dylanalloy
commited on
Commit
β’
41e6eee
1
Parent(s):
293acd9
π feat(release): Hello world
Browse files- README.md +18 -1
- adapter_config.json +19 -0
- adapter_model.bin +3 -0
- checkpoint-500/README.md +20 -0
- checkpoint-500/adapter_config.json +19 -0
- checkpoint-500/adapter_model.bin +3 -0
- checkpoint-500/optimizer.pt +3 -0
- checkpoint-500/rng_state.pth +3 -0
- checkpoint-500/scheduler.pt +3 -0
- checkpoint-500/trainer_state.json +244 -0
- checkpoint-500/training_args.bin +3 -0
README.md
CHANGED
@@ -1,3 +1,20 @@
|
|
1 |
---
|
2 |
-
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: fp4
|
15 |
+
- bnb_4bit_use_double_quant: True
|
16 |
+
- bnb_4bit_compute_dtype: bfloat16
|
17 |
+
### Framework versions
|
18 |
+
|
19 |
+
|
20 |
+
- PEFT 0.4.0.dev0
|
adapter_config.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"base_model_name_or_path": "tiiuae/falcon-7b-instruct",
|
3 |
+
"bias": "none",
|
4 |
+
"fan_in_fan_out": false,
|
5 |
+
"inference_mode": true,
|
6 |
+
"init_lora_weights": true,
|
7 |
+
"layers_pattern": null,
|
8 |
+
"layers_to_transform": null,
|
9 |
+
"lora_alpha": 32,
|
10 |
+
"lora_dropout": 0.05,
|
11 |
+
"modules_to_save": null,
|
12 |
+
"peft_type": "LORA",
|
13 |
+
"r": 16,
|
14 |
+
"revision": null,
|
15 |
+
"target_modules": [
|
16 |
+
"query_key_value"
|
17 |
+
],
|
18 |
+
"task_type": "CAUSAL_LM"
|
19 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fa73f6c6d3936e14b9dfdf7574dae16f82c699a1a0581c33792c7cd40d0d15f
|
3 |
+
size 18898161
|
checkpoint-500/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: fp4
|
15 |
+
- bnb_4bit_use_double_quant: True
|
16 |
+
- bnb_4bit_compute_dtype: bfloat16
|
17 |
+
### Framework versions
|
18 |
+
|
19 |
+
|
20 |
+
- PEFT 0.4.0.dev0
|
checkpoint-500/adapter_config.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"base_model_name_or_path": "tiiuae/falcon-7b-instruct",
|
3 |
+
"bias": "none",
|
4 |
+
"fan_in_fan_out": false,
|
5 |
+
"inference_mode": true,
|
6 |
+
"init_lora_weights": true,
|
7 |
+
"layers_pattern": null,
|
8 |
+
"layers_to_transform": null,
|
9 |
+
"lora_alpha": 32,
|
10 |
+
"lora_dropout": 0.05,
|
11 |
+
"modules_to_save": null,
|
12 |
+
"peft_type": "LORA",
|
13 |
+
"r": 16,
|
14 |
+
"revision": null,
|
15 |
+
"target_modules": [
|
16 |
+
"query_key_value"
|
17 |
+
],
|
18 |
+
"task_type": "CAUSAL_LM"
|
19 |
+
}
|
checkpoint-500/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fa73f6c6d3936e14b9dfdf7574dae16f82c699a1a0581c33792c7cd40d0d15f
|
3 |
+
size 18898161
|
checkpoint-500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ccaf89a755b52a197f0ce95e9cc0f85c6f643065c853a69a711e019650ea993
|
3 |
+
size 9531525
|
checkpoint-500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59fa958ce52ae4e7b1e29857cca68f3f14460b083219e339621647090a50c081
|
3 |
+
size 14575
|
checkpoint-500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:becc6ce1d910c1484b60d785c856d3d18b0420d3e43c97ef16af3312337b9491
|
3 |
+
size 627
|
checkpoint-500/trainer_state.json
ADDED
@@ -0,0 +1,244 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.159821000479463,
|
5 |
+
"global_step": 500,
|
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": 0.00010400000000000001,
|
13 |
+
"loss": 1.4239,
|
14 |
+
"step": 13
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.01,
|
18 |
+
"learning_rate": 0.0001999978128380225,
|
19 |
+
"loss": 1.3151,
|
20 |
+
"step": 26
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.01,
|
24 |
+
"learning_rate": 0.0001995716208873644,
|
25 |
+
"loss": 1.0994,
|
26 |
+
"step": 39
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.02,
|
30 |
+
"learning_rate": 0.0001984097857063434,
|
31 |
+
"loss": 1.0521,
|
32 |
+
"step": 52
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.02,
|
36 |
+
"learning_rate": 0.00019652089102773488,
|
37 |
+
"loss": 0.9963,
|
38 |
+
"step": 65
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.02,
|
42 |
+
"learning_rate": 0.00019391889215899299,
|
43 |
+
"loss": 1.0038,
|
44 |
+
"step": 78
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.03,
|
48 |
+
"learning_rate": 0.00019062301287930446,
|
49 |
+
"loss": 0.9647,
|
50 |
+
"step": 91
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.03,
|
54 |
+
"learning_rate": 0.00018665760341274505,
|
55 |
+
"loss": 1.0262,
|
56 |
+
"step": 104
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.04,
|
60 |
+
"learning_rate": 0.00018205196052684445,
|
61 |
+
"loss": 0.9811,
|
62 |
+
"step": 117
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.04,
|
66 |
+
"learning_rate": 0.00017684011108568592,
|
67 |
+
"loss": 0.9759,
|
68 |
+
"step": 130
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.05,
|
72 |
+
"learning_rate": 0.00017106056065666793,
|
73 |
+
"loss": 1.0042,
|
74 |
+
"step": 143
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.05,
|
78 |
+
"learning_rate": 0.0001647560090282419,
|
79 |
+
"loss": 0.9669,
|
80 |
+
"step": 156
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.05,
|
84 |
+
"learning_rate": 0.00015797303474040332,
|
85 |
+
"loss": 0.9218,
|
86 |
+
"step": 169
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.06,
|
90 |
+
"learning_rate": 0.0001507617509586517,
|
91 |
+
"loss": 0.939,
|
92 |
+
"step": 182
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.06,
|
96 |
+
"learning_rate": 0.00014317543523384928,
|
97 |
+
"loss": 0.8893,
|
98 |
+
"step": 195
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.07,
|
102 |
+
"learning_rate": 0.00013527013588334415,
|
103 |
+
"loss": 0.9348,
|
104 |
+
"step": 208
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.07,
|
108 |
+
"learning_rate": 0.00012710425790144446,
|
109 |
+
"loss": 0.9399,
|
110 |
+
"step": 221
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.07,
|
114 |
+
"learning_rate": 0.00011873813145857249,
|
115 |
+
"loss": 0.8956,
|
116 |
+
"step": 234
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.08,
|
120 |
+
"learning_rate": 0.00011023356617706052,
|
121 |
+
"loss": 0.8905,
|
122 |
+
"step": 247
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.08,
|
126 |
+
"learning_rate": 0.00010165339447663587,
|
127 |
+
"loss": 0.8825,
|
128 |
+
"step": 260
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.09,
|
132 |
+
"learning_rate": 9.30610073633956e-05,
|
133 |
+
"loss": 0.8853,
|
134 |
+
"step": 273
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.09,
|
138 |
+
"learning_rate": 8.451988609189987e-05,
|
139 |
+
"loss": 0.9191,
|
140 |
+
"step": 286
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.1,
|
144 |
+
"learning_rate": 7.6093133160502e-05,
|
145 |
+
"loss": 0.8472,
|
146 |
+
"step": 299
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.1,
|
150 |
+
"learning_rate": 6.784300610496048e-05,
|
151 |
+
"loss": 0.9249,
|
152 |
+
"step": 312
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.1,
|
156 |
+
"learning_rate": 5.983045753470308e-05,
|
157 |
+
"loss": 0.8763,
|
158 |
+
"step": 325
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.11,
|
162 |
+
"learning_rate": 5.2114684809993044e-05,
|
163 |
+
"loss": 0.824,
|
164 |
+
"step": 338
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.11,
|
168 |
+
"learning_rate": 4.475269268701868e-05,
|
169 |
+
"loss": 0.8627,
|
170 |
+
"step": 351
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.12,
|
174 |
+
"learning_rate": 3.779887216211995e-05,
|
175 |
+
"loss": 0.8474,
|
176 |
+
"step": 364
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.12,
|
180 |
+
"learning_rate": 3.1304598626685545e-05,
|
181 |
+
"loss": 0.8444,
|
182 |
+
"step": 377
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.12,
|
186 |
+
"learning_rate": 2.5317852301584643e-05,
|
187 |
+
"loss": 0.837,
|
188 |
+
"step": 390
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.13,
|
192 |
+
"learning_rate": 1.988286375539391e-05,
|
193 |
+
"loss": 0.8613,
|
194 |
+
"step": 403
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.13,
|
198 |
+
"learning_rate": 1.5039787125361326e-05,
|
199 |
+
"loss": 0.8878,
|
200 |
+
"step": 416
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.14,
|
204 |
+
"learning_rate": 1.0824403455375288e-05,
|
205 |
+
"loss": 0.8382,
|
206 |
+
"step": 429
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.14,
|
210 |
+
"learning_rate": 7.267856342703461e-06,
|
211 |
+
"loss": 0.8802,
|
212 |
+
"step": 442
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.15,
|
216 |
+
"learning_rate": 4.3964218465642355e-06,
|
217 |
+
"loss": 0.9216,
|
218 |
+
"step": 455
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.15,
|
222 |
+
"learning_rate": 2.2313143584648423e-06,
|
223 |
+
"loss": 0.8493,
|
224 |
+
"step": 468
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.15,
|
228 |
+
"learning_rate": 7.885298685522235e-07,
|
229 |
+
"loss": 0.8862,
|
230 |
+
"step": 481
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.16,
|
234 |
+
"learning_rate": 7.872778593728258e-08,
|
235 |
+
"loss": 0.8264,
|
236 |
+
"step": 494
|
237 |
+
}
|
238 |
+
],
|
239 |
+
"max_steps": 500,
|
240 |
+
"num_train_epochs": 1,
|
241 |
+
"total_flos": 1.7103152756921088e+16,
|
242 |
+
"trial_name": null,
|
243 |
+
"trial_params": null
|
244 |
+
}
|
checkpoint-500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff88cef62c2c9d935c8c3c2644757f5be7d86948b9f853567b444fbef831d076
|
3 |
+
size 3963
|