": 0.2122,
782
+ "step": 129
783
+ },
784
+ {
785
+ "epoch": 0.01,
786
+ "learning_rate": 0.0002,
787
+ "loss": 0.1131,
788
+ "step": 130
789
+ },
790
+ {
791
+ "epoch": 0.01,
792
+ "learning_rate": 0.0002,
793
+ "loss": 0.1634,
794
+ "step": 131
795
+ },
796
+ {
797
+ "epoch": 0.01,
798
+ "learning_rate": 0.0002,
799
+ "loss": 0.3788,
800
+ "step": 132
801
+ },
802
+ {
803
+ "epoch": 0.01,
804
+ "learning_rate": 0.0002,
805
+ "loss": 0.3187,
806
+ "step": 133
807
+ },
808
+ {
809
+ "epoch": 0.01,
810
+ "learning_rate": 0.0002,
811
+ "loss": 0.1685,
812
+ "step": 134
813
+ },
814
+ {
815
+ "epoch": 0.01,
816
+ "learning_rate": 0.0002,
817
+ "loss": 1.5573,
818
+ "step": 135
819
+ },
820
+ {
821
+ "epoch": 0.01,
822
+ "learning_rate": 0.0002,
823
+ "loss": 0.3409,
824
+ "step": 136
825
+ },
826
+ {
827
+ "epoch": 0.01,
828
+ "learning_rate": 0.0002,
829
+ "loss": 1.1279,
830
+ "step": 137
831
+ },
832
+ {
833
+ "epoch": 0.01,
834
+ "learning_rate": 0.0002,
835
+ "loss": 0.1385,
836
+ "step": 138
837
+ },
838
+ {
839
+ "epoch": 0.01,
840
+ "learning_rate": 0.0002,
841
+ "loss": 0.5391,
842
+ "step": 139
843
+ },
844
+ {
845
+ "epoch": 0.01,
846
+ "learning_rate": 0.0002,
847
+ "loss": 0.9212,
848
+ "step": 140
849
+ },
850
+ {
851
+ "epoch": 0.01,
852
+ "learning_rate": 0.0002,
853
+ "loss": 0.3178,
854
+ "step": 141
855
+ },
856
+ {
857
+ "epoch": 0.01,
858
+ "learning_rate": 0.0002,
859
+ "loss": 0.1896,
860
+ "step": 142
861
+ },
862
+ {
863
+ "epoch": 0.01,
864
+ "learning_rate": 0.0002,
865
+ "loss": 0.2479,
866
+ "step": 143
867
+ },
868
+ {
869
+ "epoch": 0.01,
870
+ "learning_rate": 0.0002,
871
+ "loss": 0.0806,
872
+ "step": 144
873
+ },
874
+ {
875
+ "epoch": 0.01,
876
+ "learning_rate": 0.0002,
877
+ "loss": 0.4446,
878
+ "step": 145
879
+ },
880
+ {
881
+ "epoch": 0.01,
882
+ "learning_rate": 0.0002,
883
+ "loss": 0.1199,
884
+ "step": 146
885
+ },
886
+ {
887
+ "epoch": 0.01,
888
+ "learning_rate": 0.0002,
889
+ "loss": 0.0728,
890
+ "step": 147
891
+ },
892
+ {
893
+ "epoch": 0.01,
894
+ "learning_rate": 0.0002,
895
+ "loss": 0.2178,
896
+ "step": 148
897
+ },
898
+ {
899
+ "epoch": 0.01,
900
+ "learning_rate": 0.0002,
901
+ "loss": 0.6712,
902
+ "step": 149
903
+ },
904
+ {
905
+ "epoch": 0.01,
906
+ "learning_rate": 0.0002,
907
+ "loss": 0.0917,
908
+ "step": 150
909
+ },
910
+ {
911
+ "epoch": 0.01,
912
+ "learning_rate": 0.0002,
913
+ "loss": 0.0679,
914
+ "step": 151
915
+ },
916
+ {
917
+ "epoch": 0.01,
918
+ "learning_rate": 0.0002,
919
+ "loss": 0.2296,
920
+ "step": 152
921
+ },
922
+ {
923
+ "epoch": 0.01,
924
+ "learning_rate": 0.0002,
925
+ "loss": 0.4093,
926
+ "step": 153
927
+ },
928
+ {
929
+ "epoch": 0.01,
930
+ "learning_rate": 0.0002,
931
+ "loss": 0.7889,
932
+ "step": 154
933
+ },
934
+ {
935
+ "epoch": 0.01,
936
+ "learning_rate": 0.0002,
937
+ "loss": 0.142,
938
+ "step": 155
939
+ },
940
+ {
941
+ "epoch": 0.01,
942
+ "learning_rate": 0.0002,
943
+ "loss": 0.16,
944
+ "step": 156
945
+ },
946
+ {
947
+ "epoch": 0.01,
948
+ "learning_rate": 0.0002,
949
+ "loss": 0.2812,
950
+ "step": 157
951
+ },
952
+ {
953
+ "epoch": 0.01,
954
+ "learning_rate": 0.0002,
955
+ "loss": 0.3536,
956
+ "step": 158
957
+ },
958
+ {
959
+ "epoch": 0.01,
960
+ "learning_rate": 0.0002,
961
+ "loss": 0.2734,
962
+ "step": 159
963
+ },
964
+ {
965
+ "epoch": 0.01,
966
+ "learning_rate": 0.0002,
967
+ "loss": 1.0048,
968
+ "step": 160
969
+ },
970
+ {
971
+ "epoch": 0.01,
972
+ "learning_rate": 0.0002,
973
+ "loss": 0.2911,
974
+ "step": 161
975
+ },
976
+ {
977
+ "epoch": 0.01,
978
+ "learning_rate": 0.0002,
979
+ "loss": 0.2417,
980
+ "step": 162
981
+ },
982
+ {
983
+ "epoch": 0.01,
984
+ "learning_rate": 0.0002,
985
+ "loss": 0.8293,
986
+ "step": 163
987
+ },
988
+ {
989
+ "epoch": 0.01,
990
+ "learning_rate": 0.0002,
991
+ "loss": 0.4375,
992
+ "step": 164
993
+ },
994
+ {
995
+ "epoch": 0.01,
996
+ "learning_rate": 0.0002,
997
+ "loss": 0.7972,
998
+ "step": 165
999
+ },
1000
+ {
1001
+ "epoch": 0.01,
1002
+ "learning_rate": 0.0002,
1003
+ "loss": 0.1297,
1004
+ "step": 166
1005
+ },
1006
+ {
1007
+ "epoch": 0.01,
1008
+ "learning_rate": 0.0002,
1009
+ "loss": 0.5533,
1010
+ "step": 167
1011
+ },
1012
+ {
1013
+ "epoch": 0.01,
1014
+ "learning_rate": 0.0002,
1015
+ "loss": 0.8447,
1016
+ "step": 168
1017
+ },
1018
+ {
1019
+ "epoch": 0.01,
1020
+ "learning_rate": 0.0002,
1021
+ "loss": 0.0787,
1022
+ "step": 169
1023
+ },
1024
+ {
1025
+ "epoch": 0.01,
1026
+ "learning_rate": 0.0002,
1027
+ "loss": 0.2196,
1028
+ "step": 170
1029
+ },
1030
+ {
1031
+ "epoch": 0.01,
1032
+ "learning_rate": 0.0002,
1033
+ "loss": 0.1463,
1034
+ "step": 171
1035
+ },
1036
+ {
1037
+ "epoch": 0.01,
1038
+ "learning_rate": 0.0002,
1039
+ "loss": 0.2969,
1040
+ "step": 172
1041
+ },
1042
+ {
1043
+ "epoch": 0.01,
1044
+ "learning_rate": 0.0002,
1045
+ "loss": 0.204,
1046
+ "step": 173
1047
+ },
1048
+ {
1049
+ "epoch": 0.01,
1050
+ "learning_rate": 0.0002,
1051
+ "loss": 0.5595,
1052
+ "step": 174
1053
+ },
1054
+ {
1055
+ "epoch": 0.01,
1056
+ "learning_rate": 0.0002,
1057
+ "loss": 0.1947,
1058
+ "step": 175
1059
+ },
1060
+ {
1061
+ "epoch": 0.01,
1062
+ "learning_rate": 0.0002,
1063
+ "loss": 0.239,
1064
+ "step": 176
1065
+ },
1066
+ {
1067
+ "epoch": 0.01,
1068
+ "learning_rate": 0.0002,
1069
+ "loss": 0.0937,
1070
+ "step": 177
1071
+ },
1072
+ {
1073
+ "epoch": 0.01,
1074
+ "learning_rate": 0.0002,
1075
+ "loss": 0.0284,
1076
+ "step": 178
1077
+ },
1078
+ {
1079
+ "epoch": 0.01,
1080
+ "learning_rate": 0.0002,
1081
+ "loss": 0.4115,
1082
+ "step": 179
1083
+ },
1084
+ {
1085
+ "epoch": 0.01,
1086
+ "learning_rate": 0.0002,
1087
+ "loss": 0.1322,
1088
+ "step": 180
1089
+ },
1090
+ {
1091
+ "epoch": 0.01,
1092
+ "learning_rate": 0.0002,
1093
+ "loss": 0.3562,
1094
+ "step": 181
1095
+ },
1096
+ {
1097
+ "epoch": 0.01,
1098
+ "learning_rate": 0.0002,
1099
+ "loss": 0.5618,
1100
+ "step": 182
1101
+ },
1102
+ {
1103
+ "epoch": 0.01,
1104
+ "learning_rate": 0.0002,
1105
+ "loss": 0.5469,
1106
+ "step": 183
1107
+ },
1108
+ {
1109
+ "epoch": 0.01,
1110
+ "learning_rate": 0.0002,
1111
+ "loss": 0.2538,
1112
+ "step": 184
1113
+ },
1114
+ {
1115
+ "epoch": 0.01,
1116
+ "learning_rate": 0.0002,
1117
+ "loss": 0.3875,
1118
+ "step": 185
1119
+ },
1120
+ {
1121
+ "epoch": 0.01,
1122
+ "learning_rate": 0.0002,
1123
+ "loss": 0.1755,
1124
+ "step": 186
1125
+ },
1126
+ {
1127
+ "epoch": 0.01,
1128
+ "learning_rate": 0.0002,
1129
+ "loss": 0.5634,
1130
+ "step": 187
1131
+ },
1132
+ {
1133
+ "epoch": 0.01,
1134
+ "learning_rate": 0.0002,
1135
+ "loss": 0.5176,
1136
+ "step": 188
1137
+ },
1138
+ {
1139
+ "epoch": 0.01,
1140
+ "learning_rate": 0.0002,
1141
+ "loss": 0.3164,
1142
+ "step": 189
1143
+ },
1144
+ {
1145
+ "epoch": 0.01,
1146
+ "learning_rate": 0.0002,
1147
+ "loss": 0.1107,
1148
+ "step": 190
1149
+ },
1150
+ {
1151
+ "epoch": 0.01,
1152
+ "learning_rate": 0.0002,
1153
+ "loss": 0.7371,
1154
+ "step": 191
1155
+ },
1156
+ {
1157
+ "epoch": 0.01,
1158
+ "learning_rate": 0.0002,
1159
+ "loss": 0.3597,
1160
+ "step": 192
1161
+ },
1162
+ {
1163
+ "epoch": 0.01,
1164
+ "learning_rate": 0.0002,
1165
+ "loss": 0.6858,
1166
+ "step": 193
1167
+ },
1168
+ {
1169
+ "epoch": 0.01,
1170
+ "learning_rate": 0.0002,
1171
+ "loss": 0.2797,
1172
+ "step": 194
1173
+ },
1174
+ {
1175
+ "epoch": 0.01,
1176
+ "learning_rate": 0.0002,
1177
+ "loss": 0.5096,
1178
+ "step": 195
1179
+ },
1180
+ {
1181
+ "epoch": 0.01,
1182
+ "learning_rate": 0.0002,
1183
+ "loss": 0.4265,
1184
+ "step": 196
1185
+ },
1186
+ {
1187
+ "epoch": 0.01,
1188
+ "learning_rate": 0.0002,
1189
+ "loss": 0.4173,
1190
+ "step": 197
1191
+ },
1192
+ {
1193
+ "epoch": 0.01,
1194
+ "learning_rate": 0.0002,
1195
+ "loss": 0.1054,
1196
+ "step": 198
1197
+ },
1198
+ {
1199
+ "epoch": 0.01,
1200
+ "learning_rate": 0.0002,
1201
+ "loss": 0.112,
1202
+ "step": 199
1203
+ },
1204
+ {
1205
+ "epoch": 0.01,
1206
+ "learning_rate": 0.0002,
1207
+ "loss": 0.316,
1208
+ "step": 200
1209
+ },
1210
+ {
1211
+ "epoch": 0.01,
1212
+ "eval_loss": 0.3453182876110077,
1213
+ "eval_runtime": 435.8836,
1214
+ "eval_samples_per_second": 2.294,
1215
+ "eval_steps_per_second": 1.147,
1216
+ "step": 200
1217
+ },
1218
+ {
1219
+ "epoch": 0.01,
1220
+ "mmlu_eval_accuracy": 0.4811559812252676,
1221
+ "mmlu_eval_accuracy_abstract_algebra": 0.45454545454545453,
1222
+ "mmlu_eval_accuracy_anatomy": 0.5,
1223
+ "mmlu_eval_accuracy_astronomy": 0.25,
1224
+ "mmlu_eval_accuracy_business_ethics": 0.6363636363636364,
1225
+ "mmlu_eval_accuracy_clinical_knowledge": 0.41379310344827586,
1226
+ "mmlu_eval_accuracy_college_biology": 0.5,
1227
+ "mmlu_eval_accuracy_college_chemistry": 0.125,
1228
+ "mmlu_eval_accuracy_college_computer_science": 0.45454545454545453,
1229
+ "mmlu_eval_accuracy_college_mathematics": 0.45454545454545453,
1230
+ "mmlu_eval_accuracy_college_medicine": 0.5454545454545454,
1231
+ "mmlu_eval_accuracy_college_physics": 0.36363636363636365,
1232
+ "mmlu_eval_accuracy_computer_security": 0.6363636363636364,
1233
+ "mmlu_eval_accuracy_conceptual_physics": 0.3076923076923077,
1234
+ "mmlu_eval_accuracy_econometrics": 0.3333333333333333,
1235
+ "mmlu_eval_accuracy_electrical_engineering": 0.25,
1236
+ "mmlu_eval_accuracy_elementary_mathematics": 0.2926829268292683,
1237
+ "mmlu_eval_accuracy_formal_logic": 0.21428571428571427,
1238
+ "mmlu_eval_accuracy_global_facts": 0.0,
1239
+ "mmlu_eval_accuracy_high_school_biology": 0.375,
1240
+ "mmlu_eval_accuracy_high_school_chemistry": 0.3181818181818182,
1241
+ "mmlu_eval_accuracy_high_school_computer_science": 0.5555555555555556,
1242
+ "mmlu_eval_accuracy_high_school_european_history": 0.7222222222222222,
1243
+ "mmlu_eval_accuracy_high_school_geography": 0.8181818181818182,
1244
+ "mmlu_eval_accuracy_high_school_government_and_politics": 0.6666666666666666,
1245
+ "mmlu_eval_accuracy_high_school_macroeconomics": 0.4186046511627907,
1246
+ "mmlu_eval_accuracy_high_school_mathematics": 0.27586206896551724,
1247
+ "mmlu_eval_accuracy_high_school_microeconomics": 0.5769230769230769,
1248
+ "mmlu_eval_accuracy_high_school_physics": 0.4117647058823529,
1249
+ "mmlu_eval_accuracy_high_school_psychology": 0.7166666666666667,
1250
+ "mmlu_eval_accuracy_high_school_statistics": 0.34782608695652173,
1251
+ "mmlu_eval_accuracy_high_school_us_history": 0.6818181818181818,
1252
+ "mmlu_eval_accuracy_high_school_world_history": 0.5384615384615384,
1253
+ "mmlu_eval_accuracy_human_aging": 0.6086956521739131,
1254
+ "mmlu_eval_accuracy_human_sexuality": 0.3333333333333333,
1255
+ "mmlu_eval_accuracy_international_law": 0.7692307692307693,
1256
+ "mmlu_eval_accuracy_jurisprudence": 0.45454545454545453,
1257
+ "mmlu_eval_accuracy_logical_fallacies": 0.7777777777777778,
1258
+ "mmlu_eval_accuracy_machine_learning": 0.45454545454545453,
1259
+ "mmlu_eval_accuracy_management": 0.7272727272727273,
1260
+ "mmlu_eval_accuracy_marketing": 0.88,
1261
+ "mmlu_eval_accuracy_medical_genetics": 0.7272727272727273,
1262
+ "mmlu_eval_accuracy_miscellaneous": 0.5813953488372093,
1263
+ "mmlu_eval_accuracy_moral_disputes": 0.42105263157894735,
1264
+ "mmlu_eval_accuracy_moral_scenarios": 0.35,
1265
+ "mmlu_eval_accuracy_nutrition": 0.6363636363636364,
1266
+ "mmlu_eval_accuracy_philosophy": 0.47058823529411764,
1267
+ "mmlu_eval_accuracy_prehistory": 0.34285714285714286,
1268
+ "mmlu_eval_accuracy_professional_accounting": 0.22580645161290322,
1269
+ "mmlu_eval_accuracy_professional_law": 0.3176470588235294,
1270
+ "mmlu_eval_accuracy_professional_medicine": 0.2903225806451613,
1271
+ "mmlu_eval_accuracy_professional_psychology": 0.4492753623188406,
1272
+ "mmlu_eval_accuracy_public_relations": 0.4166666666666667,
1273
+ "mmlu_eval_accuracy_security_studies": 0.5185185185185185,
1274
+ "mmlu_eval_accuracy_sociology": 0.5909090909090909,
1275
+ "mmlu_eval_accuracy_us_foreign_policy": 0.6363636363636364,
1276
+ "mmlu_eval_accuracy_virology": 0.5,
1277
+ "mmlu_eval_accuracy_world_religions": 0.7894736842105263,
1278
+ "mmlu_loss": 0.9429792200577477,
1279
+ "step": 200
1280
+ }
1281
+ ],
1282
+ "max_steps": 5000,
1283
+ "num_train_epochs": 1,
1284
+ "total_flos": 3.4693272745672704e+16,
1285
+ "trial_name": null,
1286
+ "trial_params": null
1287
+ }
checkpoint-200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd28a065deb906dd6787d5be775d7f7fef1c3352a93f2dc2266d20467a05b48d
3
+ size 6011
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "<unk>"
6
+ }
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 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": null,
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "pad_token": null,
24
+ "padding_side": "right",
25
+ "sp_model_kwargs": {},
26
+ "spaces_between_special_tokens": false,
27
+ "tokenizer_class": "LlamaTokenizer",
28
+ "unk_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "use_default_system_prompt": true
37
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd28a065deb906dd6787d5be775d7f7fef1c3352a93f2dc2266d20467a05b48d
3
+ size 6011