Hugging Face's logo

guitarnoob
/
msaai520_test3

Text Generation
TensorBoard
Trained with AutoTrain
Model card Files Metrics Community
guitarnoob commited on
Commit
575f885
•
1 Parent(s): 6dd1e02

Upload folder using huggingface_hub

Browse files
Files changed (25) hide show
  1. README.md +9 -0
  2. adapter_config.json +23 -0
  3. adapter_model.bin +3 -0
  4. added_tokens.json +5 -0
  5. checkpoint-81/README.md +34 -0
  6. checkpoint-81/adapter_config.json +23 -0
  7. checkpoint-81/adapter_model.bin +3 -0
  8. checkpoint-81/added_tokens.json +5 -0
  9. checkpoint-81/optimizer.pt +3 -0
  10. checkpoint-81/pytorch_model.bin +3 -0
  11. checkpoint-81/rng_state.pth +3 -0
  12. checkpoint-81/scheduler.pt +3 -0
  13. checkpoint-81/special_tokens_map.json +6 -0
  14. checkpoint-81/tokenizer.json +0 -0
  15. checkpoint-81/tokenizer.model +3 -0
  16. checkpoint-81/tokenizer_config.json +40 -0
  17. checkpoint-81/trainer_state.json +505 -0
  18. checkpoint-81/training_args.bin +3 -0
  19. runs/Oct04_03-55-27_da1013185a39/events.out.tfevents.1696391727.da1013185a39.2747.0 +3 -0
  20. special_tokens_map.json +6 -0
  21. tokenizer.json +0 -0
  22. tokenizer.model +3 -0
  23. tokenizer_config.json +40 -0
  24. training_args.bin +3 -0
  25. 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 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "lora_alpha": 32,
12
+ "lora_dropout": 0.05,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 16,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "q_proj",
20
+ "v_proj"
21
+ ],
22
+ "task_type": "CAUSAL_LM"
23
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87edffd2e5b17515cd2b0fddb0a26413693b989273d8b1b420ac5a2a5efa7cab
3
+ size 33600461
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<s>": 1,
4
+ "<unk>": 0
5
+ }
checkpoint-81/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-81/adapter_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "lora_alpha": 32,
12
+ "lora_dropout": 0.05,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 16,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "q_proj",
20
+ "v_proj"
21
+ ],
22
+ "task_type": "CAUSAL_LM"
23
+ }
checkpoint-81/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87edffd2e5b17515cd2b0fddb0a26413693b989273d8b1b420ac5a2a5efa7cab
3
+ size 33600461
checkpoint-81/added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<s>": 1,
4
+ "<unk>": 0
5
+ }
checkpoint-81/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3303af0b9020fc26d31bc3445069b7379a76aed79c134a7db465a9322bc34822
3
+ size 67216581
checkpoint-81/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-81/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0c4972a176ddf072f8e776096153cd451867574f297dd45740670364c11fe15
3
+ size 14575
checkpoint-81/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69a00f67571b09f09c6fdef41b462b87e4439a18bfc17a527e25aee7ac876976
3
+ size 627
checkpoint-81/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-81/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-81/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-81/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": "</s>",
35
+ "padding_side": "right",
36
+ "sp_model_kwargs": {},
37
+ "tokenizer_class": "LlamaTokenizer",
38
+ "unk_token": "<unk>",
39
+ "use_default_system_prompt": true
40
+ }
checkpoint-81/trainer_state.json ADDED
@@ -0,0 +1,505 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 9.0,
5
+ "eval_steps": 500,
6
+ "global_step": 81,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.11,
13
+ "learning_rate": 2.2222222222222223e-05,
14
+ "loss": 0.977,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.22,
19
+ "learning_rate": 4.4444444444444447e-05,
20
+ "loss": 0.9399,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.33,
25
+ "learning_rate": 6.666666666666667e-05,
26
+ "loss": 0.9147,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.44,
31
+ "learning_rate": 8.888888888888889e-05,
32
+ "loss": 0.9426,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.56,
37
+ "learning_rate": 0.00011111111111111112,
38
+ "loss": 0.9001,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.67,
43
+ "learning_rate": 0.00013333333333333334,
44
+ "loss": 0.8425,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.78,
49
+ "learning_rate": 0.00015555555555555556,
50
+ "loss": 0.77,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.89,
55
+ "learning_rate": 0.00017777777777777779,
56
+ "loss": 0.7601,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 1.0,
61
+ "learning_rate": 0.0002,
62
+ "loss": 0.6534,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 1.11,
67
+ "learning_rate": 0.00019722222222222225,
68
+ "loss": 0.5944,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 1.22,
73
+ "learning_rate": 0.00019444444444444446,
74
+ "loss": 0.5356,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 1.33,
79
+ "learning_rate": 0.00019166666666666667,
80
+ "loss": 0.5692,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 1.44,
85
+ "learning_rate": 0.00018888888888888888,
86
+ "loss": 0.5362,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 1.56,
91
+ "learning_rate": 0.00018611111111111112,
92
+ "loss": 0.5117,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 1.67,
97
+ "learning_rate": 0.00018333333333333334,
98
+ "loss": 0.5097,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 1.78,
103
+ "learning_rate": 0.00018055555555555557,
104
+ "loss": 0.505,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 1.89,
109
+ "learning_rate": 0.00017777777777777779,
110
+ "loss": 0.4853,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 2.0,
115
+ "learning_rate": 0.000175,
116
+ "loss": 0.4904,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 2.11,
121
+ "learning_rate": 0.00017222222222222224,
122
+ "loss": 0.4615,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 2.22,
127
+ "learning_rate": 0.00016944444444444445,
128
+ "loss": 0.4441,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 2.33,
133
+ "learning_rate": 0.0001666666666666667,
134
+ "loss": 0.417,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 2.44,
139
+ "learning_rate": 0.0001638888888888889,
140
+ "loss": 0.4511,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 2.56,
145
+ "learning_rate": 0.0001611111111111111,
146
+ "loss": 0.4555,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 2.67,
151
+ "learning_rate": 0.00015833333333333332,
152
+ "loss": 0.4463,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 2.78,
157
+ "learning_rate": 0.00015555555555555556,
158
+ "loss": 0.4365,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 2.89,
163
+ "learning_rate": 0.00015277777777777777,
164
+ "loss": 0.4109,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 3.0,
169
+ "learning_rate": 0.00015000000000000001,
170
+ "loss": 0.4286,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 3.11,
175
+ "learning_rate": 0.00014722222222222223,
176
+ "loss": 0.4158,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 3.22,
181
+ "learning_rate": 0.00014444444444444444,
182
+ "loss": 0.3736,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 3.33,
187
+ "learning_rate": 0.00014166666666666668,
188
+ "loss": 0.4037,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 3.44,
193
+ "learning_rate": 0.0001388888888888889,
194
+ "loss": 0.3772,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 3.56,
199
+ "learning_rate": 0.00013611111111111113,
200
+ "loss": 0.3651,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 3.67,
205
+ "learning_rate": 0.00013333333333333334,
206
+ "loss": 0.3477,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 3.78,
211
+ "learning_rate": 0.00013055555555555555,
212
+ "loss": 0.2898,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 3.89,
217
+ "learning_rate": 0.00012777777777777776,
218
+ "loss": 0.1953,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 4.0,
223
+ "learning_rate": 0.000125,
224
+ "loss": 0.178,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 4.11,
229
+ "learning_rate": 0.00012222222222222224,
230
+ "loss": 0.2101,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 4.22,
235
+ "learning_rate": 0.00011944444444444445,
236
+ "loss": 0.2007,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 4.33,
241
+ "learning_rate": 0.00011666666666666668,
242
+ "loss": 0.1865,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 4.44,
247
+ "learning_rate": 0.00011388888888888889,
248
+ "loss": 0.1969,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 4.56,
253
+ "learning_rate": 0.00011111111111111112,
254
+ "loss": 0.1721,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 4.67,
259
+ "learning_rate": 0.00010833333333333333,
260
+ "loss": 0.1643,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 4.78,
265
+ "learning_rate": 0.00010555555555555557,
266
+ "loss": 0.1572,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 4.89,
271
+ "learning_rate": 0.00010277777777777778,
272
+ "loss": 0.1591,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 5.0,
277
+ "learning_rate": 0.0001,
278
+ "loss": 0.1492,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 5.11,
283
+ "learning_rate": 9.722222222222223e-05,
284
+ "loss": 0.1498,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 5.22,
289
+ "learning_rate": 9.444444444444444e-05,
290
+ "loss": 0.1616,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 5.33,
295
+ "learning_rate": 9.166666666666667e-05,
296
+ "loss": 0.1482,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 5.44,
301
+ "learning_rate": 8.888888888888889e-05,
302
+ "loss": 0.1597,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 5.56,
307
+ "learning_rate": 8.611111111111112e-05,
308
+ "loss": 0.1424,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 5.67,
313
+ "learning_rate": 8.333333333333334e-05,
314
+ "loss": 0.1559,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 5.78,
319
+ "learning_rate": 8.055555555555556e-05,
320
+ "loss": 0.1534,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 5.89,
325
+ "learning_rate": 7.777777777777778e-05,
326
+ "loss": 0.1435,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 6.0,
331
+ "learning_rate": 7.500000000000001e-05,
332
+ "loss": 0.1403,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 6.11,
337
+ "learning_rate": 7.222222222222222e-05,
338
+ "loss": 0.1218,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 6.22,
343
+ "learning_rate": 6.944444444444444e-05,
344
+ "loss": 0.1392,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 6.33,
349
+ "learning_rate": 6.666666666666667e-05,
350
+ "loss": 0.1482,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 6.44,
355
+ "learning_rate": 6.388888888888888e-05,
356
+ "loss": 0.1293,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 6.56,
361
+ "learning_rate": 6.111111111111112e-05,
362
+ "loss": 0.1356,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 6.67,
367
+ "learning_rate": 5.833333333333334e-05,
368
+ "loss": 0.163,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 6.78,
373
+ "learning_rate": 5.555555555555556e-05,
374
+ "loss": 0.1335,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 6.89,
379
+ "learning_rate": 5.2777777777777784e-05,
380
+ "loss": 0.1408,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 7.0,
385
+ "learning_rate": 5e-05,
386
+ "loss": 0.1422,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 7.11,
391
+ "learning_rate": 4.722222222222222e-05,
392
+ "loss": 0.1331,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 7.22,
397
+ "learning_rate": 4.4444444444444447e-05,
398
+ "loss": 0.1496,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 7.33,
403
+ "learning_rate": 4.166666666666667e-05,
404
+ "loss": 0.1397,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 7.44,
409
+ "learning_rate": 3.888888888888889e-05,
410
+ "loss": 0.1488,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 7.56,
415
+ "learning_rate": 3.611111111111111e-05,
416
+ "loss": 0.1112,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 7.67,
421
+ "learning_rate": 3.3333333333333335e-05,
422
+ "loss": 0.1117,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 7.78,
427
+ "learning_rate": 3.055555555555556e-05,
428
+ "loss": 0.1299,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 7.89,
433
+ "learning_rate": 2.777777777777778e-05,
434
+ "loss": 0.1347,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 8.0,
439
+ "learning_rate": 2.5e-05,
440
+ "loss": 0.1364,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 8.11,
445
+ "learning_rate": 2.2222222222222223e-05,
446
+ "loss": 0.1064,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 8.22,
451
+ "learning_rate": 1.9444444444444445e-05,
452
+ "loss": 0.1367,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 8.33,
457
+ "learning_rate": 1.6666666666666667e-05,
458
+ "loss": 0.1491,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 8.44,
463
+ "learning_rate": 1.388888888888889e-05,
464
+ "loss": 0.1234,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 8.56,
469
+ "learning_rate": 1.1111111111111112e-05,
470
+ "loss": 0.1157,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 8.67,
475
+ "learning_rate": 8.333333333333334e-06,
476
+ "loss": 0.124,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 8.78,
481
+ "learning_rate": 5.555555555555556e-06,
482
+ "loss": 0.1321,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 8.89,
487
+ "learning_rate": 2.777777777777778e-06,
488
+ "loss": 0.1337,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 9.0,
493
+ "learning_rate": 0.0,
494
+ "loss": 0.1398,
495
+ "step": 81
496
+ }
497
+ ],
498
+ "logging_steps": 1,
499
+ "max_steps": 81,
500
+ "num_train_epochs": 9,
501
+ "save_steps": 500,
502
+ "total_flos": 1.3169647046098944e+16,
503
+ "trial_name": null,
504
+ "trial_params": null
505
+ }
checkpoint-81/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dceb6a5b0d0c0de96202af59cf74ea707be32e33b6488438bd492688c0c82eba
3
+ size 4091
runs/Oct04_03-55-27_da1013185a39/events.out.tfevents.1696391727.da1013185a39.2747.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e495a2e144df256c775398a4ab099feb4f07dde0fa570d6de9ce51cc7c6ff569
3
+ size 17360
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
+ }
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": 1024,
34
+ "pad_token": "</s>",
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:dceb6a5b0d0c0de96202af59cf74ea707be32e33b6488438bd492688c0c82eba
3
+ size 4091
training_params.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model": "meta-llama/Llama-2-7b-chat-hf", "data_path": "data/", "project_name": "my_autotrain_llm", "train_split": "train", "valid_split": null, "text_column": "text", "lr": 0.0002, "epochs": 9, "batch_size": 4, "warmup_ratio": 0.1, "gradient_accumulation": 1, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.0, "max_grad_norm": 1.0, "seed": 42, "add_eos_token": false, "block_size": 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": false, "push_to_hub": true, "use_int8": false, "model_max_length": 1024, "repo_id": "guitarnoob/msaai520_test3", "use_int4": true, "trainer": "default", "target_modules": null, "merge_adapter": false, "username": null, "use_flash_attention_2": false}