Hugging Face's logo

pierreguillou
/
llama-2-7b-hf-text2image-prompts-Liege-test

Text Generation
Transformers
PyTorch
TensorBoard
llama
Trained with AutoTrain
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
pierreguillou commited on
Commit
aa169ac
•
1 Parent(s): 36445d8

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-65/README.md +34 -0
  5. checkpoint-65/adapter_config.json +21 -0
  6. checkpoint-65/adapter_model.bin +3 -0
  7. checkpoint-65/optimizer.pt +3 -0
  8. checkpoint-65/pytorch_model.bin +3 -0
  9. checkpoint-65/rng_state.pth +3 -0
  10. checkpoint-65/scheduler.pt +3 -0
  11. checkpoint-65/special_tokens_map.json +6 -0
  12. checkpoint-65/tokenizer.json +0 -0
  13. checkpoint-65/tokenizer.model +3 -0
  14. checkpoint-65/tokenizer_config.json +40 -0
  15. checkpoint-65/trainer_state.json +489 -0
  16. checkpoint-65/training_args.bin +3 -0
  17. config.json +26 -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 +298 -0
  22. runs/Sep22_17-25-30_9c422ebb7bfe/events.out.tfevents.1695403531.9c422ebb7bfe.12983.0 +3 -0
  23. special_tokens_map.json +5 -0
  24. tokenizer.json +0 -0
  25. tokenizer.model +3 -0
  26. tokenizer_config.json +40 -0
  27. training_args.bin +3 -0
  28. training_params.json +1 -0
README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - autotrain
4
+ - text-generation
5
+ widget:
6
+ - text: "I love AutoTrain because "
7
+ ---
8
+
9
+ # Model Trained Using AutoTrain
adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "meta-llama/Llama-2-7b-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 sha256:33d4407d7ee6f93b6296fcab38ba08caa3ed5f15e4663b56e877249e9a47496c
3
+ size 33600461
checkpoint-65/README.md ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: False
10
+ - load_in_4bit: True
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: nf4
16
+ - bnb_4bit_use_double_quant: False
17
+ - bnb_4bit_compute_dtype: float16
18
+
19
+ The following `bitsandbytes` quantization config was used during training:
20
+ - quant_method: bitsandbytes
21
+ - load_in_8bit: False
22
+ - load_in_4bit: True
23
+ - llm_int8_threshold: 6.0
24
+ - llm_int8_skip_modules: None
25
+ - llm_int8_enable_fp32_cpu_offload: False
26
+ - llm_int8_has_fp16_weight: False
27
+ - bnb_4bit_quant_type: nf4
28
+ - bnb_4bit_use_double_quant: False
29
+ - bnb_4bit_compute_dtype: float16
30
+ ### Framework versions
31
+
32
+ - PEFT 0.6.0.dev0
33
+
34
+ - PEFT 0.6.0.dev0
checkpoint-65/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "meta-llama/Llama-2-7b-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-65/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33d4407d7ee6f93b6296fcab38ba08caa3ed5f15e4663b56e877249e9a47496c
3
+ size 33600461
checkpoint-65/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d161eb18f27d3d431f2b4674d0feef60aa22b3448011d613c55527710f707bd3
3
+ size 67216581
checkpoint-65/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-65/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be57dc0af2516cc92a9cd6be3dc09acbc7328030209f51bcea0448a890de8241
3
+ size 14575
checkpoint-65/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c60541a5daa8e24f22f0dc5a2521f083868f7ae6766973307b5670d5973f40d
3
+ size 627
checkpoint-65/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "</s>",
5
+ "unk_token": "<unk>"
6
+ }
checkpoint-65/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-65/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-65/tokenizer_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "additional_special_tokens": [],
29
+ "bos_token": "<s>",
30
+ "clean_up_tokenization_spaces": false,
31
+ "eos_token": "</s>",
32
+ "legacy": false,
33
+ "model_max_length": 1024,
34
+ "pad_token": null,
35
+ "padding_side": "right",
36
+ "sp_model_kwargs": {},
37
+ "tokenizer_class": "LlamaTokenizer",
38
+ "unk_token": "<unk>",
39
+ "use_default_system_prompt": true
40
+ }
checkpoint-65/trainer_state.json ADDED
@@ -0,0 +1,489 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.1841961294412613,
3
+ "best_model_checkpoint": "llama-2-7b-hf-text2image-prompts-Liege/checkpoint-65",
4
+ "epoch": 10.0,
5
+ "eval_steps": 500,
6
+ "global_step": 65,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.15,
13
+ "learning_rate": 2.2222222222222223e-05,
14
+ "loss": 1.0005,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.31,
19
+ "learning_rate": 4.4444444444444447e-05,
20
+ "loss": 0.9403,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.46,
25
+ "learning_rate": 6.666666666666667e-05,
26
+ "loss": 0.9234,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.62,
31
+ "learning_rate": 8.888888888888889e-05,
32
+ "loss": 0.9738,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.77,
37
+ "learning_rate": 0.00011111111111111112,
38
+ "loss": 0.9561,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.92,
43
+ "learning_rate": 0.00013333333333333334,
44
+ "loss": 0.9102,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.92,
49
+ "eval_loss": 0.8407344222068787,
50
+ "eval_runtime": 5.7929,
51
+ "eval_samples_per_second": 0.691,
52
+ "eval_steps_per_second": 0.691,
53
+ "step": 6
54
+ },
55
+ {
56
+ "epoch": 1.08,
57
+ "learning_rate": 0.00015555555555555556,
58
+ "loss": 0.9346,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 1.23,
63
+ "learning_rate": 0.00017777777777777779,
64
+ "loss": 0.8937,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 1.38,
69
+ "learning_rate": 0.0002,
70
+ "loss": 0.8569,
71
+ "step": 9
72
+ },
73
+ {
74
+ "epoch": 1.54,
75
+ "learning_rate": 0.00019753086419753085,
76
+ "loss": 0.8014,
77
+ "step": 10
78
+ },
79
+ {
80
+ "epoch": 1.69,
81
+ "learning_rate": 0.00019506172839506175,
82
+ "loss": 0.7843,
83
+ "step": 11
84
+ },
85
+ {
86
+ "epoch": 1.85,
87
+ "learning_rate": 0.0001925925925925926,
88
+ "loss": 0.7857,
89
+ "step": 12
90
+ },
91
+ {
92
+ "epoch": 2.0,
93
+ "learning_rate": 0.00019012345679012346,
94
+ "loss": 0.711,
95
+ "step": 13
96
+ },
97
+ {
98
+ "epoch": 2.0,
99
+ "eval_loss": 0.6122090816497803,
100
+ "eval_runtime": 5.6653,
101
+ "eval_samples_per_second": 0.706,
102
+ "eval_steps_per_second": 0.706,
103
+ "step": 13
104
+ },
105
+ {
106
+ "epoch": 2.15,
107
+ "learning_rate": 0.00018765432098765433,
108
+ "loss": 0.6708,
109
+ "step": 14
110
+ },
111
+ {
112
+ "epoch": 2.31,
113
+ "learning_rate": 0.0001851851851851852,
114
+ "loss": 0.6309,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 2.46,
119
+ "learning_rate": 0.00018271604938271605,
120
+ "loss": 0.5825,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 2.62,
125
+ "learning_rate": 0.00018024691358024692,
126
+ "loss": 0.548,
127
+ "step": 17
128
+ },
129
+ {
130
+ "epoch": 2.77,
131
+ "learning_rate": 0.00017777777777777779,
132
+ "loss": 0.5468,
133
+ "step": 18
134
+ },
135
+ {
136
+ "epoch": 2.92,
137
+ "learning_rate": 0.00017530864197530866,
138
+ "loss": 0.4747,
139
+ "step": 19
140
+ },
141
+ {
142
+ "epoch": 2.92,
143
+ "eval_loss": 0.41001003980636597,
144
+ "eval_runtime": 5.6712,
145
+ "eval_samples_per_second": 0.705,
146
+ "eval_steps_per_second": 0.705,
147
+ "step": 19
148
+ },
149
+ {
150
+ "epoch": 3.08,
151
+ "learning_rate": 0.0001728395061728395,
152
+ "loss": 0.4748,
153
+ "step": 20
154
+ },
155
+ {
156
+ "epoch": 3.23,
157
+ "learning_rate": 0.00017037037037037037,
158
+ "loss": 0.4252,
159
+ "step": 21
160
+ },
161
+ {
162
+ "epoch": 3.38,
163
+ "learning_rate": 0.00016790123456790124,
164
+ "loss": 0.3978,
165
+ "step": 22
166
+ },
167
+ {
168
+ "epoch": 3.54,
169
+ "learning_rate": 0.0001654320987654321,
170
+ "loss": 0.361,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 3.69,
175
+ "learning_rate": 0.00016296296296296295,
176
+ "loss": 0.3544,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 3.85,
181
+ "learning_rate": 0.00016049382716049385,
182
+ "loss": 0.3317,
183
+ "step": 25
184
+ },
185
+ {
186
+ "epoch": 4.0,
187
+ "learning_rate": 0.0001580246913580247,
188
+ "loss": 0.2919,
189
+ "step": 26
190
+ },
191
+ {
192
+ "epoch": 4.0,
193
+ "eval_loss": 0.2563404142856598,
194
+ "eval_runtime": 5.6469,
195
+ "eval_samples_per_second": 0.708,
196
+ "eval_steps_per_second": 0.708,
197
+ "step": 26
198
+ },
199
+ {
200
+ "epoch": 4.15,
201
+ "learning_rate": 0.00015555555555555556,
202
+ "loss": 0.2837,
203
+ "step": 27
204
+ },
205
+ {
206
+ "epoch": 4.31,
207
+ "learning_rate": 0.0001530864197530864,
208
+ "loss": 0.2923,
209
+ "step": 28
210
+ },
211
+ {
212
+ "epoch": 4.46,
213
+ "learning_rate": 0.0001506172839506173,
214
+ "loss": 0.2485,
215
+ "step": 29
216
+ },
217
+ {
218
+ "epoch": 4.62,
219
+ "learning_rate": 0.00014814814814814815,
220
+ "loss": 0.2767,
221
+ "step": 30
222
+ },
223
+ {
224
+ "epoch": 4.77,
225
+ "learning_rate": 0.00014567901234567902,
226
+ "loss": 0.2626,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 4.92,
231
+ "learning_rate": 0.00014320987654320989,
232
+ "loss": 0.2513,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 4.92,
237
+ "eval_loss": 0.22316063940525055,
238
+ "eval_runtime": 5.6083,
239
+ "eval_samples_per_second": 0.713,
240
+ "eval_steps_per_second": 0.713,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 5.08,
245
+ "learning_rate": 0.00014074074074074076,
246
+ "loss": 0.2462,
247
+ "step": 33
248
+ },
249
+ {
250
+ "epoch": 5.23,
251
+ "learning_rate": 0.0001382716049382716,
252
+ "loss": 0.2339,
253
+ "step": 34
254
+ },
255
+ {
256
+ "epoch": 5.38,
257
+ "learning_rate": 0.00013580246913580247,
258
+ "loss": 0.2269,
259
+ "step": 35
260
+ },
261
+ {
262
+ "epoch": 5.54,
263
+ "learning_rate": 0.00013333333333333334,
264
+ "loss": 0.2558,
265
+ "step": 36
266
+ },
267
+ {
268
+ "epoch": 5.69,
269
+ "learning_rate": 0.0001308641975308642,
270
+ "loss": 0.2005,
271
+ "step": 37
272
+ },
273
+ {
274
+ "epoch": 5.85,
275
+ "learning_rate": 0.00012839506172839505,
276
+ "loss": 0.2104,
277
+ "step": 38
278
+ },
279
+ {
280
+ "epoch": 6.0,
281
+ "learning_rate": 0.00012592592592592592,
282
+ "loss": 0.2161,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 6.0,
287
+ "eval_loss": 0.20953989028930664,
288
+ "eval_runtime": 5.6454,
289
+ "eval_samples_per_second": 0.709,
290
+ "eval_steps_per_second": 0.709,
291
+ "step": 39
292
+ },
293
+ {
294
+ "epoch": 6.15,
295
+ "learning_rate": 0.0001234567901234568,
296
+ "loss": 0.2015,
297
+ "step": 40
298
+ },
299
+ {
300
+ "epoch": 6.31,
301
+ "learning_rate": 0.00012098765432098766,
302
+ "loss": 0.2465,
303
+ "step": 41
304
+ },
305
+ {
306
+ "epoch": 6.46,
307
+ "learning_rate": 0.00011851851851851852,
308
+ "loss": 0.194,
309
+ "step": 42
310
+ },
311
+ {
312
+ "epoch": 6.62,
313
+ "learning_rate": 0.00011604938271604939,
314
+ "loss": 0.191,
315
+ "step": 43
316
+ },
317
+ {
318
+ "epoch": 6.77,
319
+ "learning_rate": 0.00011358024691358025,
320
+ "loss": 0.2012,
321
+ "step": 44
322
+ },
323
+ {
324
+ "epoch": 6.92,
325
+ "learning_rate": 0.00011111111111111112,
326
+ "loss": 0.1807,
327
+ "step": 45
328
+ },
329
+ {
330
+ "epoch": 6.92,
331
+ "eval_loss": 0.2051384598016739,
332
+ "eval_runtime": 5.64,
333
+ "eval_samples_per_second": 0.709,
334
+ "eval_steps_per_second": 0.709,
335
+ "step": 45
336
+ },
337
+ {
338
+ "epoch": 7.08,
339
+ "learning_rate": 0.00010864197530864197,
340
+ "loss": 0.2073,
341
+ "step": 46
342
+ },
343
+ {
344
+ "epoch": 7.23,
345
+ "learning_rate": 0.00010617283950617284,
346
+ "loss": 0.1691,
347
+ "step": 47
348
+ },
349
+ {
350
+ "epoch": 7.38,
351
+ "learning_rate": 0.0001037037037037037,
352
+ "loss": 0.1751,
353
+ "step": 48
354
+ },
355
+ {
356
+ "epoch": 7.54,
357
+ "learning_rate": 0.00010123456790123458,
358
+ "loss": 0.1844,
359
+ "step": 49
360
+ },
361
+ {
362
+ "epoch": 7.69,
363
+ "learning_rate": 9.876543209876543e-05,
364
+ "loss": 0.1975,
365
+ "step": 50
366
+ },
367
+ {
368
+ "epoch": 7.85,
369
+ "learning_rate": 9.62962962962963e-05,
370
+ "loss": 0.1567,
371
+ "step": 51
372
+ },
373
+ {
374
+ "epoch": 8.0,
375
+ "learning_rate": 9.382716049382717e-05,
376
+ "loss": 0.1815,
377
+ "step": 52
378
+ },
379
+ {
380
+ "epoch": 8.0,
381
+ "eval_loss": 0.2019922435283661,
382
+ "eval_runtime": 5.629,
383
+ "eval_samples_per_second": 0.711,
384
+ "eval_steps_per_second": 0.711,
385
+ "step": 52
386
+ },
387
+ {
388
+ "epoch": 8.15,
389
+ "learning_rate": 9.135802469135802e-05,
390
+ "loss": 0.1686,
391
+ "step": 53
392
+ },
393
+ {
394
+ "epoch": 8.31,
395
+ "learning_rate": 8.888888888888889e-05,
396
+ "loss": 0.1496,
397
+ "step": 54
398
+ },
399
+ {
400
+ "epoch": 8.46,
401
+ "learning_rate": 8.641975308641975e-05,
402
+ "loss": 0.1446,
403
+ "step": 55
404
+ },
405
+ {
406
+ "epoch": 8.62,
407
+ "learning_rate": 8.395061728395062e-05,
408
+ "loss": 0.1649,
409
+ "step": 56
410
+ },
411
+ {
412
+ "epoch": 8.77,
413
+ "learning_rate": 8.148148148148148e-05,
414
+ "loss": 0.1539,
415
+ "step": 57
416
+ },
417
+ {
418
+ "epoch": 8.92,
419
+ "learning_rate": 7.901234567901235e-05,
420
+ "loss": 0.1652,
421
+ "step": 58
422
+ },
423
+ {
424
+ "epoch": 8.92,
425
+ "eval_loss": 0.1942683905363083,
426
+ "eval_runtime": 5.6323,
427
+ "eval_samples_per_second": 0.71,
428
+ "eval_steps_per_second": 0.71,
429
+ "step": 58
430
+ },
431
+ {
432
+ "epoch": 9.08,
433
+ "learning_rate": 7.65432098765432e-05,
434
+ "loss": 0.1352,
435
+ "step": 59
436
+ },
437
+ {
438
+ "epoch": 9.23,
439
+ "learning_rate": 7.407407407407407e-05,
440
+ "loss": 0.1361,
441
+ "step": 60
442
+ },
443
+ {
444
+ "epoch": 9.38,
445
+ "learning_rate": 7.160493827160494e-05,
446
+ "loss": 0.1214,
447
+ "step": 61
448
+ },
449
+ {
450
+ "epoch": 9.54,
451
+ "learning_rate": 6.91358024691358e-05,
452
+ "loss": 0.1329,
453
+ "step": 62
454
+ },
455
+ {
456
+ "epoch": 9.69,
457
+ "learning_rate": 6.666666666666667e-05,
458
+ "loss": 0.1072,
459
+ "step": 63
460
+ },
461
+ {
462
+ "epoch": 9.85,
463
+ "learning_rate": 6.419753086419753e-05,
464
+ "loss": 0.1123,
465
+ "step": 64
466
+ },
467
+ {
468
+ "epoch": 10.0,
469
+ "learning_rate": 6.17283950617284e-05,
470
+ "loss": 0.13,
471
+ "step": 65
472
+ },
473
+ {
474
+ "epoch": 10.0,
475
+ "eval_loss": 0.1841961294412613,
476
+ "eval_runtime": 5.6483,
477
+ "eval_samples_per_second": 0.708,
478
+ "eval_steps_per_second": 0.708,
479
+ "step": 65
480
+ }
481
+ ],
482
+ "logging_steps": 1,
483
+ "max_steps": 90,
484
+ "num_train_epochs": 15,
485
+ "save_steps": 500,
486
+ "total_flos": 1.056823528390656e+16,
487
+ "trial_name": null,
488
+ "trial_params": null
489
+ }
checkpoint-65/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d664ac4087139ee22b7c31e61a77b4cc7b7552fa4059fc3a801bd8545aa7ac0
3
+ size 4091
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-2-7b-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-05,
19
+ "rope_scaling": null,
20
+ "rope_theta": 10000.0,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.34.0.dev0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "do_sample": true,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.6,
8
+ "top_p": 0.9,
9
+ "transformers_version": "4.34.0.dev0"
10
+ }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b11b2116794ba41538084ab71e0daef5d1fd1baa226caadb0747699624e303e5
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 sha256:557375803d40a178d47b5a43b4810deabdc3dfb2309f6eb7f8a8a0f3f8abc341
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/Sep22_17-25-30_9c422ebb7bfe/events.out.tfevents.1695403531.9c422ebb7bfe.12983.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:093fec147ad6eb39d207a626b406f9d5ad44c8b970178af927aee2d06392b2d4
3
+ size 22509
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "unk_token": "<unk>"
5
+ }
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 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "additional_special_tokens": [],
29
+ "bos_token": "<s>",
30
+ "clean_up_tokenization_spaces": false,
31
+ "eos_token": "</s>",
32
+ "legacy": false,
33
+ "model_max_length": 1000000000000000019884624838656,
34
+ "pad_token": null,
35
+ "padding_side": "right",
36
+ "sp_model_kwargs": {},
37
+ "tokenizer_class": "LlamaTokenizer",
38
+ "unk_token": "<unk>",
39
+ "use_default_system_prompt": true
40
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d664ac4087139ee22b7c31e61a77b4cc7b7552fa4059fc3a801bd8545aa7ac0
3
+ size 4091
training_params.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model": "meta-llama/Llama-2-7b-hf", "data_path": "data/", "project_name": "llama-2-7b-hf-text2image-prompts-Liege", "train_split": "train_updated", "valid_split": "valid_updated", "text_column": "Texte", "lr": 0.0002, "epochs": 15, "batch_size": 1, "warmup_ratio": 0.1, "gradient_accumulation": 4, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.01, "max_grad_norm": 1.0, "seed": 42, "add_eos_token": false, "block_size": 1024, "use_peft": true, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.05, "logging_steps": -1, "evaluation_strategy": "epoch", "save_total_limit": 1, "save_strategy": "epoch", "auto_find_batch_size": false, "fp16": true, "push_to_hub": true, "use_int8": false, "model_max_length": 1024, "repo_id": "pierreguillou/llama-2-7b-hf-text2image-prompts-Liege", "use_int4": true, "trainer": "default", "target_modules": null, "merge_adapter": true, "username": null}