Hugging Face's logo

ArunMoonpai
/
CodeLlama-SQL-13b

Question Answering
PEFT
PyTorch
English
llama
Model card Files Community
3
Abinesh Sivakumar commited on
Commit
8018296
·
1 Parent(s): eb54c05

Delete https:

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1000/README.md +0 -21
  2. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1000/adapter_config.json +0 -21
  3. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1000/adapter_model.bin +0 -3
  4. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1000/optimizer.pt +0 -3
  5. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1000/rng_state.pth +0 -3
  6. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1000/scheduler.pt +0 -3
  7. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1000/trainer_state.json +0 -319
  8. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1000/training_args.bin +0 -3
  9. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1500/README.md +0 -21
  10. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1500/adapter_config.json +0 -21
  11. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1500/adapter_model.bin +0 -3
  12. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1500/optimizer.pt +0 -3
  13. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1500/rng_state.pth +0 -3
  14. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1500/scheduler.pt +0 -3
  15. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1500/trainer_state.json +0 -469
  16. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1500/training_args.bin +0 -3
  17. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2000/README.md +0 -21
  18. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2000/adapter_config.json +0 -21
  19. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2000/adapter_model.bin +0 -3
  20. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2000/optimizer.pt +0 -3
  21. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2000/rng_state.pth +0 -3
  22. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2000/scheduler.pt +0 -3
  23. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2000/trainer_state.json +0 -619
  24. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2000/training_args.bin +0 -3
  25. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2500/README.md +0 -21
  26. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2500/adapter_config.json +0 -21
  27. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2500/adapter_model.bin +0 -3
  28. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2500/optimizer.pt +0 -3
  29. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2500/rng_state.pth +0 -3
  30. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2500/scheduler.pt +0 -3
  31. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2500/trainer_state.json +0 -769
  32. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2500/training_args.bin +0 -3
  33. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3000/README.md +0 -21
  34. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3000/adapter_config.json +0 -21
  35. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3000/adapter_model.bin +0 -3
  36. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3000/optimizer.pt +0 -3
  37. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3000/rng_state.pth +0 -3
  38. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3000/scheduler.pt +0 -3
  39. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3000/trainer_state.json +0 -919
  40. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3000/training_args.bin +0 -3
  41. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3500/README.md +0 -21
  42. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3500/adapter_config.json +0 -21
  43. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3500/adapter_model.bin +0 -3
  44. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3500/optimizer.pt +0 -3
  45. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3500/rng_state.pth +0 -3
  46. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3500/scheduler.pt +0 -3
  47. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3500/trainer_state.json +0 -1069
  48. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3500/training_args.bin +0 -3
  49. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-4000/README.md +0 -21
  50. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-4000/adapter_config.json +0 -21
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1000/README.md DELETED
@@ -1,21 +0,0 @@
1
- ---
2
- library_name: peft
3
- ---
4
- ## Training procedure
5
-
6
-
7
- The following `bitsandbytes` quantization config was used during training:
8
- - quant_method: QuantizationMethod.BITS_AND_BYTES
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: True
17
- - bnb_4bit_compute_dtype: bfloat16
18
- ### Framework versions
19
-
20
-
21
- - PEFT 0.4.0.dev0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1000/adapter_config.json DELETED
@@ -1,21 +0,0 @@
1
- {
2
- "base_model_name_or_path": "codellama/CodeLlama-13b-Instruct-hf",
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": 8,
14
- "revision": null,
15
- "target_modules": [
16
- "q_proj",
17
- "k_proj",
18
- "v_proj"
19
- ],
20
- "task_type": "CAUSAL_LM"
21
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1000/adapter_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f914b0990947e8af0d7abfcde78e4512e8b5bc4e639b4f9b095212d03a40e7f2
3
- size 39407821
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1000/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d38567d868c29aaa39241ddaf2fde670173ed97a39499456176416b39413be8
3
- size 78844165
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1000/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:898a6948390b5093738fb7b2c97359379a9b2ed8cb45fd6bf5d632aea978f1a3
3
- size 14575
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1000/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:23efe624b19e546b381a09029c8ee3430909ac7bb2ed04e2f93a318e70a679ed
3
- size 627
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1000/trainer_state.json DELETED
@@ -1,319 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 0.1018109624953867,
5
- "eval_steps": 500,
6
- "global_step": 1000,
7
- "is_hyper_param_search": false,
8
- "is_local_process_zero": true,
9
- "is_world_process_zero": true,
10
- "log_history": [
11
- {
12
- "epoch": 0.0,
13
- "learning_rate": 4e-05,
14
- "loss": 3.5766,
15
- "step": 20
16
- },
17
- {
18
- "epoch": 0.0,
19
- "learning_rate": 8e-05,
20
- "loss": 2.9038,
21
- "step": 40
22
- },
23
- {
24
- "epoch": 0.01,
25
- "learning_rate": 0.00012,
26
- "loss": 1.9072,
27
- "step": 60
28
- },
29
- {
30
- "epoch": 0.01,
31
- "learning_rate": 0.00016,
32
- "loss": 1.7359,
33
- "step": 80
34
- },
35
- {
36
- "epoch": 0.01,
37
- "learning_rate": 0.0002,
38
- "loss": 1.5349,
39
- "step": 100
40
- },
41
- {
42
- "epoch": 0.01,
43
- "learning_rate": 0.00019958856202427486,
44
- "loss": 1.4908,
45
- "step": 120
46
- },
47
- {
48
- "epoch": 0.01,
49
- "learning_rate": 0.00019917712404854968,
50
- "loss": 1.4931,
51
- "step": 140
52
- },
53
- {
54
- "epoch": 0.02,
55
- "learning_rate": 0.00019876568607282453,
56
- "loss": 1.4201,
57
- "step": 160
58
- },
59
- {
60
- "epoch": 0.02,
61
- "learning_rate": 0.00019835424809709937,
62
- "loss": 1.4541,
63
- "step": 180
64
- },
65
- {
66
- "epoch": 0.02,
67
- "learning_rate": 0.00019794281012137422,
68
- "loss": 1.4102,
69
- "step": 200
70
- },
71
- {
72
- "epoch": 0.02,
73
- "learning_rate": 0.00019753137214564904,
74
- "loss": 1.3861,
75
- "step": 220
76
- },
77
- {
78
- "epoch": 0.02,
79
- "learning_rate": 0.0001971199341699239,
80
- "loss": 1.3939,
81
- "step": 240
82
- },
83
- {
84
- "epoch": 0.03,
85
- "learning_rate": 0.00019670849619419874,
86
- "loss": 1.3883,
87
- "step": 260
88
- },
89
- {
90
- "epoch": 0.03,
91
- "learning_rate": 0.00019629705821847356,
92
- "loss": 1.3257,
93
- "step": 280
94
- },
95
- {
96
- "epoch": 0.03,
97
- "learning_rate": 0.0001958856202427484,
98
- "loss": 1.386,
99
- "step": 300
100
- },
101
- {
102
- "epoch": 0.03,
103
- "learning_rate": 0.00019547418226702326,
104
- "loss": 1.3746,
105
- "step": 320
106
- },
107
- {
108
- "epoch": 0.03,
109
- "learning_rate": 0.0001950627442912981,
110
- "loss": 1.3266,
111
- "step": 340
112
- },
113
- {
114
- "epoch": 0.04,
115
- "learning_rate": 0.00019465130631557293,
116
- "loss": 1.3591,
117
- "step": 360
118
- },
119
- {
120
- "epoch": 0.04,
121
- "learning_rate": 0.00019423986833984777,
122
- "loss": 1.3464,
123
- "step": 380
124
- },
125
- {
126
- "epoch": 0.04,
127
- "learning_rate": 0.00019382843036412262,
128
- "loss": 1.3573,
129
- "step": 400
130
- },
131
- {
132
- "epoch": 0.04,
133
- "learning_rate": 0.00019341699238839744,
134
- "loss": 1.3455,
135
- "step": 420
136
- },
137
- {
138
- "epoch": 0.04,
139
- "learning_rate": 0.0001930055544126723,
140
- "loss": 1.3223,
141
- "step": 440
142
- },
143
- {
144
- "epoch": 0.05,
145
- "learning_rate": 0.00019259411643694714,
146
- "loss": 1.3293,
147
- "step": 460
148
- },
149
- {
150
- "epoch": 0.05,
151
- "learning_rate": 0.000192182678461222,
152
- "loss": 1.3033,
153
- "step": 480
154
- },
155
- {
156
- "epoch": 0.05,
157
- "learning_rate": 0.0001917712404854968,
158
- "loss": 1.3323,
159
- "step": 500
160
- },
161
- {
162
- "epoch": 0.05,
163
- "learning_rate": 0.00019135980250977166,
164
- "loss": 1.2838,
165
- "step": 520
166
- },
167
- {
168
- "epoch": 0.05,
169
- "learning_rate": 0.0001909483645340465,
170
- "loss": 1.332,
171
- "step": 540
172
- },
173
- {
174
- "epoch": 0.06,
175
- "learning_rate": 0.00019053692655832133,
176
- "loss": 1.3118,
177
- "step": 560
178
- },
179
- {
180
- "epoch": 0.06,
181
- "learning_rate": 0.00019012548858259617,
182
- "loss": 1.3237,
183
- "step": 580
184
- },
185
- {
186
- "epoch": 0.06,
187
- "learning_rate": 0.00018971405060687102,
188
- "loss": 1.2541,
189
- "step": 600
190
- },
191
- {
192
- "epoch": 0.06,
193
- "learning_rate": 0.00018930261263114587,
194
- "loss": 1.28,
195
- "step": 620
196
- },
197
- {
198
- "epoch": 0.07,
199
- "learning_rate": 0.0001888911746554207,
200
- "loss": 1.231,
201
- "step": 640
202
- },
203
- {
204
- "epoch": 0.07,
205
- "learning_rate": 0.00018847973667969554,
206
- "loss": 1.2676,
207
- "step": 660
208
- },
209
- {
210
- "epoch": 0.07,
211
- "learning_rate": 0.0001880682987039704,
212
- "loss": 1.2909,
213
- "step": 680
214
- },
215
- {
216
- "epoch": 0.07,
217
- "learning_rate": 0.0001876568607282452,
218
- "loss": 1.2499,
219
- "step": 700
220
- },
221
- {
222
- "epoch": 0.07,
223
- "learning_rate": 0.00018724542275252006,
224
- "loss": 1.2679,
225
- "step": 720
226
- },
227
- {
228
- "epoch": 0.08,
229
- "learning_rate": 0.0001868339847767949,
230
- "loss": 1.2674,
231
- "step": 740
232
- },
233
- {
234
- "epoch": 0.08,
235
- "learning_rate": 0.00018642254680106975,
236
- "loss": 1.2736,
237
- "step": 760
238
- },
239
- {
240
- "epoch": 0.08,
241
- "learning_rate": 0.00018601110882534457,
242
- "loss": 1.2843,
243
- "step": 780
244
- },
245
- {
246
- "epoch": 0.08,
247
- "learning_rate": 0.00018559967084961942,
248
- "loss": 1.281,
249
- "step": 800
250
- },
251
- {
252
- "epoch": 0.08,
253
- "learning_rate": 0.00018518823287389427,
254
- "loss": 1.3699,
255
- "step": 820
256
- },
257
- {
258
- "epoch": 0.09,
259
- "learning_rate": 0.0001847767948981691,
260
- "loss": 1.2705,
261
- "step": 840
262
- },
263
- {
264
- "epoch": 0.09,
265
- "learning_rate": 0.00018436535692244394,
266
- "loss": 1.2279,
267
- "step": 860
268
- },
269
- {
270
- "epoch": 0.09,
271
- "learning_rate": 0.0001839539189467188,
272
- "loss": 1.2779,
273
- "step": 880
274
- },
275
- {
276
- "epoch": 0.09,
277
- "learning_rate": 0.00018354248097099364,
278
- "loss": 1.2086,
279
- "step": 900
280
- },
281
- {
282
- "epoch": 0.09,
283
- "learning_rate": 0.00018313104299526846,
284
- "loss": 1.2999,
285
- "step": 920
286
- },
287
- {
288
- "epoch": 0.1,
289
- "learning_rate": 0.0001827196050195433,
290
- "loss": 1.2503,
291
- "step": 940
292
- },
293
- {
294
- "epoch": 0.1,
295
- "learning_rate": 0.00018230816704381815,
296
- "loss": 1.2466,
297
- "step": 960
298
- },
299
- {
300
- "epoch": 0.1,
301
- "learning_rate": 0.00018189672906809297,
302
- "loss": 1.2113,
303
- "step": 980
304
- },
305
- {
306
- "epoch": 0.1,
307
- "learning_rate": 0.00018148529109236782,
308
- "loss": 1.2356,
309
- "step": 1000
310
- }
311
- ],
312
- "logging_steps": 20,
313
- "max_steps": 9822,
314
- "num_train_epochs": 1,
315
- "save_steps": 500,
316
- "total_flos": 1.45080101465088e+16,
317
- "trial_name": null,
318
- "trial_params": null
319
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1000/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8819fc087370c0c0dd1869922822cf7a5ebe84fa7a7194c69a0ec917ff22569b
3
- size 4027
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1500/README.md DELETED
@@ -1,21 +0,0 @@
1
- ---
2
- library_name: peft
3
- ---
4
- ## Training procedure
5
-
6
-
7
- The following `bitsandbytes` quantization config was used during training:
8
- - quant_method: QuantizationMethod.BITS_AND_BYTES
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: True
17
- - bnb_4bit_compute_dtype: bfloat16
18
- ### Framework versions
19
-
20
-
21
- - PEFT 0.4.0.dev0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1500/adapter_config.json DELETED
@@ -1,21 +0,0 @@
1
- {
2
- "base_model_name_or_path": "codellama/CodeLlama-13b-Instruct-hf",
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": 8,
14
- "revision": null,
15
- "target_modules": [
16
- "q_proj",
17
- "k_proj",
18
- "v_proj"
19
- ],
20
- "task_type": "CAUSAL_LM"
21
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1500/adapter_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c6b0831fc2d11fac7dd78434203aefcffbfbc4a3abe53ba55fc1832f3e0a656
3
- size 39407821
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1500/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:db850f3db5ddc9d314504fbc945e2f5f38dc9904f7041be2d2b8b2258bdb5292
3
- size 78844165
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1500/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0184552a92e3eea244ca8525508faa432cc2ef3b3619da07af22a8f830deedd7
3
- size 14575
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1500/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:39ecefbbaaea1fa61a9e8640351957e5ab0b16bcd5b68bc8acb5a1ae782aa095
3
- size 627
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1500/trainer_state.json DELETED
@@ -1,469 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 0.15271644374308005,
5
- "eval_steps": 500,
6
- "global_step": 1500,
7
- "is_hyper_param_search": false,
8
- "is_local_process_zero": true,
9
- "is_world_process_zero": true,
10
- "log_history": [
11
- {
12
- "epoch": 0.0,
13
- "learning_rate": 4e-05,
14
- "loss": 3.5766,
15
- "step": 20
16
- },
17
- {
18
- "epoch": 0.0,
19
- "learning_rate": 8e-05,
20
- "loss": 2.9038,
21
- "step": 40
22
- },
23
- {
24
- "epoch": 0.01,
25
- "learning_rate": 0.00012,
26
- "loss": 1.9072,
27
- "step": 60
28
- },
29
- {
30
- "epoch": 0.01,
31
- "learning_rate": 0.00016,
32
- "loss": 1.7359,
33
- "step": 80
34
- },
35
- {
36
- "epoch": 0.01,
37
- "learning_rate": 0.0002,
38
- "loss": 1.5349,
39
- "step": 100
40
- },
41
- {
42
- "epoch": 0.01,
43
- "learning_rate": 0.00019958856202427486,
44
- "loss": 1.4908,
45
- "step": 120
46
- },
47
- {
48
- "epoch": 0.01,
49
- "learning_rate": 0.00019917712404854968,
50
- "loss": 1.4931,
51
- "step": 140
52
- },
53
- {
54
- "epoch": 0.02,
55
- "learning_rate": 0.00019876568607282453,
56
- "loss": 1.4201,
57
- "step": 160
58
- },
59
- {
60
- "epoch": 0.02,
61
- "learning_rate": 0.00019835424809709937,
62
- "loss": 1.4541,
63
- "step": 180
64
- },
65
- {
66
- "epoch": 0.02,
67
- "learning_rate": 0.00019794281012137422,
68
- "loss": 1.4102,
69
- "step": 200
70
- },
71
- {
72
- "epoch": 0.02,
73
- "learning_rate": 0.00019753137214564904,
74
- "loss": 1.3861,
75
- "step": 220
76
- },
77
- {
78
- "epoch": 0.02,
79
- "learning_rate": 0.0001971199341699239,
80
- "loss": 1.3939,
81
- "step": 240
82
- },
83
- {
84
- "epoch": 0.03,
85
- "learning_rate": 0.00019670849619419874,
86
- "loss": 1.3883,
87
- "step": 260
88
- },
89
- {
90
- "epoch": 0.03,
91
- "learning_rate": 0.00019629705821847356,
92
- "loss": 1.3257,
93
- "step": 280
94
- },
95
- {
96
- "epoch": 0.03,
97
- "learning_rate": 0.0001958856202427484,
98
- "loss": 1.386,
99
- "step": 300
100
- },
101
- {
102
- "epoch": 0.03,
103
- "learning_rate": 0.00019547418226702326,
104
- "loss": 1.3746,
105
- "step": 320
106
- },
107
- {
108
- "epoch": 0.03,
109
- "learning_rate": 0.0001950627442912981,
110
- "loss": 1.3266,
111
- "step": 340
112
- },
113
- {
114
- "epoch": 0.04,
115
- "learning_rate": 0.00019465130631557293,
116
- "loss": 1.3591,
117
- "step": 360
118
- },
119
- {
120
- "epoch": 0.04,
121
- "learning_rate": 0.00019423986833984777,
122
- "loss": 1.3464,
123
- "step": 380
124
- },
125
- {
126
- "epoch": 0.04,
127
- "learning_rate": 0.00019382843036412262,
128
- "loss": 1.3573,
129
- "step": 400
130
- },
131
- {
132
- "epoch": 0.04,
133
- "learning_rate": 0.00019341699238839744,
134
- "loss": 1.3455,
135
- "step": 420
136
- },
137
- {
138
- "epoch": 0.04,
139
- "learning_rate": 0.0001930055544126723,
140
- "loss": 1.3223,
141
- "step": 440
142
- },
143
- {
144
- "epoch": 0.05,
145
- "learning_rate": 0.00019259411643694714,
146
- "loss": 1.3293,
147
- "step": 460
148
- },
149
- {
150
- "epoch": 0.05,
151
- "learning_rate": 0.000192182678461222,
152
- "loss": 1.3033,
153
- "step": 480
154
- },
155
- {
156
- "epoch": 0.05,
157
- "learning_rate": 0.0001917712404854968,
158
- "loss": 1.3323,
159
- "step": 500
160
- },
161
- {
162
- "epoch": 0.05,
163
- "learning_rate": 0.00019135980250977166,
164
- "loss": 1.2838,
165
- "step": 520
166
- },
167
- {
168
- "epoch": 0.05,
169
- "learning_rate": 0.0001909483645340465,
170
- "loss": 1.332,
171
- "step": 540
172
- },
173
- {
174
- "epoch": 0.06,
175
- "learning_rate": 0.00019053692655832133,
176
- "loss": 1.3118,
177
- "step": 560
178
- },
179
- {
180
- "epoch": 0.06,
181
- "learning_rate": 0.00019012548858259617,
182
- "loss": 1.3237,
183
- "step": 580
184
- },
185
- {
186
- "epoch": 0.06,
187
- "learning_rate": 0.00018971405060687102,
188
- "loss": 1.2541,
189
- "step": 600
190
- },
191
- {
192
- "epoch": 0.06,
193
- "learning_rate": 0.00018930261263114587,
194
- "loss": 1.28,
195
- "step": 620
196
- },
197
- {
198
- "epoch": 0.07,
199
- "learning_rate": 0.0001888911746554207,
200
- "loss": 1.231,
201
- "step": 640
202
- },
203
- {
204
- "epoch": 0.07,
205
- "learning_rate": 0.00018847973667969554,
206
- "loss": 1.2676,
207
- "step": 660
208
- },
209
- {
210
- "epoch": 0.07,
211
- "learning_rate": 0.0001880682987039704,
212
- "loss": 1.2909,
213
- "step": 680
214
- },
215
- {
216
- "epoch": 0.07,
217
- "learning_rate": 0.0001876568607282452,
218
- "loss": 1.2499,
219
- "step": 700
220
- },
221
- {
222
- "epoch": 0.07,
223
- "learning_rate": 0.00018724542275252006,
224
- "loss": 1.2679,
225
- "step": 720
226
- },
227
- {
228
- "epoch": 0.08,
229
- "learning_rate": 0.0001868339847767949,
230
- "loss": 1.2674,
231
- "step": 740
232
- },
233
- {
234
- "epoch": 0.08,
235
- "learning_rate": 0.00018642254680106975,
236
- "loss": 1.2736,
237
- "step": 760
238
- },
239
- {
240
- "epoch": 0.08,
241
- "learning_rate": 0.00018601110882534457,
242
- "loss": 1.2843,
243
- "step": 780
244
- },
245
- {
246
- "epoch": 0.08,
247
- "learning_rate": 0.00018559967084961942,
248
- "loss": 1.281,
249
- "step": 800
250
- },
251
- {
252
- "epoch": 0.08,
253
- "learning_rate": 0.00018518823287389427,
254
- "loss": 1.3699,
255
- "step": 820
256
- },
257
- {
258
- "epoch": 0.09,
259
- "learning_rate": 0.0001847767948981691,
260
- "loss": 1.2705,
261
- "step": 840
262
- },
263
- {
264
- "epoch": 0.09,
265
- "learning_rate": 0.00018436535692244394,
266
- "loss": 1.2279,
267
- "step": 860
268
- },
269
- {
270
- "epoch": 0.09,
271
- "learning_rate": 0.0001839539189467188,
272
- "loss": 1.2779,
273
- "step": 880
274
- },
275
- {
276
- "epoch": 0.09,
277
- "learning_rate": 0.00018354248097099364,
278
- "loss": 1.2086,
279
- "step": 900
280
- },
281
- {
282
- "epoch": 0.09,
283
- "learning_rate": 0.00018313104299526846,
284
- "loss": 1.2999,
285
- "step": 920
286
- },
287
- {
288
- "epoch": 0.1,
289
- "learning_rate": 0.0001827196050195433,
290
- "loss": 1.2503,
291
- "step": 940
292
- },
293
- {
294
- "epoch": 0.1,
295
- "learning_rate": 0.00018230816704381815,
296
- "loss": 1.2466,
297
- "step": 960
298
- },
299
- {
300
- "epoch": 0.1,
301
- "learning_rate": 0.00018189672906809297,
302
- "loss": 1.2113,
303
- "step": 980
304
- },
305
- {
306
- "epoch": 0.1,
307
- "learning_rate": 0.00018148529109236782,
308
- "loss": 1.2356,
309
- "step": 1000
310
- },
311
- {
312
- "epoch": 0.1,
313
- "learning_rate": 0.00018107385311664267,
314
- "loss": 1.2631,
315
- "step": 1020
316
- },
317
- {
318
- "epoch": 0.11,
319
- "learning_rate": 0.00018066241514091752,
320
- "loss": 1.2443,
321
- "step": 1040
322
- },
323
- {
324
- "epoch": 0.11,
325
- "learning_rate": 0.00018025097716519234,
326
- "loss": 1.2406,
327
- "step": 1060
328
- },
329
- {
330
- "epoch": 0.11,
331
- "learning_rate": 0.0001798395391894672,
332
- "loss": 1.2308,
333
- "step": 1080
334
- },
335
- {
336
- "epoch": 0.11,
337
- "learning_rate": 0.00017942810121374204,
338
- "loss": 1.2649,
339
- "step": 1100
340
- },
341
- {
342
- "epoch": 0.11,
343
- "learning_rate": 0.00017901666323801686,
344
- "loss": 1.2263,
345
- "step": 1120
346
- },
347
- {
348
- "epoch": 0.12,
349
- "learning_rate": 0.0001786052252622917,
350
- "loss": 1.2869,
351
- "step": 1140
352
- },
353
- {
354
- "epoch": 0.12,
355
- "learning_rate": 0.00017819378728656655,
356
- "loss": 1.2255,
357
- "step": 1160
358
- },
359
- {
360
- "epoch": 0.12,
361
- "learning_rate": 0.0001777823493108414,
362
- "loss": 1.2596,
363
- "step": 1180
364
- },
365
- {
366
- "epoch": 0.12,
367
- "learning_rate": 0.00017737091133511622,
368
- "loss": 1.2748,
369
- "step": 1200
370
- },
371
- {
372
- "epoch": 0.12,
373
- "learning_rate": 0.00017695947335939107,
374
- "loss": 1.2587,
375
- "step": 1220
376
- },
377
- {
378
- "epoch": 0.13,
379
- "learning_rate": 0.00017654803538366592,
380
- "loss": 1.2651,
381
- "step": 1240
382
- },
383
- {
384
- "epoch": 0.13,
385
- "learning_rate": 0.00017613659740794074,
386
- "loss": 1.2659,
387
- "step": 1260
388
- },
389
- {
390
- "epoch": 0.13,
391
- "learning_rate": 0.0001757251594322156,
392
- "loss": 1.2077,
393
- "step": 1280
394
- },
395
- {
396
- "epoch": 0.13,
397
- "learning_rate": 0.00017531372145649044,
398
- "loss": 1.25,
399
- "step": 1300
400
- },
401
- {
402
- "epoch": 0.13,
403
- "learning_rate": 0.00017490228348076528,
404
- "loss": 1.2149,
405
- "step": 1320
406
- },
407
- {
408
- "epoch": 0.14,
409
- "learning_rate": 0.0001744908455050401,
410
- "loss": 1.2417,
411
- "step": 1340
412
- },
413
- {
414
- "epoch": 0.14,
415
- "learning_rate": 0.00017407940752931498,
416
- "loss": 1.1939,
417
- "step": 1360
418
- },
419
- {
420
- "epoch": 0.14,
421
- "learning_rate": 0.00017366796955358983,
422
- "loss": 1.2688,
423
- "step": 1380
424
- },
425
- {
426
- "epoch": 0.14,
427
- "learning_rate": 0.00017325653157786465,
428
- "loss": 1.2287,
429
- "step": 1400
430
- },
431
- {
432
- "epoch": 0.14,
433
- "learning_rate": 0.0001728450936021395,
434
- "loss": 1.2931,
435
- "step": 1420
436
- },
437
- {
438
- "epoch": 0.15,
439
- "learning_rate": 0.00017243365562641435,
440
- "loss": 1.2695,
441
- "step": 1440
442
- },
443
- {
444
- "epoch": 0.15,
445
- "learning_rate": 0.00017202221765068917,
446
- "loss": 1.2228,
447
- "step": 1460
448
- },
449
- {
450
- "epoch": 0.15,
451
- "learning_rate": 0.00017161077967496401,
452
- "loss": 1.2419,
453
- "step": 1480
454
- },
455
- {
456
- "epoch": 0.15,
457
- "learning_rate": 0.00017119934169923886,
458
- "loss": 1.2483,
459
- "step": 1500
460
- }
461
- ],
462
- "logging_steps": 20,
463
- "max_steps": 9822,
464
- "num_train_epochs": 1,
465
- "save_steps": 500,
466
- "total_flos": 2.177523382889472e+16,
467
- "trial_name": null,
468
- "trial_params": null
469
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1500/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8819fc087370c0c0dd1869922822cf7a5ebe84fa7a7194c69a0ec917ff22569b
3
- size 4027
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2000/README.md DELETED
@@ -1,21 +0,0 @@
1
- ---
2
- library_name: peft
3
- ---
4
- ## Training procedure
5
-
6
-
7
- The following `bitsandbytes` quantization config was used during training:
8
- - quant_method: QuantizationMethod.BITS_AND_BYTES
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: True
17
- - bnb_4bit_compute_dtype: bfloat16
18
- ### Framework versions
19
-
20
-
21
- - PEFT 0.4.0.dev0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2000/adapter_config.json DELETED
@@ -1,21 +0,0 @@
1
- {
2
- "base_model_name_or_path": "codellama/CodeLlama-13b-Instruct-hf",
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": 8,
14
- "revision": null,
15
- "target_modules": [
16
- "q_proj",
17
- "k_proj",
18
- "v_proj"
19
- ],
20
- "task_type": "CAUSAL_LM"
21
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2000/adapter_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf61645713ce00098c5c8cc926e5605bd03b1b707618486b06702b128bbe5eaf
3
- size 39407821
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2000/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5050b0af89198d5f8bd3cd59ea636fb02bda929e29ce98fa4ca2b838a733c6e9
3
- size 78844165
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2000/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c95f00681f2f9ca9879f2b6557dcf0d12bcb73e1a027aa0fcdd2f0c5c7828aa9
3
- size 14575
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2000/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3a1ccb9a0f957748e69d536bb952c4ccbae393eb0f6c8061358a6633020031a
3
- size 627
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2000/trainer_state.json DELETED
@@ -1,619 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 0.2036219249907734,
5
- "eval_steps": 500,
6
- "global_step": 2000,
7
- "is_hyper_param_search": false,
8
- "is_local_process_zero": true,
9
- "is_world_process_zero": true,
10
- "log_history": [
11
- {
12
- "epoch": 0.0,
13
- "learning_rate": 4e-05,
14
- "loss": 3.5766,
15
- "step": 20
16
- },
17
- {
18
- "epoch": 0.0,
19
- "learning_rate": 8e-05,
20
- "loss": 2.9038,
21
- "step": 40
22
- },
23
- {
24
- "epoch": 0.01,
25
- "learning_rate": 0.00012,
26
- "loss": 1.9072,
27
- "step": 60
28
- },
29
- {
30
- "epoch": 0.01,
31
- "learning_rate": 0.00016,
32
- "loss": 1.7359,
33
- "step": 80
34
- },
35
- {
36
- "epoch": 0.01,
37
- "learning_rate": 0.0002,
38
- "loss": 1.5349,
39
- "step": 100
40
- },
41
- {
42
- "epoch": 0.01,
43
- "learning_rate": 0.00019958856202427486,
44
- "loss": 1.4908,
45
- "step": 120
46
- },
47
- {
48
- "epoch": 0.01,
49
- "learning_rate": 0.00019917712404854968,
50
- "loss": 1.4931,
51
- "step": 140
52
- },
53
- {
54
- "epoch": 0.02,
55
- "learning_rate": 0.00019876568607282453,
56
- "loss": 1.4201,
57
- "step": 160
58
- },
59
- {
60
- "epoch": 0.02,
61
- "learning_rate": 0.00019835424809709937,
62
- "loss": 1.4541,
63
- "step": 180
64
- },
65
- {
66
- "epoch": 0.02,
67
- "learning_rate": 0.00019794281012137422,
68
- "loss": 1.4102,
69
- "step": 200
70
- },
71
- {
72
- "epoch": 0.02,
73
- "learning_rate": 0.00019753137214564904,
74
- "loss": 1.3861,
75
- "step": 220
76
- },
77
- {
78
- "epoch": 0.02,
79
- "learning_rate": 0.0001971199341699239,
80
- "loss": 1.3939,
81
- "step": 240
82
- },
83
- {
84
- "epoch": 0.03,
85
- "learning_rate": 0.00019670849619419874,
86
- "loss": 1.3883,
87
- "step": 260
88
- },
89
- {
90
- "epoch": 0.03,
91
- "learning_rate": 0.00019629705821847356,
92
- "loss": 1.3257,
93
- "step": 280
94
- },
95
- {
96
- "epoch": 0.03,
97
- "learning_rate": 0.0001958856202427484,
98
- "loss": 1.386,
99
- "step": 300
100
- },
101
- {
102
- "epoch": 0.03,
103
- "learning_rate": 0.00019547418226702326,
104
- "loss": 1.3746,
105
- "step": 320
106
- },
107
- {
108
- "epoch": 0.03,
109
- "learning_rate": 0.0001950627442912981,
110
- "loss": 1.3266,
111
- "step": 340
112
- },
113
- {
114
- "epoch": 0.04,
115
- "learning_rate": 0.00019465130631557293,
116
- "loss": 1.3591,
117
- "step": 360
118
- },
119
- {
120
- "epoch": 0.04,
121
- "learning_rate": 0.00019423986833984777,
122
- "loss": 1.3464,
123
- "step": 380
124
- },
125
- {
126
- "epoch": 0.04,
127
- "learning_rate": 0.00019382843036412262,
128
- "loss": 1.3573,
129
- "step": 400
130
- },
131
- {
132
- "epoch": 0.04,
133
- "learning_rate": 0.00019341699238839744,
134
- "loss": 1.3455,
135
- "step": 420
136
- },
137
- {
138
- "epoch": 0.04,
139
- "learning_rate": 0.0001930055544126723,
140
- "loss": 1.3223,
141
- "step": 440
142
- },
143
- {
144
- "epoch": 0.05,
145
- "learning_rate": 0.00019259411643694714,
146
- "loss": 1.3293,
147
- "step": 460
148
- },
149
- {
150
- "epoch": 0.05,
151
- "learning_rate": 0.000192182678461222,
152
- "loss": 1.3033,
153
- "step": 480
154
- },
155
- {
156
- "epoch": 0.05,
157
- "learning_rate": 0.0001917712404854968,
158
- "loss": 1.3323,
159
- "step": 500
160
- },
161
- {
162
- "epoch": 0.05,
163
- "learning_rate": 0.00019135980250977166,
164
- "loss": 1.2838,
165
- "step": 520
166
- },
167
- {
168
- "epoch": 0.05,
169
- "learning_rate": 0.0001909483645340465,
170
- "loss": 1.332,
171
- "step": 540
172
- },
173
- {
174
- "epoch": 0.06,
175
- "learning_rate": 0.00019053692655832133,
176
- "loss": 1.3118,
177
- "step": 560
178
- },
179
- {
180
- "epoch": 0.06,
181
- "learning_rate": 0.00019012548858259617,
182
- "loss": 1.3237,
183
- "step": 580
184
- },
185
- {
186
- "epoch": 0.06,
187
- "learning_rate": 0.00018971405060687102,
188
- "loss": 1.2541,
189
- "step": 600
190
- },
191
- {
192
- "epoch": 0.06,
193
- "learning_rate": 0.00018930261263114587,
194
- "loss": 1.28,
195
- "step": 620
196
- },
197
- {
198
- "epoch": 0.07,
199
- "learning_rate": 0.0001888911746554207,
200
- "loss": 1.231,
201
- "step": 640
202
- },
203
- {
204
- "epoch": 0.07,
205
- "learning_rate": 0.00018847973667969554,
206
- "loss": 1.2676,
207
- "step": 660
208
- },
209
- {
210
- "epoch": 0.07,
211
- "learning_rate": 0.0001880682987039704,
212
- "loss": 1.2909,
213
- "step": 680
214
- },
215
- {
216
- "epoch": 0.07,
217
- "learning_rate": 0.0001876568607282452,
218
- "loss": 1.2499,
219
- "step": 700
220
- },
221
- {
222
- "epoch": 0.07,
223
- "learning_rate": 0.00018724542275252006,
224
- "loss": 1.2679,
225
- "step": 720
226
- },
227
- {
228
- "epoch": 0.08,
229
- "learning_rate": 0.0001868339847767949,
230
- "loss": 1.2674,
231
- "step": 740
232
- },
233
- {
234
- "epoch": 0.08,
235
- "learning_rate": 0.00018642254680106975,
236
- "loss": 1.2736,
237
- "step": 760
238
- },
239
- {
240
- "epoch": 0.08,
241
- "learning_rate": 0.00018601110882534457,
242
- "loss": 1.2843,
243
- "step": 780
244
- },
245
- {
246
- "epoch": 0.08,
247
- "learning_rate": 0.00018559967084961942,
248
- "loss": 1.281,
249
- "step": 800
250
- },
251
- {
252
- "epoch": 0.08,
253
- "learning_rate": 0.00018518823287389427,
254
- "loss": 1.3699,
255
- "step": 820
256
- },
257
- {
258
- "epoch": 0.09,
259
- "learning_rate": 0.0001847767948981691,
260
- "loss": 1.2705,
261
- "step": 840
262
- },
263
- {
264
- "epoch": 0.09,
265
- "learning_rate": 0.00018436535692244394,
266
- "loss": 1.2279,
267
- "step": 860
268
- },
269
- {
270
- "epoch": 0.09,
271
- "learning_rate": 0.0001839539189467188,
272
- "loss": 1.2779,
273
- "step": 880
274
- },
275
- {
276
- "epoch": 0.09,
277
- "learning_rate": 0.00018354248097099364,
278
- "loss": 1.2086,
279
- "step": 900
280
- },
281
- {
282
- "epoch": 0.09,
283
- "learning_rate": 0.00018313104299526846,
284
- "loss": 1.2999,
285
- "step": 920
286
- },
287
- {
288
- "epoch": 0.1,
289
- "learning_rate": 0.0001827196050195433,
290
- "loss": 1.2503,
291
- "step": 940
292
- },
293
- {
294
- "epoch": 0.1,
295
- "learning_rate": 0.00018230816704381815,
296
- "loss": 1.2466,
297
- "step": 960
298
- },
299
- {
300
- "epoch": 0.1,
301
- "learning_rate": 0.00018189672906809297,
302
- "loss": 1.2113,
303
- "step": 980
304
- },
305
- {
306
- "epoch": 0.1,
307
- "learning_rate": 0.00018148529109236782,
308
- "loss": 1.2356,
309
- "step": 1000
310
- },
311
- {
312
- "epoch": 0.1,
313
- "learning_rate": 0.00018107385311664267,
314
- "loss": 1.2631,
315
- "step": 1020
316
- },
317
- {
318
- "epoch": 0.11,
319
- "learning_rate": 0.00018066241514091752,
320
- "loss": 1.2443,
321
- "step": 1040
322
- },
323
- {
324
- "epoch": 0.11,
325
- "learning_rate": 0.00018025097716519234,
326
- "loss": 1.2406,
327
- "step": 1060
328
- },
329
- {
330
- "epoch": 0.11,
331
- "learning_rate": 0.0001798395391894672,
332
- "loss": 1.2308,
333
- "step": 1080
334
- },
335
- {
336
- "epoch": 0.11,
337
- "learning_rate": 0.00017942810121374204,
338
- "loss": 1.2649,
339
- "step": 1100
340
- },
341
- {
342
- "epoch": 0.11,
343
- "learning_rate": 0.00017901666323801686,
344
- "loss": 1.2263,
345
- "step": 1120
346
- },
347
- {
348
- "epoch": 0.12,
349
- "learning_rate": 0.0001786052252622917,
350
- "loss": 1.2869,
351
- "step": 1140
352
- },
353
- {
354
- "epoch": 0.12,
355
- "learning_rate": 0.00017819378728656655,
356
- "loss": 1.2255,
357
- "step": 1160
358
- },
359
- {
360
- "epoch": 0.12,
361
- "learning_rate": 0.0001777823493108414,
362
- "loss": 1.2596,
363
- "step": 1180
364
- },
365
- {
366
- "epoch": 0.12,
367
- "learning_rate": 0.00017737091133511622,
368
- "loss": 1.2748,
369
- "step": 1200
370
- },
371
- {
372
- "epoch": 0.12,
373
- "learning_rate": 0.00017695947335939107,
374
- "loss": 1.2587,
375
- "step": 1220
376
- },
377
- {
378
- "epoch": 0.13,
379
- "learning_rate": 0.00017654803538366592,
380
- "loss": 1.2651,
381
- "step": 1240
382
- },
383
- {
384
- "epoch": 0.13,
385
- "learning_rate": 0.00017613659740794074,
386
- "loss": 1.2659,
387
- "step": 1260
388
- },
389
- {
390
- "epoch": 0.13,
391
- "learning_rate": 0.0001757251594322156,
392
- "loss": 1.2077,
393
- "step": 1280
394
- },
395
- {
396
- "epoch": 0.13,
397
- "learning_rate": 0.00017531372145649044,
398
- "loss": 1.25,
399
- "step": 1300
400
- },
401
- {
402
- "epoch": 0.13,
403
- "learning_rate": 0.00017490228348076528,
404
- "loss": 1.2149,
405
- "step": 1320
406
- },
407
- {
408
- "epoch": 0.14,
409
- "learning_rate": 0.0001744908455050401,
410
- "loss": 1.2417,
411
- "step": 1340
412
- },
413
- {
414
- "epoch": 0.14,
415
- "learning_rate": 0.00017407940752931498,
416
- "loss": 1.1939,
417
- "step": 1360
418
- },
419
- {
420
- "epoch": 0.14,
421
- "learning_rate": 0.00017366796955358983,
422
- "loss": 1.2688,
423
- "step": 1380
424
- },
425
- {
426
- "epoch": 0.14,
427
- "learning_rate": 0.00017325653157786465,
428
- "loss": 1.2287,
429
- "step": 1400
430
- },
431
- {
432
- "epoch": 0.14,
433
- "learning_rate": 0.0001728450936021395,
434
- "loss": 1.2931,
435
- "step": 1420
436
- },
437
- {
438
- "epoch": 0.15,
439
- "learning_rate": 0.00017243365562641435,
440
- "loss": 1.2695,
441
- "step": 1440
442
- },
443
- {
444
- "epoch": 0.15,
445
- "learning_rate": 0.00017202221765068917,
446
- "loss": 1.2228,
447
- "step": 1460
448
- },
449
- {
450
- "epoch": 0.15,
451
- "learning_rate": 0.00017161077967496401,
452
- "loss": 1.2419,
453
- "step": 1480
454
- },
455
- {
456
- "epoch": 0.15,
457
- "learning_rate": 0.00017119934169923886,
458
- "loss": 1.2483,
459
- "step": 1500
460
- },
461
- {
462
- "epoch": 0.15,
463
- "learning_rate": 0.0001707879037235137,
464
- "loss": 1.2144,
465
- "step": 1520
466
- },
467
- {
468
- "epoch": 0.16,
469
- "learning_rate": 0.00017037646574778853,
470
- "loss": 1.2148,
471
- "step": 1540
472
- },
473
- {
474
- "epoch": 0.16,
475
- "learning_rate": 0.00016996502777206338,
476
- "loss": 1.2196,
477
- "step": 1560
478
- },
479
- {
480
- "epoch": 0.16,
481
- "learning_rate": 0.00016955358979633823,
482
- "loss": 1.2581,
483
- "step": 1580
484
- },
485
- {
486
- "epoch": 0.16,
487
- "learning_rate": 0.00016914215182061305,
488
- "loss": 1.2414,
489
- "step": 1600
490
- },
491
- {
492
- "epoch": 0.16,
493
- "learning_rate": 0.0001687307138448879,
494
- "loss": 1.2357,
495
- "step": 1620
496
- },
497
- {
498
- "epoch": 0.17,
499
- "learning_rate": 0.00016831927586916274,
500
- "loss": 1.22,
501
- "step": 1640
502
- },
503
- {
504
- "epoch": 0.17,
505
- "learning_rate": 0.0001679078378934376,
506
- "loss": 1.2234,
507
- "step": 1660
508
- },
509
- {
510
- "epoch": 0.17,
511
- "learning_rate": 0.00016749639991771241,
512
- "loss": 1.2291,
513
- "step": 1680
514
- },
515
- {
516
- "epoch": 0.17,
517
- "learning_rate": 0.00016708496194198726,
518
- "loss": 1.2344,
519
- "step": 1700
520
- },
521
- {
522
- "epoch": 0.18,
523
- "learning_rate": 0.0001666735239662621,
524
- "loss": 1.1987,
525
- "step": 1720
526
- },
527
- {
528
- "epoch": 0.18,
529
- "learning_rate": 0.00016626208599053693,
530
- "loss": 1.2232,
531
- "step": 1740
532
- },
533
- {
534
- "epoch": 0.18,
535
- "learning_rate": 0.00016585064801481178,
536
- "loss": 1.2402,
537
- "step": 1760
538
- },
539
- {
540
- "epoch": 0.18,
541
- "learning_rate": 0.00016543921003908663,
542
- "loss": 1.1475,
543
- "step": 1780
544
- },
545
- {
546
- "epoch": 0.18,
547
- "learning_rate": 0.00016502777206336148,
548
- "loss": 1.272,
549
- "step": 1800
550
- },
551
- {
552
- "epoch": 0.19,
553
- "learning_rate": 0.0001646163340876363,
554
- "loss": 1.2369,
555
- "step": 1820
556
- },
557
- {
558
- "epoch": 0.19,
559
- "learning_rate": 0.00016420489611191114,
560
- "loss": 1.212,
561
- "step": 1840
562
- },
563
- {
564
- "epoch": 0.19,
565
- "learning_rate": 0.000163793458136186,
566
- "loss": 1.2191,
567
- "step": 1860
568
- },
569
- {
570
- "epoch": 0.19,
571
- "learning_rate": 0.00016338202016046081,
572
- "loss": 1.1953,
573
- "step": 1880
574
- },
575
- {
576
- "epoch": 0.19,
577
- "learning_rate": 0.00016297058218473566,
578
- "loss": 1.2126,
579
- "step": 1900
580
- },
581
- {
582
- "epoch": 0.2,
583
- "learning_rate": 0.0001625591442090105,
584
- "loss": 1.2396,
585
- "step": 1920
586
- },
587
- {
588
- "epoch": 0.2,
589
- "learning_rate": 0.00016214770623328536,
590
- "loss": 1.1468,
591
- "step": 1940
592
- },
593
- {
594
- "epoch": 0.2,
595
- "learning_rate": 0.00016173626825756018,
596
- "loss": 1.1847,
597
- "step": 1960
598
- },
599
- {
600
- "epoch": 0.2,
601
- "learning_rate": 0.00016132483028183503,
602
- "loss": 1.2214,
603
- "step": 1980
604
- },
605
- {
606
- "epoch": 0.2,
607
- "learning_rate": 0.00016091339230610988,
608
- "loss": 1.2138,
609
- "step": 2000
610
- }
611
- ],
612
- "logging_steps": 20,
613
- "max_steps": 9822,
614
- "num_train_epochs": 1,
615
- "save_steps": 500,
616
- "total_flos": 2.908887907648512e+16,
617
- "trial_name": null,
618
- "trial_params": null
619
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2000/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8819fc087370c0c0dd1869922822cf7a5ebe84fa7a7194c69a0ec917ff22569b
3
- size 4027
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2500/README.md DELETED
@@ -1,21 +0,0 @@
1
- ---
2
- library_name: peft
3
- ---
4
- ## Training procedure
5
-
6
-
7
- The following `bitsandbytes` quantization config was used during training:
8
- - quant_method: QuantizationMethod.BITS_AND_BYTES
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: True
17
- - bnb_4bit_compute_dtype: bfloat16
18
- ### Framework versions
19
-
20
-
21
- - PEFT 0.4.0.dev0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2500/adapter_config.json DELETED
@@ -1,21 +0,0 @@
1
- {
2
- "base_model_name_or_path": "codellama/CodeLlama-13b-Instruct-hf",
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": 8,
14
- "revision": null,
15
- "target_modules": [
16
- "q_proj",
17
- "k_proj",
18
- "v_proj"
19
- ],
20
- "task_type": "CAUSAL_LM"
21
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2500/adapter_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:73b3f2adc6f6374cde7c108b031e0e6e67250ba8ce32edff87c930ac2bc8a9b6
3
- size 39407821
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2500/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:eef06d7a537ff69f8b6e232bc2afa874c4db9e9d988185bd577ae9f68571c70c
3
- size 78844165
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2500/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c809d18b15e0dc9b961ac3ae55d2aeb3ae3e9cb845b4d706a495fc7c322a705
3
- size 14575
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2500/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c679b8c55ca25ae4648665ff45322feeafc7eb782af9af7326fcad2a0a90886
3
- size 627
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2500/trainer_state.json DELETED
@@ -1,769 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 0.2545274062384667,
5
- "eval_steps": 500,
6
- "global_step": 2500,
7
- "is_hyper_param_search": false,
8
- "is_local_process_zero": true,
9
- "is_world_process_zero": true,
10
- "log_history": [
11
- {
12
- "epoch": 0.0,
13
- "learning_rate": 4e-05,
14
- "loss": 3.5766,
15
- "step": 20
16
- },
17
- {
18
- "epoch": 0.0,
19
- "learning_rate": 8e-05,
20
- "loss": 2.9038,
21
- "step": 40
22
- },
23
- {
24
- "epoch": 0.01,
25
- "learning_rate": 0.00012,
26
- "loss": 1.9072,
27
- "step": 60
28
- },
29
- {
30
- "epoch": 0.01,
31
- "learning_rate": 0.00016,
32
- "loss": 1.7359,
33
- "step": 80
34
- },
35
- {
36
- "epoch": 0.01,
37
- "learning_rate": 0.0002,
38
- "loss": 1.5349,
39
- "step": 100
40
- },
41
- {
42
- "epoch": 0.01,
43
- "learning_rate": 0.00019958856202427486,
44
- "loss": 1.4908,
45
- "step": 120
46
- },
47
- {
48
- "epoch": 0.01,
49
- "learning_rate": 0.00019917712404854968,
50
- "loss": 1.4931,
51
- "step": 140
52
- },
53
- {
54
- "epoch": 0.02,
55
- "learning_rate": 0.00019876568607282453,
56
- "loss": 1.4201,
57
- "step": 160
58
- },
59
- {
60
- "epoch": 0.02,
61
- "learning_rate": 0.00019835424809709937,
62
- "loss": 1.4541,
63
- "step": 180
64
- },
65
- {
66
- "epoch": 0.02,
67
- "learning_rate": 0.00019794281012137422,
68
- "loss": 1.4102,
69
- "step": 200
70
- },
71
- {
72
- "epoch": 0.02,
73
- "learning_rate": 0.00019753137214564904,
74
- "loss": 1.3861,
75
- "step": 220
76
- },
77
- {
78
- "epoch": 0.02,
79
- "learning_rate": 0.0001971199341699239,
80
- "loss": 1.3939,
81
- "step": 240
82
- },
83
- {
84
- "epoch": 0.03,
85
- "learning_rate": 0.00019670849619419874,
86
- "loss": 1.3883,
87
- "step": 260
88
- },
89
- {
90
- "epoch": 0.03,
91
- "learning_rate": 0.00019629705821847356,
92
- "loss": 1.3257,
93
- "step": 280
94
- },
95
- {
96
- "epoch": 0.03,
97
- "learning_rate": 0.0001958856202427484,
98
- "loss": 1.386,
99
- "step": 300
100
- },
101
- {
102
- "epoch": 0.03,
103
- "learning_rate": 0.00019547418226702326,
104
- "loss": 1.3746,
105
- "step": 320
106
- },
107
- {
108
- "epoch": 0.03,
109
- "learning_rate": 0.0001950627442912981,
110
- "loss": 1.3266,
111
- "step": 340
112
- },
113
- {
114
- "epoch": 0.04,
115
- "learning_rate": 0.00019465130631557293,
116
- "loss": 1.3591,
117
- "step": 360
118
- },
119
- {
120
- "epoch": 0.04,
121
- "learning_rate": 0.00019423986833984777,
122
- "loss": 1.3464,
123
- "step": 380
124
- },
125
- {
126
- "epoch": 0.04,
127
- "learning_rate": 0.00019382843036412262,
128
- "loss": 1.3573,
129
- "step": 400
130
- },
131
- {
132
- "epoch": 0.04,
133
- "learning_rate": 0.00019341699238839744,
134
- "loss": 1.3455,
135
- "step": 420
136
- },
137
- {
138
- "epoch": 0.04,
139
- "learning_rate": 0.0001930055544126723,
140
- "loss": 1.3223,
141
- "step": 440
142
- },
143
- {
144
- "epoch": 0.05,
145
- "learning_rate": 0.00019259411643694714,
146
- "loss": 1.3293,
147
- "step": 460
148
- },
149
- {
150
- "epoch": 0.05,
151
- "learning_rate": 0.000192182678461222,
152
- "loss": 1.3033,
153
- "step": 480
154
- },
155
- {
156
- "epoch": 0.05,
157
- "learning_rate": 0.0001917712404854968,
158
- "loss": 1.3323,
159
- "step": 500
160
- },
161
- {
162
- "epoch": 0.05,
163
- "learning_rate": 0.00019135980250977166,
164
- "loss": 1.2838,
165
- "step": 520
166
- },
167
- {
168
- "epoch": 0.05,
169
- "learning_rate": 0.0001909483645340465,
170
- "loss": 1.332,
171
- "step": 540
172
- },
173
- {
174
- "epoch": 0.06,
175
- "learning_rate": 0.00019053692655832133,
176
- "loss": 1.3118,
177
- "step": 560
178
- },
179
- {
180
- "epoch": 0.06,
181
- "learning_rate": 0.00019012548858259617,
182
- "loss": 1.3237,
183
- "step": 580
184
- },
185
- {
186
- "epoch": 0.06,
187
- "learning_rate": 0.00018971405060687102,
188
- "loss": 1.2541,
189
- "step": 600
190
- },
191
- {
192
- "epoch": 0.06,
193
- "learning_rate": 0.00018930261263114587,
194
- "loss": 1.28,
195
- "step": 620
196
- },
197
- {
198
- "epoch": 0.07,
199
- "learning_rate": 0.0001888911746554207,
200
- "loss": 1.231,
201
- "step": 640
202
- },
203
- {
204
- "epoch": 0.07,
205
- "learning_rate": 0.00018847973667969554,
206
- "loss": 1.2676,
207
- "step": 660
208
- },
209
- {
210
- "epoch": 0.07,
211
- "learning_rate": 0.0001880682987039704,
212
- "loss": 1.2909,
213
- "step": 680
214
- },
215
- {
216
- "epoch": 0.07,
217
- "learning_rate": 0.0001876568607282452,
218
- "loss": 1.2499,
219
- "step": 700
220
- },
221
- {
222
- "epoch": 0.07,
223
- "learning_rate": 0.00018724542275252006,
224
- "loss": 1.2679,
225
- "step": 720
226
- },
227
- {
228
- "epoch": 0.08,
229
- "learning_rate": 0.0001868339847767949,
230
- "loss": 1.2674,
231
- "step": 740
232
- },
233
- {
234
- "epoch": 0.08,
235
- "learning_rate": 0.00018642254680106975,
236
- "loss": 1.2736,
237
- "step": 760
238
- },
239
- {
240
- "epoch": 0.08,
241
- "learning_rate": 0.00018601110882534457,
242
- "loss": 1.2843,
243
- "step": 780
244
- },
245
- {
246
- "epoch": 0.08,
247
- "learning_rate": 0.00018559967084961942,
248
- "loss": 1.281,
249
- "step": 800
250
- },
251
- {
252
- "epoch": 0.08,
253
- "learning_rate": 0.00018518823287389427,
254
- "loss": 1.3699,
255
- "step": 820
256
- },
257
- {
258
- "epoch": 0.09,
259
- "learning_rate": 0.0001847767948981691,
260
- "loss": 1.2705,
261
- "step": 840
262
- },
263
- {
264
- "epoch": 0.09,
265
- "learning_rate": 0.00018436535692244394,
266
- "loss": 1.2279,
267
- "step": 860
268
- },
269
- {
270
- "epoch": 0.09,
271
- "learning_rate": 0.0001839539189467188,
272
- "loss": 1.2779,
273
- "step": 880
274
- },
275
- {
276
- "epoch": 0.09,
277
- "learning_rate": 0.00018354248097099364,
278
- "loss": 1.2086,
279
- "step": 900
280
- },
281
- {
282
- "epoch": 0.09,
283
- "learning_rate": 0.00018313104299526846,
284
- "loss": 1.2999,
285
- "step": 920
286
- },
287
- {
288
- "epoch": 0.1,
289
- "learning_rate": 0.0001827196050195433,
290
- "loss": 1.2503,
291
- "step": 940
292
- },
293
- {
294
- "epoch": 0.1,
295
- "learning_rate": 0.00018230816704381815,
296
- "loss": 1.2466,
297
- "step": 960
298
- },
299
- {
300
- "epoch": 0.1,
301
- "learning_rate": 0.00018189672906809297,
302
- "loss": 1.2113,
303
- "step": 980
304
- },
305
- {
306
- "epoch": 0.1,
307
- "learning_rate": 0.00018148529109236782,
308
- "loss": 1.2356,
309
- "step": 1000
310
- },
311
- {
312
- "epoch": 0.1,
313
- "learning_rate": 0.00018107385311664267,
314
- "loss": 1.2631,
315
- "step": 1020
316
- },
317
- {
318
- "epoch": 0.11,
319
- "learning_rate": 0.00018066241514091752,
320
- "loss": 1.2443,
321
- "step": 1040
322
- },
323
- {
324
- "epoch": 0.11,
325
- "learning_rate": 0.00018025097716519234,
326
- "loss": 1.2406,
327
- "step": 1060
328
- },
329
- {
330
- "epoch": 0.11,
331
- "learning_rate": 0.0001798395391894672,
332
- "loss": 1.2308,
333
- "step": 1080
334
- },
335
- {
336
- "epoch": 0.11,
337
- "learning_rate": 0.00017942810121374204,
338
- "loss": 1.2649,
339
- "step": 1100
340
- },
341
- {
342
- "epoch": 0.11,
343
- "learning_rate": 0.00017901666323801686,
344
- "loss": 1.2263,
345
- "step": 1120
346
- },
347
- {
348
- "epoch": 0.12,
349
- "learning_rate": 0.0001786052252622917,
350
- "loss": 1.2869,
351
- "step": 1140
352
- },
353
- {
354
- "epoch": 0.12,
355
- "learning_rate": 0.00017819378728656655,
356
- "loss": 1.2255,
357
- "step": 1160
358
- },
359
- {
360
- "epoch": 0.12,
361
- "learning_rate": 0.0001777823493108414,
362
- "loss": 1.2596,
363
- "step": 1180
364
- },
365
- {
366
- "epoch": 0.12,
367
- "learning_rate": 0.00017737091133511622,
368
- "loss": 1.2748,
369
- "step": 1200
370
- },
371
- {
372
- "epoch": 0.12,
373
- "learning_rate": 0.00017695947335939107,
374
- "loss": 1.2587,
375
- "step": 1220
376
- },
377
- {
378
- "epoch": 0.13,
379
- "learning_rate": 0.00017654803538366592,
380
- "loss": 1.2651,
381
- "step": 1240
382
- },
383
- {
384
- "epoch": 0.13,
385
- "learning_rate": 0.00017613659740794074,
386
- "loss": 1.2659,
387
- "step": 1260
388
- },
389
- {
390
- "epoch": 0.13,
391
- "learning_rate": 0.0001757251594322156,
392
- "loss": 1.2077,
393
- "step": 1280
394
- },
395
- {
396
- "epoch": 0.13,
397
- "learning_rate": 0.00017531372145649044,
398
- "loss": 1.25,
399
- "step": 1300
400
- },
401
- {
402
- "epoch": 0.13,
403
- "learning_rate": 0.00017490228348076528,
404
- "loss": 1.2149,
405
- "step": 1320
406
- },
407
- {
408
- "epoch": 0.14,
409
- "learning_rate": 0.0001744908455050401,
410
- "loss": 1.2417,
411
- "step": 1340
412
- },
413
- {
414
- "epoch": 0.14,
415
- "learning_rate": 0.00017407940752931498,
416
- "loss": 1.1939,
417
- "step": 1360
418
- },
419
- {
420
- "epoch": 0.14,
421
- "learning_rate": 0.00017366796955358983,
422
- "loss": 1.2688,
423
- "step": 1380
424
- },
425
- {
426
- "epoch": 0.14,
427
- "learning_rate": 0.00017325653157786465,
428
- "loss": 1.2287,
429
- "step": 1400
430
- },
431
- {
432
- "epoch": 0.14,
433
- "learning_rate": 0.0001728450936021395,
434
- "loss": 1.2931,
435
- "step": 1420
436
- },
437
- {
438
- "epoch": 0.15,
439
- "learning_rate": 0.00017243365562641435,
440
- "loss": 1.2695,
441
- "step": 1440
442
- },
443
- {
444
- "epoch": 0.15,
445
- "learning_rate": 0.00017202221765068917,
446
- "loss": 1.2228,
447
- "step": 1460
448
- },
449
- {
450
- "epoch": 0.15,
451
- "learning_rate": 0.00017161077967496401,
452
- "loss": 1.2419,
453
- "step": 1480
454
- },
455
- {
456
- "epoch": 0.15,
457
- "learning_rate": 0.00017119934169923886,
458
- "loss": 1.2483,
459
- "step": 1500
460
- },
461
- {
462
- "epoch": 0.15,
463
- "learning_rate": 0.0001707879037235137,
464
- "loss": 1.2144,
465
- "step": 1520
466
- },
467
- {
468
- "epoch": 0.16,
469
- "learning_rate": 0.00017037646574778853,
470
- "loss": 1.2148,
471
- "step": 1540
472
- },
473
- {
474
- "epoch": 0.16,
475
- "learning_rate": 0.00016996502777206338,
476
- "loss": 1.2196,
477
- "step": 1560
478
- },
479
- {
480
- "epoch": 0.16,
481
- "learning_rate": 0.00016955358979633823,
482
- "loss": 1.2581,
483
- "step": 1580
484
- },
485
- {
486
- "epoch": 0.16,
487
- "learning_rate": 0.00016914215182061305,
488
- "loss": 1.2414,
489
- "step": 1600
490
- },
491
- {
492
- "epoch": 0.16,
493
- "learning_rate": 0.0001687307138448879,
494
- "loss": 1.2357,
495
- "step": 1620
496
- },
497
- {
498
- "epoch": 0.17,
499
- "learning_rate": 0.00016831927586916274,
500
- "loss": 1.22,
501
- "step": 1640
502
- },
503
- {
504
- "epoch": 0.17,
505
- "learning_rate": 0.0001679078378934376,
506
- "loss": 1.2234,
507
- "step": 1660
508
- },
509
- {
510
- "epoch": 0.17,
511
- "learning_rate": 0.00016749639991771241,
512
- "loss": 1.2291,
513
- "step": 1680
514
- },
515
- {
516
- "epoch": 0.17,
517
- "learning_rate": 0.00016708496194198726,
518
- "loss": 1.2344,
519
- "step": 1700
520
- },
521
- {
522
- "epoch": 0.18,
523
- "learning_rate": 0.0001666735239662621,
524
- "loss": 1.1987,
525
- "step": 1720
526
- },
527
- {
528
- "epoch": 0.18,
529
- "learning_rate": 0.00016626208599053693,
530
- "loss": 1.2232,
531
- "step": 1740
532
- },
533
- {
534
- "epoch": 0.18,
535
- "learning_rate": 0.00016585064801481178,
536
- "loss": 1.2402,
537
- "step": 1760
538
- },
539
- {
540
- "epoch": 0.18,
541
- "learning_rate": 0.00016543921003908663,
542
- "loss": 1.1475,
543
- "step": 1780
544
- },
545
- {
546
- "epoch": 0.18,
547
- "learning_rate": 0.00016502777206336148,
548
- "loss": 1.272,
549
- "step": 1800
550
- },
551
- {
552
- "epoch": 0.19,
553
- "learning_rate": 0.0001646163340876363,
554
- "loss": 1.2369,
555
- "step": 1820
556
- },
557
- {
558
- "epoch": 0.19,
559
- "learning_rate": 0.00016420489611191114,
560
- "loss": 1.212,
561
- "step": 1840
562
- },
563
- {
564
- "epoch": 0.19,
565
- "learning_rate": 0.000163793458136186,
566
- "loss": 1.2191,
567
- "step": 1860
568
- },
569
- {
570
- "epoch": 0.19,
571
- "learning_rate": 0.00016338202016046081,
572
- "loss": 1.1953,
573
- "step": 1880
574
- },
575
- {
576
- "epoch": 0.19,
577
- "learning_rate": 0.00016297058218473566,
578
- "loss": 1.2126,
579
- "step": 1900
580
- },
581
- {
582
- "epoch": 0.2,
583
- "learning_rate": 0.0001625591442090105,
584
- "loss": 1.2396,
585
- "step": 1920
586
- },
587
- {
588
- "epoch": 0.2,
589
- "learning_rate": 0.00016214770623328536,
590
- "loss": 1.1468,
591
- "step": 1940
592
- },
593
- {
594
- "epoch": 0.2,
595
- "learning_rate": 0.00016173626825756018,
596
- "loss": 1.1847,
597
- "step": 1960
598
- },
599
- {
600
- "epoch": 0.2,
601
- "learning_rate": 0.00016132483028183503,
602
- "loss": 1.2214,
603
- "step": 1980
604
- },
605
- {
606
- "epoch": 0.2,
607
- "learning_rate": 0.00016091339230610988,
608
- "loss": 1.2138,
609
- "step": 2000
610
- },
611
- {
612
- "epoch": 0.21,
613
- "learning_rate": 0.0001605019543303847,
614
- "loss": 1.2158,
615
- "step": 2020
616
- },
617
- {
618
- "epoch": 0.21,
619
- "learning_rate": 0.00016009051635465954,
620
- "loss": 1.2065,
621
- "step": 2040
622
- },
623
- {
624
- "epoch": 0.21,
625
- "learning_rate": 0.0001596790783789344,
626
- "loss": 1.2048,
627
- "step": 2060
628
- },
629
- {
630
- "epoch": 0.21,
631
- "learning_rate": 0.00015926764040320924,
632
- "loss": 1.1904,
633
- "step": 2080
634
- },
635
- {
636
- "epoch": 0.21,
637
- "learning_rate": 0.00015885620242748406,
638
- "loss": 1.1872,
639
- "step": 2100
640
- },
641
- {
642
- "epoch": 0.22,
643
- "learning_rate": 0.0001584447644517589,
644
- "loss": 1.2087,
645
- "step": 2120
646
- },
647
- {
648
- "epoch": 0.22,
649
- "learning_rate": 0.00015803332647603376,
650
- "loss": 1.1909,
651
- "step": 2140
652
- },
653
- {
654
- "epoch": 0.22,
655
- "learning_rate": 0.00015762188850030858,
656
- "loss": 1.2609,
657
- "step": 2160
658
- },
659
- {
660
- "epoch": 0.22,
661
- "learning_rate": 0.00015721045052458343,
662
- "loss": 1.2083,
663
- "step": 2180
664
- },
665
- {
666
- "epoch": 0.22,
667
- "learning_rate": 0.00015679901254885827,
668
- "loss": 1.2205,
669
- "step": 2200
670
- },
671
- {
672
- "epoch": 0.23,
673
- "learning_rate": 0.00015638757457313312,
674
- "loss": 1.1966,
675
- "step": 2220
676
- },
677
- {
678
- "epoch": 0.23,
679
- "learning_rate": 0.00015597613659740794,
680
- "loss": 1.235,
681
- "step": 2240
682
- },
683
- {
684
- "epoch": 0.23,
685
- "learning_rate": 0.0001555646986216828,
686
- "loss": 1.2488,
687
- "step": 2260
688
- },
689
- {
690
- "epoch": 0.23,
691
- "learning_rate": 0.00015515326064595764,
692
- "loss": 1.2229,
693
- "step": 2280
694
- },
695
- {
696
- "epoch": 0.23,
697
- "learning_rate": 0.00015474182267023246,
698
- "loss": 1.1874,
699
- "step": 2300
700
- },
701
- {
702
- "epoch": 0.24,
703
- "learning_rate": 0.0001543303846945073,
704
- "loss": 1.1724,
705
- "step": 2320
706
- },
707
- {
708
- "epoch": 0.24,
709
- "learning_rate": 0.00015391894671878216,
710
- "loss": 1.1786,
711
- "step": 2340
712
- },
713
- {
714
- "epoch": 0.24,
715
- "learning_rate": 0.000153507508743057,
716
- "loss": 1.1913,
717
- "step": 2360
718
- },
719
- {
720
- "epoch": 0.24,
721
- "learning_rate": 0.00015309607076733183,
722
- "loss": 1.2138,
723
- "step": 2380
724
- },
725
- {
726
- "epoch": 0.24,
727
- "learning_rate": 0.00015268463279160667,
728
- "loss": 1.1954,
729
- "step": 2400
730
- },
731
- {
732
- "epoch": 0.25,
733
- "learning_rate": 0.00015227319481588152,
734
- "loss": 1.1926,
735
- "step": 2420
736
- },
737
- {
738
- "epoch": 0.25,
739
- "learning_rate": 0.00015186175684015634,
740
- "loss": 1.1893,
741
- "step": 2440
742
- },
743
- {
744
- "epoch": 0.25,
745
- "learning_rate": 0.0001514503188644312,
746
- "loss": 1.2152,
747
- "step": 2460
748
- },
749
- {
750
- "epoch": 0.25,
751
- "learning_rate": 0.00015103888088870604,
752
- "loss": 1.199,
753
- "step": 2480
754
- },
755
- {
756
- "epoch": 0.25,
757
- "learning_rate": 0.0001506274429129809,
758
- "loss": 1.1966,
759
- "step": 2500
760
- }
761
- ],
762
- "logging_steps": 20,
763
- "max_steps": 9822,
764
- "num_train_epochs": 1,
765
- "save_steps": 500,
766
- "total_flos": 3.630490997971968e+16,
767
- "trial_name": null,
768
- "trial_params": null
769
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2500/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8819fc087370c0c0dd1869922822cf7a5ebe84fa7a7194c69a0ec917ff22569b
3
- size 4027
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3000/README.md DELETED
@@ -1,21 +0,0 @@
1
- ---
2
- library_name: peft
3
- ---
4
- ## Training procedure
5
-
6
-
7
- The following `bitsandbytes` quantization config was used during training:
8
- - quant_method: QuantizationMethod.BITS_AND_BYTES
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: True
17
- - bnb_4bit_compute_dtype: bfloat16
18
- ### Framework versions
19
-
20
-
21
- - PEFT 0.4.0.dev0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3000/adapter_config.json DELETED
@@ -1,21 +0,0 @@
1
- {
2
- "base_model_name_or_path": "codellama/CodeLlama-13b-Instruct-hf",
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": 8,
14
- "revision": null,
15
- "target_modules": [
16
- "q_proj",
17
- "k_proj",
18
- "v_proj"
19
- ],
20
- "task_type": "CAUSAL_LM"
21
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3000/adapter_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1cdf1a21aa36468ca7324817c18dbea0d9c993caad72356c80f67ad27c5adec
3
- size 39407821
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3000/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc724ccb44ba7121ad649ed5a9f6f1072058b00e8e1ed4b66ffeff3b1cf5b498
3
- size 78844165
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3000/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bfdf34f826fc1a3a954cb62126716372e4d6d4979b90192aa8b2d7bd0eb6172
3
- size 14575
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3000/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca081c200d1f1cff74b76fe2637a142c241d77bc5919ab25bcff1d4293ebf505
3
- size 627
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3000/trainer_state.json DELETED
@@ -1,919 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 0.3054328874861601,
5
- "eval_steps": 500,
6
- "global_step": 3000,
7
- "is_hyper_param_search": false,
8
- "is_local_process_zero": true,
9
- "is_world_process_zero": true,
10
- "log_history": [
11
- {
12
- "epoch": 0.0,
13
- "learning_rate": 4e-05,
14
- "loss": 3.5766,
15
- "step": 20
16
- },
17
- {
18
- "epoch": 0.0,
19
- "learning_rate": 8e-05,
20
- "loss": 2.9038,
21
- "step": 40
22
- },
23
- {
24
- "epoch": 0.01,
25
- "learning_rate": 0.00012,
26
- "loss": 1.9072,
27
- "step": 60
28
- },
29
- {
30
- "epoch": 0.01,
31
- "learning_rate": 0.00016,
32
- "loss": 1.7359,
33
- "step": 80
34
- },
35
- {
36
- "epoch": 0.01,
37
- "learning_rate": 0.0002,
38
- "loss": 1.5349,
39
- "step": 100
40
- },
41
- {
42
- "epoch": 0.01,
43
- "learning_rate": 0.00019958856202427486,
44
- "loss": 1.4908,
45
- "step": 120
46
- },
47
- {
48
- "epoch": 0.01,
49
- "learning_rate": 0.00019917712404854968,
50
- "loss": 1.4931,
51
- "step": 140
52
- },
53
- {
54
- "epoch": 0.02,
55
- "learning_rate": 0.00019876568607282453,
56
- "loss": 1.4201,
57
- "step": 160
58
- },
59
- {
60
- "epoch": 0.02,
61
- "learning_rate": 0.00019835424809709937,
62
- "loss": 1.4541,
63
- "step": 180
64
- },
65
- {
66
- "epoch": 0.02,
67
- "learning_rate": 0.00019794281012137422,
68
- "loss": 1.4102,
69
- "step": 200
70
- },
71
- {
72
- "epoch": 0.02,
73
- "learning_rate": 0.00019753137214564904,
74
- "loss": 1.3861,
75
- "step": 220
76
- },
77
- {
78
- "epoch": 0.02,
79
- "learning_rate": 0.0001971199341699239,
80
- "loss": 1.3939,
81
- "step": 240
82
- },
83
- {
84
- "epoch": 0.03,
85
- "learning_rate": 0.00019670849619419874,
86
- "loss": 1.3883,
87
- "step": 260
88
- },
89
- {
90
- "epoch": 0.03,
91
- "learning_rate": 0.00019629705821847356,
92
- "loss": 1.3257,
93
- "step": 280
94
- },
95
- {
96
- "epoch": 0.03,
97
- "learning_rate": 0.0001958856202427484,
98
- "loss": 1.386,
99
- "step": 300
100
- },
101
- {
102
- "epoch": 0.03,
103
- "learning_rate": 0.00019547418226702326,
104
- "loss": 1.3746,
105
- "step": 320
106
- },
107
- {
108
- "epoch": 0.03,
109
- "learning_rate": 0.0001950627442912981,
110
- "loss": 1.3266,
111
- "step": 340
112
- },
113
- {
114
- "epoch": 0.04,
115
- "learning_rate": 0.00019465130631557293,
116
- "loss": 1.3591,
117
- "step": 360
118
- },
119
- {
120
- "epoch": 0.04,
121
- "learning_rate": 0.00019423986833984777,
122
- "loss": 1.3464,
123
- "step": 380
124
- },
125
- {
126
- "epoch": 0.04,
127
- "learning_rate": 0.00019382843036412262,
128
- "loss": 1.3573,
129
- "step": 400
130
- },
131
- {
132
- "epoch": 0.04,
133
- "learning_rate": 0.00019341699238839744,
134
- "loss": 1.3455,
135
- "step": 420
136
- },
137
- {
138
- "epoch": 0.04,
139
- "learning_rate": 0.0001930055544126723,
140
- "loss": 1.3223,
141
- "step": 440
142
- },
143
- {
144
- "epoch": 0.05,
145
- "learning_rate": 0.00019259411643694714,
146
- "loss": 1.3293,
147
- "step": 460
148
- },
149
- {
150
- "epoch": 0.05,
151
- "learning_rate": 0.000192182678461222,
152
- "loss": 1.3033,
153
- "step": 480
154
- },
155
- {
156
- "epoch": 0.05,
157
- "learning_rate": 0.0001917712404854968,
158
- "loss": 1.3323,
159
- "step": 500
160
- },
161
- {
162
- "epoch": 0.05,
163
- "learning_rate": 0.00019135980250977166,
164
- "loss": 1.2838,
165
- "step": 520
166
- },
167
- {
168
- "epoch": 0.05,
169
- "learning_rate": 0.0001909483645340465,
170
- "loss": 1.332,
171
- "step": 540
172
- },
173
- {
174
- "epoch": 0.06,
175
- "learning_rate": 0.00019053692655832133,
176
- "loss": 1.3118,
177
- "step": 560
178
- },
179
- {
180
- "epoch": 0.06,
181
- "learning_rate": 0.00019012548858259617,
182
- "loss": 1.3237,
183
- "step": 580
184
- },
185
- {
186
- "epoch": 0.06,
187
- "learning_rate": 0.00018971405060687102,
188
- "loss": 1.2541,
189
- "step": 600
190
- },
191
- {
192
- "epoch": 0.06,
193
- "learning_rate": 0.00018930261263114587,
194
- "loss": 1.28,
195
- "step": 620
196
- },
197
- {
198
- "epoch": 0.07,
199
- "learning_rate": 0.0001888911746554207,
200
- "loss": 1.231,
201
- "step": 640
202
- },
203
- {
204
- "epoch": 0.07,
205
- "learning_rate": 0.00018847973667969554,
206
- "loss": 1.2676,
207
- "step": 660
208
- },
209
- {
210
- "epoch": 0.07,
211
- "learning_rate": 0.0001880682987039704,
212
- "loss": 1.2909,
213
- "step": 680
214
- },
215
- {
216
- "epoch": 0.07,
217
- "learning_rate": 0.0001876568607282452,
218
- "loss": 1.2499,
219
- "step": 700
220
- },
221
- {
222
- "epoch": 0.07,
223
- "learning_rate": 0.00018724542275252006,
224
- "loss": 1.2679,
225
- "step": 720
226
- },
227
- {
228
- "epoch": 0.08,
229
- "learning_rate": 0.0001868339847767949,
230
- "loss": 1.2674,
231
- "step": 740
232
- },
233
- {
234
- "epoch": 0.08,
235
- "learning_rate": 0.00018642254680106975,
236
- "loss": 1.2736,
237
- "step": 760
238
- },
239
- {
240
- "epoch": 0.08,
241
- "learning_rate": 0.00018601110882534457,
242
- "loss": 1.2843,
243
- "step": 780
244
- },
245
- {
246
- "epoch": 0.08,
247
- "learning_rate": 0.00018559967084961942,
248
- "loss": 1.281,
249
- "step": 800
250
- },
251
- {
252
- "epoch": 0.08,
253
- "learning_rate": 0.00018518823287389427,
254
- "loss": 1.3699,
255
- "step": 820
256
- },
257
- {
258
- "epoch": 0.09,
259
- "learning_rate": 0.0001847767948981691,
260
- "loss": 1.2705,
261
- "step": 840
262
- },
263
- {
264
- "epoch": 0.09,
265
- "learning_rate": 0.00018436535692244394,
266
- "loss": 1.2279,
267
- "step": 860
268
- },
269
- {
270
- "epoch": 0.09,
271
- "learning_rate": 0.0001839539189467188,
272
- "loss": 1.2779,
273
- "step": 880
274
- },
275
- {
276
- "epoch": 0.09,
277
- "learning_rate": 0.00018354248097099364,
278
- "loss": 1.2086,
279
- "step": 900
280
- },
281
- {
282
- "epoch": 0.09,
283
- "learning_rate": 0.00018313104299526846,
284
- "loss": 1.2999,
285
- "step": 920
286
- },
287
- {
288
- "epoch": 0.1,
289
- "learning_rate": 0.0001827196050195433,
290
- "loss": 1.2503,
291
- "step": 940
292
- },
293
- {
294
- "epoch": 0.1,
295
- "learning_rate": 0.00018230816704381815,
296
- "loss": 1.2466,
297
- "step": 960
298
- },
299
- {
300
- "epoch": 0.1,
301
- "learning_rate": 0.00018189672906809297,
302
- "loss": 1.2113,
303
- "step": 980
304
- },
305
- {
306
- "epoch": 0.1,
307
- "learning_rate": 0.00018148529109236782,
308
- "loss": 1.2356,
309
- "step": 1000
310
- },
311
- {
312
- "epoch": 0.1,
313
- "learning_rate": 0.00018107385311664267,
314
- "loss": 1.2631,
315
- "step": 1020
316
- },
317
- {
318
- "epoch": 0.11,
319
- "learning_rate": 0.00018066241514091752,
320
- "loss": 1.2443,
321
- "step": 1040
322
- },
323
- {
324
- "epoch": 0.11,
325
- "learning_rate": 0.00018025097716519234,
326
- "loss": 1.2406,
327
- "step": 1060
328
- },
329
- {
330
- "epoch": 0.11,
331
- "learning_rate": 0.0001798395391894672,
332
- "loss": 1.2308,
333
- "step": 1080
334
- },
335
- {
336
- "epoch": 0.11,
337
- "learning_rate": 0.00017942810121374204,
338
- "loss": 1.2649,
339
- "step": 1100
340
- },
341
- {
342
- "epoch": 0.11,
343
- "learning_rate": 0.00017901666323801686,
344
- "loss": 1.2263,
345
- "step": 1120
346
- },
347
- {
348
- "epoch": 0.12,
349
- "learning_rate": 0.0001786052252622917,
350
- "loss": 1.2869,
351
- "step": 1140
352
- },
353
- {
354
- "epoch": 0.12,
355
- "learning_rate": 0.00017819378728656655,
356
- "loss": 1.2255,
357
- "step": 1160
358
- },
359
- {
360
- "epoch": 0.12,
361
- "learning_rate": 0.0001777823493108414,
362
- "loss": 1.2596,
363
- "step": 1180
364
- },
365
- {
366
- "epoch": 0.12,
367
- "learning_rate": 0.00017737091133511622,
368
- "loss": 1.2748,
369
- "step": 1200
370
- },
371
- {
372
- "epoch": 0.12,
373
- "learning_rate": 0.00017695947335939107,
374
- "loss": 1.2587,
375
- "step": 1220
376
- },
377
- {
378
- "epoch": 0.13,
379
- "learning_rate": 0.00017654803538366592,
380
- "loss": 1.2651,
381
- "step": 1240
382
- },
383
- {
384
- "epoch": 0.13,
385
- "learning_rate": 0.00017613659740794074,
386
- "loss": 1.2659,
387
- "step": 1260
388
- },
389
- {
390
- "epoch": 0.13,
391
- "learning_rate": 0.0001757251594322156,
392
- "loss": 1.2077,
393
- "step": 1280
394
- },
395
- {
396
- "epoch": 0.13,
397
- "learning_rate": 0.00017531372145649044,
398
- "loss": 1.25,
399
- "step": 1300
400
- },
401
- {
402
- "epoch": 0.13,
403
- "learning_rate": 0.00017490228348076528,
404
- "loss": 1.2149,
405
- "step": 1320
406
- },
407
- {
408
- "epoch": 0.14,
409
- "learning_rate": 0.0001744908455050401,
410
- "loss": 1.2417,
411
- "step": 1340
412
- },
413
- {
414
- "epoch": 0.14,
415
- "learning_rate": 0.00017407940752931498,
416
- "loss": 1.1939,
417
- "step": 1360
418
- },
419
- {
420
- "epoch": 0.14,
421
- "learning_rate": 0.00017366796955358983,
422
- "loss": 1.2688,
423
- "step": 1380
424
- },
425
- {
426
- "epoch": 0.14,
427
- "learning_rate": 0.00017325653157786465,
428
- "loss": 1.2287,
429
- "step": 1400
430
- },
431
- {
432
- "epoch": 0.14,
433
- "learning_rate": 0.0001728450936021395,
434
- "loss": 1.2931,
435
- "step": 1420
436
- },
437
- {
438
- "epoch": 0.15,
439
- "learning_rate": 0.00017243365562641435,
440
- "loss": 1.2695,
441
- "step": 1440
442
- },
443
- {
444
- "epoch": 0.15,
445
- "learning_rate": 0.00017202221765068917,
446
- "loss": 1.2228,
447
- "step": 1460
448
- },
449
- {
450
- "epoch": 0.15,
451
- "learning_rate": 0.00017161077967496401,
452
- "loss": 1.2419,
453
- "step": 1480
454
- },
455
- {
456
- "epoch": 0.15,
457
- "learning_rate": 0.00017119934169923886,
458
- "loss": 1.2483,
459
- "step": 1500
460
- },
461
- {
462
- "epoch": 0.15,
463
- "learning_rate": 0.0001707879037235137,
464
- "loss": 1.2144,
465
- "step": 1520
466
- },
467
- {
468
- "epoch": 0.16,
469
- "learning_rate": 0.00017037646574778853,
470
- "loss": 1.2148,
471
- "step": 1540
472
- },
473
- {
474
- "epoch": 0.16,
475
- "learning_rate": 0.00016996502777206338,
476
- "loss": 1.2196,
477
- "step": 1560
478
- },
479
- {
480
- "epoch": 0.16,
481
- "learning_rate": 0.00016955358979633823,
482
- "loss": 1.2581,
483
- "step": 1580
484
- },
485
- {
486
- "epoch": 0.16,
487
- "learning_rate": 0.00016914215182061305,
488
- "loss": 1.2414,
489
- "step": 1600
490
- },
491
- {
492
- "epoch": 0.16,
493
- "learning_rate": 0.0001687307138448879,
494
- "loss": 1.2357,
495
- "step": 1620
496
- },
497
- {
498
- "epoch": 0.17,
499
- "learning_rate": 0.00016831927586916274,
500
- "loss": 1.22,
501
- "step": 1640
502
- },
503
- {
504
- "epoch": 0.17,
505
- "learning_rate": 0.0001679078378934376,
506
- "loss": 1.2234,
507
- "step": 1660
508
- },
509
- {
510
- "epoch": 0.17,
511
- "learning_rate": 0.00016749639991771241,
512
- "loss": 1.2291,
513
- "step": 1680
514
- },
515
- {
516
- "epoch": 0.17,
517
- "learning_rate": 0.00016708496194198726,
518
- "loss": 1.2344,
519
- "step": 1700
520
- },
521
- {
522
- "epoch": 0.18,
523
- "learning_rate": 0.0001666735239662621,
524
- "loss": 1.1987,
525
- "step": 1720
526
- },
527
- {
528
- "epoch": 0.18,
529
- "learning_rate": 0.00016626208599053693,
530
- "loss": 1.2232,
531
- "step": 1740
532
- },
533
- {
534
- "epoch": 0.18,
535
- "learning_rate": 0.00016585064801481178,
536
- "loss": 1.2402,
537
- "step": 1760
538
- },
539
- {
540
- "epoch": 0.18,
541
- "learning_rate": 0.00016543921003908663,
542
- "loss": 1.1475,
543
- "step": 1780
544
- },
545
- {
546
- "epoch": 0.18,
547
- "learning_rate": 0.00016502777206336148,
548
- "loss": 1.272,
549
- "step": 1800
550
- },
551
- {
552
- "epoch": 0.19,
553
- "learning_rate": 0.0001646163340876363,
554
- "loss": 1.2369,
555
- "step": 1820
556
- },
557
- {
558
- "epoch": 0.19,
559
- "learning_rate": 0.00016420489611191114,
560
- "loss": 1.212,
561
- "step": 1840
562
- },
563
- {
564
- "epoch": 0.19,
565
- "learning_rate": 0.000163793458136186,
566
- "loss": 1.2191,
567
- "step": 1860
568
- },
569
- {
570
- "epoch": 0.19,
571
- "learning_rate": 0.00016338202016046081,
572
- "loss": 1.1953,
573
- "step": 1880
574
- },
575
- {
576
- "epoch": 0.19,
577
- "learning_rate": 0.00016297058218473566,
578
- "loss": 1.2126,
579
- "step": 1900
580
- },
581
- {
582
- "epoch": 0.2,
583
- "learning_rate": 0.0001625591442090105,
584
- "loss": 1.2396,
585
- "step": 1920
586
- },
587
- {
588
- "epoch": 0.2,
589
- "learning_rate": 0.00016214770623328536,
590
- "loss": 1.1468,
591
- "step": 1940
592
- },
593
- {
594
- "epoch": 0.2,
595
- "learning_rate": 0.00016173626825756018,
596
- "loss": 1.1847,
597
- "step": 1960
598
- },
599
- {
600
- "epoch": 0.2,
601
- "learning_rate": 0.00016132483028183503,
602
- "loss": 1.2214,
603
- "step": 1980
604
- },
605
- {
606
- "epoch": 0.2,
607
- "learning_rate": 0.00016091339230610988,
608
- "loss": 1.2138,
609
- "step": 2000
610
- },
611
- {
612
- "epoch": 0.21,
613
- "learning_rate": 0.0001605019543303847,
614
- "loss": 1.2158,
615
- "step": 2020
616
- },
617
- {
618
- "epoch": 0.21,
619
- "learning_rate": 0.00016009051635465954,
620
- "loss": 1.2065,
621
- "step": 2040
622
- },
623
- {
624
- "epoch": 0.21,
625
- "learning_rate": 0.0001596790783789344,
626
- "loss": 1.2048,
627
- "step": 2060
628
- },
629
- {
630
- "epoch": 0.21,
631
- "learning_rate": 0.00015926764040320924,
632
- "loss": 1.1904,
633
- "step": 2080
634
- },
635
- {
636
- "epoch": 0.21,
637
- "learning_rate": 0.00015885620242748406,
638
- "loss": 1.1872,
639
- "step": 2100
640
- },
641
- {
642
- "epoch": 0.22,
643
- "learning_rate": 0.0001584447644517589,
644
- "loss": 1.2087,
645
- "step": 2120
646
- },
647
- {
648
- "epoch": 0.22,
649
- "learning_rate": 0.00015803332647603376,
650
- "loss": 1.1909,
651
- "step": 2140
652
- },
653
- {
654
- "epoch": 0.22,
655
- "learning_rate": 0.00015762188850030858,
656
- "loss": 1.2609,
657
- "step": 2160
658
- },
659
- {
660
- "epoch": 0.22,
661
- "learning_rate": 0.00015721045052458343,
662
- "loss": 1.2083,
663
- "step": 2180
664
- },
665
- {
666
- "epoch": 0.22,
667
- "learning_rate": 0.00015679901254885827,
668
- "loss": 1.2205,
669
- "step": 2200
670
- },
671
- {
672
- "epoch": 0.23,
673
- "learning_rate": 0.00015638757457313312,
674
- "loss": 1.1966,
675
- "step": 2220
676
- },
677
- {
678
- "epoch": 0.23,
679
- "learning_rate": 0.00015597613659740794,
680
- "loss": 1.235,
681
- "step": 2240
682
- },
683
- {
684
- "epoch": 0.23,
685
- "learning_rate": 0.0001555646986216828,
686
- "loss": 1.2488,
687
- "step": 2260
688
- },
689
- {
690
- "epoch": 0.23,
691
- "learning_rate": 0.00015515326064595764,
692
- "loss": 1.2229,
693
- "step": 2280
694
- },
695
- {
696
- "epoch": 0.23,
697
- "learning_rate": 0.00015474182267023246,
698
- "loss": 1.1874,
699
- "step": 2300
700
- },
701
- {
702
- "epoch": 0.24,
703
- "learning_rate": 0.0001543303846945073,
704
- "loss": 1.1724,
705
- "step": 2320
706
- },
707
- {
708
- "epoch": 0.24,
709
- "learning_rate": 0.00015391894671878216,
710
- "loss": 1.1786,
711
- "step": 2340
712
- },
713
- {
714
- "epoch": 0.24,
715
- "learning_rate": 0.000153507508743057,
716
- "loss": 1.1913,
717
- "step": 2360
718
- },
719
- {
720
- "epoch": 0.24,
721
- "learning_rate": 0.00015309607076733183,
722
- "loss": 1.2138,
723
- "step": 2380
724
- },
725
- {
726
- "epoch": 0.24,
727
- "learning_rate": 0.00015268463279160667,
728
- "loss": 1.1954,
729
- "step": 2400
730
- },
731
- {
732
- "epoch": 0.25,
733
- "learning_rate": 0.00015227319481588152,
734
- "loss": 1.1926,
735
- "step": 2420
736
- },
737
- {
738
- "epoch": 0.25,
739
- "learning_rate": 0.00015186175684015634,
740
- "loss": 1.1893,
741
- "step": 2440
742
- },
743
- {
744
- "epoch": 0.25,
745
- "learning_rate": 0.0001514503188644312,
746
- "loss": 1.2152,
747
- "step": 2460
748
- },
749
- {
750
- "epoch": 0.25,
751
- "learning_rate": 0.00015103888088870604,
752
- "loss": 1.199,
753
- "step": 2480
754
- },
755
- {
756
- "epoch": 0.25,
757
- "learning_rate": 0.0001506274429129809,
758
- "loss": 1.1966,
759
- "step": 2500
760
- },
761
- {
762
- "epoch": 0.26,
763
- "learning_rate": 0.0001502160049372557,
764
- "loss": 1.2042,
765
- "step": 2520
766
- },
767
- {
768
- "epoch": 0.26,
769
- "learning_rate": 0.00014980456696153056,
770
- "loss": 1.1901,
771
- "step": 2540
772
- },
773
- {
774
- "epoch": 0.26,
775
- "learning_rate": 0.0001493931289858054,
776
- "loss": 1.2023,
777
- "step": 2560
778
- },
779
- {
780
- "epoch": 0.26,
781
- "learning_rate": 0.00014898169101008023,
782
- "loss": 1.1597,
783
- "step": 2580
784
- },
785
- {
786
- "epoch": 0.26,
787
- "learning_rate": 0.00014857025303435507,
788
- "loss": 1.1828,
789
- "step": 2600
790
- },
791
- {
792
- "epoch": 0.27,
793
- "learning_rate": 0.00014815881505862992,
794
- "loss": 1.1907,
795
- "step": 2620
796
- },
797
- {
798
- "epoch": 0.27,
799
- "learning_rate": 0.00014774737708290477,
800
- "loss": 1.1477,
801
- "step": 2640
802
- },
803
- {
804
- "epoch": 0.27,
805
- "learning_rate": 0.0001473359391071796,
806
- "loss": 1.2146,
807
- "step": 2660
808
- },
809
- {
810
- "epoch": 0.27,
811
- "learning_rate": 0.00014692450113145444,
812
- "loss": 1.2327,
813
- "step": 2680
814
- },
815
- {
816
- "epoch": 0.27,
817
- "learning_rate": 0.0001465130631557293,
818
- "loss": 1.1747,
819
- "step": 2700
820
- },
821
- {
822
- "epoch": 0.28,
823
- "learning_rate": 0.0001461016251800041,
824
- "loss": 1.1745,
825
- "step": 2720
826
- },
827
- {
828
- "epoch": 0.28,
829
- "learning_rate": 0.00014569018720427896,
830
- "loss": 1.1914,
831
- "step": 2740
832
- },
833
- {
834
- "epoch": 0.28,
835
- "learning_rate": 0.0001452787492285538,
836
- "loss": 1.1781,
837
- "step": 2760
838
- },
839
- {
840
- "epoch": 0.28,
841
- "learning_rate": 0.00014486731125282865,
842
- "loss": 1.1819,
843
- "step": 2780
844
- },
845
- {
846
- "epoch": 0.29,
847
- "learning_rate": 0.00014445587327710347,
848
- "loss": 1.1894,
849
- "step": 2800
850
- },
851
- {
852
- "epoch": 0.29,
853
- "learning_rate": 0.00014404443530137832,
854
- "loss": 1.2198,
855
- "step": 2820
856
- },
857
- {
858
- "epoch": 0.29,
859
- "learning_rate": 0.00014363299732565317,
860
- "loss": 1.1464,
861
- "step": 2840
862
- },
863
- {
864
- "epoch": 0.29,
865
- "learning_rate": 0.000143221559349928,
866
- "loss": 1.2039,
867
- "step": 2860
868
- },
869
- {
870
- "epoch": 0.29,
871
- "learning_rate": 0.00014281012137420284,
872
- "loss": 1.1758,
873
- "step": 2880
874
- },
875
- {
876
- "epoch": 0.3,
877
- "learning_rate": 0.0001423986833984777,
878
- "loss": 1.1958,
879
- "step": 2900
880
- },
881
- {
882
- "epoch": 0.3,
883
- "learning_rate": 0.00014198724542275254,
884
- "loss": 1.2163,
885
- "step": 2920
886
- },
887
- {
888
- "epoch": 0.3,
889
- "learning_rate": 0.00014157580744702736,
890
- "loss": 1.1724,
891
- "step": 2940
892
- },
893
- {
894
- "epoch": 0.3,
895
- "learning_rate": 0.0001411643694713022,
896
- "loss": 1.1339,
897
- "step": 2960
898
- },
899
- {
900
- "epoch": 0.3,
901
- "learning_rate": 0.00014075293149557705,
902
- "loss": 1.1752,
903
- "step": 2980
904
- },
905
- {
906
- "epoch": 0.31,
907
- "learning_rate": 0.00014034149351985187,
908
- "loss": 1.2221,
909
- "step": 3000
910
- }
911
- ],
912
- "logging_steps": 20,
913
- "max_steps": 9822,
914
- "num_train_epochs": 1,
915
- "save_steps": 500,
916
- "total_flos": 4.354600931033088e+16,
917
- "trial_name": null,
918
- "trial_params": null
919
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3000/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8819fc087370c0c0dd1869922822cf7a5ebe84fa7a7194c69a0ec917ff22569b
3
- size 4027
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3500/README.md DELETED
@@ -1,21 +0,0 @@
1
- ---
2
- library_name: peft
3
- ---
4
- ## Training procedure
5
-
6
-
7
- The following `bitsandbytes` quantization config was used during training:
8
- - quant_method: QuantizationMethod.BITS_AND_BYTES
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: True
17
- - bnb_4bit_compute_dtype: bfloat16
18
- ### Framework versions
19
-
20
-
21
- - PEFT 0.4.0.dev0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3500/adapter_config.json DELETED
@@ -1,21 +0,0 @@
1
- {
2
- "base_model_name_or_path": "codellama/CodeLlama-13b-Instruct-hf",
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": 8,
14
- "revision": null,
15
- "target_modules": [
16
- "q_proj",
17
- "k_proj",
18
- "v_proj"
19
- ],
20
- "task_type": "CAUSAL_LM"
21
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3500/adapter_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:521f84dabed28cf35859ef05146c0171c22391e57dea16b1e4d0556eb54e4e31
3
- size 39407821
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3500/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5422fc43dd6fd45aa435cf2033829bfbac9d5137da712d2b8184c9879cc062f3
3
- size 78844165
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3500/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7b184e8b069b3c1f57297aa4ec5d496c4e561754a274e25a0d6f7951852d0c7
3
- size 14575
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3500/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:902a812f67d1fbc515b8e9637f7a043a8e94503bc816c37f0218207b22ea285a
3
- size 627
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3500/trainer_state.json DELETED
@@ -1,1069 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 0.35633836873385344,
5
- "eval_steps": 500,
6
- "global_step": 3500,
7
- "is_hyper_param_search": false,
8
- "is_local_process_zero": true,
9
- "is_world_process_zero": true,
10
- "log_history": [
11
- {
12
- "epoch": 0.0,
13
- "learning_rate": 4e-05,
14
- "loss": 3.5766,
15
- "step": 20
16
- },
17
- {
18
- "epoch": 0.0,
19
- "learning_rate": 8e-05,
20
- "loss": 2.9038,
21
- "step": 40
22
- },
23
- {
24
- "epoch": 0.01,
25
- "learning_rate": 0.00012,
26
- "loss": 1.9072,
27
- "step": 60
28
- },
29
- {
30
- "epoch": 0.01,
31
- "learning_rate": 0.00016,
32
- "loss": 1.7359,
33
- "step": 80
34
- },
35
- {
36
- "epoch": 0.01,
37
- "learning_rate": 0.0002,
38
- "loss": 1.5349,
39
- "step": 100
40
- },
41
- {
42
- "epoch": 0.01,
43
- "learning_rate": 0.00019958856202427486,
44
- "loss": 1.4908,
45
- "step": 120
46
- },
47
- {
48
- "epoch": 0.01,
49
- "learning_rate": 0.00019917712404854968,
50
- "loss": 1.4931,
51
- "step": 140
52
- },
53
- {
54
- "epoch": 0.02,
55
- "learning_rate": 0.00019876568607282453,
56
- "loss": 1.4201,
57
- "step": 160
58
- },
59
- {
60
- "epoch": 0.02,
61
- "learning_rate": 0.00019835424809709937,
62
- "loss": 1.4541,
63
- "step": 180
64
- },
65
- {
66
- "epoch": 0.02,
67
- "learning_rate": 0.00019794281012137422,
68
- "loss": 1.4102,
69
- "step": 200
70
- },
71
- {
72
- "epoch": 0.02,
73
- "learning_rate": 0.00019753137214564904,
74
- "loss": 1.3861,
75
- "step": 220
76
- },
77
- {
78
- "epoch": 0.02,
79
- "learning_rate": 0.0001971199341699239,
80
- "loss": 1.3939,
81
- "step": 240
82
- },
83
- {
84
- "epoch": 0.03,
85
- "learning_rate": 0.00019670849619419874,
86
- "loss": 1.3883,
87
- "step": 260
88
- },
89
- {
90
- "epoch": 0.03,
91
- "learning_rate": 0.00019629705821847356,
92
- "loss": 1.3257,
93
- "step": 280
94
- },
95
- {
96
- "epoch": 0.03,
97
- "learning_rate": 0.0001958856202427484,
98
- "loss": 1.386,
99
- "step": 300
100
- },
101
- {
102
- "epoch": 0.03,
103
- "learning_rate": 0.00019547418226702326,
104
- "loss": 1.3746,
105
- "step": 320
106
- },
107
- {
108
- "epoch": 0.03,
109
- "learning_rate": 0.0001950627442912981,
110
- "loss": 1.3266,
111
- "step": 340
112
- },
113
- {
114
- "epoch": 0.04,
115
- "learning_rate": 0.00019465130631557293,
116
- "loss": 1.3591,
117
- "step": 360
118
- },
119
- {
120
- "epoch": 0.04,
121
- "learning_rate": 0.00019423986833984777,
122
- "loss": 1.3464,
123
- "step": 380
124
- },
125
- {
126
- "epoch": 0.04,
127
- "learning_rate": 0.00019382843036412262,
128
- "loss": 1.3573,
129
- "step": 400
130
- },
131
- {
132
- "epoch": 0.04,
133
- "learning_rate": 0.00019341699238839744,
134
- "loss": 1.3455,
135
- "step": 420
136
- },
137
- {
138
- "epoch": 0.04,
139
- "learning_rate": 0.0001930055544126723,
140
- "loss": 1.3223,
141
- "step": 440
142
- },
143
- {
144
- "epoch": 0.05,
145
- "learning_rate": 0.00019259411643694714,
146
- "loss": 1.3293,
147
- "step": 460
148
- },
149
- {
150
- "epoch": 0.05,
151
- "learning_rate": 0.000192182678461222,
152
- "loss": 1.3033,
153
- "step": 480
154
- },
155
- {
156
- "epoch": 0.05,
157
- "learning_rate": 0.0001917712404854968,
158
- "loss": 1.3323,
159
- "step": 500
160
- },
161
- {
162
- "epoch": 0.05,
163
- "learning_rate": 0.00019135980250977166,
164
- "loss": 1.2838,
165
- "step": 520
166
- },
167
- {
168
- "epoch": 0.05,
169
- "learning_rate": 0.0001909483645340465,
170
- "loss": 1.332,
171
- "step": 540
172
- },
173
- {
174
- "epoch": 0.06,
175
- "learning_rate": 0.00019053692655832133,
176
- "loss": 1.3118,
177
- "step": 560
178
- },
179
- {
180
- "epoch": 0.06,
181
- "learning_rate": 0.00019012548858259617,
182
- "loss": 1.3237,
183
- "step": 580
184
- },
185
- {
186
- "epoch": 0.06,
187
- "learning_rate": 0.00018971405060687102,
188
- "loss": 1.2541,
189
- "step": 600
190
- },
191
- {
192
- "epoch": 0.06,
193
- "learning_rate": 0.00018930261263114587,
194
- "loss": 1.28,
195
- "step": 620
196
- },
197
- {
198
- "epoch": 0.07,
199
- "learning_rate": 0.0001888911746554207,
200
- "loss": 1.231,
201
- "step": 640
202
- },
203
- {
204
- "epoch": 0.07,
205
- "learning_rate": 0.00018847973667969554,
206
- "loss": 1.2676,
207
- "step": 660
208
- },
209
- {
210
- "epoch": 0.07,
211
- "learning_rate": 0.0001880682987039704,
212
- "loss": 1.2909,
213
- "step": 680
214
- },
215
- {
216
- "epoch": 0.07,
217
- "learning_rate": 0.0001876568607282452,
218
- "loss": 1.2499,
219
- "step": 700
220
- },
221
- {
222
- "epoch": 0.07,
223
- "learning_rate": 0.00018724542275252006,
224
- "loss": 1.2679,
225
- "step": 720
226
- },
227
- {
228
- "epoch": 0.08,
229
- "learning_rate": 0.0001868339847767949,
230
- "loss": 1.2674,
231
- "step": 740
232
- },
233
- {
234
- "epoch": 0.08,
235
- "learning_rate": 0.00018642254680106975,
236
- "loss": 1.2736,
237
- "step": 760
238
- },
239
- {
240
- "epoch": 0.08,
241
- "learning_rate": 0.00018601110882534457,
242
- "loss": 1.2843,
243
- "step": 780
244
- },
245
- {
246
- "epoch": 0.08,
247
- "learning_rate": 0.00018559967084961942,
248
- "loss": 1.281,
249
- "step": 800
250
- },
251
- {
252
- "epoch": 0.08,
253
- "learning_rate": 0.00018518823287389427,
254
- "loss": 1.3699,
255
- "step": 820
256
- },
257
- {
258
- "epoch": 0.09,
259
- "learning_rate": 0.0001847767948981691,
260
- "loss": 1.2705,
261
- "step": 840
262
- },
263
- {
264
- "epoch": 0.09,
265
- "learning_rate": 0.00018436535692244394,
266
- "loss": 1.2279,
267
- "step": 860
268
- },
269
- {
270
- "epoch": 0.09,
271
- "learning_rate": 0.0001839539189467188,
272
- "loss": 1.2779,
273
- "step": 880
274
- },
275
- {
276
- "epoch": 0.09,
277
- "learning_rate": 0.00018354248097099364,
278
- "loss": 1.2086,
279
- "step": 900
280
- },
281
- {
282
- "epoch": 0.09,
283
- "learning_rate": 0.00018313104299526846,
284
- "loss": 1.2999,
285
- "step": 920
286
- },
287
- {
288
- "epoch": 0.1,
289
- "learning_rate": 0.0001827196050195433,
290
- "loss": 1.2503,
291
- "step": 940
292
- },
293
- {
294
- "epoch": 0.1,
295
- "learning_rate": 0.00018230816704381815,
296
- "loss": 1.2466,
297
- "step": 960
298
- },
299
- {
300
- "epoch": 0.1,
301
- "learning_rate": 0.00018189672906809297,
302
- "loss": 1.2113,
303
- "step": 980
304
- },
305
- {
306
- "epoch": 0.1,
307
- "learning_rate": 0.00018148529109236782,
308
- "loss": 1.2356,
309
- "step": 1000
310
- },
311
- {
312
- "epoch": 0.1,
313
- "learning_rate": 0.00018107385311664267,
314
- "loss": 1.2631,
315
- "step": 1020
316
- },
317
- {
318
- "epoch": 0.11,
319
- "learning_rate": 0.00018066241514091752,
320
- "loss": 1.2443,
321
- "step": 1040
322
- },
323
- {
324
- "epoch": 0.11,
325
- "learning_rate": 0.00018025097716519234,
326
- "loss": 1.2406,
327
- "step": 1060
328
- },
329
- {
330
- "epoch": 0.11,
331
- "learning_rate": 0.0001798395391894672,
332
- "loss": 1.2308,
333
- "step": 1080
334
- },
335
- {
336
- "epoch": 0.11,
337
- "learning_rate": 0.00017942810121374204,
338
- "loss": 1.2649,
339
- "step": 1100
340
- },
341
- {
342
- "epoch": 0.11,
343
- "learning_rate": 0.00017901666323801686,
344
- "loss": 1.2263,
345
- "step": 1120
346
- },
347
- {
348
- "epoch": 0.12,
349
- "learning_rate": 0.0001786052252622917,
350
- "loss": 1.2869,
351
- "step": 1140
352
- },
353
- {
354
- "epoch": 0.12,
355
- "learning_rate": 0.00017819378728656655,
356
- "loss": 1.2255,
357
- "step": 1160
358
- },
359
- {
360
- "epoch": 0.12,
361
- "learning_rate": 0.0001777823493108414,
362
- "loss": 1.2596,
363
- "step": 1180
364
- },
365
- {
366
- "epoch": 0.12,
367
- "learning_rate": 0.00017737091133511622,
368
- "loss": 1.2748,
369
- "step": 1200
370
- },
371
- {
372
- "epoch": 0.12,
373
- "learning_rate": 0.00017695947335939107,
374
- "loss": 1.2587,
375
- "step": 1220
376
- },
377
- {
378
- "epoch": 0.13,
379
- "learning_rate": 0.00017654803538366592,
380
- "loss": 1.2651,
381
- "step": 1240
382
- },
383
- {
384
- "epoch": 0.13,
385
- "learning_rate": 0.00017613659740794074,
386
- "loss": 1.2659,
387
- "step": 1260
388
- },
389
- {
390
- "epoch": 0.13,
391
- "learning_rate": 0.0001757251594322156,
392
- "loss": 1.2077,
393
- "step": 1280
394
- },
395
- {
396
- "epoch": 0.13,
397
- "learning_rate": 0.00017531372145649044,
398
- "loss": 1.25,
399
- "step": 1300
400
- },
401
- {
402
- "epoch": 0.13,
403
- "learning_rate": 0.00017490228348076528,
404
- "loss": 1.2149,
405
- "step": 1320
406
- },
407
- {
408
- "epoch": 0.14,
409
- "learning_rate": 0.0001744908455050401,
410
- "loss": 1.2417,
411
- "step": 1340
412
- },
413
- {
414
- "epoch": 0.14,
415
- "learning_rate": 0.00017407940752931498,
416
- "loss": 1.1939,
417
- "step": 1360
418
- },
419
- {
420
- "epoch": 0.14,
421
- "learning_rate": 0.00017366796955358983,
422
- "loss": 1.2688,
423
- "step": 1380
424
- },
425
- {
426
- "epoch": 0.14,
427
- "learning_rate": 0.00017325653157786465,
428
- "loss": 1.2287,
429
- "step": 1400
430
- },
431
- {
432
- "epoch": 0.14,
433
- "learning_rate": 0.0001728450936021395,
434
- "loss": 1.2931,
435
- "step": 1420
436
- },
437
- {
438
- "epoch": 0.15,
439
- "learning_rate": 0.00017243365562641435,
440
- "loss": 1.2695,
441
- "step": 1440
442
- },
443
- {
444
- "epoch": 0.15,
445
- "learning_rate": 0.00017202221765068917,
446
- "loss": 1.2228,
447
- "step": 1460
448
- },
449
- {
450
- "epoch": 0.15,
451
- "learning_rate": 0.00017161077967496401,
452
- "loss": 1.2419,
453
- "step": 1480
454
- },
455
- {
456
- "epoch": 0.15,
457
- "learning_rate": 0.00017119934169923886,
458
- "loss": 1.2483,
459
- "step": 1500
460
- },
461
- {
462
- "epoch": 0.15,
463
- "learning_rate": 0.0001707879037235137,
464
- "loss": 1.2144,
465
- "step": 1520
466
- },
467
- {
468
- "epoch": 0.16,
469
- "learning_rate": 0.00017037646574778853,
470
- "loss": 1.2148,
471
- "step": 1540
472
- },
473
- {
474
- "epoch": 0.16,
475
- "learning_rate": 0.00016996502777206338,
476
- "loss": 1.2196,
477
- "step": 1560
478
- },
479
- {
480
- "epoch": 0.16,
481
- "learning_rate": 0.00016955358979633823,
482
- "loss": 1.2581,
483
- "step": 1580
484
- },
485
- {
486
- "epoch": 0.16,
487
- "learning_rate": 0.00016914215182061305,
488
- "loss": 1.2414,
489
- "step": 1600
490
- },
491
- {
492
- "epoch": 0.16,
493
- "learning_rate": 0.0001687307138448879,
494
- "loss": 1.2357,
495
- "step": 1620
496
- },
497
- {
498
- "epoch": 0.17,
499
- "learning_rate": 0.00016831927586916274,
500
- "loss": 1.22,
501
- "step": 1640
502
- },
503
- {
504
- "epoch": 0.17,
505
- "learning_rate": 0.0001679078378934376,
506
- "loss": 1.2234,
507
- "step": 1660
508
- },
509
- {
510
- "epoch": 0.17,
511
- "learning_rate": 0.00016749639991771241,
512
- "loss": 1.2291,
513
- "step": 1680
514
- },
515
- {
516
- "epoch": 0.17,
517
- "learning_rate": 0.00016708496194198726,
518
- "loss": 1.2344,
519
- "step": 1700
520
- },
521
- {
522
- "epoch": 0.18,
523
- "learning_rate": 0.0001666735239662621,
524
- "loss": 1.1987,
525
- "step": 1720
526
- },
527
- {
528
- "epoch": 0.18,
529
- "learning_rate": 0.00016626208599053693,
530
- "loss": 1.2232,
531
- "step": 1740
532
- },
533
- {
534
- "epoch": 0.18,
535
- "learning_rate": 0.00016585064801481178,
536
- "loss": 1.2402,
537
- "step": 1760
538
- },
539
- {
540
- "epoch": 0.18,
541
- "learning_rate": 0.00016543921003908663,
542
- "loss": 1.1475,
543
- "step": 1780
544
- },
545
- {
546
- "epoch": 0.18,
547
- "learning_rate": 0.00016502777206336148,
548
- "loss": 1.272,
549
- "step": 1800
550
- },
551
- {
552
- "epoch": 0.19,
553
- "learning_rate": 0.0001646163340876363,
554
- "loss": 1.2369,
555
- "step": 1820
556
- },
557
- {
558
- "epoch": 0.19,
559
- "learning_rate": 0.00016420489611191114,
560
- "loss": 1.212,
561
- "step": 1840
562
- },
563
- {
564
- "epoch": 0.19,
565
- "learning_rate": 0.000163793458136186,
566
- "loss": 1.2191,
567
- "step": 1860
568
- },
569
- {
570
- "epoch": 0.19,
571
- "learning_rate": 0.00016338202016046081,
572
- "loss": 1.1953,
573
- "step": 1880
574
- },
575
- {
576
- "epoch": 0.19,
577
- "learning_rate": 0.00016297058218473566,
578
- "loss": 1.2126,
579
- "step": 1900
580
- },
581
- {
582
- "epoch": 0.2,
583
- "learning_rate": 0.0001625591442090105,
584
- "loss": 1.2396,
585
- "step": 1920
586
- },
587
- {
588
- "epoch": 0.2,
589
- "learning_rate": 0.00016214770623328536,
590
- "loss": 1.1468,
591
- "step": 1940
592
- },
593
- {
594
- "epoch": 0.2,
595
- "learning_rate": 0.00016173626825756018,
596
- "loss": 1.1847,
597
- "step": 1960
598
- },
599
- {
600
- "epoch": 0.2,
601
- "learning_rate": 0.00016132483028183503,
602
- "loss": 1.2214,
603
- "step": 1980
604
- },
605
- {
606
- "epoch": 0.2,
607
- "learning_rate": 0.00016091339230610988,
608
- "loss": 1.2138,
609
- "step": 2000
610
- },
611
- {
612
- "epoch": 0.21,
613
- "learning_rate": 0.0001605019543303847,
614
- "loss": 1.2158,
615
- "step": 2020
616
- },
617
- {
618
- "epoch": 0.21,
619
- "learning_rate": 0.00016009051635465954,
620
- "loss": 1.2065,
621
- "step": 2040
622
- },
623
- {
624
- "epoch": 0.21,
625
- "learning_rate": 0.0001596790783789344,
626
- "loss": 1.2048,
627
- "step": 2060
628
- },
629
- {
630
- "epoch": 0.21,
631
- "learning_rate": 0.00015926764040320924,
632
- "loss": 1.1904,
633
- "step": 2080
634
- },
635
- {
636
- "epoch": 0.21,
637
- "learning_rate": 0.00015885620242748406,
638
- "loss": 1.1872,
639
- "step": 2100
640
- },
641
- {
642
- "epoch": 0.22,
643
- "learning_rate": 0.0001584447644517589,
644
- "loss": 1.2087,
645
- "step": 2120
646
- },
647
- {
648
- "epoch": 0.22,
649
- "learning_rate": 0.00015803332647603376,
650
- "loss": 1.1909,
651
- "step": 2140
652
- },
653
- {
654
- "epoch": 0.22,
655
- "learning_rate": 0.00015762188850030858,
656
- "loss": 1.2609,
657
- "step": 2160
658
- },
659
- {
660
- "epoch": 0.22,
661
- "learning_rate": 0.00015721045052458343,
662
- "loss": 1.2083,
663
- "step": 2180
664
- },
665
- {
666
- "epoch": 0.22,
667
- "learning_rate": 0.00015679901254885827,
668
- "loss": 1.2205,
669
- "step": 2200
670
- },
671
- {
672
- "epoch": 0.23,
673
- "learning_rate": 0.00015638757457313312,
674
- "loss": 1.1966,
675
- "step": 2220
676
- },
677
- {
678
- "epoch": 0.23,
679
- "learning_rate": 0.00015597613659740794,
680
- "loss": 1.235,
681
- "step": 2240
682
- },
683
- {
684
- "epoch": 0.23,
685
- "learning_rate": 0.0001555646986216828,
686
- "loss": 1.2488,
687
- "step": 2260
688
- },
689
- {
690
- "epoch": 0.23,
691
- "learning_rate": 0.00015515326064595764,
692
- "loss": 1.2229,
693
- "step": 2280
694
- },
695
- {
696
- "epoch": 0.23,
697
- "learning_rate": 0.00015474182267023246,
698
- "loss": 1.1874,
699
- "step": 2300
700
- },
701
- {
702
- "epoch": 0.24,
703
- "learning_rate": 0.0001543303846945073,
704
- "loss": 1.1724,
705
- "step": 2320
706
- },
707
- {
708
- "epoch": 0.24,
709
- "learning_rate": 0.00015391894671878216,
710
- "loss": 1.1786,
711
- "step": 2340
712
- },
713
- {
714
- "epoch": 0.24,
715
- "learning_rate": 0.000153507508743057,
716
- "loss": 1.1913,
717
- "step": 2360
718
- },
719
- {
720
- "epoch": 0.24,
721
- "learning_rate": 0.00015309607076733183,
722
- "loss": 1.2138,
723
- "step": 2380
724
- },
725
- {
726
- "epoch": 0.24,
727
- "learning_rate": 0.00015268463279160667,
728
- "loss": 1.1954,
729
- "step": 2400
730
- },
731
- {
732
- "epoch": 0.25,
733
- "learning_rate": 0.00015227319481588152,
734
- "loss": 1.1926,
735
- "step": 2420
736
- },
737
- {
738
- "epoch": 0.25,
739
- "learning_rate": 0.00015186175684015634,
740
- "loss": 1.1893,
741
- "step": 2440
742
- },
743
- {
744
- "epoch": 0.25,
745
- "learning_rate": 0.0001514503188644312,
746
- "loss": 1.2152,
747
- "step": 2460
748
- },
749
- {
750
- "epoch": 0.25,
751
- "learning_rate": 0.00015103888088870604,
752
- "loss": 1.199,
753
- "step": 2480
754
- },
755
- {
756
- "epoch": 0.25,
757
- "learning_rate": 0.0001506274429129809,
758
- "loss": 1.1966,
759
- "step": 2500
760
- },
761
- {
762
- "epoch": 0.26,
763
- "learning_rate": 0.0001502160049372557,
764
- "loss": 1.2042,
765
- "step": 2520
766
- },
767
- {
768
- "epoch": 0.26,
769
- "learning_rate": 0.00014980456696153056,
770
- "loss": 1.1901,
771
- "step": 2540
772
- },
773
- {
774
- "epoch": 0.26,
775
- "learning_rate": 0.0001493931289858054,
776
- "loss": 1.2023,
777
- "step": 2560
778
- },
779
- {
780
- "epoch": 0.26,
781
- "learning_rate": 0.00014898169101008023,
782
- "loss": 1.1597,
783
- "step": 2580
784
- },
785
- {
786
- "epoch": 0.26,
787
- "learning_rate": 0.00014857025303435507,
788
- "loss": 1.1828,
789
- "step": 2600
790
- },
791
- {
792
- "epoch": 0.27,
793
- "learning_rate": 0.00014815881505862992,
794
- "loss": 1.1907,
795
- "step": 2620
796
- },
797
- {
798
- "epoch": 0.27,
799
- "learning_rate": 0.00014774737708290477,
800
- "loss": 1.1477,
801
- "step": 2640
802
- },
803
- {
804
- "epoch": 0.27,
805
- "learning_rate": 0.0001473359391071796,
806
- "loss": 1.2146,
807
- "step": 2660
808
- },
809
- {
810
- "epoch": 0.27,
811
- "learning_rate": 0.00014692450113145444,
812
- "loss": 1.2327,
813
- "step": 2680
814
- },
815
- {
816
- "epoch": 0.27,
817
- "learning_rate": 0.0001465130631557293,
818
- "loss": 1.1747,
819
- "step": 2700
820
- },
821
- {
822
- "epoch": 0.28,
823
- "learning_rate": 0.0001461016251800041,
824
- "loss": 1.1745,
825
- "step": 2720
826
- },
827
- {
828
- "epoch": 0.28,
829
- "learning_rate": 0.00014569018720427896,
830
- "loss": 1.1914,
831
- "step": 2740
832
- },
833
- {
834
- "epoch": 0.28,
835
- "learning_rate": 0.0001452787492285538,
836
- "loss": 1.1781,
837
- "step": 2760
838
- },
839
- {
840
- "epoch": 0.28,
841
- "learning_rate": 0.00014486731125282865,
842
- "loss": 1.1819,
843
- "step": 2780
844
- },
845
- {
846
- "epoch": 0.29,
847
- "learning_rate": 0.00014445587327710347,
848
- "loss": 1.1894,
849
- "step": 2800
850
- },
851
- {
852
- "epoch": 0.29,
853
- "learning_rate": 0.00014404443530137832,
854
- "loss": 1.2198,
855
- "step": 2820
856
- },
857
- {
858
- "epoch": 0.29,
859
- "learning_rate": 0.00014363299732565317,
860
- "loss": 1.1464,
861
- "step": 2840
862
- },
863
- {
864
- "epoch": 0.29,
865
- "learning_rate": 0.000143221559349928,
866
- "loss": 1.2039,
867
- "step": 2860
868
- },
869
- {
870
- "epoch": 0.29,
871
- "learning_rate": 0.00014281012137420284,
872
- "loss": 1.1758,
873
- "step": 2880
874
- },
875
- {
876
- "epoch": 0.3,
877
- "learning_rate": 0.0001423986833984777,
878
- "loss": 1.1958,
879
- "step": 2900
880
- },
881
- {
882
- "epoch": 0.3,
883
- "learning_rate": 0.00014198724542275254,
884
- "loss": 1.2163,
885
- "step": 2920
886
- },
887
- {
888
- "epoch": 0.3,
889
- "learning_rate": 0.00014157580744702736,
890
- "loss": 1.1724,
891
- "step": 2940
892
- },
893
- {
894
- "epoch": 0.3,
895
- "learning_rate": 0.0001411643694713022,
896
- "loss": 1.1339,
897
- "step": 2960
898
- },
899
- {
900
- "epoch": 0.3,
901
- "learning_rate": 0.00014075293149557705,
902
- "loss": 1.1752,
903
- "step": 2980
904
- },
905
- {
906
- "epoch": 0.31,
907
- "learning_rate": 0.00014034149351985187,
908
- "loss": 1.2221,
909
- "step": 3000
910
- },
911
- {
912
- "epoch": 0.31,
913
- "learning_rate": 0.00013993005554412672,
914
- "loss": 1.1954,
915
- "step": 3020
916
- },
917
- {
918
- "epoch": 0.31,
919
- "learning_rate": 0.00013951861756840157,
920
- "loss": 1.1904,
921
- "step": 3040
922
- },
923
- {
924
- "epoch": 0.31,
925
- "learning_rate": 0.00013910717959267642,
926
- "loss": 1.1601,
927
- "step": 3060
928
- },
929
- {
930
- "epoch": 0.31,
931
- "learning_rate": 0.00013869574161695124,
932
- "loss": 1.148,
933
- "step": 3080
934
- },
935
- {
936
- "epoch": 0.32,
937
- "learning_rate": 0.0001382843036412261,
938
- "loss": 1.2106,
939
- "step": 3100
940
- },
941
- {
942
- "epoch": 0.32,
943
- "learning_rate": 0.00013787286566550094,
944
- "loss": 1.1367,
945
- "step": 3120
946
- },
947
- {
948
- "epoch": 0.32,
949
- "learning_rate": 0.00013746142768977576,
950
- "loss": 1.1951,
951
- "step": 3140
952
- },
953
- {
954
- "epoch": 0.32,
955
- "learning_rate": 0.0001370499897140506,
956
- "loss": 1.1706,
957
- "step": 3160
958
- },
959
- {
960
- "epoch": 0.32,
961
- "learning_rate": 0.00013663855173832545,
962
- "loss": 1.1872,
963
- "step": 3180
964
- },
965
- {
966
- "epoch": 0.33,
967
- "learning_rate": 0.0001362271137626003,
968
- "loss": 1.1498,
969
- "step": 3200
970
- },
971
- {
972
- "epoch": 0.33,
973
- "learning_rate": 0.00013581567578687512,
974
- "loss": 1.2111,
975
- "step": 3220
976
- },
977
- {
978
- "epoch": 0.33,
979
- "learning_rate": 0.00013540423781114997,
980
- "loss": 1.1774,
981
- "step": 3240
982
- },
983
- {
984
- "epoch": 0.33,
985
- "learning_rate": 0.00013499279983542482,
986
- "loss": 1.1927,
987
- "step": 3260
988
- },
989
- {
990
- "epoch": 0.33,
991
- "learning_rate": 0.00013458136185969964,
992
- "loss": 1.1903,
993
- "step": 3280
994
- },
995
- {
996
- "epoch": 0.34,
997
- "learning_rate": 0.0001341699238839745,
998
- "loss": 1.1976,
999
- "step": 3300
1000
- },
1001
- {
1002
- "epoch": 0.34,
1003
- "learning_rate": 0.00013375848590824934,
1004
- "loss": 1.1687,
1005
- "step": 3320
1006
- },
1007
- {
1008
- "epoch": 0.34,
1009
- "learning_rate": 0.00013334704793252418,
1010
- "loss": 1.1598,
1011
- "step": 3340
1012
- },
1013
- {
1014
- "epoch": 0.34,
1015
- "learning_rate": 0.000132935609956799,
1016
- "loss": 1.1414,
1017
- "step": 3360
1018
- },
1019
- {
1020
- "epoch": 0.34,
1021
- "learning_rate": 0.00013252417198107385,
1022
- "loss": 1.169,
1023
- "step": 3380
1024
- },
1025
- {
1026
- "epoch": 0.35,
1027
- "learning_rate": 0.0001321127340053487,
1028
- "loss": 1.1676,
1029
- "step": 3400
1030
- },
1031
- {
1032
- "epoch": 0.35,
1033
- "learning_rate": 0.00013170129602962352,
1034
- "loss": 1.2179,
1035
- "step": 3420
1036
- },
1037
- {
1038
- "epoch": 0.35,
1039
- "learning_rate": 0.00013128985805389837,
1040
- "loss": 1.2435,
1041
- "step": 3440
1042
- },
1043
- {
1044
- "epoch": 0.35,
1045
- "learning_rate": 0.00013087842007817322,
1046
- "loss": 1.1457,
1047
- "step": 3460
1048
- },
1049
- {
1050
- "epoch": 0.35,
1051
- "learning_rate": 0.00013046698210244807,
1052
- "loss": 1.1818,
1053
- "step": 3480
1054
- },
1055
- {
1056
- "epoch": 0.36,
1057
- "learning_rate": 0.0001300555441267229,
1058
- "loss": 1.1666,
1059
- "step": 3500
1060
- }
1061
- ],
1062
- "logging_steps": 20,
1063
- "max_steps": 9822,
1064
- "num_train_epochs": 1,
1065
- "save_steps": 500,
1066
- "total_flos": 5.077651028865024e+16,
1067
- "trial_name": null,
1068
- "trial_params": null
1069
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3500/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8819fc087370c0c0dd1869922822cf7a5ebe84fa7a7194c69a0ec917ff22569b
3
- size 4027
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-4000/README.md DELETED
@@ -1,21 +0,0 @@
1
- ---
2
- library_name: peft
3
- ---
4
- ## Training procedure
5
-
6
-
7
- The following `bitsandbytes` quantization config was used during training:
8
- - quant_method: QuantizationMethod.BITS_AND_BYTES
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: True
17
- - bnb_4bit_compute_dtype: bfloat16
18
- ### Framework versions
19
-
20
-
21
- - PEFT 0.4.0.dev0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-4000/adapter_config.json DELETED
@@ -1,21 +0,0 @@
1
- {
2
- "base_model_name_or_path": "codellama/CodeLlama-13b-Instruct-hf",
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": 8,
14
- "revision": null,
15
- "target_modules": [
16
- "q_proj",
17
- "k_proj",
18
- "v_proj"
19
- ],
20
- "task_type": "CAUSAL_LM"
21
- }