Hugging Face's logo

nl-to-logql
/
llama-3.1-logql

PEFT
Safetensors
llama
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Community
sidbin commited on
Commit
835384b
·
verified ·
1 Parent(s): 148f1b5

Upload checkpoint-26/trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. checkpoint-26/trainer_state.json +287 -0
checkpoint-26/trainer_state.json ADDED
@@ -0,0 +1,287 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 3,
6
+ "global_step": 26,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.07692307692307693,
13
+ "grad_norm": 6.9555134773254395,
14
+ "learning_rate": 1e-05,
15
+ "loss": 2.1647,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.07692307692307693,
20
+ "eval_loss": 2.2015950679779053,
21
+ "eval_runtime": 0.5143,
22
+ "eval_samples_per_second": 42.778,
23
+ "eval_steps_per_second": 1.944,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.15384615384615385,
28
+ "grad_norm": 7.17453670501709,
29
+ "learning_rate": 2e-05,
30
+ "loss": 2.1358,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.23076923076923078,
35
+ "grad_norm": 7.099859714508057,
36
+ "learning_rate": 3e-05,
37
+ "loss": 2.1505,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.23076923076923078,
42
+ "eval_loss": 2.116824150085449,
43
+ "eval_runtime": 0.5016,
44
+ "eval_samples_per_second": 43.86,
45
+ "eval_steps_per_second": 1.994,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.3076923076923077,
50
+ "grad_norm": 7.153745651245117,
51
+ "learning_rate": 4e-05,
52
+ "loss": 2.1955,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.38461538461538464,
57
+ "grad_norm": 5.896260738372803,
58
+ "learning_rate": 5e-05,
59
+ "loss": 1.9378,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.46153846153846156,
64
+ "grad_norm": 5.061944484710693,
65
+ "learning_rate": 6e-05,
66
+ "loss": 1.7332,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.46153846153846156,
71
+ "eval_loss": 1.5603915452957153,
72
+ "eval_runtime": 0.4962,
73
+ "eval_samples_per_second": 44.34,
74
+ "eval_steps_per_second": 2.015,
75
+ "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.5384615384615384,
79
+ "grad_norm": 4.622457981109619,
80
+ "learning_rate": 7e-05,
81
+ "loss": 1.5975,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.6153846153846154,
86
+ "grad_norm": 4.024200439453125,
87
+ "learning_rate": 8e-05,
88
+ "loss": 1.3523,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.6923076923076923,
93
+ "grad_norm": 3.341926097869873,
94
+ "learning_rate": 9e-05,
95
+ "loss": 1.0807,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.6923076923076923,
100
+ "eval_loss": 0.878767728805542,
101
+ "eval_runtime": 0.5037,
102
+ "eval_samples_per_second": 43.68,
103
+ "eval_steps_per_second": 1.985,
104
+ "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.7692307692307693,
108
+ "grad_norm": 3.572037696838379,
109
+ "learning_rate": 0.0001,
110
+ "loss": 0.8712,
111
+ "step": 10
112
+ },
113
+ {
114
+ "epoch": 0.8461538461538461,
115
+ "grad_norm": 2.6981351375579834,
116
+ "learning_rate": 9.986018985905901e-05,
117
+ "loss": 0.694,
118
+ "step": 11
119
+ },
120
+ {
121
+ "epoch": 0.9230769230769231,
122
+ "grad_norm": 2.876271963119507,
123
+ "learning_rate": 9.944154131125642e-05,
124
+ "loss": 0.5284,
125
+ "step": 12
126
+ },
127
+ {
128
+ "epoch": 0.9230769230769231,
129
+ "eval_loss": 0.4853472411632538,
130
+ "eval_runtime": 0.5088,
131
+ "eval_samples_per_second": 43.236,
132
+ "eval_steps_per_second": 1.965,
133
+ "step": 12
134
+ },
135
+ {
136
+ "epoch": 1.0,
137
+ "grad_norm": 2.3492231369018555,
138
+ "learning_rate": 9.874639560909117e-05,
139
+ "loss": 0.4715,
140
+ "step": 13
141
+ },
142
+ {
143
+ "epoch": 1.0769230769230769,
144
+ "grad_norm": 1.5317707061767578,
145
+ "learning_rate": 9.777864028930705e-05,
146
+ "loss": 0.3566,
147
+ "step": 14
148
+ },
149
+ {
150
+ "epoch": 1.1538461538461537,
151
+ "grad_norm": 1.37990140914917,
152
+ "learning_rate": 9.654368743221022e-05,
153
+ "loss": 0.3215,
154
+ "step": 15
155
+ },
156
+ {
157
+ "epoch": 1.1538461538461537,
158
+ "eval_loss": 0.291117787361145,
159
+ "eval_runtime": 0.5024,
160
+ "eval_samples_per_second": 43.789,
161
+ "eval_steps_per_second": 1.99,
162
+ "step": 15
163
+ },
164
+ {
165
+ "epoch": 1.2307692307692308,
166
+ "grad_norm": 1.4043002128601074,
167
+ "learning_rate": 9.504844339512095e-05,
168
+ "loss": 0.2691,
169
+ "step": 16
170
+ },
171
+ {
172
+ "epoch": 1.3076923076923077,
173
+ "grad_norm": 1.0550378561019897,
174
+ "learning_rate": 9.330127018922194e-05,
175
+ "loss": 0.2266,
176
+ "step": 17
177
+ },
178
+ {
179
+ "epoch": 1.3846153846153846,
180
+ "grad_norm": 0.9474859833717346,
181
+ "learning_rate": 9.131193871579975e-05,
182
+ "loss": 0.2114,
183
+ "step": 18
184
+ },
185
+ {
186
+ "epoch": 1.3846153846153846,
187
+ "eval_loss": 0.19578741490840912,
188
+ "eval_runtime": 0.503,
189
+ "eval_samples_per_second": 43.739,
190
+ "eval_steps_per_second": 1.988,
191
+ "step": 18
192
+ },
193
+ {
194
+ "epoch": 1.4615384615384617,
195
+ "grad_norm": 0.984850287437439,
196
+ "learning_rate": 8.90915741234015e-05,
197
+ "loss": 0.1919,
198
+ "step": 19
199
+ },
200
+ {
201
+ "epoch": 1.5384615384615383,
202
+ "grad_norm": 0.8843994140625,
203
+ "learning_rate": 8.665259359149132e-05,
204
+ "loss": 0.1432,
205
+ "step": 20
206
+ },
207
+ {
208
+ "epoch": 1.6153846153846154,
209
+ "grad_norm": 0.8318038582801819,
210
+ "learning_rate": 8.400863688854597e-05,
211
+ "loss": 0.1493,
212
+ "step": 21
213
+ },
214
+ {
215
+ "epoch": 1.6153846153846154,
216
+ "eval_loss": 0.1373557448387146,
217
+ "eval_runtime": 0.5325,
218
+ "eval_samples_per_second": 41.316,
219
+ "eval_steps_per_second": 1.878,
220
+ "step": 21
221
+ },
222
+ {
223
+ "epoch": 1.6923076923076923,
224
+ "grad_norm": 0.7481142282485962,
225
+ "learning_rate": 8.117449009293668e-05,
226
+ "loss": 0.1359,
227
+ "step": 22
228
+ },
229
+ {
230
+ "epoch": 1.7692307692307692,
231
+ "grad_norm": 0.777579665184021,
232
+ "learning_rate": 7.81660029031811e-05,
233
+ "loss": 0.1135,
234
+ "step": 23
235
+ },
236
+ {
237
+ "epoch": 1.8461538461538463,
238
+ "grad_norm": 0.6446991562843323,
239
+ "learning_rate": 7.500000000000001e-05,
240
+ "loss": 0.1081,
241
+ "step": 24
242
+ },
243
+ {
244
+ "epoch": 1.8461538461538463,
245
+ "eval_loss": 0.10664429515600204,
246
+ "eval_runtime": 0.4983,
247
+ "eval_samples_per_second": 44.146,
248
+ "eval_steps_per_second": 2.007,
249
+ "step": 24
250
+ },
251
+ {
252
+ "epoch": 1.9230769230769231,
253
+ "grad_norm": 0.699760913848877,
254
+ "learning_rate": 7.169418695587791e-05,
255
+ "loss": 0.104,
256
+ "step": 25
257
+ },
258
+ {
259
+ "epoch": 2.0,
260
+ "grad_norm": 0.7046389579772949,
261
+ "learning_rate": 6.826705121831976e-05,
262
+ "loss": 0.0943,
263
+ "step": 26
264
+ }
265
+ ],
266
+ "logging_steps": 1,
267
+ "max_steps": 52,
268
+ "num_input_tokens_seen": 0,
269
+ "num_train_epochs": 4,
270
+ "save_steps": 500,
271
+ "stateful_callbacks": {
272
+ "TrainerControl": {
273
+ "args": {
274
+ "should_epoch_stop": false,
275
+ "should_evaluate": false,
276
+ "should_log": false,
277
+ "should_save": true,
278
+ "should_training_stop": false
279
+ },
280
+ "attributes": {}
281
+ }
282
+ },
283
+ "total_flos": 2.120225792406323e+16,
284
+ "train_batch_size": 4,
285
+ "trial_name": null,
286
+ "trial_params": null
287
+ }