Hugging Face's logo

axrafTic
/
text2sqlProspeciton

Text Generation
PEFT
Safetensors
French
text2sql
text-to-sql
lora
qlora
schema-linking
qwen2.5-coder
french
conversational
Model card Files
xet
 Community
axrafTic commited on
Commit
1ee16ea
·
verified ·
1 Parent(s): 6dc3e4f

Delete trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +0 -295
trainer_state.json DELETED
@@ -1,295 +0,0 @@
1
- {
2
- "best_metric": 0.041570067405700684,
3
- "best_model_checkpoint": "./sql_lora_approach_b/checkpoint-34",
4
- "epoch": 2.9565217391304346,
5
- "eval_steps": 500,
6
- "global_step": 34,
7
- "is_hyper_param_search": false,
8
- "is_local_process_zero": true,
9
- "is_world_process_zero": true,
10
- "log_history": [
11
- {
12
- "epoch": 0.08695652173913043,
13
- "grad_norm": 1.1549581289291382,
14
- "learning_rate": 6.666666666666667e-05,
15
- "loss": 1.7303,
16
- "step": 1
17
- },
18
- {
19
- "epoch": 0.17391304347826086,
20
- "grad_norm": 1.1289726495742798,
21
- "learning_rate": 0.00013333333333333334,
22
- "loss": 1.7252,
23
- "step": 2
24
- },
25
- {
26
- "epoch": 0.2608695652173913,
27
- "grad_norm": 0.934922993183136,
28
- "learning_rate": 0.0002,
29
- "loss": 1.597,
30
- "step": 3
31
- },
32
- {
33
- "epoch": 0.34782608695652173,
34
- "grad_norm": 0.8451507091522217,
35
- "learning_rate": 0.00019981755542233177,
36
- "loss": 1.3325,
37
- "step": 4
38
- },
39
- {
40
- "epoch": 0.43478260869565216,
41
- "grad_norm": 0.9650647640228271,
42
- "learning_rate": 0.0001992708874098054,
43
- "loss": 1.038,
44
- "step": 5
45
- },
46
- {
47
- "epoch": 0.5217391304347826,
48
- "grad_norm": 1.6881967782974243,
49
- "learning_rate": 0.00019836199069471437,
50
- "loss": 0.7972,
51
- "step": 6
52
- },
53
- {
54
- "epoch": 0.6086956521739131,
55
- "grad_norm": 0.9939894080162048,
56
- "learning_rate": 0.0001970941817426052,
57
- "loss": 0.5526,
58
- "step": 7
59
- },
60
- {
61
- "epoch": 0.6956521739130435,
62
- "grad_norm": 0.9496100544929504,
63
- "learning_rate": 0.00019547208665085457,
64
- "loss": 0.3339,
65
- "step": 8
66
- },
67
- {
68
- "epoch": 0.782608695652174,
69
- "grad_norm": 0.7385075688362122,
70
- "learning_rate": 0.0001935016242685415,
71
- "loss": 0.1994,
72
- "step": 9
73
- },
74
- {
75
- "epoch": 0.8695652173913043,
76
- "grad_norm": 0.5156198740005493,
77
- "learning_rate": 0.00019118998459920902,
78
- "loss": 0.0954,
79
- "step": 10
80
- },
81
- {
82
- "epoch": 0.9565217391304348,
83
- "grad_norm": 0.3693973124027252,
84
- "learning_rate": 0.000188545602565321,
85
- "loss": 0.06,
86
- "step": 11
87
- },
88
- {
89
- "epoch": 0.9565217391304348,
90
- "eval_loss": 0.06161738932132721,
91
- "eval_runtime": 16.8375,
92
- "eval_samples_per_second": 0.535,
93
- "eval_steps_per_second": 0.535,
94
- "step": 11
95
- },
96
- {
97
- "epoch": 1.0434782608695652,
98
- "grad_norm": 0.3475421965122223,
99
- "learning_rate": 0.00018557812723014476,
100
- "loss": 0.0668,
101
- "step": 12
102
- },
103
- {
104
- "epoch": 1.1304347826086956,
105
- "grad_norm": 0.2272304743528366,
106
- "learning_rate": 0.00018229838658936564,
107
- "loss": 0.0472,
108
- "step": 13
109
- },
110
- {
111
- "epoch": 1.2173913043478262,
112
- "grad_norm": 0.18348968029022217,
113
- "learning_rate": 0.00017871834806090501,
114
- "loss": 0.0408,
115
- "step": 14
116
- },
117
- {
118
- "epoch": 1.3043478260869565,
119
- "grad_norm": 0.1996564120054245,
120
- "learning_rate": 0.00017485107481711012,
121
- "loss": 0.0533,
122
- "step": 15
123
- },
124
- {
125
- "epoch": 1.391304347826087,
126
- "grad_norm": 0.17511172592639923,
127
- "learning_rate": 0.00017071067811865476,
128
- "loss": 0.042,
129
- "step": 16
130
- },
131
- {
132
- "epoch": 1.4782608695652173,
133
- "grad_norm": 0.14677977561950684,
134
- "learning_rate": 0.00016631226582407952,
135
- "loss": 0.0318,
136
- "step": 17
137
- },
138
- {
139
- "epoch": 1.5652173913043477,
140
- "grad_norm": 0.19209422171115875,
141
- "learning_rate": 0.00016167188726285434,
142
- "loss": 0.0478,
143
- "step": 18
144
- },
145
- {
146
- "epoch": 1.6521739130434783,
147
- "grad_norm": 0.222362220287323,
148
- "learning_rate": 0.00015680647467311557,
149
- "loss": 0.0578,
150
- "step": 19
151
- },
152
- {
153
- "epoch": 1.7391304347826086,
154
- "grad_norm": 0.1985371708869934,
155
- "learning_rate": 0.00015173378141776568,
156
- "loss": 0.039,
157
- "step": 20
158
- },
159
- {
160
- "epoch": 1.8260869565217392,
161
- "grad_norm": 0.19283267855644226,
162
- "learning_rate": 0.00014647231720437686,
163
- "loss": 0.0338,
164
- "step": 21
165
- },
166
- {
167
- "epoch": 1.9130434782608696,
168
- "grad_norm": 0.18836742639541626,
169
- "learning_rate": 0.0001410412805452757,
170
- "loss": 0.0367,
171
- "step": 22
172
- },
173
- {
174
- "epoch": 2.0,
175
- "grad_norm": 0.22117920219898224,
176
- "learning_rate": 0.00013546048870425356,
177
- "loss": 0.0562,
178
- "step": 23
179
- },
180
- {
181
- "epoch": 2.0,
182
- "eval_loss": 0.042378202080726624,
183
- "eval_runtime": 16.8523,
184
- "eval_samples_per_second": 0.534,
185
- "eval_steps_per_second": 0.534,
186
- "step": 23
187
- },
188
- {
189
- "epoch": 2.0869565217391304,
190
- "grad_norm": 0.08625093847513199,
191
- "learning_rate": 0.00012975030538552032,
192
- "loss": 0.0223,
193
- "step": 24
194
- },
195
- {
196
- "epoch": 2.1739130434782608,
197
- "grad_norm": 0.10370675474405289,
198
- "learning_rate": 0.0001239315664287558,
199
- "loss": 0.0292,
200
- "step": 25
201
- },
202
- {
203
- "epoch": 2.260869565217391,
204
- "grad_norm": 0.15547294914722443,
205
- "learning_rate": 0.0001180255037813906,
206
- "loss": 0.0403,
207
- "step": 26
208
- },
209
- {
210
- "epoch": 2.3478260869565215,
211
- "grad_norm": 0.1734398603439331,
212
- "learning_rate": 0.0001120536680255323,
213
- "loss": 0.0341,
214
- "step": 27
215
- },
216
- {
217
- "epoch": 2.4347826086956523,
218
- "grad_norm": 0.12611858546733856,
219
- "learning_rate": 0.00010603784974222861,
220
- "loss": 0.025,
221
- "step": 28
222
- },
223
- {
224
- "epoch": 2.5217391304347827,
225
- "grad_norm": 0.11490053683519363,
226
- "learning_rate": 0.0001,
227
- "loss": 0.0254,
228
- "step": 29
229
- },
230
- {
231
- "epoch": 2.608695652173913,
232
- "grad_norm": 0.11299990862607956,
233
- "learning_rate": 9.396215025777139e-05,
234
- "loss": 0.0287,
235
- "step": 30
236
- },
237
- {
238
- "epoch": 2.6956521739130435,
239
- "grad_norm": 0.09447255730628967,
240
- "learning_rate": 8.79463319744677e-05,
241
- "loss": 0.0226,
242
- "step": 31
243
- },
244
- {
245
- "epoch": 2.782608695652174,
246
- "grad_norm": 0.13230058550834656,
247
- "learning_rate": 8.197449621860943e-05,
248
- "loss": 0.0277,
249
- "step": 32
250
- },
251
- {
252
- "epoch": 2.869565217391304,
253
- "grad_norm": 0.13557763397693634,
254
- "learning_rate": 7.606843357124426e-05,
255
- "loss": 0.0325,
256
- "step": 33
257
- },
258
- {
259
- "epoch": 2.9565217391304346,
260
- "grad_norm": 0.10920581966638565,
261
- "learning_rate": 7.024969461447972e-05,
262
- "loss": 0.0219,
263
- "step": 34
264
- },
265
- {
266
- "epoch": 2.9565217391304346,
267
- "eval_loss": 0.041570067405700684,
268
- "eval_runtime": 16.9013,
269
- "eval_samples_per_second": 0.533,
270
- "eval_steps_per_second": 0.533,
271
- "step": 34
272
- }
273
- ],
274
- "logging_steps": 1,
275
- "max_steps": 55,
276
- "num_input_tokens_seen": 0,
277
- "num_train_epochs": 5,
278
- "save_steps": 500,
279
- "stateful_callbacks": {
280
- "TrainerControl": {
281
- "args": {
282
- "should_epoch_stop": false,
283
- "should_evaluate": false,
284
- "should_log": false,
285
- "should_save": true,
286
- "should_training_stop": false
287
- },
288
- "attributes": {}
289
- }
290
- },
291
- "total_flos": 1208798594408448.0,
292
- "train_batch_size": 1,
293
- "trial_name": null,
294
- "trial_params": null
295
- }