Hugging Face's logo

ArunMoonpai
/
CodeLlama-SQL-13b

Question Answering
PEFT
PyTorch
English
llama
Model card Files Community
3
Abinesh Sivakumar commited on
Commit
eb54c05
•
1 Parent(s): 9cacadf

Upload folder using huggingface_hub

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 +21 -0
  2. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1000/adapter_config.json +21 -0
  3. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1000/adapter_model.bin +3 -0
  4. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1000/optimizer.pt +3 -0
  5. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1000/rng_state.pth +3 -0
  6. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1000/scheduler.pt +3 -0
  7. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1000/trainer_state.json +319 -0
  8. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1000/training_args.bin +3 -0
  9. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1500/README.md +21 -0
  10. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1500/adapter_config.json +21 -0
  11. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1500/adapter_model.bin +3 -0
  12. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1500/optimizer.pt +3 -0
  13. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1500/rng_state.pth +3 -0
  14. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1500/scheduler.pt +3 -0
  15. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1500/trainer_state.json +469 -0
  16. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1500/training_args.bin +3 -0
  17. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2000/README.md +21 -0
  18. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2000/adapter_config.json +21 -0
  19. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2000/adapter_model.bin +3 -0
  20. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2000/optimizer.pt +3 -0
  21. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2000/rng_state.pth +3 -0
  22. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2000/scheduler.pt +3 -0
  23. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2000/trainer_state.json +619 -0
  24. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2000/training_args.bin +3 -0
  25. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2500/README.md +21 -0
  26. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2500/adapter_config.json +21 -0
  27. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2500/adapter_model.bin +3 -0
  28. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2500/optimizer.pt +3 -0
  29. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2500/rng_state.pth +3 -0
  30. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2500/scheduler.pt +3 -0
  31. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2500/trainer_state.json +769 -0
  32. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-2500/training_args.bin +3 -0
  33. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3000/README.md +21 -0
  34. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3000/adapter_config.json +21 -0
  35. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3000/adapter_model.bin +3 -0
  36. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3000/optimizer.pt +3 -0
  37. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3000/rng_state.pth +3 -0
  38. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3000/scheduler.pt +3 -0
  39. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3000/trainer_state.json +919 -0
  40. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3000/training_args.bin +3 -0
  41. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3500/README.md +21 -0
  42. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3500/adapter_config.json +21 -0
  43. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3500/adapter_model.bin +3 -0
  44. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3500/optimizer.pt +3 -0
  45. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3500/rng_state.pth +3 -0
  46. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3500/scheduler.pt +3 -0
  47. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3500/trainer_state.json +1069 -0
  48. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-3500/training_args.bin +3 -0
  49. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-4000/README.md +21 -0
  50. https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-4000/adapter_config.json +21 -0
https:/huggingface.co/AbineshMoonpai/CodeLlama-SQL-13b/tree/main/trainer_outputs/checkpoint-1000/README.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
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 ADDED
@@ -0,0 +1,319 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
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 ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
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 ADDED
@@ -0,0 +1,469 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
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 ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
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 ADDED
@@ -0,0 +1,619 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
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 ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
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 ADDED
@@ -0,0 +1,769 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
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 ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
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 ADDED
@@ -0,0 +1,919 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
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 ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
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 ADDED
@@ -0,0 +1,1069 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
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 ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }