Hugging Face's logo

sqllama
/
lora-spider-dono

Model card Files Community
chrisdono commited on
Commit
348e85d
•
1 Parent(s): bf1eccc

initial model

Browse files
Files changed (18) hide show
  1. adapter_config.json +18 -0
  2. adapter_model.bin +3 -0
  3. checkpoint-200/optimizer.pt +3 -0
  4. checkpoint-200/pytorch_model.bin +3 -0
  5. checkpoint-200/rng_state_0.pth +3 -0
  6. checkpoint-200/rng_state_1.pth +3 -0
  7. checkpoint-200/scaler.pt +3 -0
  8. checkpoint-200/scheduler.pt +3 -0
  9. checkpoint-200/trainer_state.json +144 -0
  10. checkpoint-200/training_args.bin +3 -0
  11. checkpoint-400/optimizer.pt +3 -0
  12. checkpoint-400/pytorch_model.bin +3 -0
  13. checkpoint-400/rng_state_0.pth +3 -0
  14. checkpoint-400/rng_state_1.pth +3 -0
  15. checkpoint-400/scaler.pt +3 -0
  16. checkpoint-400/scheduler.pt +3 -0
  17. checkpoint-400/trainer_state.json +272 -0
  18. checkpoint-400/training_args.bin +3 -0
adapter_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "decapoda-research/llama-7b-hf",
3
+ "bias": "none",
4
+ "enable_lora": null,
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "lora_alpha": 16,
8
+ "lora_dropout": 0.05,
9
+ "merge_weights": false,
10
+ "modules_to_save": null,
11
+ "peft_type": "LORA",
12
+ "r": 8,
13
+ "target_modules": [
14
+ "q_proj",
15
+ "v_proj"
16
+ ],
17
+ "task_type": "CAUSAL_LM"
18
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60959df5e5356a74ea5128c243f0decc94974f3aee82289932321a252e9059ec
3
+ size 16822989
checkpoint-200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0391d2903a4c4d7c68776aeca89a90231fed563b984ec6504d8c16cc99250735
3
+ size 33661637
checkpoint-200/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edfa7e365576335abc0ee684c76be0490729120708254b07c4900129adc1eecf
3
+ size 16822989
checkpoint-200/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22272e3838963bad9b0a3193dce5b231ec52af46288ed966f9c19fee3d2ae2ad
3
+ size 14583
checkpoint-200/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a84efcd3c2c174f123d98c04e7f9972f182f515c9aeafef4e77248e60e90d277
3
+ size 14583
checkpoint-200/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:583ecc2f44cc28ade6a818085a67c9dd43aab7204e28dc890d90673c0012999d
3
+ size 557
checkpoint-200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fc76cbc476d6c5b799c66d42a42c1dc58371e2d426a17f7f86b68d90c540296
3
+ size 627
checkpoint-200/trainer_state.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.40256267786026,
3
+ "best_model_checkpoint": "./lora-alpaca/checkpoint-200",
4
+ "epoch": 1.2738853503184713,
5
+ "global_step": 200,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.06,
12
+ "learning_rate": 9e-06,
13
+ "loss": 1.6528,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.13,
18
+ "learning_rate": 1.9e-05,
19
+ "loss": 1.6025,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.19,
24
+ "learning_rate": 2.9e-05,
25
+ "loss": 1.561,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.25,
30
+ "learning_rate": 3.9000000000000006e-05,
31
+ "loss": 1.4915,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.32,
36
+ "learning_rate": 4.9e-05,
37
+ "loss": 1.3214,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.38,
42
+ "learning_rate": 5.8e-05,
43
+ "loss": 1.0774,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.45,
48
+ "learning_rate": 6.800000000000001e-05,
49
+ "loss": 0.779,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.51,
54
+ "learning_rate": 7.7e-05,
55
+ "loss": 0.6797,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.57,
60
+ "learning_rate": 8.7e-05,
61
+ "loss": 0.6521,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.64,
66
+ "learning_rate": 9.7e-05,
67
+ "loss": 0.6304,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.7,
72
+ "learning_rate": 9.811320754716981e-05,
73
+ "loss": 0.6108,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 0.76,
78
+ "learning_rate": 9.54177897574124e-05,
79
+ "loss": 0.5722,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 0.83,
84
+ "learning_rate": 9.272237196765498e-05,
85
+ "loss": 0.5561,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 0.89,
90
+ "learning_rate": 9.002695417789758e-05,
91
+ "loss": 0.5548,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 0.96,
96
+ "learning_rate": 8.733153638814017e-05,
97
+ "loss": 0.524,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 1.02,
102
+ "learning_rate": 8.463611859838275e-05,
103
+ "loss": 0.4927,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 1.08,
108
+ "learning_rate": 8.194070080862534e-05,
109
+ "loss": 0.4659,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 1.15,
114
+ "learning_rate": 7.924528301886794e-05,
115
+ "loss": 0.4499,
116
+ "step": 180
117
+ },
118
+ {
119
+ "epoch": 1.21,
120
+ "learning_rate": 7.654986522911051e-05,
121
+ "loss": 0.4195,
122
+ "step": 190
123
+ },
124
+ {
125
+ "epoch": 1.27,
126
+ "learning_rate": 7.385444743935311e-05,
127
+ "loss": 0.3974,
128
+ "step": 200
129
+ },
130
+ {
131
+ "epoch": 1.27,
132
+ "eval_loss": 0.40256267786026,
133
+ "eval_runtime": 181.1381,
134
+ "eval_samples_per_second": 11.041,
135
+ "eval_steps_per_second": 0.69,
136
+ "step": 200
137
+ }
138
+ ],
139
+ "max_steps": 471,
140
+ "num_train_epochs": 3,
141
+ "total_flos": 6.475033720179917e+16,
142
+ "trial_name": null,
143
+ "trial_params": null
144
+ }
checkpoint-200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20f73ff8f89707f8685548bde5cd81546e84cf93095d7a2c4bdd8fdb070cfdfa
3
+ size 3579
checkpoint-400/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:935d38019538df04b835b5381d186a20df9ec9509675eb663563652ddb62659b
3
+ size 33661637
checkpoint-400/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b5a5c36dec73457d04fbef821fd500848db5da6045f62a9b222f490e3814773
3
+ size 16822989
checkpoint-400/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:486f3502738016febd9f8a728671e9dfe89c40c49a2a485ca9e88fa9ae0b4809
3
+ size 14583
checkpoint-400/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e469f97b21f27007e1fc28a86d1afc87a0ced21bf080ee58ea0984fcc192604d
3
+ size 14583
checkpoint-400/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90fe8879a9d3412079fe26e571484ae924fb4da4e293ed5217bc8de0554b353d
3
+ size 557
checkpoint-400/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ce4692b05a49f09bf743b35e9f44b99d4b8eea5e4cbdac8463f5f73a6a0270d
3
+ size 627
checkpoint-400/trainer_state.json ADDED
@@ -0,0 +1,272 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.22180575132369995,
3
+ "best_model_checkpoint": "./lora-alpaca/checkpoint-400",
4
+ "epoch": 2.5477707006369426,
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": 0.06,
12
+ "learning_rate": 9e-06,
13
+ "loss": 1.6528,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.13,
18
+ "learning_rate": 1.9e-05,
19
+ "loss": 1.6025,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.19,
24
+ "learning_rate": 2.9e-05,
25
+ "loss": 1.561,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.25,
30
+ "learning_rate": 3.9000000000000006e-05,
31
+ "loss": 1.4915,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.32,
36
+ "learning_rate": 4.9e-05,
37
+ "loss": 1.3214,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.38,
42
+ "learning_rate": 5.8e-05,
43
+ "loss": 1.0774,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.45,
48
+ "learning_rate": 6.800000000000001e-05,
49
+ "loss": 0.779,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.51,
54
+ "learning_rate": 7.7e-05,
55
+ "loss": 0.6797,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.57,
60
+ "learning_rate": 8.7e-05,
61
+ "loss": 0.6521,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.64,
66
+ "learning_rate": 9.7e-05,
67
+ "loss": 0.6304,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.7,
72
+ "learning_rate": 9.811320754716981e-05,
73
+ "loss": 0.6108,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 0.76,
78
+ "learning_rate": 9.54177897574124e-05,
79
+ "loss": 0.5722,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 0.83,
84
+ "learning_rate": 9.272237196765498e-05,
85
+ "loss": 0.5561,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 0.89,
90
+ "learning_rate": 9.002695417789758e-05,
91
+ "loss": 0.5548,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 0.96,
96
+ "learning_rate": 8.733153638814017e-05,
97
+ "loss": 0.524,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 1.02,
102
+ "learning_rate": 8.463611859838275e-05,
103
+ "loss": 0.4927,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 1.08,
108
+ "learning_rate": 8.194070080862534e-05,
109
+ "loss": 0.4659,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 1.15,
114
+ "learning_rate": 7.924528301886794e-05,
115
+ "loss": 0.4499,
116
+ "step": 180
117
+ },
118
+ {
119
+ "epoch": 1.21,
120
+ "learning_rate": 7.654986522911051e-05,
121
+ "loss": 0.4195,
122
+ "step": 190
123
+ },
124
+ {
125
+ "epoch": 1.27,
126
+ "learning_rate": 7.385444743935311e-05,
127
+ "loss": 0.3974,
128
+ "step": 200
129
+ },
130
+ {
131
+ "epoch": 1.27,
132
+ "eval_loss": 0.40256267786026,
133
+ "eval_runtime": 181.1381,
134
+ "eval_samples_per_second": 11.041,
135
+ "eval_steps_per_second": 0.69,
136
+ "step": 200
137
+ },
138
+ {
139
+ "epoch": 1.34,
140
+ "learning_rate": 7.115902964959569e-05,
141
+ "loss": 0.4,
142
+ "step": 210
143
+ },
144
+ {
145
+ "epoch": 1.4,
146
+ "learning_rate": 6.846361185983828e-05,
147
+ "loss": 0.3646,
148
+ "step": 220
149
+ },
150
+ {
151
+ "epoch": 1.46,
152
+ "learning_rate": 6.576819407008087e-05,
153
+ "loss": 0.3631,
154
+ "step": 230
155
+ },
156
+ {
157
+ "epoch": 1.53,
158
+ "learning_rate": 6.307277628032345e-05,
159
+ "loss": 0.3311,
160
+ "step": 240
161
+ },
162
+ {
163
+ "epoch": 1.59,
164
+ "learning_rate": 6.037735849056604e-05,
165
+ "loss": 0.314,
166
+ "step": 250
167
+ },
168
+ {
169
+ "epoch": 1.66,
170
+ "learning_rate": 5.768194070080862e-05,
171
+ "loss": 0.2988,
172
+ "step": 260
173
+ },
174
+ {
175
+ "epoch": 1.72,
176
+ "learning_rate": 5.4986522911051216e-05,
177
+ "loss": 0.3057,
178
+ "step": 270
179
+ },
180
+ {
181
+ "epoch": 1.78,
182
+ "learning_rate": 5.22911051212938e-05,
183
+ "loss": 0.2644,
184
+ "step": 280
185
+ },
186
+ {
187
+ "epoch": 1.85,
188
+ "learning_rate": 4.959568733153639e-05,
189
+ "loss": 0.2682,
190
+ "step": 290
191
+ },
192
+ {
193
+ "epoch": 1.91,
194
+ "learning_rate": 4.690026954177898e-05,
195
+ "loss": 0.2529,
196
+ "step": 300
197
+ },
198
+ {
199
+ "epoch": 1.97,
200
+ "learning_rate": 4.420485175202157e-05,
201
+ "loss": 0.2477,
202
+ "step": 310
203
+ },
204
+ {
205
+ "epoch": 2.04,
206
+ "learning_rate": 4.150943396226415e-05,
207
+ "loss": 0.2584,
208
+ "step": 320
209
+ },
210
+ {
211
+ "epoch": 2.1,
212
+ "learning_rate": 3.881401617250674e-05,
213
+ "loss": 0.2394,
214
+ "step": 330
215
+ },
216
+ {
217
+ "epoch": 2.17,
218
+ "learning_rate": 3.611859838274933e-05,
219
+ "loss": 0.2355,
220
+ "step": 340
221
+ },
222
+ {
223
+ "epoch": 2.23,
224
+ "learning_rate": 3.342318059299192e-05,
225
+ "loss": 0.2405,
226
+ "step": 350
227
+ },
228
+ {
229
+ "epoch": 2.29,
230
+ "learning_rate": 3.0727762803234503e-05,
231
+ "loss": 0.2166,
232
+ "step": 360
233
+ },
234
+ {
235
+ "epoch": 2.36,
236
+ "learning_rate": 2.803234501347709e-05,
237
+ "loss": 0.2176,
238
+ "step": 370
239
+ },
240
+ {
241
+ "epoch": 2.42,
242
+ "learning_rate": 2.5336927223719675e-05,
243
+ "loss": 0.2213,
244
+ "step": 380
245
+ },
246
+ {
247
+ "epoch": 2.48,
248
+ "learning_rate": 2.2641509433962265e-05,
249
+ "loss": 0.2197,
250
+ "step": 390
251
+ },
252
+ {
253
+ "epoch": 2.55,
254
+ "learning_rate": 1.9946091644204854e-05,
255
+ "loss": 0.2089,
256
+ "step": 400
257
+ },
258
+ {
259
+ "epoch": 2.55,
260
+ "eval_loss": 0.22180575132369995,
261
+ "eval_runtime": 180.8986,
262
+ "eval_samples_per_second": 11.056,
263
+ "eval_steps_per_second": 0.691,
264
+ "step": 400
265
+ }
266
+ ],
267
+ "max_steps": 471,
268
+ "num_train_epochs": 3,
269
+ "total_flos": 1.2950067440359834e+17,
270
+ "trial_name": null,
271
+ "trial_params": null
272
+ }
checkpoint-400/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20f73ff8f89707f8685548bde5cd81546e84cf93095d7a2c4bdd8fdb070cfdfa
3
+ size 3579