Hugging Face's logo

Flyfer
/
llama2-testv7

Text Generation
Trained with AutoTrain
Model card Files
xet
Community
Flyfer commited on
Commit
68ba5c8
·
1 Parent(s): 58d12d7

Upload folder using huggingface_hub

Browse files
Files changed (23) hide show
  1. README.md +9 -0
  2. adapter_config.json +21 -0
  3. adapter_model.bin +3 -0
  4. added_tokens.json +3 -0
  5. checkpoint-154/README.md +34 -0
  6. checkpoint-154/adapter_config.json +21 -0
  7. checkpoint-154/adapter_model.bin +3 -0
  8. checkpoint-154/added_tokens.json +3 -0
  9. checkpoint-154/optimizer.pt +3 -0
  10. checkpoint-154/rng_state.pth +3 -0
  11. checkpoint-154/scheduler.pt +3 -0
  12. checkpoint-154/special_tokens_map.json +24 -0
  13. checkpoint-154/tokenizer.json +0 -0
  14. checkpoint-154/tokenizer.model +3 -0
  15. checkpoint-154/tokenizer_config.json +46 -0
  16. checkpoint-154/trainer_state.json +325 -0
  17. checkpoint-154/training_args.bin +3 -0
  18. special_tokens_map.json +24 -0
  19. tokenizer.json +0 -0
  20. tokenizer.model +3 -0
  21. tokenizer_config.json +46 -0
  22. training_args.bin +3 -0
  23. training_params.json +1 -0
README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - autotrain
4
+ - text-generation
5
+ widget:
6
+ - text: "I love AutoTrain because "
7
+ ---
8
+
9
+ # Model Trained Using AutoTrain
adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "NousResearch/Llama-2-7b-chat-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": 32,
11
+ "lora_dropout": 0.05,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 16,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7483e58db8af7bb663654210667b7259138e42e051f5406dd8c805bb37009e2a
3
+ size 33600906
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<pad>": 32000
3
+ }
checkpoint-154/README.md ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: False
10
+ - load_in_4bit: True
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: nf4
16
+ - bnb_4bit_use_double_quant: False
17
+ - bnb_4bit_compute_dtype: float16
18
+
19
+ The following `bitsandbytes` quantization config was used during training:
20
+ - quant_method: bitsandbytes
21
+ - load_in_8bit: False
22
+ - load_in_4bit: True
23
+ - llm_int8_threshold: 6.0
24
+ - llm_int8_skip_modules: None
25
+ - llm_int8_enable_fp32_cpu_offload: False
26
+ - llm_int8_has_fp16_weight: False
27
+ - bnb_4bit_quant_type: nf4
28
+ - bnb_4bit_use_double_quant: False
29
+ - bnb_4bit_compute_dtype: float16
30
+ ### Framework versions
31
+
32
+ - PEFT 0.5.0
33
+
34
+ - PEFT 0.5.0
checkpoint-154/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "NousResearch/Llama-2-7b-chat-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": 32,
11
+ "lora_dropout": 0.05,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 16,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
checkpoint-154/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7483e58db8af7bb663654210667b7259138e42e051f5406dd8c805bb37009e2a
3
+ size 33600906
checkpoint-154/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<pad>": 32000
3
+ }
checkpoint-154/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de7d600a393d3acbb9950f378acc42217e40f76bc931d7fc311f852315e0e210
3
+ size 67217018
checkpoint-154/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a608af5361bff2a5ea1a14ca6072fe24e075f2159d7cf041bc0b55f90e4d3aa
3
+ size 14244
checkpoint-154/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55ae6965a168548c41246e994292a3d67c149e919e27e49dbe577e53643d8513
3
+ size 1064
checkpoint-154/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-154/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-154/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-154/tokenizer_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "32000": {
28
+ "content": "<pad>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "</s>",
39
+ "legacy": false,
40
+ "model_max_length": 2048,
41
+ "pad_token": "<unk>",
42
+ "sp_model_kwargs": {},
43
+ "tokenizer_class": "LlamaTokenizer",
44
+ "unk_token": "<unk>",
45
+ "use_default_system_prompt": true
46
+ }
checkpoint-154/trainer_state.json ADDED
@@ -0,0 +1,325 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 21.38888888888889,
5
+ "eval_steps": 500,
6
+ "global_step": 154,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.17,
13
+ "learning_rate": 1.5e-05,
14
+ "loss": 1.7268,
15
+ "step": 3
16
+ },
17
+ {
18
+ "epoch": 0.33,
19
+ "learning_rate": 3e-05,
20
+ "loss": 1.959,
21
+ "step": 6
22
+ },
23
+ {
24
+ "epoch": 1.11,
25
+ "learning_rate": 4.5e-05,
26
+ "loss": 1.8528,
27
+ "step": 9
28
+ },
29
+ {
30
+ "epoch": 1.28,
31
+ "learning_rate": 6e-05,
32
+ "loss": 1.5683,
33
+ "step": 12
34
+ },
35
+ {
36
+ "epoch": 2.06,
37
+ "learning_rate": 7.500000000000001e-05,
38
+ "loss": 1.7871,
39
+ "step": 15
40
+ },
41
+ {
42
+ "epoch": 2.22,
43
+ "learning_rate": 9e-05,
44
+ "loss": 1.3609,
45
+ "step": 18
46
+ },
47
+ {
48
+ "epoch": 2.39,
49
+ "learning_rate": 0.000105,
50
+ "loss": 1.5358,
51
+ "step": 21
52
+ },
53
+ {
54
+ "epoch": 3.17,
55
+ "learning_rate": 0.00012,
56
+ "loss": 1.4303,
57
+ "step": 24
58
+ },
59
+ {
60
+ "epoch": 3.33,
61
+ "learning_rate": 0.00013500000000000003,
62
+ "loss": 1.2275,
63
+ "step": 27
64
+ },
65
+ {
66
+ "epoch": 4.11,
67
+ "learning_rate": 0.00015000000000000001,
68
+ "loss": 1.3846,
69
+ "step": 30
70
+ },
71
+ {
72
+ "epoch": 4.28,
73
+ "learning_rate": 0.000165,
74
+ "loss": 1.1696,
75
+ "step": 33
76
+ },
77
+ {
78
+ "epoch": 5.06,
79
+ "learning_rate": 0.00018,
80
+ "loss": 0.8513,
81
+ "step": 36
82
+ },
83
+ {
84
+ "epoch": 5.22,
85
+ "learning_rate": 0.000195,
86
+ "loss": 0.9204,
87
+ "step": 39
88
+ },
89
+ {
90
+ "epoch": 5.39,
91
+ "learning_rate": 0.00019887640449438204,
92
+ "loss": 0.8819,
93
+ "step": 42
94
+ },
95
+ {
96
+ "epoch": 6.17,
97
+ "learning_rate": 0.00019719101123595508,
98
+ "loss": 0.7262,
99
+ "step": 45
100
+ },
101
+ {
102
+ "epoch": 6.33,
103
+ "learning_rate": 0.0001955056179775281,
104
+ "loss": 0.622,
105
+ "step": 48
106
+ },
107
+ {
108
+ "epoch": 7.11,
109
+ "learning_rate": 0.00019382022471910114,
110
+ "loss": 0.45,
111
+ "step": 51
112
+ },
113
+ {
114
+ "epoch": 7.28,
115
+ "learning_rate": 0.00019213483146067416,
116
+ "loss": 0.5254,
117
+ "step": 54
118
+ },
119
+ {
120
+ "epoch": 8.06,
121
+ "learning_rate": 0.0001904494382022472,
122
+ "loss": 0.4256,
123
+ "step": 57
124
+ },
125
+ {
126
+ "epoch": 8.22,
127
+ "learning_rate": 0.00018876404494382024,
128
+ "loss": 0.3008,
129
+ "step": 60
130
+ },
131
+ {
132
+ "epoch": 8.39,
133
+ "learning_rate": 0.00018707865168539326,
134
+ "loss": 0.3208,
135
+ "step": 63
136
+ },
137
+ {
138
+ "epoch": 9.17,
139
+ "learning_rate": 0.0001853932584269663,
140
+ "loss": 0.235,
141
+ "step": 66
142
+ },
143
+ {
144
+ "epoch": 9.33,
145
+ "learning_rate": 0.00018370786516853932,
146
+ "loss": 0.3065,
147
+ "step": 69
148
+ },
149
+ {
150
+ "epoch": 10.11,
151
+ "learning_rate": 0.00018202247191011236,
152
+ "loss": 0.2178,
153
+ "step": 72
154
+ },
155
+ {
156
+ "epoch": 10.28,
157
+ "learning_rate": 0.0001803370786516854,
158
+ "loss": 0.2144,
159
+ "step": 75
160
+ },
161
+ {
162
+ "epoch": 11.06,
163
+ "learning_rate": 0.00017865168539325842,
164
+ "loss": 0.157,
165
+ "step": 78
166
+ },
167
+ {
168
+ "epoch": 11.22,
169
+ "learning_rate": 0.00017696629213483146,
170
+ "loss": 0.1541,
171
+ "step": 81
172
+ },
173
+ {
174
+ "epoch": 11.39,
175
+ "learning_rate": 0.0001752808988764045,
176
+ "loss": 0.1394,
177
+ "step": 84
178
+ },
179
+ {
180
+ "epoch": 12.17,
181
+ "learning_rate": 0.00017359550561797752,
182
+ "loss": 0.1196,
183
+ "step": 87
184
+ },
185
+ {
186
+ "epoch": 12.33,
187
+ "learning_rate": 0.00017191011235955056,
188
+ "loss": 0.1,
189
+ "step": 90
190
+ },
191
+ {
192
+ "epoch": 13.11,
193
+ "learning_rate": 0.0001702247191011236,
194
+ "loss": 0.0882,
195
+ "step": 93
196
+ },
197
+ {
198
+ "epoch": 13.28,
199
+ "learning_rate": 0.00016853932584269662,
200
+ "loss": 0.0671,
201
+ "step": 96
202
+ },
203
+ {
204
+ "epoch": 14.06,
205
+ "learning_rate": 0.00016685393258426967,
206
+ "loss": 0.0509,
207
+ "step": 99
208
+ },
209
+ {
210
+ "epoch": 14.22,
211
+ "learning_rate": 0.0001651685393258427,
212
+ "loss": 0.0435,
213
+ "step": 102
214
+ },
215
+ {
216
+ "epoch": 14.39,
217
+ "learning_rate": 0.00016348314606741575,
218
+ "loss": 0.0529,
219
+ "step": 105
220
+ },
221
+ {
222
+ "epoch": 15.17,
223
+ "learning_rate": 0.00016179775280898877,
224
+ "loss": 0.0349,
225
+ "step": 108
226
+ },
227
+ {
228
+ "epoch": 15.33,
229
+ "learning_rate": 0.0001601123595505618,
230
+ "loss": 0.0298,
231
+ "step": 111
232
+ },
233
+ {
234
+ "epoch": 16.11,
235
+ "learning_rate": 0.00015842696629213485,
236
+ "loss": 0.0405,
237
+ "step": 114
238
+ },
239
+ {
240
+ "epoch": 16.28,
241
+ "learning_rate": 0.00015674157303370787,
242
+ "loss": 0.0279,
243
+ "step": 117
244
+ },
245
+ {
246
+ "epoch": 17.06,
247
+ "learning_rate": 0.0001550561797752809,
248
+ "loss": 0.033,
249
+ "step": 120
250
+ },
251
+ {
252
+ "epoch": 17.22,
253
+ "learning_rate": 0.00015337078651685396,
254
+ "loss": 0.0221,
255
+ "step": 123
256
+ },
257
+ {
258
+ "epoch": 17.39,
259
+ "learning_rate": 0.00015168539325842697,
260
+ "loss": 0.0253,
261
+ "step": 126
262
+ },
263
+ {
264
+ "epoch": 18.17,
265
+ "learning_rate": 0.00015000000000000001,
266
+ "loss": 0.0188,
267
+ "step": 129
268
+ },
269
+ {
270
+ "epoch": 18.33,
271
+ "learning_rate": 0.00014831460674157306,
272
+ "loss": 0.0229,
273
+ "step": 132
274
+ },
275
+ {
276
+ "epoch": 19.11,
277
+ "learning_rate": 0.00014662921348314607,
278
+ "loss": 0.0168,
279
+ "step": 135
280
+ },
281
+ {
282
+ "epoch": 19.28,
283
+ "learning_rate": 0.00014494382022471912,
284
+ "loss": 0.023,
285
+ "step": 138
286
+ },
287
+ {
288
+ "epoch": 20.06,
289
+ "learning_rate": 0.00014325842696629216,
290
+ "loss": 0.0177,
291
+ "step": 141
292
+ },
293
+ {
294
+ "epoch": 20.22,
295
+ "learning_rate": 0.00014157303370786517,
296
+ "loss": 0.016,
297
+ "step": 144
298
+ },
299
+ {
300
+ "epoch": 20.39,
301
+ "learning_rate": 0.00013988764044943822,
302
+ "loss": 0.0176,
303
+ "step": 147
304
+ },
305
+ {
306
+ "epoch": 21.17,
307
+ "learning_rate": 0.00013820224719101123,
308
+ "loss": 0.0109,
309
+ "step": 150
310
+ },
311
+ {
312
+ "epoch": 21.33,
313
+ "learning_rate": 0.00013651685393258428,
314
+ "loss": 0.0161,
315
+ "step": 153
316
+ }
317
+ ],
318
+ "logging_steps": 3,
319
+ "max_steps": 396,
320
+ "num_train_epochs": 22,
321
+ "save_steps": 500,
322
+ "total_flos": 1.251930185662464e+16,
323
+ "trial_name": null,
324
+ "trial_params": null
325
+ }
checkpoint-154/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e7ab582b7b3a2b260bc35170e904fa3be21b5cfec97526fb2d485050cd37421
3
+ size 4472
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "32000": {
28
+ "content": "<pad>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "</s>",
39
+ "legacy": false,
40
+ "model_max_length": 2048,
41
+ "pad_token": "<unk>",
42
+ "sp_model_kwargs": {},
43
+ "tokenizer_class": "LlamaTokenizer",
44
+ "unk_token": "<unk>",
45
+ "use_default_system_prompt": true
46
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e7ab582b7b3a2b260bc35170e904fa3be21b5cfec97526fb2d485050cd37421
3
+ size 4472
training_params.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model": "NousResearch/Llama-2-7b-chat-hf", "data_path": "Flyfer/CBDataSetBeta1", "project_name": "TestProject", "train_split": "train", "valid_split": null, "text_column": "text", "rejected_text_column": "rejected", "lr": 0.0002, "epochs": 22, "batch_size": 2, "warmup_ratio": 0.1, "gradient_accumulation": 1, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.0, "max_grad_norm": 1.0, "seed": 42, "add_eos_token": false, "block_size": -1, "use_peft": true, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.05, "logging_steps": -1, "evaluation_strategy": "epoch", "save_total_limit": 1, "save_strategy": "epoch", "auto_find_batch_size": false, "fp16": false, "push_to_hub": true, "use_int8": false, "model_max_length": 2048, "repo_id": "Flyfer/llama2-testv7", "use_int4": true, "trainer": "sft", "target_modules": null, "merge_adapter": false, "username": null, "use_flash_attention_2": false, "log": "none", "disable_gradient_checkpointing": false, "model_ref": null, "dpo_beta": 0.1, "prompt_text_column": "prompt"}