Hugging Face's logo

moogician
/
kodcode-v1-checkpoint-28

Safetensors
qwen2
Model card Files
xet
Community
moogician commited on
Commit
6998937
·
verified ·
1 Parent(s): ce57f6e

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +229 -0
trainer_state.json ADDED
@@ -0,0 +1,229 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0361990950226245,
5
+ "eval_steps": 500,
6
+ "global_step": 28,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03619909502262444,
13
+ "grad_norm": 2.867363214492798,
14
+ "learning_rate": 3.7037037037037036e-07,
15
+ "loss": 0.7721,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.07239819004524888,
20
+ "grad_norm": 2.795196771621704,
21
+ "learning_rate": 7.407407407407407e-07,
22
+ "loss": 0.7534,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.1085972850678733,
27
+ "grad_norm": 2.8518760204315186,
28
+ "learning_rate": 1.111111111111111e-06,
29
+ "loss": 0.7531,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.14479638009049775,
34
+ "grad_norm": 2.7276031970977783,
35
+ "learning_rate": 1.4814814814814815e-06,
36
+ "loss": 0.7604,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.18099547511312217,
41
+ "grad_norm": 2.6922106742858887,
42
+ "learning_rate": 1.8518518518518519e-06,
43
+ "loss": 0.7775,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.2171945701357466,
48
+ "grad_norm": 2.8505051136016846,
49
+ "learning_rate": 2.222222222222222e-06,
50
+ "loss": 0.7689,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.25339366515837103,
55
+ "grad_norm": 2.711665153503418,
56
+ "learning_rate": 2.5925925925925925e-06,
57
+ "loss": 0.7687,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.2895927601809955,
62
+ "grad_norm": 2.7716190814971924,
63
+ "learning_rate": 2.962962962962963e-06,
64
+ "loss": 0.769,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.3257918552036199,
69
+ "grad_norm": 2.607780933380127,
70
+ "learning_rate": 3.3333333333333333e-06,
71
+ "loss": 0.7674,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.36199095022624433,
76
+ "grad_norm": 2.305697202682495,
77
+ "learning_rate": 3.7037037037037037e-06,
78
+ "loss": 0.7529,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.39819004524886875,
83
+ "grad_norm": 1.5863313674926758,
84
+ "learning_rate": 4.074074074074074e-06,
85
+ "loss": 0.7259,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.4343891402714932,
90
+ "grad_norm": 1.2682443857192993,
91
+ "learning_rate": 4.444444444444444e-06,
92
+ "loss": 0.7206,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.47058823529411764,
97
+ "grad_norm": 1.010533332824707,
98
+ "learning_rate": 4.814814814814815e-06,
99
+ "loss": 0.6921,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.5067873303167421,
104
+ "grad_norm": 0.9136636257171631,
105
+ "learning_rate": 5.185185185185185e-06,
106
+ "loss": 0.6987,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.5429864253393665,
111
+ "grad_norm": 1.275439739227295,
112
+ "learning_rate": 5.555555555555557e-06,
113
+ "loss": 0.6997,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.579185520361991,
118
+ "grad_norm": 1.4839826822280884,
119
+ "learning_rate": 5.925925925925926e-06,
120
+ "loss": 0.6773,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.6153846153846154,
125
+ "grad_norm": 1.5695866346359253,
126
+ "learning_rate": 6.296296296296297e-06,
127
+ "loss": 0.6582,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.6515837104072398,
132
+ "grad_norm": 1.6517796516418457,
133
+ "learning_rate": 6.666666666666667e-06,
134
+ "loss": 0.6912,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.6877828054298643,
139
+ "grad_norm": 1.3464380502700806,
140
+ "learning_rate": 7.0370370370370375e-06,
141
+ "loss": 0.6636,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.7239819004524887,
146
+ "grad_norm": 1.0865730047225952,
147
+ "learning_rate": 7.4074074074074075e-06,
148
+ "loss": 0.6571,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.7601809954751131,
153
+ "grad_norm": 0.8862206339836121,
154
+ "learning_rate": 7.77777777777778e-06,
155
+ "loss": 0.6583,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.7963800904977375,
160
+ "grad_norm": 0.9783180952072144,
161
+ "learning_rate": 8.148148148148148e-06,
162
+ "loss": 0.6688,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.832579185520362,
167
+ "grad_norm": 0.7160141468048096,
168
+ "learning_rate": 8.518518518518519e-06,
169
+ "loss": 0.6408,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.8687782805429864,
174
+ "grad_norm": 0.6991405487060547,
175
+ "learning_rate": 8.888888888888888e-06,
176
+ "loss": 0.6447,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.9049773755656109,
181
+ "grad_norm": 0.7763178944587708,
182
+ "learning_rate": 9.25925925925926e-06,
183
+ "loss": 0.6512,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.9411764705882353,
188
+ "grad_norm": 0.5905259847640991,
189
+ "learning_rate": 9.62962962962963e-06,
190
+ "loss": 0.6337,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.9773755656108597,
195
+ "grad_norm": 0.7515297532081604,
196
+ "learning_rate": 1e-05,
197
+ "loss": 0.655,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 1.0361990950226245,
202
+ "grad_norm": 1.260597825050354,
203
+ "learning_rate": 9.999582149277188e-06,
204
+ "loss": 1.2675,
205
+ "step": 28
206
+ }
207
+ ],
208
+ "logging_steps": 1,
209
+ "max_steps": 270,
210
+ "num_input_tokens_seen": 0,
211
+ "num_train_epochs": 10,
212
+ "save_steps": 28,
213
+ "stateful_callbacks": {
214
+ "TrainerControl": {
215
+ "args": {
216
+ "should_epoch_stop": false,
217
+ "should_evaluate": false,
218
+ "should_log": false,
219
+ "should_save": true,
220
+ "should_training_stop": false
221
+ },
222
+ "attributes": {}
223
+ }
224
+ },
225
+ "total_flos": 35571485245440.0,
226
+ "train_batch_size": 1,
227
+ "trial_name": null,
228
+ "trial_params": null
229
+ }