Hugging Face's logo

nl-to-logql
/
gemma-2-logql

PEFT
Safetensors
gemma2
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Community
sidbin commited on
Commit
84ba663
•
1 Parent(s): 80781cc

Upload checkpoint-26/trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. checkpoint-26/trainer_state.json +255 -0
checkpoint-26/trainer_state.json ADDED
@@ -0,0 +1,255 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 6,
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": 0.038461538461538464,
13
+ "grad_norm": 8.71969985961914,
14
+ "learning_rate": 1e-05,
15
+ "loss": 1.7925,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.038461538461538464,
20
+ "eval_loss": 2.0411531925201416,
21
+ "eval_runtime": 1.6566,
22
+ "eval_samples_per_second": 13.28,
23
+ "eval_steps_per_second": 1.207,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.07692307692307693,
28
+ "grad_norm": 4.587398052215576,
29
+ "learning_rate": 2e-05,
30
+ "loss": 2.1894,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.11538461538461539,
35
+ "grad_norm": 4.494429111480713,
36
+ "learning_rate": 3e-05,
37
+ "loss": 1.9438,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.15384615384615385,
42
+ "grad_norm": 7.78571891784668,
43
+ "learning_rate": 4e-05,
44
+ "loss": 1.9463,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.19230769230769232,
49
+ "grad_norm": 6.792930603027344,
50
+ "learning_rate": 5e-05,
51
+ "loss": 1.8652,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.23076923076923078,
56
+ "grad_norm": 10.765946388244629,
57
+ "learning_rate": 6e-05,
58
+ "loss": 1.6872,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.23076923076923078,
63
+ "eval_loss": 1.6089171171188354,
64
+ "eval_runtime": 1.667,
65
+ "eval_samples_per_second": 13.198,
66
+ "eval_steps_per_second": 1.2,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.2692307692307692,
71
+ "grad_norm": 3.0110535621643066,
72
+ "learning_rate": 7e-05,
73
+ "loss": 1.6877,
74
+ "step": 7
75
+ },
76
+ {
77
+ "epoch": 0.3076923076923077,
78
+ "grad_norm": 2.871809959411621,
79
+ "learning_rate": 8e-05,
80
+ "loss": 1.4855,
81
+ "step": 8
82
+ },
83
+ {
84
+ "epoch": 0.34615384615384615,
85
+ "grad_norm": 2.223036050796509,
86
+ "learning_rate": 9e-05,
87
+ "loss": 1.2108,
88
+ "step": 9
89
+ },
90
+ {
91
+ "epoch": 0.38461538461538464,
92
+ "grad_norm": 2.2891507148742676,
93
+ "learning_rate": 0.0001,
94
+ "loss": 1.0259,
95
+ "step": 10
96
+ },
97
+ {
98
+ "epoch": 0.4230769230769231,
99
+ "grad_norm": 2.058546543121338,
100
+ "learning_rate": 9.997207818651274e-05,
101
+ "loss": 0.8116,
102
+ "step": 11
103
+ },
104
+ {
105
+ "epoch": 0.46153846153846156,
106
+ "grad_norm": 2.8107495307922363,
107
+ "learning_rate": 9.988834393115767e-05,
108
+ "loss": 0.6967,
109
+ "step": 12
110
+ },
111
+ {
112
+ "epoch": 0.46153846153846156,
113
+ "eval_loss": 0.6327503323554993,
114
+ "eval_runtime": 1.6315,
115
+ "eval_samples_per_second": 13.485,
116
+ "eval_steps_per_second": 1.226,
117
+ "step": 12
118
+ },
119
+ {
120
+ "epoch": 0.5,
121
+ "grad_norm": 2.0721328258514404,
122
+ "learning_rate": 9.974889075442521e-05,
123
+ "loss": 0.5983,
124
+ "step": 13
125
+ },
126
+ {
127
+ "epoch": 0.5384615384615384,
128
+ "grad_norm": 1.9303380250930786,
129
+ "learning_rate": 9.9553874407739e-05,
130
+ "loss": 0.4963,
131
+ "step": 14
132
+ },
133
+ {
134
+ "epoch": 0.5769230769230769,
135
+ "grad_norm": 1.40817391872406,
136
+ "learning_rate": 9.930351269950143e-05,
137
+ "loss": 0.3881,
138
+ "step": 15
139
+ },
140
+ {
141
+ "epoch": 0.6153846153846154,
142
+ "grad_norm": 1.4169831275939941,
143
+ "learning_rate": 9.899808525182935e-05,
144
+ "loss": 0.3139,
145
+ "step": 16
146
+ },
147
+ {
148
+ "epoch": 0.6538461538461539,
149
+ "grad_norm": 0.9847315549850464,
150
+ "learning_rate": 9.863793318825186e-05,
151
+ "loss": 0.2776,
152
+ "step": 17
153
+ },
154
+ {
155
+ "epoch": 0.6923076923076923,
156
+ "grad_norm": 1.2575572729110718,
157
+ "learning_rate": 9.822345875271883e-05,
158
+ "loss": 0.3327,
159
+ "step": 18
160
+ },
161
+ {
162
+ "epoch": 0.6923076923076923,
163
+ "eval_loss": 0.2710803747177124,
164
+ "eval_runtime": 1.6739,
165
+ "eval_samples_per_second": 13.143,
166
+ "eval_steps_per_second": 1.195,
167
+ "step": 18
168
+ },
169
+ {
170
+ "epoch": 0.7307692307692307,
171
+ "grad_norm": 0.7373743057250977,
172
+ "learning_rate": 9.775512486034563e-05,
173
+ "loss": 0.1967,
174
+ "step": 19
175
+ },
176
+ {
177
+ "epoch": 0.7692307692307693,
178
+ "grad_norm": 0.8841055035591125,
179
+ "learning_rate": 9.723345458039594e-05,
180
+ "loss": 0.244,
181
+ "step": 20
182
+ },
183
+ {
184
+ "epoch": 0.8076923076923077,
185
+ "grad_norm": 0.8621382713317871,
186
+ "learning_rate": 9.665903055208014e-05,
187
+ "loss": 0.1927,
188
+ "step": 21
189
+ },
190
+ {
191
+ "epoch": 0.8461538461538461,
192
+ "grad_norm": 0.9871663451194763,
193
+ "learning_rate": 9.603249433382144e-05,
194
+ "loss": 0.2435,
195
+ "step": 22
196
+ },
197
+ {
198
+ "epoch": 0.8846153846153846,
199
+ "grad_norm": 0.6780880689620972,
200
+ "learning_rate": 9.535454568671704e-05,
201
+ "loss": 0.1498,
202
+ "step": 23
203
+ },
204
+ {
205
+ "epoch": 0.9230769230769231,
206
+ "grad_norm": 0.7006078958511353,
207
+ "learning_rate": 9.462594179299406e-05,
208
+ "loss": 0.1784,
209
+ "step": 24
210
+ },
211
+ {
212
+ "epoch": 0.9230769230769231,
213
+ "eval_loss": 0.17325076460838318,
214
+ "eval_runtime": 1.6307,
215
+ "eval_samples_per_second": 13.491,
216
+ "eval_steps_per_second": 1.226,
217
+ "step": 24
218
+ },
219
+ {
220
+ "epoch": 0.9615384615384616,
221
+ "grad_norm": 0.69418865442276,
222
+ "learning_rate": 9.384749641033359e-05,
223
+ "loss": 0.2146,
224
+ "step": 25
225
+ },
226
+ {
227
+ "epoch": 1.0,
228
+ "grad_norm": 0.5629783272743225,
229
+ "learning_rate": 9.302007896300698e-05,
230
+ "loss": 0.1474,
231
+ "step": 26
232
+ }
233
+ ],
234
+ "logging_steps": 1,
235
+ "max_steps": 104,
236
+ "num_input_tokens_seen": 0,
237
+ "num_train_epochs": 4,
238
+ "save_steps": 500,
239
+ "stateful_callbacks": {
240
+ "TrainerControl": {
241
+ "args": {
242
+ "should_epoch_stop": false,
243
+ "should_evaluate": false,
244
+ "should_log": false,
245
+ "should_save": true,
246
+ "should_training_stop": false
247
+ },
248
+ "attributes": {}
249
+ }
250
+ },
251
+ "total_flos": 1.3435852608765952e+16,
252
+ "train_batch_size": 4,
253
+ "trial_name": null,
254
+ "trial_params": null
255
+ }