Hugging Face's logo

Prahaladha
/
math-checkpoints

Transformers
Safetensors
Generated from Trainer
sft
trl
unsloth
Model card Files
xet
Community
Prahaladha commited on
Commit
798fea0
·
verified ·
1 Parent(s): 2db4525

Upload phaseC_hard/checkpoint-368/trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. phaseC_hard/checkpoint-368/trainer_state.json +286 -0
phaseC_hard/checkpoint-368/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": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 368,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.027220142905750255,
14
+ "grad_norm": 0.3601450026035309,
15
+ "learning_rate": 9.473684210526315e-06,
16
+ "loss": 0.6011,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.05444028581150051,
21
+ "grad_norm": 0.2935282588005066,
22
+ "learning_rate": 2e-05,
23
+ "loss": 0.599,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.08166042871725077,
28
+ "grad_norm": 0.30616095662117004,
29
+ "learning_rate": 1.9959512065977673e-05,
30
+ "loss": 0.6105,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.10888057162300102,
35
+ "grad_norm": 0.3090261220932007,
36
+ "learning_rate": 1.9838376118470965e-05,
37
+ "loss": 0.5534,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.13610071452875128,
42
+ "grad_norm": 0.3344835042953491,
43
+ "learning_rate": 1.963757306632996e-05,
44
+ "loss": 0.5616,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.16332085743450153,
49
+ "grad_norm": 0.3386900722980499,
50
+ "learning_rate": 1.9358728929699966e-05,
51
+ "loss": 0.5706,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.1905410003402518,
56
+ "grad_norm": 0.3411266505718231,
57
+ "learning_rate": 1.900410167318226e-05,
58
+ "loss": 0.5812,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.21776114324600204,
63
+ "grad_norm": 0.32641148567199707,
64
+ "learning_rate": 1.8576562921769727e-05,
65
+ "loss": 0.5834,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.2449812861517523,
70
+ "grad_norm": 0.350433886051178,
71
+ "learning_rate": 1.8079574707614202e-05,
72
+ "loss": 0.6085,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.27220142905750255,
77
+ "grad_norm": 0.3266001343727112,
78
+ "learning_rate": 1.7517161435920606e-05,
79
+ "loss": 0.5598,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.2994215719632528,
84
+ "grad_norm": 0.2847185432910919,
85
+ "learning_rate": 1.689387729697646e-05,
86
+ "loss": 0.5402,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.32664171486900306,
91
+ "grad_norm": 0.29473233222961426,
92
+ "learning_rate": 1.621476938820071e-05,
93
+ "loss": 0.5294,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.3538618577747533,
98
+ "grad_norm": 0.2978656589984894,
99
+ "learning_rate": 1.5485336844834274e-05,
100
+ "loss": 0.5531,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.3810820006805036,
105
+ "grad_norm": 0.30052629113197327,
106
+ "learning_rate": 1.4711486310215053e-05,
107
+ "loss": 0.5191,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.40830214358625383,
112
+ "grad_norm": 0.29999110102653503,
113
+ "learning_rate": 1.3899484106220816e-05,
114
+ "loss": 0.5227,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.4355222864920041,
119
+ "grad_norm": 0.2978653013706207,
120
+ "learning_rate": 1.3055905491183822e-05,
121
+ "loss": 0.5692,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.46274242939775434,
126
+ "grad_norm": 0.28718307614326477,
127
+ "learning_rate": 1.2187581416165721e-05,
128
+ "loss": 0.5399,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.4899625723035046,
133
+ "grad_norm": 0.3078838884830475,
134
+ "learning_rate": 1.1301543210738383e-05,
135
+ "loss": 0.5865,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.5171827152092549,
140
+ "grad_norm": 0.3012241721153259,
141
+ "learning_rate": 1.040496564618233e-05,
142
+ "loss": 0.5321,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.5444028581150051,
147
+ "grad_norm": 0.3235582709312439,
148
+ "learning_rate": 9.505108837153489e-06,
149
+ "loss": 0.5486,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.5716230010207554,
154
+ "grad_norm": 0.3122597634792328,
155
+ "learning_rate": 8.609259452274559e-06,
156
+ "loss": 0.5399,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.5988431439265056,
161
+ "grad_norm": 0.3299028277397156,
162
+ "learning_rate": 7.724671709703328e-06,
163
+ "loss": 0.5577,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.6260632868322559,
168
+ "grad_norm": 0.3655756711959839,
169
+ "learning_rate": 6.858508635471428e-06,
170
+ "loss": 0.5929,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.6532834297380061,
175
+ "grad_norm": 0.26812079548835754,
176
+ "learning_rate": 6.01778406025928e-06,
177
+ "loss": 0.5583,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.6805035726437564,
182
+ "grad_norm": 0.3320719599723816,
183
+ "learning_rate": 5.209305824293307e-06,
184
+ "loss": 0.5676,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.7077237155495066,
189
+ "grad_norm": 0.3280523121356964,
190
+ "learning_rate": 4.439620650268771e-06,
191
+ "loss": 0.5631,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.7349438584552569,
196
+ "grad_norm": 0.32598164677619934,
197
+ "learning_rate": 3.7149611306944356e-06,
198
+ "loss": 0.5531,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.7621640013610071,
203
+ "grad_norm": 0.3093312084674835,
204
+ "learning_rate": 3.041195258933749e-06,
205
+ "loss": 0.5701,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.7893841442667574,
210
+ "grad_norm": 0.38252192735671997,
211
+ "learning_rate": 2.4237789126191715e-06,
212
+ "loss": 0.5394,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.8166042871725077,
217
+ "grad_norm": 0.3158980906009674,
218
+ "learning_rate": 1.8677116742094858e-06,
219
+ "loss": 0.5671,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.8438244300782579,
224
+ "grad_norm": 0.33259591460227966,
225
+ "learning_rate": 1.3774963464368295e-06,
226
+ "loss": 0.5653,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.8710445729840082,
231
+ "grad_norm": 0.3289727568626404,
232
+ "learning_rate": 9.571024904707238e-07,
233
+ "loss": 0.6028,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.8982647158897584,
238
+ "grad_norm": 0.338840514421463,
239
+ "learning_rate": 6.099342820519183e-07,
240
+ "loss": 0.5445,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.9254848587955087,
245
+ "grad_norm": 0.3472974896430969,
246
+ "learning_rate": 3.38802945883836e-07,
247
+ "loss": 0.5915,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.9527050017012589,
252
+ "grad_norm": 0.31952792406082153,
253
+ "learning_rate": 1.4590399149650769e-07,
254
+ "loss": 0.5696,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.9799251446070092,
259
+ "grad_norm": 0.3372432589530945,
260
+ "learning_rate": 3.27994349175742e-08,
261
+ "loss": 0.5575,
262
+ "step": 360
263
+ }
264
+ ],
265
+ "logging_steps": 10,
266
+ "max_steps": 368,
267
+ "num_input_tokens_seen": 0,
268
+ "num_train_epochs": 1,
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": 1.9595908963212288e+17,
283
+ "train_batch_size": 1,
284
+ "trial_name": null,
285
+ "trial_params": null
286
+ }