Hugging Face's logo

Prahaladha
/
math-checkpoints

Transformers
Safetensors
Generated from Trainer
sft
trl
unsloth
Model card Files
xet
Community
Prahaladha commited on
Commit
2925064
·
verified ·
1 Parent(s): bfdacf8

Upload checkpoint-366/trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. checkpoint-366/trainer_state.json +286 -0
checkpoint-366/trainer_state.json ADDED
@@ -0,0 +1,286 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 366,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0547945205479452,
14
+ "grad_norm": 1.181526780128479,
15
+ "learning_rate": 4.736842105263158e-05,
16
+ "loss": 1.799,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.1095890410958904,
21
+ "grad_norm": 0.522590160369873,
22
+ "learning_rate": 0.0001,
23
+ "loss": 1.2094,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.1643835616438356,
28
+ "grad_norm": 0.3870140314102173,
29
+ "learning_rate": 9.979522160511282e-05,
30
+ "loss": 0.8021,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.2191780821917808,
35
+ "grad_norm": 0.3272338807582855,
36
+ "learning_rate": 9.918256378809177e-05,
37
+ "loss": 0.7125,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.273972602739726,
42
+ "grad_norm": 0.39106306433677673,
43
+ "learning_rate": 9.816704491231226e-05,
44
+ "loss": 0.6694,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.3287671232876712,
49
+ "grad_norm": 0.5298248529434204,
50
+ "learning_rate": 9.675698323078865e-05,
51
+ "loss": 0.6647,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.3835616438356164,
56
+ "grad_norm": 0.33846038579940796,
57
+ "learning_rate": 9.496392875023432e-05,
58
+ "loss": 0.612,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.4383561643835616,
63
+ "grad_norm": 0.3002408444881439,
64
+ "learning_rate": 9.280256862338821e-05,
65
+ "loss": 0.5868,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.4931506849315068,
70
+ "grad_norm": 0.27812713384628296,
71
+ "learning_rate": 9.029060684455229e-05,
72
+ "loss": 0.599,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.547945205479452,
77
+ "grad_norm": 0.3248140513896942,
78
+ "learning_rate": 8.744861923377001e-05,
79
+ "loss": 0.5933,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.6027397260273972,
84
+ "grad_norm": 0.36872419714927673,
85
+ "learning_rate": 8.429988489749046e-05,
86
+ "loss": 0.5952,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.6575342465753424,
91
+ "grad_norm": 0.3348616659641266,
92
+ "learning_rate": 8.087019554624595e-05,
93
+ "loss": 0.5813,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.7123287671232876,
98
+ "grad_norm": 0.33727309107780457,
99
+ "learning_rate": 7.718764423124892e-05,
100
+ "loss": 0.5511,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.7671232876712328,
105
+ "grad_norm": 0.35852885246276855,
106
+ "learning_rate": 7.32823952303943e-05,
107
+ "loss": 0.5837,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.821917808219178,
112
+ "grad_norm": 0.37122035026550293,
113
+ "learning_rate": 6.918643696856333e-05,
114
+ "loss": 0.5604,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.8767123287671232,
119
+ "grad_norm": 0.3272222578525543,
120
+ "learning_rate": 6.493331999609131e-05,
121
+ "loss": 0.5318,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.9315068493150684,
126
+ "grad_norm": 0.3521849513053894,
127
+ "learning_rate": 6.055788217165383e-05,
128
+ "loss": 0.5598,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.9863013698630136,
133
+ "grad_norm": 0.3393417000770569,
134
+ "learning_rate": 5.609596330063558e-05,
135
+ "loss": 0.5626,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 1.0383561643835617,
140
+ "grad_norm": 0.29794371128082275,
141
+ "learning_rate": 5.1584111566417515e-05,
142
+ "loss": 0.5401,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 1.093150684931507,
147
+ "grad_norm": 0.40294867753982544,
148
+ "learning_rate": 4.705928415924373e-05,
149
+ "loss": 0.4977,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 1.1479452054794521,
154
+ "grad_norm": 0.3701549768447876,
155
+ "learning_rate": 4.255854455485753e-05,
156
+ "loss": 0.4893,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 1.2027397260273973,
161
+ "grad_norm": 0.41681772470474243,
162
+ "learning_rate": 3.811875892253853e-05,
163
+ "loss": 0.509,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 1.2575342465753425,
168
+ "grad_norm": 0.47252005338668823,
169
+ "learning_rate": 3.377629414930396e-05,
170
+ "loss": 0.4866,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 1.3123287671232877,
175
+ "grad_norm": 0.5522735118865967,
176
+ "learning_rate": 2.9566719953798473e-05,
177
+ "loss": 0.4788,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 1.367123287671233,
182
+ "grad_norm": 0.3663751780986786,
183
+ "learning_rate": 2.552451752989865e-05,
184
+ "loss": 0.5067,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 1.4219178082191781,
189
+ "grad_norm": 0.3987874388694763,
190
+ "learning_rate": 2.168279710657149e-05,
191
+ "loss": 0.4634,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 1.4767123287671233,
196
+ "grad_norm": 0.5115519762039185,
197
+ "learning_rate": 1.8073026737492782e-05,
198
+ "loss": 0.4912,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 1.5315068493150685,
203
+ "grad_norm": 0.5251284241676331,
204
+ "learning_rate": 1.4724774541946146e-05,
205
+ "loss": 0.5087,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 1.5863013698630137,
210
+ "grad_norm": 0.5367189049720764,
211
+ "learning_rate": 1.1665466508342877e-05,
212
+ "loss": 0.462,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 1.641095890410959,
217
+ "grad_norm": 0.6373235583305359,
218
+ "learning_rate": 8.920161844226415e-06,
219
+ "loss": 0.482,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 1.6958904109589041,
224
+ "grad_norm": 0.5205274820327759,
225
+ "learning_rate": 6.511347712900545e-06,
226
+ "loss": 0.4816,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 1.7506849315068493,
231
+ "grad_norm": 0.42115122079849243,
232
+ "learning_rate": 4.458755038021029e-06,
233
+ "loss": 0.4663,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 1.8054794520547945,
238
+ "grad_norm": 0.5167638659477234,
239
+ "learning_rate": 2.7791968849206428e-06,
240
+ "loss": 0.4938,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 1.8602739726027397,
245
+ "grad_norm": 0.544147253036499,
246
+ "learning_rate": 1.4864307425078327e-06,
247
+ "loss": 0.4824,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 1.915068493150685,
252
+ "grad_norm": 0.4460655748844147,
253
+ "learning_rate": 5.910458338069191e-07,
254
+ "loss": 0.4946,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 1.9698630136986301,
259
+ "grad_norm": 0.5717807412147522,
260
+ "learning_rate": 1.0037637819431123e-07,
261
+ "loss": 0.4736,
262
+ "step": 360
263
+ }
264
+ ],
265
+ "logging_steps": 10,
266
+ "max_steps": 366,
267
+ "num_input_tokens_seen": 0,
268
+ "num_train_epochs": 2,
269
+ "save_steps": 200,
270
+ "stateful_callbacks": {
271
+ "TrainerControl": {
272
+ "args": {
273
+ "should_epoch_stop": false,
274
+ "should_evaluate": false,
275
+ "should_log": false,
276
+ "should_save": true,
277
+ "should_training_stop": true
278
+ },
279
+ "attributes": {}
280
+ }
281
+ },
282
+ "total_flos": 1.27377858339115e+17,
283
+ "train_batch_size": 2,
284
+ "trial_name": null,
285
+ "trial_params": null
286
+ }