Hugging Face's logo

johaanm
/
llama2-openassistant-chatbased

Text Generation
Transformers
PyTorch
TensorBoard
llama
Trained with AutoTrain
text-generation-inference
Model card Files
xet
Metrics Community
johaanm commited on
Commit
e70e30b
·
1 Parent(s): f23bdd6

Upload folder using huggingface_hub

Browse files
Files changed (28) hide show
  1. README.md +9 -0
  2. adapter_config.json +21 -0
  3. adapter_model.bin +3 -0
  4. checkpoint-150/README.md +32 -0
  5. checkpoint-150/adapter_config.json +21 -0
  6. checkpoint-150/adapter_model.bin +3 -0
  7. checkpoint-150/optimizer.pt +3 -0
  8. checkpoint-150/pytorch_model.bin +3 -0
  9. checkpoint-150/rng_state.pth +3 -0
  10. checkpoint-150/scheduler.pt +3 -0
  11. checkpoint-150/special_tokens_map.json +24 -0
  12. checkpoint-150/tokenizer.json +0 -0
  13. checkpoint-150/tokenizer.model +3 -0
  14. checkpoint-150/tokenizer_config.json +33 -0
  15. checkpoint-150/trainer_state.json +466 -0
  16. checkpoint-150/training_args.bin +3 -0
  17. config.json +27 -0
  18. generation_config.json +10 -0
  19. pytorch_model-00001-of-00002.bin +3 -0
  20. pytorch_model-00002-of-00002.bin +3 -0
  21. pytorch_model.bin.index.json +330 -0
  22. runs/Aug14_05-55-13_3f88d1fbe573/events.out.tfevents.1691992513.3f88d1fbe573.4714.0 +3 -0
  23. special_tokens_map.json +23 -0
  24. tokenizer.json +0 -0
  25. tokenizer.model +3 -0
  26. tokenizer_config.json +33 -0
  27. training_args.bin +3 -0
  28. training_params.json +41 -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": "Trelis/Llama-2-7b-chat-hf-sharded-bf16",
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 sha256:91dfb479d5940db3163dfca0f249b34966c922b3501ccfa1dc5d78587ff13989
3
+ size 33600461
checkpoint-150/README.md ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: False
16
+ - bnb_4bit_compute_dtype: float16
17
+
18
+ The following `bitsandbytes` quantization config was used during training:
19
+ - load_in_8bit: False
20
+ - load_in_4bit: True
21
+ - llm_int8_threshold: 6.0
22
+ - llm_int8_skip_modules: None
23
+ - llm_int8_enable_fp32_cpu_offload: False
24
+ - llm_int8_has_fp16_weight: False
25
+ - bnb_4bit_quant_type: nf4
26
+ - bnb_4bit_use_double_quant: False
27
+ - bnb_4bit_compute_dtype: float16
28
+ ### Framework versions
29
+
30
+ - PEFT 0.4.0
31
+
32
+ - PEFT 0.4.0
checkpoint-150/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "Trelis/Llama-2-7b-chat-hf-sharded-bf16",
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-150/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91dfb479d5940db3163dfca0f249b34966c922b3501ccfa1dc5d78587ff13989
3
+ size 33600461
checkpoint-150/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a833aaf22e52d41208683b233b3a31232407d99441b821f9471eec660ffa285c
3
+ size 67216581
checkpoint-150/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c152074a486243089e4fc0fdee0a373a30fb0e0a6e40eb5fd0d36fdafc97a155
3
+ size 443
checkpoint-150/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee9dce79049b2b8aafa6e209bb847994547119cf9001dc4aaa7fcb7a8c855251
3
+ size 14575
checkpoint-150/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d27fa363ab34773a23ba8bfeb188759d0e0a2fff8f65d0c364eb9cd67e7b2b01
3
+ size 627
checkpoint-150/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-150/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-150/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-150/tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "clean_up_tokenization_spaces": false,
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "legacy": false,
20
+ "model_max_length": 1024,
21
+ "pad_token": null,
22
+ "sp_model_kwargs": {},
23
+ "tokenizer_class": "LlamaTokenizer",
24
+ "unk_token": {
25
+ "__type": "AddedToken",
26
+ "content": "<unk>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "use_fast": false
33
+ }
checkpoint-150/trainer_state.json ADDED
@@ -0,0 +1,466 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "global_step": 150,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.13,
12
+ "learning_rate": 5.333333333333333e-05,
13
+ "loss": 0.8383,
14
+ "step": 2
15
+ },
16
+ {
17
+ "epoch": 0.27,
18
+ "learning_rate": 0.00010666666666666667,
19
+ "loss": 0.8509,
20
+ "step": 4
21
+ },
22
+ {
23
+ "epoch": 0.4,
24
+ "learning_rate": 0.00016,
25
+ "loss": 0.8373,
26
+ "step": 6
27
+ },
28
+ {
29
+ "epoch": 0.53,
30
+ "learning_rate": 0.00021333333333333333,
31
+ "loss": 0.8067,
32
+ "step": 8
33
+ },
34
+ {
35
+ "epoch": 0.67,
36
+ "learning_rate": 0.0002666666666666667,
37
+ "loss": 0.5774,
38
+ "step": 10
39
+ },
40
+ {
41
+ "epoch": 0.8,
42
+ "learning_rate": 0.00032,
43
+ "loss": 0.5267,
44
+ "step": 12
45
+ },
46
+ {
47
+ "epoch": 0.93,
48
+ "learning_rate": 0.0003733333333333334,
49
+ "loss": 0.551,
50
+ "step": 14
51
+ },
52
+ {
53
+ "epoch": 1.07,
54
+ "learning_rate": 0.00039703703703703705,
55
+ "loss": 0.4659,
56
+ "step": 16
57
+ },
58
+ {
59
+ "epoch": 1.2,
60
+ "learning_rate": 0.0003911111111111111,
61
+ "loss": 0.4995,
62
+ "step": 18
63
+ },
64
+ {
65
+ "epoch": 1.33,
66
+ "learning_rate": 0.0003851851851851852,
67
+ "loss": 0.5013,
68
+ "step": 20
69
+ },
70
+ {
71
+ "epoch": 1.47,
72
+ "learning_rate": 0.0003792592592592593,
73
+ "loss": 0.3762,
74
+ "step": 22
75
+ },
76
+ {
77
+ "epoch": 1.6,
78
+ "learning_rate": 0.0003733333333333334,
79
+ "loss": 0.3964,
80
+ "step": 24
81
+ },
82
+ {
83
+ "epoch": 1.73,
84
+ "learning_rate": 0.00036740740740740744,
85
+ "loss": 0.4134,
86
+ "step": 26
87
+ },
88
+ {
89
+ "epoch": 1.87,
90
+ "learning_rate": 0.0003614814814814815,
91
+ "loss": 0.3222,
92
+ "step": 28
93
+ },
94
+ {
95
+ "epoch": 2.0,
96
+ "learning_rate": 0.00035555555555555557,
97
+ "loss": 0.2872,
98
+ "step": 30
99
+ },
100
+ {
101
+ "epoch": 2.13,
102
+ "learning_rate": 0.00034962962962962964,
103
+ "loss": 0.3529,
104
+ "step": 32
105
+ },
106
+ {
107
+ "epoch": 2.27,
108
+ "learning_rate": 0.0003437037037037037,
109
+ "loss": 0.282,
110
+ "step": 34
111
+ },
112
+ {
113
+ "epoch": 2.4,
114
+ "learning_rate": 0.00033777777777777777,
115
+ "loss": 0.2544,
116
+ "step": 36
117
+ },
118
+ {
119
+ "epoch": 2.53,
120
+ "learning_rate": 0.00033185185185185184,
121
+ "loss": 0.212,
122
+ "step": 38
123
+ },
124
+ {
125
+ "epoch": 2.67,
126
+ "learning_rate": 0.0003259259259259259,
127
+ "loss": 0.1252,
128
+ "step": 40
129
+ },
130
+ {
131
+ "epoch": 2.8,
132
+ "learning_rate": 0.00032,
133
+ "loss": 0.1933,
134
+ "step": 42
135
+ },
136
+ {
137
+ "epoch": 2.93,
138
+ "learning_rate": 0.0003140740740740741,
139
+ "loss": 0.1614,
140
+ "step": 44
141
+ },
142
+ {
143
+ "epoch": 3.07,
144
+ "learning_rate": 0.00030814814814814816,
145
+ "loss": 0.1694,
146
+ "step": 46
147
+ },
148
+ {
149
+ "epoch": 3.2,
150
+ "learning_rate": 0.0003022222222222222,
151
+ "loss": 0.1645,
152
+ "step": 48
153
+ },
154
+ {
155
+ "epoch": 3.33,
156
+ "learning_rate": 0.0002962962962962963,
157
+ "loss": 0.1532,
158
+ "step": 50
159
+ },
160
+ {
161
+ "epoch": 3.47,
162
+ "learning_rate": 0.0002903703703703704,
163
+ "loss": 0.1115,
164
+ "step": 52
165
+ },
166
+ {
167
+ "epoch": 3.6,
168
+ "learning_rate": 0.0002844444444444445,
169
+ "loss": 0.0873,
170
+ "step": 54
171
+ },
172
+ {
173
+ "epoch": 3.73,
174
+ "learning_rate": 0.00027851851851851855,
175
+ "loss": 0.1409,
176
+ "step": 56
177
+ },
178
+ {
179
+ "epoch": 3.87,
180
+ "learning_rate": 0.0002725925925925926,
181
+ "loss": 0.1363,
182
+ "step": 58
183
+ },
184
+ {
185
+ "epoch": 4.0,
186
+ "learning_rate": 0.0002666666666666667,
187
+ "loss": 0.12,
188
+ "step": 60
189
+ },
190
+ {
191
+ "epoch": 4.13,
192
+ "learning_rate": 0.0002607407407407408,
193
+ "loss": 0.0858,
194
+ "step": 62
195
+ },
196
+ {
197
+ "epoch": 4.27,
198
+ "learning_rate": 0.0002548148148148148,
199
+ "loss": 0.1151,
200
+ "step": 64
201
+ },
202
+ {
203
+ "epoch": 4.4,
204
+ "learning_rate": 0.0002488888888888889,
205
+ "loss": 0.0631,
206
+ "step": 66
207
+ },
208
+ {
209
+ "epoch": 4.53,
210
+ "learning_rate": 0.00024296296296296297,
211
+ "loss": 0.1468,
212
+ "step": 68
213
+ },
214
+ {
215
+ "epoch": 4.67,
216
+ "learning_rate": 0.00023703703703703704,
217
+ "loss": 0.1032,
218
+ "step": 70
219
+ },
220
+ {
221
+ "epoch": 4.8,
222
+ "learning_rate": 0.0002311111111111111,
223
+ "loss": 0.0626,
224
+ "step": 72
225
+ },
226
+ {
227
+ "epoch": 4.93,
228
+ "learning_rate": 0.0002251851851851852,
229
+ "loss": 0.0551,
230
+ "step": 74
231
+ },
232
+ {
233
+ "epoch": 5.07,
234
+ "learning_rate": 0.00021925925925925927,
235
+ "loss": 0.0717,
236
+ "step": 76
237
+ },
238
+ {
239
+ "epoch": 5.2,
240
+ "learning_rate": 0.00021333333333333333,
241
+ "loss": 0.0711,
242
+ "step": 78
243
+ },
244
+ {
245
+ "epoch": 5.33,
246
+ "learning_rate": 0.0002074074074074074,
247
+ "loss": 0.0717,
248
+ "step": 80
249
+ },
250
+ {
251
+ "epoch": 5.47,
252
+ "learning_rate": 0.00020148148148148147,
253
+ "loss": 0.0886,
254
+ "step": 82
255
+ },
256
+ {
257
+ "epoch": 5.6,
258
+ "learning_rate": 0.00019555555555555556,
259
+ "loss": 0.0527,
260
+ "step": 84
261
+ },
262
+ {
263
+ "epoch": 5.73,
264
+ "learning_rate": 0.00018962962962962965,
265
+ "loss": 0.0633,
266
+ "step": 86
267
+ },
268
+ {
269
+ "epoch": 5.87,
270
+ "learning_rate": 0.00018370370370370372,
271
+ "loss": 0.0424,
272
+ "step": 88
273
+ },
274
+ {
275
+ "epoch": 6.0,
276
+ "learning_rate": 0.00017777777777777779,
277
+ "loss": 0.0431,
278
+ "step": 90
279
+ },
280
+ {
281
+ "epoch": 6.13,
282
+ "learning_rate": 0.00017185185185185185,
283
+ "loss": 0.0538,
284
+ "step": 92
285
+ },
286
+ {
287
+ "epoch": 6.27,
288
+ "learning_rate": 0.00016592592592592592,
289
+ "loss": 0.0526,
290
+ "step": 94
291
+ },
292
+ {
293
+ "epoch": 6.4,
294
+ "learning_rate": 0.00016,
295
+ "loss": 0.055,
296
+ "step": 96
297
+ },
298
+ {
299
+ "epoch": 6.53,
300
+ "learning_rate": 0.00015407407407407408,
301
+ "loss": 0.0518,
302
+ "step": 98
303
+ },
304
+ {
305
+ "epoch": 6.67,
306
+ "learning_rate": 0.00014814814814814815,
307
+ "loss": 0.0484,
308
+ "step": 100
309
+ },
310
+ {
311
+ "epoch": 6.8,
312
+ "learning_rate": 0.00014222222222222224,
313
+ "loss": 0.0526,
314
+ "step": 102
315
+ },
316
+ {
317
+ "epoch": 6.93,
318
+ "learning_rate": 0.0001362962962962963,
319
+ "loss": 0.0544,
320
+ "step": 104
321
+ },
322
+ {
323
+ "epoch": 7.07,
324
+ "learning_rate": 0.0001303703703703704,
325
+ "loss": 0.036,
326
+ "step": 106
327
+ },
328
+ {
329
+ "epoch": 7.2,
330
+ "learning_rate": 0.00012444444444444444,
331
+ "loss": 0.0475,
332
+ "step": 108
333
+ },
334
+ {
335
+ "epoch": 7.33,
336
+ "learning_rate": 0.00011851851851851852,
337
+ "loss": 0.0466,
338
+ "step": 110
339
+ },
340
+ {
341
+ "epoch": 7.47,
342
+ "learning_rate": 0.0001125925925925926,
343
+ "loss": 0.0416,
344
+ "step": 112
345
+ },
346
+ {
347
+ "epoch": 7.6,
348
+ "learning_rate": 0.00010666666666666667,
349
+ "loss": 0.0387,
350
+ "step": 114
351
+ },
352
+ {
353
+ "epoch": 7.73,
354
+ "learning_rate": 0.00010074074074074073,
355
+ "loss": 0.0494,
356
+ "step": 116
357
+ },
358
+ {
359
+ "epoch": 7.87,
360
+ "learning_rate": 9.481481481481483e-05,
361
+ "loss": 0.0451,
362
+ "step": 118
363
+ },
364
+ {
365
+ "epoch": 8.0,
366
+ "learning_rate": 8.888888888888889e-05,
367
+ "loss": 0.0348,
368
+ "step": 120
369
+ },
370
+ {
371
+ "epoch": 8.13,
372
+ "learning_rate": 8.296296296296296e-05,
373
+ "loss": 0.0487,
374
+ "step": 122
375
+ },
376
+ {
377
+ "epoch": 8.27,
378
+ "learning_rate": 7.703703703703704e-05,
379
+ "loss": 0.0331,
380
+ "step": 124
381
+ },
382
+ {
383
+ "epoch": 8.4,
384
+ "learning_rate": 7.111111111111112e-05,
385
+ "loss": 0.0261,
386
+ "step": 126
387
+ },
388
+ {
389
+ "epoch": 8.53,
390
+ "learning_rate": 6.51851851851852e-05,
391
+ "loss": 0.0353,
392
+ "step": 128
393
+ },
394
+ {
395
+ "epoch": 8.67,
396
+ "learning_rate": 5.925925925925926e-05,
397
+ "loss": 0.0548,
398
+ "step": 130
399
+ },
400
+ {
401
+ "epoch": 8.8,
402
+ "learning_rate": 5.333333333333333e-05,
403
+ "loss": 0.0324,
404
+ "step": 132
405
+ },
406
+ {
407
+ "epoch": 8.93,
408
+ "learning_rate": 4.740740740740741e-05,
409
+ "loss": 0.0362,
410
+ "step": 134
411
+ },
412
+ {
413
+ "epoch": 9.07,
414
+ "learning_rate": 4.148148148148148e-05,
415
+ "loss": 0.0258,
416
+ "step": 136
417
+ },
418
+ {
419
+ "epoch": 9.2,
420
+ "learning_rate": 3.555555555555556e-05,
421
+ "loss": 0.0328,
422
+ "step": 138
423
+ },
424
+ {
425
+ "epoch": 9.33,
426
+ "learning_rate": 2.962962962962963e-05,
427
+ "loss": 0.0325,
428
+ "step": 140
429
+ },
430
+ {
431
+ "epoch": 9.47,
432
+ "learning_rate": 2.3703703703703707e-05,
433
+ "loss": 0.0245,
434
+ "step": 142
435
+ },
436
+ {
437
+ "epoch": 9.6,
438
+ "learning_rate": 1.777777777777778e-05,
439
+ "loss": 0.0294,
440
+ "step": 144
441
+ },
442
+ {
443
+ "epoch": 9.73,
444
+ "learning_rate": 1.1851851851851853e-05,
445
+ "loss": 0.0439,
446
+ "step": 146
447
+ },
448
+ {
449
+ "epoch": 9.87,
450
+ "learning_rate": 5.925925925925927e-06,
451
+ "loss": 0.0412,
452
+ "step": 148
453
+ },
454
+ {
455
+ "epoch": 10.0,
456
+ "learning_rate": 0.0,
457
+ "loss": 0.0352,
458
+ "step": 150
459
+ }
460
+ ],
461
+ "max_steps": 150,
462
+ "num_train_epochs": 10,
463
+ "total_flos": 2.407321351225344e+16,
464
+ "trial_name": null,
465
+ "trial_params": null
466
+ }
checkpoint-150/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58e462db190c0d2efd35a269dd7f41d92ecf79506535ba53a08031c375945369
3
+ size 3963
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Trelis/Llama-2-7b-chat-hf-sharded-bf16",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
12
+ "max_length": 4096,
13
+ "max_position_embeddings": 2048,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 32,
18
+ "pad_token_id": 0,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "float16",
24
+ "transformers_version": "4.31.0",
25
+ "use_cache": true,
26
+ "vocab_size": 32000
27
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.9,
8
+ "top_p": 0.6,
9
+ "transformers_version": "4.31.0"
10
+ }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6364d8611c493f1f3bfd60f49d5fb35f390b26d0593b98aacb0dcb268d5eeec9
3
+ size 9976634558
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd3c407f75481644243d3108aacef1a5c4764636c32819f3487c244efa34f8b0
3
+ size 3500315539
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,330 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13476839424
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00002-of-00002.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
17
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
18
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
22
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
23
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
24
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
25
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
27
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
28
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
29
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
30
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
31
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
32
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
33
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
34
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
35
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
37
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
38
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
39
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
40
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
41
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
42
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
43
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
44
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
45
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
47
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
48
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
49
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
50
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
51
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
52
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
53
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
54
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
55
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
57
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
58
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
59
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
60
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
61
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
62
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
63
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
64
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
65
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
67
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
68
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
69
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
70
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
71
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
72
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
73
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
74
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
75
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
77
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
78
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
79
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
80
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
81
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
82
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
83
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
84
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
85
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
87
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
88
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
89
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
90
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
91
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
92
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
93
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
94
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
95
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
97
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
98
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
99
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
100
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
101
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
102
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
103
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
104
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
105
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
107
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
108
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
109
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
110
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
111
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
112
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
113
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
114
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
115
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
117
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
118
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
119
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
120
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
121
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
122
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
123
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
124
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
125
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
127
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
128
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
129
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
130
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
131
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
132
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
133
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
134
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
135
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
137
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
138
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
139
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
140
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
141
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
142
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
143
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
144
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
145
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
147
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
148
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
149
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
150
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
151
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
152
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
153
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
154
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
155
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
157
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
158
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
159
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
160
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
161
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
162
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
163
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
164
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
165
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
167
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
168
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
169
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
170
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
171
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
172
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
173
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
174
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
175
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
177
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
178
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
179
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
180
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
181
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
182
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
183
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
184
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
185
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
187
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
188
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
189
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
190
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
191
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
192
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
193
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
194
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
195
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
197
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
198
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
199
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
200
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
201
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
202
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
203
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
204
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
205
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
207
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
208
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
209
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
210
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
211
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
212
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
213
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
214
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
215
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
217
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
218
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
219
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
220
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
221
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
222
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
223
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
224
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
225
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
227
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
228
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
229
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
230
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
231
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
232
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
233
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
234
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
235
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
237
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
238
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
239
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
240
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
241
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
242
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
243
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
244
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
245
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
247
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
248
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
249
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
250
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
251
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
252
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
253
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
254
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
255
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
257
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
258
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
259
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
260
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
261
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
262
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
263
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
264
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
265
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
267
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
268
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
269
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
270
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
271
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
272
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
273
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
274
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
275
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
276
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
277
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
278
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
279
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
280
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
281
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
282
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
283
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
284
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
285
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
286
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
287
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
288
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
289
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
290
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
291
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
292
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
293
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
294
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
295
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
296
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
297
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
298
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
299
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
300
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
301
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
302
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
303
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
304
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
305
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
306
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
307
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
308
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
309
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
310
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
311
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
312
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
313
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
314
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
315
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
316
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
317
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
318
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
319
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
320
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
321
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
322
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
323
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
324
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
325
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
326
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
327
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
328
+ "model.norm.weight": "pytorch_model-00002-of-00002.bin"
329
+ }
330
+ }
runs/Aug14_05-55-13_3f88d1fbe573/events.out.tfevents.1691992513.3f88d1fbe573.4714.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64f97dd51031003811983e8800b7dbd66370b5f2faf610b4690dc84fcad107fe
3
+ size 16341
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
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 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "clean_up_tokenization_spaces": false,
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "legacy": false,
20
+ "model_max_length": 1000000000000000019884624838656,
21
+ "pad_token": null,
22
+ "sp_model_kwargs": {},
23
+ "tokenizer_class": "LlamaTokenizer",
24
+ "unk_token": {
25
+ "__type": "AddedToken",
26
+ "content": "<unk>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "use_fast": false
33
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58e462db190c0d2efd35a269dd7f41d92ecf79506535ba53a08031c375945369
3
+ size 3963
training_params.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_name": "Trelis/Llama-2-7b-chat-hf-sharded-bf16",
3
+ "data_path": "/content/train",
4
+ "train_split": "train",
5
+ "valid_split": null,
6
+ "text_column": "text",
7
+ "huggingface_token": null,
8
+ "learning_rate": 0.0004,
9
+ "num_train_epochs": 10,
10
+ "train_batch_size": 8,
11
+ "eval_batch_size": 4,
12
+ "warmup_ratio": 0.1,
13
+ "gradient_accumulation_steps": 1,
14
+ "optimizer": "adamw_torch",
15
+ "scheduler": "linear",
16
+ "weight_decay": 0.0,
17
+ "max_grad_norm": 1.0,
18
+ "seed": 42,
19
+ "add_eos_token": false,
20
+ "block_size": -1,
21
+ "use_peft": true,
22
+ "lora_r": 16,
23
+ "lora_alpha": 32,
24
+ "lora_dropout": 0.05,
25
+ "training_type": "generic",
26
+ "train_on_inputs": false,
27
+ "logging_steps": -1,
28
+ "project_name": "llama2-tutor",
29
+ "evaluation_strategy": "epoch",
30
+ "save_total_limit": 1,
31
+ "save_strategy": "epoch",
32
+ "auto_find_batch_size": false,
33
+ "fp16": false,
34
+ "push_to_hub": true,
35
+ "use_int8": false,
36
+ "model_max_length": 1024,
37
+ "repo_id": "johaanm/llama2-openassistant-chatbased",
38
+ "use_int4": true,
39
+ "trainer": "sft",
40
+ "target_modules": null
41
+ }