Hugging Face's logo

Flyfer
/
llama2-test20ep5bat

Text Generation
Trained with AutoTrain
Model card Files
xet
 Community
Flyfer commited on
Commit
8424172
·
1 Parent(s): ffeb65f

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-60/README.md +34 -0
  6. checkpoint-60/adapter_config.json +21 -0
  7. checkpoint-60/adapter_model.bin +3 -0
  8. checkpoint-60/added_tokens.json +3 -0
  9. checkpoint-60/optimizer.pt +3 -0
  10. checkpoint-60/rng_state.pth +3 -0
  11. checkpoint-60/scheduler.pt +3 -0
  12. checkpoint-60/special_tokens_map.json +24 -0
  13. checkpoint-60/tokenizer.json +0 -0
  14. checkpoint-60/tokenizer.model +3 -0
  15. checkpoint-60/tokenizer_config.json +46 -0
  16. checkpoint-60/trainer_state.json +379 -0
  17. checkpoint-60/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 sha256:6bde61bdb1b8f24c8d49be20ef1009596885ef0b02fcd862b6357718c2015ce0
3
+ size 33600906
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<pad>": 32000
3
+ }
checkpoint-60/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-60/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-60/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bde61bdb1b8f24c8d49be20ef1009596885ef0b02fcd862b6357718c2015ce0
3
+ size 33600906
checkpoint-60/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<pad>": 32000
3
+ }
checkpoint-60/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5080189da6c0cd3df375b6ade664262dc6ba60b354d401b47292ee216083481d
3
+ size 67217018
checkpoint-60/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b97db4ab069eeaae1cc918b1a09b6640cb10bcb18043ce7b6fb65164feec6308
3
+ size 14244
checkpoint-60/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51a6c082b9c6e4e9e83610b50fee3539c60143b41fd013004f712dae84a159ee
3
+ size 1064
checkpoint-60/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-60/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-60/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-60/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-60/trainer_state.json ADDED
@@ -0,0 +1,379 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 19.428571428571427,
5
+ "eval_steps": 500,
6
+ "global_step": 60,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.14,
13
+ "learning_rate": 1.4285714285714285e-05,
14
+ "loss": 1.7815,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.29,
19
+ "learning_rate": 2.857142857142857e-05,
20
+ "loss": 1.8831,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.43,
25
+ "learning_rate": 4.2857142857142856e-05,
26
+ "loss": 1.825,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 1.14,
31
+ "learning_rate": 5.714285714285714e-05,
32
+ "loss": 1.951,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 1.29,
37
+ "learning_rate": 7.142857142857143e-05,
38
+ "loss": 1.5805,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 1.43,
43
+ "learning_rate": 8.571428571428571e-05,
44
+ "loss": 1.859,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 2.14,
49
+ "learning_rate": 0.0001,
50
+ "loss": 1.7268,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 2.29,
55
+ "learning_rate": 0.00011428571428571428,
56
+ "loss": 1.4927,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 2.43,
61
+ "learning_rate": 0.00012857142857142858,
62
+ "loss": 1.8618,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 3.14,
67
+ "learning_rate": 0.00014285714285714287,
68
+ "loss": 1.6209,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 3.29,
73
+ "learning_rate": 0.00015714285714285716,
74
+ "loss": 1.5352,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 3.43,
79
+ "learning_rate": 0.00017142857142857143,
80
+ "loss": 1.3475,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 4.14,
85
+ "learning_rate": 0.00018571428571428572,
86
+ "loss": 1.6543,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 4.29,
91
+ "learning_rate": 0.0002,
92
+ "loss": 1.3424,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 4.43,
97
+ "learning_rate": 0.00019841269841269844,
98
+ "loss": 1.0813,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 5.14,
103
+ "learning_rate": 0.00019682539682539682,
104
+ "loss": 1.2542,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 5.29,
109
+ "learning_rate": 0.00019523809523809525,
110
+ "loss": 1.3668,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 5.43,
115
+ "learning_rate": 0.00019365079365079365,
116
+ "loss": 1.2575,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 6.14,
121
+ "learning_rate": 0.00019206349206349208,
122
+ "loss": 1.2714,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 6.29,
127
+ "learning_rate": 0.00019047619047619048,
128
+ "loss": 1.0502,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 6.43,
133
+ "learning_rate": 0.00018888888888888888,
134
+ "loss": 1.2165,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 7.14,
139
+ "learning_rate": 0.00018730158730158731,
140
+ "loss": 1.1839,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 7.29,
145
+ "learning_rate": 0.00018571428571428572,
146
+ "loss": 1.0632,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 7.43,
151
+ "learning_rate": 0.00018412698412698412,
152
+ "loss": 0.9129,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 8.14,
157
+ "learning_rate": 0.00018253968253968255,
158
+ "loss": 0.9559,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 8.29,
163
+ "learning_rate": 0.00018095238095238095,
164
+ "loss": 0.9037,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 8.43,
169
+ "learning_rate": 0.00017936507936507938,
170
+ "loss": 0.99,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 9.14,
175
+ "learning_rate": 0.00017777777777777779,
176
+ "loss": 0.7489,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 9.29,
181
+ "learning_rate": 0.0001761904761904762,
182
+ "loss": 0.9113,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 9.43,
187
+ "learning_rate": 0.00017460317460317462,
188
+ "loss": 0.8181,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 10.14,
193
+ "learning_rate": 0.00017301587301587302,
194
+ "loss": 0.825,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 10.29,
199
+ "learning_rate": 0.00017142857142857143,
200
+ "loss": 0.785,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 10.43,
205
+ "learning_rate": 0.00016984126984126986,
206
+ "loss": 0.4748,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 11.14,
211
+ "learning_rate": 0.00016825396825396826,
212
+ "loss": 0.6036,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 11.29,
217
+ "learning_rate": 0.0001666666666666667,
218
+ "loss": 0.7164,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 11.43,
223
+ "learning_rate": 0.0001650793650793651,
224
+ "loss": 0.4889,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 12.14,
229
+ "learning_rate": 0.0001634920634920635,
230
+ "loss": 0.5426,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 12.29,
235
+ "learning_rate": 0.00016190476190476192,
236
+ "loss": 0.6201,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 12.43,
241
+ "learning_rate": 0.00016031746031746033,
242
+ "loss": 0.3853,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 13.14,
247
+ "learning_rate": 0.00015873015873015873,
248
+ "loss": 0.4882,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 13.29,
253
+ "learning_rate": 0.00015714285714285716,
254
+ "loss": 0.5028,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 13.43,
259
+ "learning_rate": 0.00015555555555555556,
260
+ "loss": 0.3693,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 14.14,
265
+ "learning_rate": 0.000153968253968254,
266
+ "loss": 0.3257,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 14.29,
271
+ "learning_rate": 0.00015238095238095237,
272
+ "loss": 0.4502,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 14.43,
277
+ "learning_rate": 0.0001507936507936508,
278
+ "loss": 0.4277,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 15.14,
283
+ "learning_rate": 0.00014920634920634923,
284
+ "loss": 0.4595,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 15.29,
289
+ "learning_rate": 0.00014761904761904763,
290
+ "loss": 0.3251,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 15.43,
295
+ "learning_rate": 0.00014603174603174603,
296
+ "loss": 0.2482,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 16.14,
301
+ "learning_rate": 0.00014444444444444444,
302
+ "loss": 0.3022,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 16.29,
307
+ "learning_rate": 0.00014285714285714287,
308
+ "loss": 0.2293,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 16.43,
313
+ "learning_rate": 0.0001412698412698413,
314
+ "loss": 0.3855,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 17.14,
319
+ "learning_rate": 0.00013968253968253967,
320
+ "loss": 0.2593,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 17.29,
325
+ "learning_rate": 0.0001380952380952381,
326
+ "loss": 0.2478,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 17.43,
331
+ "learning_rate": 0.0001365079365079365,
332
+ "loss": 0.279,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 18.14,
337
+ "learning_rate": 0.00013492063492063494,
338
+ "loss": 0.2797,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 18.29,
343
+ "learning_rate": 0.00013333333333333334,
344
+ "loss": 0.1801,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 18.43,
349
+ "learning_rate": 0.00013174603174603174,
350
+ "loss": 0.2129,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 19.14,
355
+ "learning_rate": 0.00013015873015873017,
356
+ "loss": 0.1864,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 19.29,
361
+ "learning_rate": 0.00012857142857142858,
362
+ "loss": 0.2059,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 19.43,
367
+ "learning_rate": 0.00012698412698412698,
368
+ "loss": 0.1823,
369
+ "step": 60
370
+ }
371
+ ],
372
+ "logging_steps": 1,
373
+ "max_steps": 140,
374
+ "num_train_epochs": 20,
375
+ "save_steps": 500,
376
+ "total_flos": 1.13811835060224e+16,
377
+ "trial_name": null,
378
+ "trial_params": null
379
+ }
checkpoint-60/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7a932d8bb10883fcb44be6fb0196ef825d99a1d63bac630eb10baf483df485d
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:f7a932d8bb10883fcb44be6fb0196ef825d99a1d63bac630eb10baf483df485d
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": 20, "batch_size": 5, "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-test20ep5bat", "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"}