Hugging Face's logo

yaleh
/
y3sa-4iz5-ind1-0

Text Generation
TensorBoard
Trained with AutoTrain
Model card Files Metrics Community
yaleh commited on
Commit
22f99ba
·
1 Parent(s): bbc6a9c

Upload folder using huggingface_hub

Browse files
Files changed (22) hide show
  1. README.md +9 -0
  2. adapter_config.json +21 -0
  3. adapter_model.bin +3 -0
  4. checkpoint-40/README.md +34 -0
  5. checkpoint-40/adapter_config.json +21 -0
  6. checkpoint-40/adapter_model.bin +3 -0
  7. checkpoint-40/optimizer.pt +3 -0
  8. checkpoint-40/rng_state.pth +3 -0
  9. checkpoint-40/scheduler.pt +3 -0
  10. checkpoint-40/special_tokens_map.json +24 -0
  11. checkpoint-40/tokenizer.json +0 -0
  12. checkpoint-40/tokenizer.model +3 -0
  13. checkpoint-40/tokenizer_config.json +36 -0
  14. checkpoint-40/trainer_state.json +259 -0
  15. checkpoint-40/training_args.bin +3 -0
  16. runs/Aug30_05-36-20_s-yaleh-autotrain-y3sa-4iz5-ind1-0-9b301-55f88cd78d-94pzz/events.out.tfevents.1693373780.s-yaleh-autotrain-y3sa-4iz5-ind1-0-9b301-55f88cd78d-94pzz.55.0 +3 -0
  17. special_tokens_map.json +24 -0
  18. tokenizer.json +0 -0
  19. tokenizer.model +3 -0
  20. tokenizer_config.json +36 -0
  21. training_args.bin +3 -0
  22. 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": "openlm-research/open_llama_3b_v2",
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": 0.1,
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 sha256:0a7e82439670e68a20ce2656718c2a84d4e14437d5d7710783bfa52a1f28612e
3
+ size 21336301
checkpoint-40/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-40/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "openlm-research/open_llama_3b_v2",
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": 0.1,
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-40/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a7e82439670e68a20ce2656718c2a84d4e14437d5d7710783bfa52a1f28612e
3
+ size 21336301
checkpoint-40/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5b5d64b311096d7d95ec9233180a73a0c68509e63e6e3084384a53e4b0def0b
3
+ size 42685509
checkpoint-40/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a57c37ed8ecdd73c9a2a1d669e9a6acd615e2baa99eb70f8e7d1baeca91c90dd
3
+ size 14575
checkpoint-40/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1756bafdbf18c4f23eac27d0316b270a0ae248d0fabd2cd45b1b1c89d9dc219f
3
+ size 627
checkpoint-40/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-40/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-40/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91b289e85fa20fd375d8b33dc12f77616f18abc6359804471d1fafcb425fecb8
3
+ size 511574
checkpoint-40/tokenizer_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": null,
22
+ "model_max_length": 2048,
23
+ "pad_token": null,
24
+ "sp_model_kwargs": {},
25
+ "spaces_between_special_tokens": false,
26
+ "tokenizer_class": "LlamaTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ },
35
+ "use_default_system_prompt": true
36
+ }
checkpoint-40/trainer_state.json ADDED
@@ -0,0 +1,259 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 40.0,
5
+ "eval_steps": 500,
6
+ "global_step": 40,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "learning_rate": 5e-05,
14
+ "loss": 1.5367,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 2.0,
19
+ "learning_rate": 0.0001,
20
+ "loss": 1.5367,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 3.0,
25
+ "learning_rate": 0.00015000000000000001,
26
+ "loss": 1.5171,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 4.0,
31
+ "learning_rate": 0.0002,
32
+ "loss": 1.4743,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 5.0,
37
+ "learning_rate": 0.00019444444444444446,
38
+ "loss": 1.4116,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 6.0,
43
+ "learning_rate": 0.00018888888888888888,
44
+ "loss": 1.3317,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 7.0,
49
+ "learning_rate": 0.00018333333333333334,
50
+ "loss": 1.271,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 8.0,
55
+ "learning_rate": 0.00017777777777777779,
56
+ "loss": 1.222,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 9.0,
61
+ "learning_rate": 0.00017222222222222224,
62
+ "loss": 1.1734,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 10.0,
67
+ "learning_rate": 0.0001666666666666667,
68
+ "loss": 1.1238,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 11.0,
73
+ "learning_rate": 0.0001611111111111111,
74
+ "loss": 1.0743,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 12.0,
79
+ "learning_rate": 0.00015555555555555556,
80
+ "loss": 1.0264,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 13.0,
85
+ "learning_rate": 0.00015000000000000001,
86
+ "loss": 0.9801,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 14.0,
91
+ "learning_rate": 0.00014444444444444444,
92
+ "loss": 0.9343,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 15.0,
97
+ "learning_rate": 0.0001388888888888889,
98
+ "loss": 0.8863,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 16.0,
103
+ "learning_rate": 0.00013333333333333334,
104
+ "loss": 0.8366,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 17.0,
109
+ "learning_rate": 0.00012777777777777776,
110
+ "loss": 0.787,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 18.0,
115
+ "learning_rate": 0.00012222222222222224,
116
+ "loss": 0.7379,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 19.0,
121
+ "learning_rate": 0.00011666666666666668,
122
+ "loss": 0.6888,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 20.0,
127
+ "learning_rate": 0.00011111111111111112,
128
+ "loss": 0.6419,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 21.0,
133
+ "learning_rate": 0.00010555555555555557,
134
+ "loss": 0.5932,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 22.0,
139
+ "learning_rate": 0.0001,
140
+ "loss": 0.5488,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 23.0,
145
+ "learning_rate": 9.444444444444444e-05,
146
+ "loss": 0.5075,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 24.0,
151
+ "learning_rate": 8.888888888888889e-05,
152
+ "loss": 0.4691,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 25.0,
157
+ "learning_rate": 8.333333333333334e-05,
158
+ "loss": 0.4302,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 26.0,
163
+ "learning_rate": 7.777777777777778e-05,
164
+ "loss": 0.3987,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 27.0,
169
+ "learning_rate": 7.222222222222222e-05,
170
+ "loss": 0.3661,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 28.0,
175
+ "learning_rate": 6.666666666666667e-05,
176
+ "loss": 0.3368,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 29.0,
181
+ "learning_rate": 6.111111111111112e-05,
182
+ "loss": 0.3117,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 30.0,
187
+ "learning_rate": 5.555555555555556e-05,
188
+ "loss": 0.2855,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 31.0,
193
+ "learning_rate": 5e-05,
194
+ "loss": 0.2632,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 32.0,
199
+ "learning_rate": 4.4444444444444447e-05,
200
+ "loss": 0.245,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 33.0,
205
+ "learning_rate": 3.888888888888889e-05,
206
+ "loss": 0.2289,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 34.0,
211
+ "learning_rate": 3.3333333333333335e-05,
212
+ "loss": 0.2144,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 35.0,
217
+ "learning_rate": 2.777777777777778e-05,
218
+ "loss": 0.2031,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 36.0,
223
+ "learning_rate": 2.2222222222222223e-05,
224
+ "loss": 0.1927,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 37.0,
229
+ "learning_rate": 1.6666666666666667e-05,
230
+ "loss": 0.1835,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 38.0,
235
+ "learning_rate": 1.1111111111111112e-05,
236
+ "loss": 0.1764,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 39.0,
241
+ "learning_rate": 5.555555555555556e-06,
242
+ "loss": 0.1709,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 40.0,
247
+ "learning_rate": 0.0,
248
+ "loss": 0.168,
249
+ "step": 40
250
+ }
251
+ ],
252
+ "logging_steps": 1,
253
+ "max_steps": 40,
254
+ "num_train_epochs": 40,
255
+ "save_steps": 500,
256
+ "total_flos": 844749078528000.0,
257
+ "trial_name": null,
258
+ "trial_params": null
259
+ }
checkpoint-40/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3359c886331ee351398867f308c9bbba9d3c0e7ca3fba26625026643aedbb67
3
+ size 4091
runs/Aug30_05-36-20_s-yaleh-autotrain-y3sa-4iz5-ind1-0-9b301-55f88cd78d-94pzz/events.out.tfevents.1693373780.s-yaleh-autotrain-y3sa-4iz5-ind1-0-9b301-55f88cd78d-94pzz.55.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba4011ca628c5f23b180837770c0bd712a4c3237fc46dd383cf2333977e73e5a
3
+ size 11002
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91b289e85fa20fd375d8b33dc12f77616f18abc6359804471d1fafcb425fecb8
3
+ size 511574
tokenizer_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": null,
22
+ "model_max_length": 2048,
23
+ "pad_token": null,
24
+ "sp_model_kwargs": {},
25
+ "spaces_between_special_tokens": false,
26
+ "tokenizer_class": "LlamaTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ },
35
+ "use_default_system_prompt": true
36
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3359c886331ee351398867f308c9bbba9d3c0e7ca3fba26625026643aedbb67
3
+ size 4091
training_params.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model": "openlm-research/open_llama_3b_v2", "data_path": "yaleh/autotrain-data-y3sa-4iz5-ind1", "project_name": "/tmp/model", "train_split": "train", "valid_split": null, "text_column": "autotrain_text", "lr": 0.0002, "epochs": 40, "batch_size": 8, "warmup_ratio": 0.1, "gradient_accumulation": 1, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.01, "max_grad_norm": 1.0, "seed": 42, "add_eos_token": true, "block_size": 1024, "use_peft": true, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.1, "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": 2048, "repo_id": "yaleh/y3sa-4iz5-ind1-0", "use_int4": true, "trainer": "sft", "target_modules": null, "merge_adapter": false, "username": "yaleh"}