Hugging Face's logo

Zestor
/
Llama-2-7b-chat-hf-apex-02082023-1255

Text Generation
Transformers
PyTorch
TensorBoard
llama
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
Zestor commited on
Commit
2651cb3
•
1 Parent(s): eec9aa8

Upload folder using huggingface_hub

Browse files
Files changed (27) hide show
  1. README.md +9 -0
  2. adapter_config.json +21 -0
  3. adapter_model.bin +3 -0
  4. checkpoint-3000/README.md +32 -0
  5. checkpoint-3000/adapter_config.json +21 -0
  6. checkpoint-3000/adapter_model.bin +3 -0
  7. checkpoint-3000/optimizer.pt +3 -0
  8. checkpoint-3000/pytorch_model.bin +3 -0
  9. checkpoint-3000/rng_state.pth +3 -0
  10. checkpoint-3000/scheduler.pt +3 -0
  11. checkpoint-3000/special_tokens_map.json +24 -0
  12. checkpoint-3000/tokenizer.json +0 -0
  13. checkpoint-3000/tokenizer.model +3 -0
  14. checkpoint-3000/tokenizer_config.json +33 -0
  15. checkpoint-3000/trainer_state.json +766 -0
  16. checkpoint-3000/training_args.bin +3 -0
  17. config.json +25 -0
  18. generation_config.json +9 -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 +298 -0
  22. runs/Aug02_16-59-02_bc0029208de3/events.out.tfevents.1690995542.bc0029208de3.41461.0 +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
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": "meta-llama/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:f288db7014ae1407ea65164260b0f579ea29bf77f516bfc3e35c17b65e64a52d
3
+ size 33600461
checkpoint-3000/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: True
9
+ - load_in_4bit: False
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: fp4
15
+ - bnb_4bit_use_double_quant: False
16
+ - bnb_4bit_compute_dtype: float32
17
+
18
+ The following `bitsandbytes` quantization config was used during training:
19
+ - load_in_8bit: True
20
+ - load_in_4bit: False
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: fp4
26
+ - bnb_4bit_use_double_quant: False
27
+ - bnb_4bit_compute_dtype: float32
28
+ ### Framework versions
29
+
30
+ - PEFT 0.5.0.dev0
31
+
32
+ - PEFT 0.5.0.dev0
checkpoint-3000/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "meta-llama/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-3000/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f288db7014ae1407ea65164260b0f579ea29bf77f516bfc3e35c17b65e64a52d
3
+ size 33600461
checkpoint-3000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f10c003d76bd92d71b7394acd4c0d6ec859bb50e1f7014c954dd1fd1d212ac6
3
+ size 67216581
checkpoint-3000/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-3000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b780a8560904ae2677a5451cf05f9fee6620c0dde447841525c61293b303445
3
+ size 14575
checkpoint-3000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11723dc79a3c9318539001d0ca7c37816ef0f67661cd1e1ab61a0d7efa26ddbe
3
+ size 627
checkpoint-3000/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-3000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-3000/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-3000/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": 2048,
21
+ "pad_token": null,
22
+ "padding_side": "right",
23
+ "sp_model_kwargs": {},
24
+ "tokenizer_class": "LlamaTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
checkpoint-3000/trainer_state.json ADDED
@@ -0,0 +1,766 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 25.0,
5
+ "global_step": 3000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.2,
12
+ "learning_rate": 1.5333333333333334e-05,
13
+ "loss": 1.135,
14
+ "step": 24
15
+ },
16
+ {
17
+ "epoch": 0.4,
18
+ "learning_rate": 3.1333333333333334e-05,
19
+ "loss": 0.9975,
20
+ "step": 48
21
+ },
22
+ {
23
+ "epoch": 0.6,
24
+ "learning_rate": 4.7333333333333336e-05,
25
+ "loss": 0.8521,
26
+ "step": 72
27
+ },
28
+ {
29
+ "epoch": 0.8,
30
+ "learning_rate": 6.333333333333333e-05,
31
+ "loss": 0.6949,
32
+ "step": 96
33
+ },
34
+ {
35
+ "epoch": 1.0,
36
+ "learning_rate": 7.933333333333334e-05,
37
+ "loss": 0.5953,
38
+ "step": 120
39
+ },
40
+ {
41
+ "epoch": 1.2,
42
+ "learning_rate": 9.533333333333334e-05,
43
+ "loss": 0.5087,
44
+ "step": 144
45
+ },
46
+ {
47
+ "epoch": 1.4,
48
+ "learning_rate": 0.00011133333333333333,
49
+ "loss": 0.4767,
50
+ "step": 168
51
+ },
52
+ {
53
+ "epoch": 1.6,
54
+ "learning_rate": 0.00012733333333333336,
55
+ "loss": 0.4546,
56
+ "step": 192
57
+ },
58
+ {
59
+ "epoch": 1.8,
60
+ "learning_rate": 0.00014333333333333334,
61
+ "loss": 0.4363,
62
+ "step": 216
63
+ },
64
+ {
65
+ "epoch": 2.0,
66
+ "learning_rate": 0.00015933333333333332,
67
+ "loss": 0.4296,
68
+ "step": 240
69
+ },
70
+ {
71
+ "epoch": 2.2,
72
+ "learning_rate": 0.00017533333333333336,
73
+ "loss": 0.3956,
74
+ "step": 264
75
+ },
76
+ {
77
+ "epoch": 2.4,
78
+ "learning_rate": 0.00019133333333333334,
79
+ "loss": 0.3875,
80
+ "step": 288
81
+ },
82
+ {
83
+ "epoch": 2.6,
84
+ "learning_rate": 0.0001991851851851852,
85
+ "loss": 0.3885,
86
+ "step": 312
87
+ },
88
+ {
89
+ "epoch": 2.8,
90
+ "learning_rate": 0.00019740740740740743,
91
+ "loss": 0.3827,
92
+ "step": 336
93
+ },
94
+ {
95
+ "epoch": 3.0,
96
+ "learning_rate": 0.00019562962962962964,
97
+ "loss": 0.378,
98
+ "step": 360
99
+ },
100
+ {
101
+ "epoch": 3.2,
102
+ "learning_rate": 0.00019385185185185187,
103
+ "loss": 0.3337,
104
+ "step": 384
105
+ },
106
+ {
107
+ "epoch": 3.4,
108
+ "learning_rate": 0.00019207407407407408,
109
+ "loss": 0.3448,
110
+ "step": 408
111
+ },
112
+ {
113
+ "epoch": 3.6,
114
+ "learning_rate": 0.00019029629629629632,
115
+ "loss": 0.3409,
116
+ "step": 432
117
+ },
118
+ {
119
+ "epoch": 3.8,
120
+ "learning_rate": 0.00018851851851851853,
121
+ "loss": 0.3446,
122
+ "step": 456
123
+ },
124
+ {
125
+ "epoch": 4.0,
126
+ "learning_rate": 0.00018674074074074074,
127
+ "loss": 0.3396,
128
+ "step": 480
129
+ },
130
+ {
131
+ "epoch": 4.2,
132
+ "learning_rate": 0.00018496296296296297,
133
+ "loss": 0.2972,
134
+ "step": 504
135
+ },
136
+ {
137
+ "epoch": 4.4,
138
+ "learning_rate": 0.00018318518518518518,
139
+ "loss": 0.3032,
140
+ "step": 528
141
+ },
142
+ {
143
+ "epoch": 4.6,
144
+ "learning_rate": 0.00018140740740740742,
145
+ "loss": 0.3051,
146
+ "step": 552
147
+ },
148
+ {
149
+ "epoch": 4.8,
150
+ "learning_rate": 0.00017962962962962963,
151
+ "loss": 0.307,
152
+ "step": 576
153
+ },
154
+ {
155
+ "epoch": 5.0,
156
+ "learning_rate": 0.00017785185185185186,
157
+ "loss": 0.3093,
158
+ "step": 600
159
+ },
160
+ {
161
+ "epoch": 5.2,
162
+ "learning_rate": 0.00017607407407407407,
163
+ "loss": 0.261,
164
+ "step": 624
165
+ },
166
+ {
167
+ "epoch": 5.4,
168
+ "learning_rate": 0.0001742962962962963,
169
+ "loss": 0.2686,
170
+ "step": 648
171
+ },
172
+ {
173
+ "epoch": 5.6,
174
+ "learning_rate": 0.00017251851851851852,
175
+ "loss": 0.2753,
176
+ "step": 672
177
+ },
178
+ {
179
+ "epoch": 5.8,
180
+ "learning_rate": 0.00017074074074074075,
181
+ "loss": 0.2802,
182
+ "step": 696
183
+ },
184
+ {
185
+ "epoch": 6.0,
186
+ "learning_rate": 0.00016896296296296296,
187
+ "loss": 0.2805,
188
+ "step": 720
189
+ },
190
+ {
191
+ "epoch": 6.2,
192
+ "learning_rate": 0.0001671851851851852,
193
+ "loss": 0.2335,
194
+ "step": 744
195
+ },
196
+ {
197
+ "epoch": 6.4,
198
+ "learning_rate": 0.0001654074074074074,
199
+ "loss": 0.234,
200
+ "step": 768
201
+ },
202
+ {
203
+ "epoch": 6.6,
204
+ "learning_rate": 0.00016362962962962964,
205
+ "loss": 0.2434,
206
+ "step": 792
207
+ },
208
+ {
209
+ "epoch": 6.8,
210
+ "learning_rate": 0.00016185185185185185,
211
+ "loss": 0.253,
212
+ "step": 816
213
+ },
214
+ {
215
+ "epoch": 7.0,
216
+ "learning_rate": 0.0001600740740740741,
217
+ "loss": 0.2481,
218
+ "step": 840
219
+ },
220
+ {
221
+ "epoch": 7.2,
222
+ "learning_rate": 0.0001582962962962963,
223
+ "loss": 0.2053,
224
+ "step": 864
225
+ },
226
+ {
227
+ "epoch": 7.4,
228
+ "learning_rate": 0.00015651851851851854,
229
+ "loss": 0.2058,
230
+ "step": 888
231
+ },
232
+ {
233
+ "epoch": 7.6,
234
+ "learning_rate": 0.00015474074074074074,
235
+ "loss": 0.213,
236
+ "step": 912
237
+ },
238
+ {
239
+ "epoch": 7.8,
240
+ "learning_rate": 0.00015296296296296298,
241
+ "loss": 0.2155,
242
+ "step": 936
243
+ },
244
+ {
245
+ "epoch": 8.0,
246
+ "learning_rate": 0.0001511851851851852,
247
+ "loss": 0.2218,
248
+ "step": 960
249
+ },
250
+ {
251
+ "epoch": 8.2,
252
+ "learning_rate": 0.00014940740740740743,
253
+ "loss": 0.1721,
254
+ "step": 984
255
+ },
256
+ {
257
+ "epoch": 8.4,
258
+ "learning_rate": 0.00014762962962962964,
259
+ "loss": 0.1812,
260
+ "step": 1008
261
+ },
262
+ {
263
+ "epoch": 8.6,
264
+ "learning_rate": 0.00014585185185185187,
265
+ "loss": 0.1858,
266
+ "step": 1032
267
+ },
268
+ {
269
+ "epoch": 8.8,
270
+ "learning_rate": 0.00014407407407407408,
271
+ "loss": 0.187,
272
+ "step": 1056
273
+ },
274
+ {
275
+ "epoch": 9.0,
276
+ "learning_rate": 0.00014229629629629632,
277
+ "loss": 0.1929,
278
+ "step": 1080
279
+ },
280
+ {
281
+ "epoch": 9.2,
282
+ "learning_rate": 0.00014051851851851853,
283
+ "loss": 0.1449,
284
+ "step": 1104
285
+ },
286
+ {
287
+ "epoch": 9.4,
288
+ "learning_rate": 0.00013874074074074076,
289
+ "loss": 0.1539,
290
+ "step": 1128
291
+ },
292
+ {
293
+ "epoch": 9.6,
294
+ "learning_rate": 0.00013696296296296297,
295
+ "loss": 0.1556,
296
+ "step": 1152
297
+ },
298
+ {
299
+ "epoch": 9.8,
300
+ "learning_rate": 0.00013518518518518518,
301
+ "loss": 0.1615,
302
+ "step": 1176
303
+ },
304
+ {
305
+ "epoch": 10.0,
306
+ "learning_rate": 0.00013340740740740742,
307
+ "loss": 0.1704,
308
+ "step": 1200
309
+ },
310
+ {
311
+ "epoch": 10.2,
312
+ "learning_rate": 0.00013162962962962963,
313
+ "loss": 0.1237,
314
+ "step": 1224
315
+ },
316
+ {
317
+ "epoch": 10.4,
318
+ "learning_rate": 0.00012985185185185186,
319
+ "loss": 0.1282,
320
+ "step": 1248
321
+ },
322
+ {
323
+ "epoch": 10.6,
324
+ "learning_rate": 0.00012807407407407407,
325
+ "loss": 0.1335,
326
+ "step": 1272
327
+ },
328
+ {
329
+ "epoch": 10.8,
330
+ "learning_rate": 0.0001262962962962963,
331
+ "loss": 0.1401,
332
+ "step": 1296
333
+ },
334
+ {
335
+ "epoch": 11.0,
336
+ "learning_rate": 0.00012451851851851852,
337
+ "loss": 0.14,
338
+ "step": 1320
339
+ },
340
+ {
341
+ "epoch": 11.2,
342
+ "learning_rate": 0.00012274074074074075,
343
+ "loss": 0.0996,
344
+ "step": 1344
345
+ },
346
+ {
347
+ "epoch": 11.4,
348
+ "learning_rate": 0.00012096296296296296,
349
+ "loss": 0.1093,
350
+ "step": 1368
351
+ },
352
+ {
353
+ "epoch": 11.6,
354
+ "learning_rate": 0.0001191851851851852,
355
+ "loss": 0.1096,
356
+ "step": 1392
357
+ },
358
+ {
359
+ "epoch": 11.8,
360
+ "learning_rate": 0.00011740740740740741,
361
+ "loss": 0.1137,
362
+ "step": 1416
363
+ },
364
+ {
365
+ "epoch": 12.0,
366
+ "learning_rate": 0.00011562962962962964,
367
+ "loss": 0.1187,
368
+ "step": 1440
369
+ },
370
+ {
371
+ "epoch": 12.2,
372
+ "learning_rate": 0.00011385185185185185,
373
+ "loss": 0.0852,
374
+ "step": 1464
375
+ },
376
+ {
377
+ "epoch": 12.4,
378
+ "learning_rate": 0.00011207407407407409,
379
+ "loss": 0.0901,
380
+ "step": 1488
381
+ },
382
+ {
383
+ "epoch": 12.6,
384
+ "learning_rate": 0.0001102962962962963,
385
+ "loss": 0.0909,
386
+ "step": 1512
387
+ },
388
+ {
389
+ "epoch": 12.8,
390
+ "learning_rate": 0.00010851851851851853,
391
+ "loss": 0.094,
392
+ "step": 1536
393
+ },
394
+ {
395
+ "epoch": 13.0,
396
+ "learning_rate": 0.00010674074074074074,
397
+ "loss": 0.1011,
398
+ "step": 1560
399
+ },
400
+ {
401
+ "epoch": 13.2,
402
+ "learning_rate": 0.00010496296296296298,
403
+ "loss": 0.0703,
404
+ "step": 1584
405
+ },
406
+ {
407
+ "epoch": 13.4,
408
+ "learning_rate": 0.00010318518518518519,
409
+ "loss": 0.0726,
410
+ "step": 1608
411
+ },
412
+ {
413
+ "epoch": 13.6,
414
+ "learning_rate": 0.00010140740740740741,
415
+ "loss": 0.0769,
416
+ "step": 1632
417
+ },
418
+ {
419
+ "epoch": 13.8,
420
+ "learning_rate": 9.962962962962963e-05,
421
+ "loss": 0.0787,
422
+ "step": 1656
423
+ },
424
+ {
425
+ "epoch": 14.0,
426
+ "learning_rate": 9.785185185185186e-05,
427
+ "loss": 0.0848,
428
+ "step": 1680
429
+ },
430
+ {
431
+ "epoch": 14.2,
432
+ "learning_rate": 9.607407407407408e-05,
433
+ "loss": 0.0604,
434
+ "step": 1704
435
+ },
436
+ {
437
+ "epoch": 14.4,
438
+ "learning_rate": 9.42962962962963e-05,
439
+ "loss": 0.0586,
440
+ "step": 1728
441
+ },
442
+ {
443
+ "epoch": 14.6,
444
+ "learning_rate": 9.251851851851852e-05,
445
+ "loss": 0.0616,
446
+ "step": 1752
447
+ },
448
+ {
449
+ "epoch": 14.8,
450
+ "learning_rate": 9.074074074074075e-05,
451
+ "loss": 0.0663,
452
+ "step": 1776
453
+ },
454
+ {
455
+ "epoch": 15.0,
456
+ "learning_rate": 8.896296296296297e-05,
457
+ "loss": 0.0651,
458
+ "step": 1800
459
+ },
460
+ {
461
+ "epoch": 15.2,
462
+ "learning_rate": 8.718518518518519e-05,
463
+ "loss": 0.0479,
464
+ "step": 1824
465
+ },
466
+ {
467
+ "epoch": 15.4,
468
+ "learning_rate": 8.540740740740742e-05,
469
+ "loss": 0.05,
470
+ "step": 1848
471
+ },
472
+ {
473
+ "epoch": 15.6,
474
+ "learning_rate": 8.362962962962964e-05,
475
+ "loss": 0.0521,
476
+ "step": 1872
477
+ },
478
+ {
479
+ "epoch": 15.8,
480
+ "learning_rate": 8.185185185185186e-05,
481
+ "loss": 0.0523,
482
+ "step": 1896
483
+ },
484
+ {
485
+ "epoch": 16.0,
486
+ "learning_rate": 8.007407407407408e-05,
487
+ "loss": 0.0535,
488
+ "step": 1920
489
+ },
490
+ {
491
+ "epoch": 16.2,
492
+ "learning_rate": 7.82962962962963e-05,
493
+ "loss": 0.0402,
494
+ "step": 1944
495
+ },
496
+ {
497
+ "epoch": 16.4,
498
+ "learning_rate": 7.651851851851853e-05,
499
+ "loss": 0.0406,
500
+ "step": 1968
501
+ },
502
+ {
503
+ "epoch": 16.6,
504
+ "learning_rate": 7.474074074074074e-05,
505
+ "loss": 0.0426,
506
+ "step": 1992
507
+ },
508
+ {
509
+ "epoch": 16.8,
510
+ "learning_rate": 7.296296296296296e-05,
511
+ "loss": 0.0414,
512
+ "step": 2016
513
+ },
514
+ {
515
+ "epoch": 17.0,
516
+ "learning_rate": 7.118518518518518e-05,
517
+ "loss": 0.0438,
518
+ "step": 2040
519
+ },
520
+ {
521
+ "epoch": 17.2,
522
+ "learning_rate": 6.94074074074074e-05,
523
+ "loss": 0.0336,
524
+ "step": 2064
525
+ },
526
+ {
527
+ "epoch": 17.4,
528
+ "learning_rate": 6.762962962962963e-05,
529
+ "loss": 0.0332,
530
+ "step": 2088
531
+ },
532
+ {
533
+ "epoch": 17.6,
534
+ "learning_rate": 6.585185185185185e-05,
535
+ "loss": 0.0342,
536
+ "step": 2112
537
+ },
538
+ {
539
+ "epoch": 17.8,
540
+ "learning_rate": 6.407407407407407e-05,
541
+ "loss": 0.0342,
542
+ "step": 2136
543
+ },
544
+ {
545
+ "epoch": 18.0,
546
+ "learning_rate": 6.22962962962963e-05,
547
+ "loss": 0.0356,
548
+ "step": 2160
549
+ },
550
+ {
551
+ "epoch": 18.2,
552
+ "learning_rate": 6.051851851851852e-05,
553
+ "loss": 0.0259,
554
+ "step": 2184
555
+ },
556
+ {
557
+ "epoch": 18.4,
558
+ "learning_rate": 5.874074074074074e-05,
559
+ "loss": 0.0269,
560
+ "step": 2208
561
+ },
562
+ {
563
+ "epoch": 18.6,
564
+ "learning_rate": 5.6962962962962965e-05,
565
+ "loss": 0.0282,
566
+ "step": 2232
567
+ },
568
+ {
569
+ "epoch": 18.8,
570
+ "learning_rate": 5.518518518518519e-05,
571
+ "loss": 0.0291,
572
+ "step": 2256
573
+ },
574
+ {
575
+ "epoch": 19.0,
576
+ "learning_rate": 5.34074074074074e-05,
577
+ "loss": 0.0297,
578
+ "step": 2280
579
+ },
580
+ {
581
+ "epoch": 19.2,
582
+ "learning_rate": 5.1629629629629626e-05,
583
+ "loss": 0.0236,
584
+ "step": 2304
585
+ },
586
+ {
587
+ "epoch": 19.4,
588
+ "learning_rate": 4.9851851851851855e-05,
589
+ "loss": 0.0234,
590
+ "step": 2328
591
+ },
592
+ {
593
+ "epoch": 19.6,
594
+ "learning_rate": 4.807407407407408e-05,
595
+ "loss": 0.0233,
596
+ "step": 2352
597
+ },
598
+ {
599
+ "epoch": 19.8,
600
+ "learning_rate": 4.62962962962963e-05,
601
+ "loss": 0.0231,
602
+ "step": 2376
603
+ },
604
+ {
605
+ "epoch": 20.0,
606
+ "learning_rate": 4.4518518518518523e-05,
607
+ "loss": 0.0231,
608
+ "step": 2400
609
+ },
610
+ {
611
+ "epoch": 20.2,
612
+ "learning_rate": 4.274074074074074e-05,
613
+ "loss": 0.0183,
614
+ "step": 2424
615
+ },
616
+ {
617
+ "epoch": 20.4,
618
+ "learning_rate": 4.096296296296296e-05,
619
+ "loss": 0.0196,
620
+ "step": 2448
621
+ },
622
+ {
623
+ "epoch": 20.6,
624
+ "learning_rate": 3.9185185185185185e-05,
625
+ "loss": 0.0197,
626
+ "step": 2472
627
+ },
628
+ {
629
+ "epoch": 20.8,
630
+ "learning_rate": 3.740740740740741e-05,
631
+ "loss": 0.0198,
632
+ "step": 2496
633
+ },
634
+ {
635
+ "epoch": 21.0,
636
+ "learning_rate": 3.562962962962963e-05,
637
+ "loss": 0.0196,
638
+ "step": 2520
639
+ },
640
+ {
641
+ "epoch": 21.2,
642
+ "learning_rate": 3.385185185185185e-05,
643
+ "loss": 0.0162,
644
+ "step": 2544
645
+ },
646
+ {
647
+ "epoch": 21.4,
648
+ "learning_rate": 3.2074074074074075e-05,
649
+ "loss": 0.016,
650
+ "step": 2568
651
+ },
652
+ {
653
+ "epoch": 21.6,
654
+ "learning_rate": 3.02962962962963e-05,
655
+ "loss": 0.0166,
656
+ "step": 2592
657
+ },
658
+ {
659
+ "epoch": 21.8,
660
+ "learning_rate": 2.851851851851852e-05,
661
+ "loss": 0.0168,
662
+ "step": 2616
663
+ },
664
+ {
665
+ "epoch": 22.0,
666
+ "learning_rate": 2.6740740740740743e-05,
667
+ "loss": 0.0167,
668
+ "step": 2640
669
+ },
670
+ {
671
+ "epoch": 22.2,
672
+ "learning_rate": 2.4962962962962963e-05,
673
+ "loss": 0.0145,
674
+ "step": 2664
675
+ },
676
+ {
677
+ "epoch": 22.4,
678
+ "learning_rate": 2.318518518518519e-05,
679
+ "loss": 0.014,
680
+ "step": 2688
681
+ },
682
+ {
683
+ "epoch": 22.6,
684
+ "learning_rate": 2.1407407407407408e-05,
685
+ "loss": 0.0135,
686
+ "step": 2712
687
+ },
688
+ {
689
+ "epoch": 22.8,
690
+ "learning_rate": 1.962962962962963e-05,
691
+ "loss": 0.014,
692
+ "step": 2736
693
+ },
694
+ {
695
+ "epoch": 23.0,
696
+ "learning_rate": 1.7851851851851853e-05,
697
+ "loss": 0.0144,
698
+ "step": 2760
699
+ },
700
+ {
701
+ "epoch": 23.2,
702
+ "learning_rate": 1.6074074074074076e-05,
703
+ "loss": 0.0123,
704
+ "step": 2784
705
+ },
706
+ {
707
+ "epoch": 23.4,
708
+ "learning_rate": 1.4296296296296297e-05,
709
+ "loss": 0.0128,
710
+ "step": 2808
711
+ },
712
+ {
713
+ "epoch": 23.6,
714
+ "learning_rate": 1.2518518518518518e-05,
715
+ "loss": 0.0128,
716
+ "step": 2832
717
+ },
718
+ {
719
+ "epoch": 23.8,
720
+ "learning_rate": 1.074074074074074e-05,
721
+ "loss": 0.0124,
722
+ "step": 2856
723
+ },
724
+ {
725
+ "epoch": 24.0,
726
+ "learning_rate": 8.962962962962963e-06,
727
+ "loss": 0.0125,
728
+ "step": 2880
729
+ },
730
+ {
731
+ "epoch": 24.2,
732
+ "learning_rate": 7.185185185185185e-06,
733
+ "loss": 0.0113,
734
+ "step": 2904
735
+ },
736
+ {
737
+ "epoch": 24.4,
738
+ "learning_rate": 5.407407407407407e-06,
739
+ "loss": 0.0112,
740
+ "step": 2928
741
+ },
742
+ {
743
+ "epoch": 24.6,
744
+ "learning_rate": 3.6296296296296302e-06,
745
+ "loss": 0.0114,
746
+ "step": 2952
747
+ },
748
+ {
749
+ "epoch": 24.8,
750
+ "learning_rate": 1.8518518518518519e-06,
751
+ "loss": 0.0118,
752
+ "step": 2976
753
+ },
754
+ {
755
+ "epoch": 25.0,
756
+ "learning_rate": 7.407407407407407e-08,
757
+ "loss": 0.0116,
758
+ "step": 3000
759
+ }
760
+ ],
761
+ "max_steps": 3000,
762
+ "num_train_epochs": 25,
763
+ "total_flos": 4.87764705411072e+17,
764
+ "trial_name": null,
765
+ "trial_params": null
766
+ }
checkpoint-3000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:263bd6cad3c6a734b3f1fe9b118c32c7e8f9d7599dbfbbe5cecca2167068c3a8
3
+ size 4027
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
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_position_embeddings": 4096,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 32,
16
+ "num_key_value_heads": 32,
17
+ "pretraining_tp": 1,
18
+ "rms_norm_eps": 1e-06,
19
+ "rope_scaling": null,
20
+ "tie_word_embeddings": false,
21
+ "torch_dtype": "float16",
22
+ "transformers_version": "4.32.0.dev0",
23
+ "use_cache": true,
24
+ "vocab_size": 32000
25
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "eos_token_id": 2,
4
+ "max_length": 4096,
5
+ "pad_token_id": 0,
6
+ "temperature": 0.9,
7
+ "top_p": 0.6,
8
+ "transformers_version": "4.32.0.dev0"
9
+ }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f768345ce7feaf698833a3397edf154fe40b6b1ffe92e9381d481435ec4e2ca7
3
+ size 9976620122
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39085b90478f9ee059addddea7a4d7d5711aba5bbf30d071892b036ec71dbd82
3
+ size 3500310787
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13476831232
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.v_proj.weight": "pytorch_model-00001-of-00002.bin",
17
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
18
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
19
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
20
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
22
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
23
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
24
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
25
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
26
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
27
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
28
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
29
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
30
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
31
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
32
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
33
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
34
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
35
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
36
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
37
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
38
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
39
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
40
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
41
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
42
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
43
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
44
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
45
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
46
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
47
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
48
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
49
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
50
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
51
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
52
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
53
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
54
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
55
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
56
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
57
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
58
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
59
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
60
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
61
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
62
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
63
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
64
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
65
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
66
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
67
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
68
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
69
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
70
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
71
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
72
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
73
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
74
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
75
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
76
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
77
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
78
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
79
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
80
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
81
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
82
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
83
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
84
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
85
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
86
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
87
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
88
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
89
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
90
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
91
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
92
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
93
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
94
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
95
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
96
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
97
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
98
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
99
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
100
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
101
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
102
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
103
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
104
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
105
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
106
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
107
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
108
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
109
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
110
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
111
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
112
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
113
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
114
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
115
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
116
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
117
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
118
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
119
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
120
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
121
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
122
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
123
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
124
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
125
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
126
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
127
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
128
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
129
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
130
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
131
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
132
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
133
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
134
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
135
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
136
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
137
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
138
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
139
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
140
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
141
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
142
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
143
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
144
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
145
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
146
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
147
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
148
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
149
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
150
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
151
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
152
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
153
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
154
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
155
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
156
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
157
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
158
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
159
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
160
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
161
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
162
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
163
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
164
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
165
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
166
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
167
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
168
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
169
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
170
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
171
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
172
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
173
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
174
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
175
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
176
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
177
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
178
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
179
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
180
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
181
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
182
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
183
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
184
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
185
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
186
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
187
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
188
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
189
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
190
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
191
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
192
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
193
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
194
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
195
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
196
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
197
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
198
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
199
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
200
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
201
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
202
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
203
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
204
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
205
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
206
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
207
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
208
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
209
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
210
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
211
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
212
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
213
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
214
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
215
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
216
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
217
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
218
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
219
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
220
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
221
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
222
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
223
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
224
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
225
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
226
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
227
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
228
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
229
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
230
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
231
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
232
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
233
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
234
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
235
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
236
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
237
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
238
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
239
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
240
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
241
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
242
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
243
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
244
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
245
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
246
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
247
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
248
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
249
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
250
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
251
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
252
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
253
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
254
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
255
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
256
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
257
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
258
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
259
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
260
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
261
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
262
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
263
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
264
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
265
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
266
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
267
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
268
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
269
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
270
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
271
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
272
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
273
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
274
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
275
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
276
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
277
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
278
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
279
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
280
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
281
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
282
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
283
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
284
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
285
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
286
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
287
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
288
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
289
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
290
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
291
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
292
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
293
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
294
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
295
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
296
+ "model.norm.weight": "pytorch_model-00002-of-00002.bin"
297
+ }
298
+ }
runs/Aug02_16-59-02_bc0029208de3/events.out.tfevents.1690995542.bc0029208de3.41461.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abaa87d71168bda98a3e851406c2a7299701797cdf620a67d58415a665ae5d7a
3
+ size 24416
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
+ "padding_side": "right",
23
+ "sp_model_kwargs": {},
24
+ "tokenizer_class": "LlamaTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:263bd6cad3c6a734b3f1fe9b118c32c7e8f9d7599dbfbbe5cecca2167068c3a8
3
+ size 4027