Hugging Face's logo

avnishkr
/
falcon_squad-instruct400

PEFT
Model card Files Community
1
avnishkr commited on
Commit
8d7b39d
•
1 Parent(s): 11ed7a8

Upload 8 files

Browse files
Files changed (8) hide show
  1. README.md +20 -0
  2. adapter_config.json +20 -0
  3. adapter_model.bin +3 -0
  4. optimizer.pt +3 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. trainer_state.json +256 -0
  8. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: False
16
+ - bnb_4bit_compute_dtype: bfloat16
17
+ ### Framework versions
18
+
19
+
20
+ - PEFT 0.4.0.dev0
adapter_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "tiiuae/falcon-7b-instruct",
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
+ "query_key_value"
18
+ ],
19
+ "task_type": "CAUSAL_LM"
20
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1fd91c242af9fb1e274346e6f153a2de742e5508d9c5e86490b96a2d0a095d6
3
+ size 18898161
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:278210f6bfa5b81b928d546df78f4dd8c68b6d88446773131425d9586259b1bb
3
+ size 9539077
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1e0be369925100e62bdb4b94818b5ff9349f81e7dcbed994dd2d86dfd036d74
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fac9cb0fcfeecc4f8c65e7ba8912528fa219f69eff8b863dae81ca2e50d1a9fe
3
+ size 627
trainer_state.json ADDED
@@ -0,0 +1,256 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.0365296803652968,
5
+ "global_step": 400,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 5e-05,
13
+ "loss": 2.6714,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.0,
18
+ "learning_rate": 0.0001,
19
+ "loss": 2.5361,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.0,
24
+ "learning_rate": 0.00015000000000000001,
25
+ "loss": 2.3465,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.0,
30
+ "learning_rate": 0.0002,
31
+ "loss": 2.0844,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.0,
36
+ "learning_rate": 0.0001999145758387301,
37
+ "loss": 2.0421,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.01,
42
+ "learning_rate": 0.000199658449300667,
43
+ "loss": 1.9894,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.01,
48
+ "learning_rate": 0.0001992320579737045,
49
+ "loss": 1.9617,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.01,
54
+ "learning_rate": 0.00019863613034027224,
55
+ "loss": 2.0536,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.01,
60
+ "learning_rate": 0.00019787168453273544,
61
+ "loss": 1.9324,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.01,
66
+ "learning_rate": 0.00019694002659393305,
67
+ "loss": 1.985,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.01,
72
+ "learning_rate": 0.0001958427482458253,
73
+ "loss": 1.9952,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 0.01,
78
+ "learning_rate": 0.00019458172417006347,
79
+ "loss": 2.007,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 0.01,
84
+ "learning_rate": 0.0001931591088051279,
85
+ "loss": 1.983,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 0.01,
90
+ "learning_rate": 0.00019157733266550575,
91
+ "loss": 1.9472,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 0.01,
96
+ "learning_rate": 0.0001898390981891979,
97
+ "loss": 2.0466,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 0.01,
102
+ "learning_rate": 0.0001879473751206489,
103
+ "loss": 2.008,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 0.02,
108
+ "learning_rate": 0.00018590539543698854,
109
+ "loss": 2.0157,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 0.02,
114
+ "learning_rate": 0.00018371664782625287,
115
+ "loss": 1.9199,
116
+ "step": 180
117
+ },
118
+ {
119
+ "epoch": 0.02,
120
+ "learning_rate": 0.0001813848717270195,
121
+ "loss": 2.04,
122
+ "step": 190
123
+ },
124
+ {
125
+ "epoch": 0.02,
126
+ "learning_rate": 0.00017891405093963938,
127
+ "loss": 1.9081,
128
+ "step": 200
129
+ },
130
+ {
131
+ "epoch": 0.02,
132
+ "learning_rate": 0.00017630840681998066,
133
+ "loss": 1.9743,
134
+ "step": 210
135
+ },
136
+ {
137
+ "epoch": 0.02,
138
+ "learning_rate": 0.00017357239106731317,
139
+ "loss": 1.9165,
140
+ "step": 220
141
+ },
142
+ {
143
+ "epoch": 0.02,
144
+ "learning_rate": 0.00017071067811865476,
145
+ "loss": 1.9622,
146
+ "step": 230
147
+ },
148
+ {
149
+ "epoch": 0.02,
150
+ "learning_rate": 0.00016772815716257412,
151
+ "loss": 1.9589,
152
+ "step": 240
153
+ },
154
+ {
155
+ "epoch": 0.02,
156
+ "learning_rate": 0.00016462992378609407,
157
+ "loss": 1.9725,
158
+ "step": 250
159
+ },
160
+ {
161
+ "epoch": 0.02,
162
+ "learning_rate": 0.0001614212712689668,
163
+ "loss": 1.9992,
164
+ "step": 260
165
+ },
166
+ {
167
+ "epoch": 0.02,
168
+ "learning_rate": 0.00015810768154019385,
169
+ "loss": 1.9791,
170
+ "step": 270
171
+ },
172
+ {
173
+ "epoch": 0.03,
174
+ "learning_rate": 0.00015469481581224272,
175
+ "loss": 1.9638,
176
+ "step": 280
177
+ },
178
+ {
179
+ "epoch": 0.03,
180
+ "learning_rate": 0.00015118850490896012,
181
+ "loss": 1.9842,
182
+ "step": 290
183
+ },
184
+ {
185
+ "epoch": 0.03,
186
+ "learning_rate": 0.00014759473930370736,
187
+ "loss": 1.9316,
188
+ "step": 300
189
+ },
190
+ {
191
+ "epoch": 0.03,
192
+ "learning_rate": 0.00014391965888473703,
193
+ "loss": 1.9995,
194
+ "step": 310
195
+ },
196
+ {
197
+ "epoch": 0.03,
198
+ "learning_rate": 0.00014016954246529696,
199
+ "loss": 1.9569,
200
+ "step": 320
201
+ },
202
+ {
203
+ "epoch": 0.03,
204
+ "learning_rate": 0.00013635079705638298,
205
+ "loss": 1.9623,
206
+ "step": 330
207
+ },
208
+ {
209
+ "epoch": 0.03,
210
+ "learning_rate": 0.00013246994692046836,
211
+ "loss": 1.9055,
212
+ "step": 340
213
+ },
214
+ {
215
+ "epoch": 0.03,
216
+ "learning_rate": 0.00012853362242491053,
217
+ "loss": 1.9084,
218
+ "step": 350
219
+ },
220
+ {
221
+ "epoch": 0.03,
222
+ "learning_rate": 0.00012454854871407994,
223
+ "loss": 2.0149,
224
+ "step": 360
225
+ },
226
+ {
227
+ "epoch": 0.03,
228
+ "learning_rate": 0.00012052153421956342,
229
+ "loss": 1.953,
230
+ "step": 370
231
+ },
232
+ {
233
+ "epoch": 0.03,
234
+ "learning_rate": 0.00011645945902807341,
235
+ "loss": 2.0303,
236
+ "step": 380
237
+ },
238
+ {
239
+ "epoch": 0.04,
240
+ "learning_rate": 0.00011236926312693479,
241
+ "loss": 1.9762,
242
+ "step": 390
243
+ },
244
+ {
245
+ "epoch": 0.04,
246
+ "learning_rate": 0.00010825793454723325,
247
+ "loss": 1.9585,
248
+ "step": 400
249
+ }
250
+ ],
251
+ "max_steps": 800,
252
+ "num_train_epochs": 1,
253
+ "total_flos": 1.637251048912128e+16,
254
+ "trial_name": null,
255
+ "trial_params": null
256
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29a0041f910705435df6304e464b15b3c1cac502f89afa175fd7e97d148b1dbe
3
+ size 3963