Hugging Face's logo

rghosh8
/
supportGPT-v7

Text Generation
PEFT
English
falcon
custom_code
Model card Files Community
rghosh08 commited on
Commit
8a07bab
·
1 Parent(s): 12a9a52

Update from ubuntu

Browse files
Files changed (23) hide show
  1. README.md +34 -1
  2. adapter_config.json +20 -0
  3. adapter_model.bin +3 -0
  4. checkpoint-1000/README.md +34 -0
  5. checkpoint-1000/adapter_config.json +20 -0
  6. checkpoint-1000/adapter_model.bin +3 -0
  7. checkpoint-1000/optimizer.pt +3 -0
  8. checkpoint-1000/rng_state.pth +3 -0
  9. checkpoint-1000/scheduler.pt +3 -0
  10. checkpoint-1000/special_tokens_map.json +17 -0
  11. checkpoint-1000/tokenizer.json +0 -0
  12. checkpoint-1000/tokenizer_config.json +118 -0
  13. checkpoint-1000/trainer_state.json +619 -0
  14. checkpoint-1000/training_args.bin +3 -0
  15. config.json +38 -0
  16. optimizer.pt +3 -0
  17. rng_state.pth +3 -0
  18. scheduler.pt +3 -0
  19. special_tokens_map.json +17 -0
  20. tokenizer.json +0 -0
  21. tokenizer_config.json +118 -0
  22. trainer_state.json +619 -0
  23. training_args.bin +3 -0
README.md CHANGED
@@ -1 +1,34 @@
1
- hello
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 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: True
29
+ - bnb_4bit_compute_dtype: float16
30
+ ### Framework versions
31
+
32
+ - PEFT 0.6.0.dev0
33
+
34
+ - PEFT 0.6.0.dev0
adapter_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "tiiuae/falcon-7b",
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
+ "query_key_value"
18
+ ],
19
+ "task_type": "CAUSAL_LM"
20
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0c2b96d8610c444a6fb069a284c273cd4d0a9bc7d2b14e760473ea92a347973
3
+ size 75521265
checkpoint-1000/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: True
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: True
29
+ - bnb_4bit_compute_dtype: float16
30
+ ### Framework versions
31
+
32
+ - PEFT 0.6.0.dev0
33
+
34
+ - PEFT 0.6.0.dev0
checkpoint-1000/adapter_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "tiiuae/falcon-7b",
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
+ "query_key_value"
18
+ ],
19
+ "task_type": "CAUSAL_LM"
20
+ }
checkpoint-1000/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0c2b96d8610c444a6fb069a284c273cd4d0a9bc7d2b14e760473ea92a347973
3
+ size 75521265
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58309f0661f54ae83280183516125b5997311ca56006607296266803fa3ecb88
3
+ size 151034501
checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18866927b9f45360d339346dd9a98ebb2315df44e637ddf894df92838b507bd2
3
+ size 14511
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bb7339d1d2da342a44f3ba5e076fb6e5d93aee86f890c002703d2b3a0750820
3
+ size 627
checkpoint-1000/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ ">>TITLE<<",
4
+ ">>ABSTRACT<<",
5
+ ">>INTRODUCTION<<",
6
+ ">>SUMMARY<<",
7
+ ">>COMMENT<<",
8
+ ">>ANSWER<<",
9
+ ">>QUESTION<<",
10
+ ">>DOMAIN<<",
11
+ ">>PREFIX<<",
12
+ ">>SUFFIX<<",
13
+ ">>MIDDLE<<"
14
+ ],
15
+ "eos_token": "<|endoftext|>",
16
+ "pad_token": "<|endoftext|>"
17
+ }
checkpoint-1000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/tokenizer_config.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": ">>TITLE<<",
6
+ "lstrip": true,
7
+ "normalized": false,
8
+ "rstrip": true,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": ">>ABSTRACT<<",
14
+ "lstrip": true,
15
+ "normalized": false,
16
+ "rstrip": true,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": ">>INTRODUCTION<<",
22
+ "lstrip": true,
23
+ "normalized": false,
24
+ "rstrip": true,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": ">>SUMMARY<<",
30
+ "lstrip": true,
31
+ "normalized": false,
32
+ "rstrip": true,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": ">>COMMENT<<",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": true,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": ">>ANSWER<<",
46
+ "lstrip": true,
47
+ "normalized": false,
48
+ "rstrip": true,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": ">>QUESTION<<",
54
+ "lstrip": true,
55
+ "normalized": false,
56
+ "rstrip": true,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": ">>DOMAIN<<",
62
+ "lstrip": true,
63
+ "normalized": false,
64
+ "rstrip": true,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": ">>PREFIX<<",
70
+ "lstrip": true,
71
+ "normalized": false,
72
+ "rstrip": true,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": ">>SUFFIX<<",
78
+ "lstrip": true,
79
+ "normalized": false,
80
+ "rstrip": true,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": ">>MIDDLE<<",
86
+ "lstrip": true,
87
+ "normalized": false,
88
+ "rstrip": true,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<|endoftext|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ }
100
+ },
101
+ "additional_special_tokens": [
102
+ ">>TITLE<<",
103
+ ">>ABSTRACT<<",
104
+ ">>INTRODUCTION<<",
105
+ ">>SUMMARY<<",
106
+ ">>COMMENT<<",
107
+ ">>ANSWER<<",
108
+ ">>QUESTION<<",
109
+ ">>DOMAIN<<",
110
+ ">>PREFIX<<",
111
+ ">>SUFFIX<<",
112
+ ">>MIDDLE<<"
113
+ ],
114
+ "clean_up_tokenization_spaces": true,
115
+ "eos_token": "<|endoftext|>",
116
+ "model_max_length": 2048,
117
+ "tokenizer_class": "PreTrainedTokenizerFast"
118
+ }
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,619 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.48953616448415127,
5
+ "eval_steps": 500,
6
+ "global_step": 1000,
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": 2.1809,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 0.0002,
20
+ "loss": 2.515,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.01,
25
+ "learning_rate": 0.0002,
26
+ "loss": 2.3848,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.02,
31
+ "learning_rate": 0.0002,
32
+ "loss": 2.2882,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 0.02,
37
+ "learning_rate": 0.0002,
38
+ "loss": 2.2283,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.03,
43
+ "learning_rate": 0.0002,
44
+ "loss": 2.1074,
45
+ "step": 60
46
+ },
47
+ {
48
+ "epoch": 0.03,
49
+ "learning_rate": 0.0002,
50
+ "loss": 2.1195,
51
+ "step": 70
52
+ },
53
+ {
54
+ "epoch": 0.04,
55
+ "learning_rate": 0.0002,
56
+ "loss": 2.1942,
57
+ "step": 80
58
+ },
59
+ {
60
+ "epoch": 0.04,
61
+ "learning_rate": 0.0002,
62
+ "loss": 2.0617,
63
+ "step": 90
64
+ },
65
+ {
66
+ "epoch": 0.05,
67
+ "learning_rate": 0.0002,
68
+ "loss": 2.2377,
69
+ "step": 100
70
+ },
71
+ {
72
+ "epoch": 0.05,
73
+ "learning_rate": 0.0002,
74
+ "loss": 2.1167,
75
+ "step": 110
76
+ },
77
+ {
78
+ "epoch": 0.06,
79
+ "learning_rate": 0.0002,
80
+ "loss": 2.0454,
81
+ "step": 120
82
+ },
83
+ {
84
+ "epoch": 0.06,
85
+ "learning_rate": 0.0002,
86
+ "loss": 2.0348,
87
+ "step": 130
88
+ },
89
+ {
90
+ "epoch": 0.07,
91
+ "learning_rate": 0.0002,
92
+ "loss": 2.1334,
93
+ "step": 140
94
+ },
95
+ {
96
+ "epoch": 0.07,
97
+ "learning_rate": 0.0002,
98
+ "loss": 2.1347,
99
+ "step": 150
100
+ },
101
+ {
102
+ "epoch": 0.08,
103
+ "learning_rate": 0.0002,
104
+ "loss": 1.9811,
105
+ "step": 160
106
+ },
107
+ {
108
+ "epoch": 0.08,
109
+ "learning_rate": 0.0002,
110
+ "loss": 2.1339,
111
+ "step": 170
112
+ },
113
+ {
114
+ "epoch": 0.09,
115
+ "learning_rate": 0.0002,
116
+ "loss": 2.1432,
117
+ "step": 180
118
+ },
119
+ {
120
+ "epoch": 0.09,
121
+ "learning_rate": 0.0002,
122
+ "loss": 1.9374,
123
+ "step": 190
124
+ },
125
+ {
126
+ "epoch": 0.1,
127
+ "learning_rate": 0.0002,
128
+ "loss": 2.078,
129
+ "step": 200
130
+ },
131
+ {
132
+ "epoch": 0.1,
133
+ "learning_rate": 0.0002,
134
+ "loss": 2.0077,
135
+ "step": 210
136
+ },
137
+ {
138
+ "epoch": 0.11,
139
+ "learning_rate": 0.0002,
140
+ "loss": 2.1386,
141
+ "step": 220
142
+ },
143
+ {
144
+ "epoch": 0.11,
145
+ "learning_rate": 0.0002,
146
+ "loss": 2.0728,
147
+ "step": 230
148
+ },
149
+ {
150
+ "epoch": 0.12,
151
+ "learning_rate": 0.0002,
152
+ "loss": 2.058,
153
+ "step": 240
154
+ },
155
+ {
156
+ "epoch": 0.12,
157
+ "learning_rate": 0.0002,
158
+ "loss": 2.1418,
159
+ "step": 250
160
+ },
161
+ {
162
+ "epoch": 0.13,
163
+ "learning_rate": 0.0002,
164
+ "loss": 1.8572,
165
+ "step": 260
166
+ },
167
+ {
168
+ "epoch": 0.13,
169
+ "learning_rate": 0.0002,
170
+ "loss": 2.0748,
171
+ "step": 270
172
+ },
173
+ {
174
+ "epoch": 0.14,
175
+ "learning_rate": 0.0002,
176
+ "loss": 2.0684,
177
+ "step": 280
178
+ },
179
+ {
180
+ "epoch": 0.14,
181
+ "learning_rate": 0.0002,
182
+ "loss": 1.9738,
183
+ "step": 290
184
+ },
185
+ {
186
+ "epoch": 0.15,
187
+ "learning_rate": 0.0002,
188
+ "loss": 2.0983,
189
+ "step": 300
190
+ },
191
+ {
192
+ "epoch": 0.15,
193
+ "learning_rate": 0.0002,
194
+ "loss": 1.9303,
195
+ "step": 310
196
+ },
197
+ {
198
+ "epoch": 0.16,
199
+ "learning_rate": 0.0002,
200
+ "loss": 2.0693,
201
+ "step": 320
202
+ },
203
+ {
204
+ "epoch": 0.16,
205
+ "learning_rate": 0.0002,
206
+ "loss": 1.9826,
207
+ "step": 330
208
+ },
209
+ {
210
+ "epoch": 0.17,
211
+ "learning_rate": 0.0002,
212
+ "loss": 2.0645,
213
+ "step": 340
214
+ },
215
+ {
216
+ "epoch": 0.17,
217
+ "learning_rate": 0.0002,
218
+ "loss": 2.016,
219
+ "step": 350
220
+ },
221
+ {
222
+ "epoch": 0.18,
223
+ "learning_rate": 0.0002,
224
+ "loss": 2.017,
225
+ "step": 360
226
+ },
227
+ {
228
+ "epoch": 0.18,
229
+ "learning_rate": 0.0002,
230
+ "loss": 1.9784,
231
+ "step": 370
232
+ },
233
+ {
234
+ "epoch": 0.19,
235
+ "learning_rate": 0.0002,
236
+ "loss": 2.0232,
237
+ "step": 380
238
+ },
239
+ {
240
+ "epoch": 0.19,
241
+ "learning_rate": 0.0002,
242
+ "loss": 2.052,
243
+ "step": 390
244
+ },
245
+ {
246
+ "epoch": 0.2,
247
+ "learning_rate": 0.0002,
248
+ "loss": 2.2058,
249
+ "step": 400
250
+ },
251
+ {
252
+ "epoch": 0.2,
253
+ "learning_rate": 0.0002,
254
+ "loss": 1.9714,
255
+ "step": 410
256
+ },
257
+ {
258
+ "epoch": 0.21,
259
+ "learning_rate": 0.0002,
260
+ "loss": 1.9989,
261
+ "step": 420
262
+ },
263
+ {
264
+ "epoch": 0.21,
265
+ "learning_rate": 0.0002,
266
+ "loss": 2.1847,
267
+ "step": 430
268
+ },
269
+ {
270
+ "epoch": 0.22,
271
+ "learning_rate": 0.0002,
272
+ "loss": 2.0508,
273
+ "step": 440
274
+ },
275
+ {
276
+ "epoch": 0.22,
277
+ "learning_rate": 0.0002,
278
+ "loss": 2.1055,
279
+ "step": 450
280
+ },
281
+ {
282
+ "epoch": 0.23,
283
+ "learning_rate": 0.0002,
284
+ "loss": 1.9516,
285
+ "step": 460
286
+ },
287
+ {
288
+ "epoch": 0.23,
289
+ "learning_rate": 0.0002,
290
+ "loss": 2.0335,
291
+ "step": 470
292
+ },
293
+ {
294
+ "epoch": 0.23,
295
+ "learning_rate": 0.0002,
296
+ "loss": 1.9142,
297
+ "step": 480
298
+ },
299
+ {
300
+ "epoch": 0.24,
301
+ "learning_rate": 0.0002,
302
+ "loss": 1.9935,
303
+ "step": 490
304
+ },
305
+ {
306
+ "epoch": 0.24,
307
+ "learning_rate": 0.0002,
308
+ "loss": 1.9775,
309
+ "step": 500
310
+ },
311
+ {
312
+ "epoch": 0.25,
313
+ "learning_rate": 0.0002,
314
+ "loss": 1.997,
315
+ "step": 510
316
+ },
317
+ {
318
+ "epoch": 0.25,
319
+ "learning_rate": 0.0002,
320
+ "loss": 1.9757,
321
+ "step": 520
322
+ },
323
+ {
324
+ "epoch": 0.26,
325
+ "learning_rate": 0.0002,
326
+ "loss": 2.039,
327
+ "step": 530
328
+ },
329
+ {
330
+ "epoch": 0.26,
331
+ "learning_rate": 0.0002,
332
+ "loss": 1.9778,
333
+ "step": 540
334
+ },
335
+ {
336
+ "epoch": 0.27,
337
+ "learning_rate": 0.0002,
338
+ "loss": 1.9335,
339
+ "step": 550
340
+ },
341
+ {
342
+ "epoch": 0.27,
343
+ "learning_rate": 0.0002,
344
+ "loss": 2.1015,
345
+ "step": 560
346
+ },
347
+ {
348
+ "epoch": 0.28,
349
+ "learning_rate": 0.0002,
350
+ "loss": 2.0541,
351
+ "step": 570
352
+ },
353
+ {
354
+ "epoch": 0.28,
355
+ "learning_rate": 0.0002,
356
+ "loss": 1.992,
357
+ "step": 580
358
+ },
359
+ {
360
+ "epoch": 0.29,
361
+ "learning_rate": 0.0002,
362
+ "loss": 1.8638,
363
+ "step": 590
364
+ },
365
+ {
366
+ "epoch": 0.29,
367
+ "learning_rate": 0.0002,
368
+ "loss": 1.9015,
369
+ "step": 600
370
+ },
371
+ {
372
+ "epoch": 0.3,
373
+ "learning_rate": 0.0002,
374
+ "loss": 1.9853,
375
+ "step": 610
376
+ },
377
+ {
378
+ "epoch": 0.3,
379
+ "learning_rate": 0.0002,
380
+ "loss": 1.8795,
381
+ "step": 620
382
+ },
383
+ {
384
+ "epoch": 0.31,
385
+ "learning_rate": 0.0002,
386
+ "loss": 1.998,
387
+ "step": 630
388
+ },
389
+ {
390
+ "epoch": 0.31,
391
+ "learning_rate": 0.0002,
392
+ "loss": 1.9117,
393
+ "step": 640
394
+ },
395
+ {
396
+ "epoch": 0.32,
397
+ "learning_rate": 0.0002,
398
+ "loss": 1.9385,
399
+ "step": 650
400
+ },
401
+ {
402
+ "epoch": 0.32,
403
+ "learning_rate": 0.0002,
404
+ "loss": 1.9176,
405
+ "step": 660
406
+ },
407
+ {
408
+ "epoch": 0.33,
409
+ "learning_rate": 0.0002,
410
+ "loss": 1.944,
411
+ "step": 670
412
+ },
413
+ {
414
+ "epoch": 0.33,
415
+ "learning_rate": 0.0002,
416
+ "loss": 1.9806,
417
+ "step": 680
418
+ },
419
+ {
420
+ "epoch": 0.34,
421
+ "learning_rate": 0.0002,
422
+ "loss": 1.9584,
423
+ "step": 690
424
+ },
425
+ {
426
+ "epoch": 0.34,
427
+ "learning_rate": 0.0002,
428
+ "loss": 1.8142,
429
+ "step": 700
430
+ },
431
+ {
432
+ "epoch": 0.35,
433
+ "learning_rate": 0.0002,
434
+ "loss": 2.1244,
435
+ "step": 710
436
+ },
437
+ {
438
+ "epoch": 0.35,
439
+ "learning_rate": 0.0002,
440
+ "loss": 2.0237,
441
+ "step": 720
442
+ },
443
+ {
444
+ "epoch": 0.36,
445
+ "learning_rate": 0.0002,
446
+ "loss": 1.9156,
447
+ "step": 730
448
+ },
449
+ {
450
+ "epoch": 0.36,
451
+ "learning_rate": 0.0002,
452
+ "loss": 1.9587,
453
+ "step": 740
454
+ },
455
+ {
456
+ "epoch": 0.37,
457
+ "learning_rate": 0.0002,
458
+ "loss": 2.0621,
459
+ "step": 750
460
+ },
461
+ {
462
+ "epoch": 0.37,
463
+ "learning_rate": 0.0002,
464
+ "loss": 1.8895,
465
+ "step": 760
466
+ },
467
+ {
468
+ "epoch": 0.38,
469
+ "learning_rate": 0.0002,
470
+ "loss": 1.9138,
471
+ "step": 770
472
+ },
473
+ {
474
+ "epoch": 0.38,
475
+ "learning_rate": 0.0002,
476
+ "loss": 1.9483,
477
+ "step": 780
478
+ },
479
+ {
480
+ "epoch": 0.39,
481
+ "learning_rate": 0.0002,
482
+ "loss": 1.9976,
483
+ "step": 790
484
+ },
485
+ {
486
+ "epoch": 0.39,
487
+ "learning_rate": 0.0002,
488
+ "loss": 1.961,
489
+ "step": 800
490
+ },
491
+ {
492
+ "epoch": 0.4,
493
+ "learning_rate": 0.0002,
494
+ "loss": 1.9718,
495
+ "step": 810
496
+ },
497
+ {
498
+ "epoch": 0.4,
499
+ "learning_rate": 0.0002,
500
+ "loss": 1.9632,
501
+ "step": 820
502
+ },
503
+ {
504
+ "epoch": 0.41,
505
+ "learning_rate": 0.0002,
506
+ "loss": 1.9603,
507
+ "step": 830
508
+ },
509
+ {
510
+ "epoch": 0.41,
511
+ "learning_rate": 0.0002,
512
+ "loss": 1.9101,
513
+ "step": 840
514
+ },
515
+ {
516
+ "epoch": 0.42,
517
+ "learning_rate": 0.0002,
518
+ "loss": 2.0021,
519
+ "step": 850
520
+ },
521
+ {
522
+ "epoch": 0.42,
523
+ "learning_rate": 0.0002,
524
+ "loss": 1.9553,
525
+ "step": 860
526
+ },
527
+ {
528
+ "epoch": 0.43,
529
+ "learning_rate": 0.0002,
530
+ "loss": 2.0327,
531
+ "step": 870
532
+ },
533
+ {
534
+ "epoch": 0.43,
535
+ "learning_rate": 0.0002,
536
+ "loss": 1.8616,
537
+ "step": 880
538
+ },
539
+ {
540
+ "epoch": 0.44,
541
+ "learning_rate": 0.0002,
542
+ "loss": 1.9514,
543
+ "step": 890
544
+ },
545
+ {
546
+ "epoch": 0.44,
547
+ "learning_rate": 0.0002,
548
+ "loss": 2.0745,
549
+ "step": 900
550
+ },
551
+ {
552
+ "epoch": 0.45,
553
+ "learning_rate": 0.0002,
554
+ "loss": 2.094,
555
+ "step": 910
556
+ },
557
+ {
558
+ "epoch": 0.45,
559
+ "learning_rate": 0.0002,
560
+ "loss": 1.7963,
561
+ "step": 920
562
+ },
563
+ {
564
+ "epoch": 0.46,
565
+ "learning_rate": 0.0002,
566
+ "loss": 1.9299,
567
+ "step": 930
568
+ },
569
+ {
570
+ "epoch": 0.46,
571
+ "learning_rate": 0.0002,
572
+ "loss": 1.9508,
573
+ "step": 940
574
+ },
575
+ {
576
+ "epoch": 0.47,
577
+ "learning_rate": 0.0002,
578
+ "loss": 1.9966,
579
+ "step": 950
580
+ },
581
+ {
582
+ "epoch": 0.47,
583
+ "learning_rate": 0.0002,
584
+ "loss": 1.9024,
585
+ "step": 960
586
+ },
587
+ {
588
+ "epoch": 0.47,
589
+ "learning_rate": 0.0002,
590
+ "loss": 1.9214,
591
+ "step": 970
592
+ },
593
+ {
594
+ "epoch": 0.48,
595
+ "learning_rate": 0.0002,
596
+ "loss": 1.9296,
597
+ "step": 980
598
+ },
599
+ {
600
+ "epoch": 0.48,
601
+ "learning_rate": 0.0002,
602
+ "loss": 2.0227,
603
+ "step": 990
604
+ },
605
+ {
606
+ "epoch": 0.49,
607
+ "learning_rate": 0.0002,
608
+ "loss": 1.9409,
609
+ "step": 1000
610
+ }
611
+ ],
612
+ "logging_steps": 10,
613
+ "max_steps": 1000,
614
+ "num_train_epochs": 1,
615
+ "save_steps": 100,
616
+ "total_flos": 8.1655308484608e+16,
617
+ "trial_name": null,
618
+ "trial_params": null
619
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a9403d5bb0f6f4b86e8d28c9151f0110403b7c3d38aea40b743eff7dee45ffd
3
+ size 4027
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tiiuae/falcon-7b",
3
+ "alibi": false,
4
+ "apply_residual_connection_post_layernorm": false,
5
+ "architectures": [
6
+ "FalconForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "auto_map": {
10
+ "AutoConfig": "tiiuae/falcon-7b--configuration_falcon.FalconConfig",
11
+ "AutoModel": "tiiuae/falcon-7b--modeling_falcon.FalconModel",
12
+ "AutoModelForCausalLM": "tiiuae/falcon-7b--modeling_falcon.FalconForCausalLM",
13
+ "AutoModelForQuestionAnswering": "tiiuae/falcon-7b--modeling_falcon.FalconForQuestionAnswering",
14
+ "AutoModelForSequenceClassification": "tiiuae/falcon-7b--modeling_falcon.FalconForSequenceClassification",
15
+ "AutoModelForTokenClassification": "tiiuae/falcon-7b--modeling_falcon.FalconForTokenClassification"
16
+ },
17
+ "bias": false,
18
+ "bos_token_id": 11,
19
+ "eos_token_id": 11,
20
+ "hidden_dropout": 0.0,
21
+ "hidden_size": 4544,
22
+ "initializer_range": 0.02,
23
+ "layer_norm_epsilon": 1e-05,
24
+ "max_position_embeddings": 2048,
25
+ "model_type": "falcon",
26
+ "multi_query": true,
27
+ "new_decoder_architecture": false,
28
+ "num_attention_heads": 71,
29
+ "num_hidden_layers": 32,
30
+ "num_kv_heads": 71,
31
+ "parallel_attn": true,
32
+ "rope_scaling": null,
33
+ "rope_theta": 10000.0,
34
+ "torch_dtype": "bfloat16",
35
+ "transformers_version": "4.34.0.dev0",
36
+ "use_cache": true,
37
+ "vocab_size": 65024
38
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58309f0661f54ae83280183516125b5997311ca56006607296266803fa3ecb88
3
+ size 151034501
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18866927b9f45360d339346dd9a98ebb2315df44e637ddf894df92838b507bd2
3
+ size 14511
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bb7339d1d2da342a44f3ba5e076fb6e5d93aee86f890c002703d2b3a0750820
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ ">>TITLE<<",
4
+ ">>ABSTRACT<<",
5
+ ">>INTRODUCTION<<",
6
+ ">>SUMMARY<<",
7
+ ">>COMMENT<<",
8
+ ">>ANSWER<<",
9
+ ">>QUESTION<<",
10
+ ">>DOMAIN<<",
11
+ ">>PREFIX<<",
12
+ ">>SUFFIX<<",
13
+ ">>MIDDLE<<"
14
+ ],
15
+ "eos_token": "<|endoftext|>",
16
+ "pad_token": "<|endoftext|>"
17
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": ">>TITLE<<",
6
+ "lstrip": true,
7
+ "normalized": false,
8
+ "rstrip": true,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": ">>ABSTRACT<<",
14
+ "lstrip": true,
15
+ "normalized": false,
16
+ "rstrip": true,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": ">>INTRODUCTION<<",
22
+ "lstrip": true,
23
+ "normalized": false,
24
+ "rstrip": true,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": ">>SUMMARY<<",
30
+ "lstrip": true,
31
+ "normalized": false,
32
+ "rstrip": true,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": ">>COMMENT<<",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": true,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": ">>ANSWER<<",
46
+ "lstrip": true,
47
+ "normalized": false,
48
+ "rstrip": true,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": ">>QUESTION<<",
54
+ "lstrip": true,
55
+ "normalized": false,
56
+ "rstrip": true,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": ">>DOMAIN<<",
62
+ "lstrip": true,
63
+ "normalized": false,
64
+ "rstrip": true,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": ">>PREFIX<<",
70
+ "lstrip": true,
71
+ "normalized": false,
72
+ "rstrip": true,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": ">>SUFFIX<<",
78
+ "lstrip": true,
79
+ "normalized": false,
80
+ "rstrip": true,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": ">>MIDDLE<<",
86
+ "lstrip": true,
87
+ "normalized": false,
88
+ "rstrip": true,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<|endoftext|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ }
100
+ },
101
+ "additional_special_tokens": [
102
+ ">>TITLE<<",
103
+ ">>ABSTRACT<<",
104
+ ">>INTRODUCTION<<",
105
+ ">>SUMMARY<<",
106
+ ">>COMMENT<<",
107
+ ">>ANSWER<<",
108
+ ">>QUESTION<<",
109
+ ">>DOMAIN<<",
110
+ ">>PREFIX<<",
111
+ ">>SUFFIX<<",
112
+ ">>MIDDLE<<"
113
+ ],
114
+ "clean_up_tokenization_spaces": true,
115
+ "eos_token": "<|endoftext|>",
116
+ "model_max_length": 2048,
117
+ "tokenizer_class": "PreTrainedTokenizerFast"
118
+ }
trainer_state.json ADDED
@@ -0,0 +1,619 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.48953616448415127,
5
+ "eval_steps": 500,
6
+ "global_step": 1000,
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": 2.1809,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 0.0002,
20
+ "loss": 2.515,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.01,
25
+ "learning_rate": 0.0002,
26
+ "loss": 2.3848,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.02,
31
+ "learning_rate": 0.0002,
32
+ "loss": 2.2882,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 0.02,
37
+ "learning_rate": 0.0002,
38
+ "loss": 2.2283,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.03,
43
+ "learning_rate": 0.0002,
44
+ "loss": 2.1074,
45
+ "step": 60
46
+ },
47
+ {
48
+ "epoch": 0.03,
49
+ "learning_rate": 0.0002,
50
+ "loss": 2.1195,
51
+ "step": 70
52
+ },
53
+ {
54
+ "epoch": 0.04,
55
+ "learning_rate": 0.0002,
56
+ "loss": 2.1942,
57
+ "step": 80
58
+ },
59
+ {
60
+ "epoch": 0.04,
61
+ "learning_rate": 0.0002,
62
+ "loss": 2.0617,
63
+ "step": 90
64
+ },
65
+ {
66
+ "epoch": 0.05,
67
+ "learning_rate": 0.0002,
68
+ "loss": 2.2377,
69
+ "step": 100
70
+ },
71
+ {
72
+ "epoch": 0.05,
73
+ "learning_rate": 0.0002,
74
+ "loss": 2.1167,
75
+ "step": 110
76
+ },
77
+ {
78
+ "epoch": 0.06,
79
+ "learning_rate": 0.0002,
80
+ "loss": 2.0454,
81
+ "step": 120
82
+ },
83
+ {
84
+ "epoch": 0.06,
85
+ "learning_rate": 0.0002,
86
+ "loss": 2.0348,
87
+ "step": 130
88
+ },
89
+ {
90
+ "epoch": 0.07,
91
+ "learning_rate": 0.0002,
92
+ "loss": 2.1334,
93
+ "step": 140
94
+ },
95
+ {
96
+ "epoch": 0.07,
97
+ "learning_rate": 0.0002,
98
+ "loss": 2.1347,
99
+ "step": 150
100
+ },
101
+ {
102
+ "epoch": 0.08,
103
+ "learning_rate": 0.0002,
104
+ "loss": 1.9811,
105
+ "step": 160
106
+ },
107
+ {
108
+ "epoch": 0.08,
109
+ "learning_rate": 0.0002,
110
+ "loss": 2.1339,
111
+ "step": 170
112
+ },
113
+ {
114
+ "epoch": 0.09,
115
+ "learning_rate": 0.0002,
116
+ "loss": 2.1432,
117
+ "step": 180
118
+ },
119
+ {
120
+ "epoch": 0.09,
121
+ "learning_rate": 0.0002,
122
+ "loss": 1.9374,
123
+ "step": 190
124
+ },
125
+ {
126
+ "epoch": 0.1,
127
+ "learning_rate": 0.0002,
128
+ "loss": 2.078,
129
+ "step": 200
130
+ },
131
+ {
132
+ "epoch": 0.1,
133
+ "learning_rate": 0.0002,
134
+ "loss": 2.0077,
135
+ "step": 210
136
+ },
137
+ {
138
+ "epoch": 0.11,
139
+ "learning_rate": 0.0002,
140
+ "loss": 2.1386,
141
+ "step": 220
142
+ },
143
+ {
144
+ "epoch": 0.11,
145
+ "learning_rate": 0.0002,
146
+ "loss": 2.0728,
147
+ "step": 230
148
+ },
149
+ {
150
+ "epoch": 0.12,
151
+ "learning_rate": 0.0002,
152
+ "loss": 2.058,
153
+ "step": 240
154
+ },
155
+ {
156
+ "epoch": 0.12,
157
+ "learning_rate": 0.0002,
158
+ "loss": 2.1418,
159
+ "step": 250
160
+ },
161
+ {
162
+ "epoch": 0.13,
163
+ "learning_rate": 0.0002,
164
+ "loss": 1.8572,
165
+ "step": 260
166
+ },
167
+ {
168
+ "epoch": 0.13,
169
+ "learning_rate": 0.0002,
170
+ "loss": 2.0748,
171
+ "step": 270
172
+ },
173
+ {
174
+ "epoch": 0.14,
175
+ "learning_rate": 0.0002,
176
+ "loss": 2.0684,
177
+ "step": 280
178
+ },
179
+ {
180
+ "epoch": 0.14,
181
+ "learning_rate": 0.0002,
182
+ "loss": 1.9738,
183
+ "step": 290
184
+ },
185
+ {
186
+ "epoch": 0.15,
187
+ "learning_rate": 0.0002,
188
+ "loss": 2.0983,
189
+ "step": 300
190
+ },
191
+ {
192
+ "epoch": 0.15,
193
+ "learning_rate": 0.0002,
194
+ "loss": 1.9303,
195
+ "step": 310
196
+ },
197
+ {
198
+ "epoch": 0.16,
199
+ "learning_rate": 0.0002,
200
+ "loss": 2.0693,
201
+ "step": 320
202
+ },
203
+ {
204
+ "epoch": 0.16,
205
+ "learning_rate": 0.0002,
206
+ "loss": 1.9826,
207
+ "step": 330
208
+ },
209
+ {
210
+ "epoch": 0.17,
211
+ "learning_rate": 0.0002,
212
+ "loss": 2.0645,
213
+ "step": 340
214
+ },
215
+ {
216
+ "epoch": 0.17,
217
+ "learning_rate": 0.0002,
218
+ "loss": 2.016,
219
+ "step": 350
220
+ },
221
+ {
222
+ "epoch": 0.18,
223
+ "learning_rate": 0.0002,
224
+ "loss": 2.017,
225
+ "step": 360
226
+ },
227
+ {
228
+ "epoch": 0.18,
229
+ "learning_rate": 0.0002,
230
+ "loss": 1.9784,
231
+ "step": 370
232
+ },
233
+ {
234
+ "epoch": 0.19,
235
+ "learning_rate": 0.0002,
236
+ "loss": 2.0232,
237
+ "step": 380
238
+ },
239
+ {
240
+ "epoch": 0.19,
241
+ "learning_rate": 0.0002,
242
+ "loss": 2.052,
243
+ "step": 390
244
+ },
245
+ {
246
+ "epoch": 0.2,
247
+ "learning_rate": 0.0002,
248
+ "loss": 2.2058,
249
+ "step": 400
250
+ },
251
+ {
252
+ "epoch": 0.2,
253
+ "learning_rate": 0.0002,
254
+ "loss": 1.9714,
255
+ "step": 410
256
+ },
257
+ {
258
+ "epoch": 0.21,
259
+ "learning_rate": 0.0002,
260
+ "loss": 1.9989,
261
+ "step": 420
262
+ },
263
+ {
264
+ "epoch": 0.21,
265
+ "learning_rate": 0.0002,
266
+ "loss": 2.1847,
267
+ "step": 430
268
+ },
269
+ {
270
+ "epoch": 0.22,
271
+ "learning_rate": 0.0002,
272
+ "loss": 2.0508,
273
+ "step": 440
274
+ },
275
+ {
276
+ "epoch": 0.22,
277
+ "learning_rate": 0.0002,
278
+ "loss": 2.1055,
279
+ "step": 450
280
+ },
281
+ {
282
+ "epoch": 0.23,
283
+ "learning_rate": 0.0002,
284
+ "loss": 1.9516,
285
+ "step": 460
286
+ },
287
+ {
288
+ "epoch": 0.23,
289
+ "learning_rate": 0.0002,
290
+ "loss": 2.0335,
291
+ "step": 470
292
+ },
293
+ {
294
+ "epoch": 0.23,
295
+ "learning_rate": 0.0002,
296
+ "loss": 1.9142,
297
+ "step": 480
298
+ },
299
+ {
300
+ "epoch": 0.24,
301
+ "learning_rate": 0.0002,
302
+ "loss": 1.9935,
303
+ "step": 490
304
+ },
305
+ {
306
+ "epoch": 0.24,
307
+ "learning_rate": 0.0002,
308
+ "loss": 1.9775,
309
+ "step": 500
310
+ },
311
+ {
312
+ "epoch": 0.25,
313
+ "learning_rate": 0.0002,
314
+ "loss": 1.997,
315
+ "step": 510
316
+ },
317
+ {
318
+ "epoch": 0.25,
319
+ "learning_rate": 0.0002,
320
+ "loss": 1.9757,
321
+ "step": 520
322
+ },
323
+ {
324
+ "epoch": 0.26,
325
+ "learning_rate": 0.0002,
326
+ "loss": 2.039,
327
+ "step": 530
328
+ },
329
+ {
330
+ "epoch": 0.26,
331
+ "learning_rate": 0.0002,
332
+ "loss": 1.9778,
333
+ "step": 540
334
+ },
335
+ {
336
+ "epoch": 0.27,
337
+ "learning_rate": 0.0002,
338
+ "loss": 1.9335,
339
+ "step": 550
340
+ },
341
+ {
342
+ "epoch": 0.27,
343
+ "learning_rate": 0.0002,
344
+ "loss": 2.1015,
345
+ "step": 560
346
+ },
347
+ {
348
+ "epoch": 0.28,
349
+ "learning_rate": 0.0002,
350
+ "loss": 2.0541,
351
+ "step": 570
352
+ },
353
+ {
354
+ "epoch": 0.28,
355
+ "learning_rate": 0.0002,
356
+ "loss": 1.992,
357
+ "step": 580
358
+ },
359
+ {
360
+ "epoch": 0.29,
361
+ "learning_rate": 0.0002,
362
+ "loss": 1.8638,
363
+ "step": 590
364
+ },
365
+ {
366
+ "epoch": 0.29,
367
+ "learning_rate": 0.0002,
368
+ "loss": 1.9015,
369
+ "step": 600
370
+ },
371
+ {
372
+ "epoch": 0.3,
373
+ "learning_rate": 0.0002,
374
+ "loss": 1.9853,
375
+ "step": 610
376
+ },
377
+ {
378
+ "epoch": 0.3,
379
+ "learning_rate": 0.0002,
380
+ "loss": 1.8795,
381
+ "step": 620
382
+ },
383
+ {
384
+ "epoch": 0.31,
385
+ "learning_rate": 0.0002,
386
+ "loss": 1.998,
387
+ "step": 630
388
+ },
389
+ {
390
+ "epoch": 0.31,
391
+ "learning_rate": 0.0002,
392
+ "loss": 1.9117,
393
+ "step": 640
394
+ },
395
+ {
396
+ "epoch": 0.32,
397
+ "learning_rate": 0.0002,
398
+ "loss": 1.9385,
399
+ "step": 650
400
+ },
401
+ {
402
+ "epoch": 0.32,
403
+ "learning_rate": 0.0002,
404
+ "loss": 1.9176,
405
+ "step": 660
406
+ },
407
+ {
408
+ "epoch": 0.33,
409
+ "learning_rate": 0.0002,
410
+ "loss": 1.944,
411
+ "step": 670
412
+ },
413
+ {
414
+ "epoch": 0.33,
415
+ "learning_rate": 0.0002,
416
+ "loss": 1.9806,
417
+ "step": 680
418
+ },
419
+ {
420
+ "epoch": 0.34,
421
+ "learning_rate": 0.0002,
422
+ "loss": 1.9584,
423
+ "step": 690
424
+ },
425
+ {
426
+ "epoch": 0.34,
427
+ "learning_rate": 0.0002,
428
+ "loss": 1.8142,
429
+ "step": 700
430
+ },
431
+ {
432
+ "epoch": 0.35,
433
+ "learning_rate": 0.0002,
434
+ "loss": 2.1244,
435
+ "step": 710
436
+ },
437
+ {
438
+ "epoch": 0.35,
439
+ "learning_rate": 0.0002,
440
+ "loss": 2.0237,
441
+ "step": 720
442
+ },
443
+ {
444
+ "epoch": 0.36,
445
+ "learning_rate": 0.0002,
446
+ "loss": 1.9156,
447
+ "step": 730
448
+ },
449
+ {
450
+ "epoch": 0.36,
451
+ "learning_rate": 0.0002,
452
+ "loss": 1.9587,
453
+ "step": 740
454
+ },
455
+ {
456
+ "epoch": 0.37,
457
+ "learning_rate": 0.0002,
458
+ "loss": 2.0621,
459
+ "step": 750
460
+ },
461
+ {
462
+ "epoch": 0.37,
463
+ "learning_rate": 0.0002,
464
+ "loss": 1.8895,
465
+ "step": 760
466
+ },
467
+ {
468
+ "epoch": 0.38,
469
+ "learning_rate": 0.0002,
470
+ "loss": 1.9138,
471
+ "step": 770
472
+ },
473
+ {
474
+ "epoch": 0.38,
475
+ "learning_rate": 0.0002,
476
+ "loss": 1.9483,
477
+ "step": 780
478
+ },
479
+ {
480
+ "epoch": 0.39,
481
+ "learning_rate": 0.0002,
482
+ "loss": 1.9976,
483
+ "step": 790
484
+ },
485
+ {
486
+ "epoch": 0.39,
487
+ "learning_rate": 0.0002,
488
+ "loss": 1.961,
489
+ "step": 800
490
+ },
491
+ {
492
+ "epoch": 0.4,
493
+ "learning_rate": 0.0002,
494
+ "loss": 1.9718,
495
+ "step": 810
496
+ },
497
+ {
498
+ "epoch": 0.4,
499
+ "learning_rate": 0.0002,
500
+ "loss": 1.9632,
501
+ "step": 820
502
+ },
503
+ {
504
+ "epoch": 0.41,
505
+ "learning_rate": 0.0002,
506
+ "loss": 1.9603,
507
+ "step": 830
508
+ },
509
+ {
510
+ "epoch": 0.41,
511
+ "learning_rate": 0.0002,
512
+ "loss": 1.9101,
513
+ "step": 840
514
+ },
515
+ {
516
+ "epoch": 0.42,
517
+ "learning_rate": 0.0002,
518
+ "loss": 2.0021,
519
+ "step": 850
520
+ },
521
+ {
522
+ "epoch": 0.42,
523
+ "learning_rate": 0.0002,
524
+ "loss": 1.9553,
525
+ "step": 860
526
+ },
527
+ {
528
+ "epoch": 0.43,
529
+ "learning_rate": 0.0002,
530
+ "loss": 2.0327,
531
+ "step": 870
532
+ },
533
+ {
534
+ "epoch": 0.43,
535
+ "learning_rate": 0.0002,
536
+ "loss": 1.8616,
537
+ "step": 880
538
+ },
539
+ {
540
+ "epoch": 0.44,
541
+ "learning_rate": 0.0002,
542
+ "loss": 1.9514,
543
+ "step": 890
544
+ },
545
+ {
546
+ "epoch": 0.44,
547
+ "learning_rate": 0.0002,
548
+ "loss": 2.0745,
549
+ "step": 900
550
+ },
551
+ {
552
+ "epoch": 0.45,
553
+ "learning_rate": 0.0002,
554
+ "loss": 2.094,
555
+ "step": 910
556
+ },
557
+ {
558
+ "epoch": 0.45,
559
+ "learning_rate": 0.0002,
560
+ "loss": 1.7963,
561
+ "step": 920
562
+ },
563
+ {
564
+ "epoch": 0.46,
565
+ "learning_rate": 0.0002,
566
+ "loss": 1.9299,
567
+ "step": 930
568
+ },
569
+ {
570
+ "epoch": 0.46,
571
+ "learning_rate": 0.0002,
572
+ "loss": 1.9508,
573
+ "step": 940
574
+ },
575
+ {
576
+ "epoch": 0.47,
577
+ "learning_rate": 0.0002,
578
+ "loss": 1.9966,
579
+ "step": 950
580
+ },
581
+ {
582
+ "epoch": 0.47,
583
+ "learning_rate": 0.0002,
584
+ "loss": 1.9024,
585
+ "step": 960
586
+ },
587
+ {
588
+ "epoch": 0.47,
589
+ "learning_rate": 0.0002,
590
+ "loss": 1.9214,
591
+ "step": 970
592
+ },
593
+ {
594
+ "epoch": 0.48,
595
+ "learning_rate": 0.0002,
596
+ "loss": 1.9296,
597
+ "step": 980
598
+ },
599
+ {
600
+ "epoch": 0.48,
601
+ "learning_rate": 0.0002,
602
+ "loss": 2.0227,
603
+ "step": 990
604
+ },
605
+ {
606
+ "epoch": 0.49,
607
+ "learning_rate": 0.0002,
608
+ "loss": 1.9409,
609
+ "step": 1000
610
+ }
611
+ ],
612
+ "logging_steps": 10,
613
+ "max_steps": 1000,
614
+ "num_train_epochs": 1,
615
+ "save_steps": 100,
616
+ "total_flos": 8.1655308484608e+16,
617
+ "trial_name": null,
618
+ "trial_params": null
619
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a9403d5bb0f6f4b86e8d28c9151f0110403b7c3d38aea40b743eff7dee45ffd
3
+ size 4027