Bifrost-AI/NextCoder-Mirage-sol-7B
223
1{
2 "best_global_step": null,
3 "best_metric": null,
4 "best_model_checkpoint": null,
5 "epoch": 0.5,
6 "eval_steps": 500,
7 "global_step": 500,
8 "is_hyper_param_search": false,
9 "is_local_process_zero": true,
10 "is_world_process_zero": true,
11 "log_history": [
12 {
13 "epoch": 0.02,
14 "grad_norm": 6.0,
15 "learning_rate": 3.8000000000000005e-06,
16 "loss": 1.4753,
17 "mean_token_accuracy": 0.6514762923121452,
18 "num_tokens": 9165.0,
19 "step": 20
20 },
21 {
22 "epoch": 0.04,
23 "grad_norm": 6.84375,
24 "learning_rate": 7.800000000000002e-06,
25 "loss": 1.3604,
26 "mean_token_accuracy": 0.6717274159193038,
27 "num_tokens": 19130.0,
28 "step": 40
29 },
30 {
31 "epoch": 0.06,
32 "grad_norm": 4.90625,
33 "learning_rate": 1.18e-05,
34 "loss": 1.2917,
35 "mean_token_accuracy": 0.691003431379795,
36 "num_tokens": 30279.0,
37 "step": 60
38 },
39 {
40 "epoch": 0.08,
41 "grad_norm": 30.625,
42 "learning_rate": 1.58e-05,
43 "loss": 0.9447,
44 "mean_token_accuracy": 0.7457822680473327,
45 "num_tokens": 42533.0,
46 "step": 80
47 },
48 {
49 "epoch": 0.1,
50 "grad_norm": 9.875,
51 "learning_rate": 1.98e-05,
52 "loss": 1.3137,
53 "mean_token_accuracy": 0.6690018624067307,
54 "num_tokens": 48242.0,
55 "step": 100
56 },
57 {
58 "epoch": 0.12,
59 "grad_norm": 18.0,
60 "learning_rate": 1.988886498744505e-05,
61 "loss": 1.0214,
62 "mean_token_accuracy": 0.7285905957221985,
63 "num_tokens": 59331.0,
64 "step": 120
65 },
66 {
67 "epoch": 0.14,
68 "grad_norm": 3.515625,
69 "learning_rate": 1.953454172319001e-05,
70 "loss": 1.0517,
71 "mean_token_accuracy": 0.7213401407003402,
72 "num_tokens": 68979.0,
73 "step": 140
74 },
75 {
76 "epoch": 0.16,
77 "grad_norm": 5.9375,
78 "learning_rate": 1.894544639838025e-05,
79 "loss": 1.1587,
80 "mean_token_accuracy": 0.7021817207336426,
81 "num_tokens": 76070.0,
82 "step": 160
83 },
84 {
85 "epoch": 0.18,
86 "grad_norm": 7.0625,
87 "learning_rate": 1.8136084495007874e-05,
88 "loss": 1.0255,
89 "mean_token_accuracy": 0.7250557497143746,
90 "num_tokens": 85738.0,
91 "step": 180
92 },
93 {
94 "epoch": 0.2,
95 "grad_norm": 18.875,
96 "learning_rate": 1.7126385189252055e-05,
97 "loss": 1.1949,
98 "mean_token_accuracy": 0.6837209314107895,
99 "num_tokens": 94928.0,
100 "step": 200
101 },
102 {
103 "epoch": 0.22,
104 "grad_norm": 7.5,
105 "learning_rate": 1.594121062902039e-05,
106 "loss": 1.0857,
107 "mean_token_accuracy": 0.7113691180944443,
108 "num_tokens": 104773.0,
109 "step": 220
110 },
111 {
112 "epoch": 0.24,
113 "grad_norm": 6.625,
114 "learning_rate": 1.4609743745354625e-05,
115 "loss": 0.9951,
116 "mean_token_accuracy": 0.7261969804763794,
117 "num_tokens": 114064.0,
118 "step": 240
119 },
120 {
121 "epoch": 0.26,
122 "grad_norm": 19.125,
123 "learning_rate": 1.3164769671815862e-05,
124 "loss": 1.0099,
125 "mean_token_accuracy": 0.7223263427615165,
126 "num_tokens": 123805.0,
127 "step": 260
128 },
129 {
130 "epoch": 0.28,
131 "grad_norm": 5.03125,
132 "learning_rate": 1.164186846568863e-05,
133 "loss": 1.0713,
134 "mean_token_accuracy": 0.7073337942361831,
135 "num_tokens": 134324.0,
136 "step": 280
137 },
138 {
139 "epoch": 0.3,
140 "grad_norm": 11.5,
141 "learning_rate": 1.0078539008887114e-05,
142 "loss": 0.9601,
143 "mean_token_accuracy": 0.7360554546117782,
144 "num_tokens": 143153.0,
145 "step": 300
146 },
147 {
148 "epoch": 0.32,
149 "grad_norm": 7.9375,
150 "learning_rate": 8.51327566103077e-06,
151 "loss": 0.9354,
152 "mean_token_accuracy": 0.7383034735918045,
153 "num_tokens": 154603.0,
154 "step": 320
155 },
156 {
157 "epoch": 0.34,
158 "grad_norm": 6.875,
159 "learning_rate": 6.984620400555044e-06,
160 "loss": 0.9676,
161 "mean_token_accuracy": 0.7273150086402893,
162 "num_tokens": 167175.0,
163 "step": 340
164 },
165 {
166 "epoch": 0.36,
167 "grad_norm": 17.625,
168 "learning_rate": 5.53021379328879e-06,
169 "loss": 1.085,
170 "mean_token_accuracy": 0.715969854593277,
171 "num_tokens": 176751.0,
172 "step": 360
173 },
174 {
175 "epoch": 0.38,
176 "grad_norm": 6.0625,
177 "learning_rate": 4.185868156801695e-06,
178 "loss": 1.0635,
179 "mean_token_accuracy": 0.7170247107744216,
180 "num_tokens": 185233.0,
181 "step": 380
182 },
183 {
184 "epoch": 0.4,
185 "grad_norm": 7.25,
186 "learning_rate": 2.9846857422914434e-06,
187 "loss": 1.0838,
188 "mean_token_accuracy": 0.7044813245534897,
189 "num_tokens": 193072.0,
190 "step": 400
191 },
192 {
193 "epoch": 0.42,
194 "grad_norm": 6.21875,
195 "learning_rate": 1.956243647299155e-06,
196 "loss": 1.006,
197 "mean_token_accuracy": 0.7172566086053849,
198 "num_tokens": 204372.0,
199 "step": 420
200 },
201 {
202 "epoch": 0.44,
203 "grad_norm": 11.8125,
204 "learning_rate": 1.1258655294071686e-06,
205 "loss": 0.9791,
206 "mean_token_accuracy": 0.727970740199089,
207 "num_tokens": 216681.0,
208 "step": 440
209 },
210 {
211 "epoch": 0.46,
212 "grad_norm": 5.5,
213 "learning_rate": 5.13998053744954e-07,
214 "loss": 1.0866,
215 "mean_token_accuracy": 0.7147636383771896,
216 "num_tokens": 226708.0,
217 "step": 460
218 },
219 {
220 "epoch": 0.48,
221 "grad_norm": 11.5,
222 "learning_rate": 1.357074282350457e-07,
223 "loss": 1.01,
224 "mean_token_accuracy": 0.7146593451499939,
225 "num_tokens": 237866.0,
226 "step": 480
227 },
228 {
229 "epoch": 0.5,
230 "grad_norm": 6.90625,
231 "learning_rate": 3.0842355210336515e-10,
232 "loss": 1.1541,
233 "mean_token_accuracy": 0.68363136947155,
234 "num_tokens": 245487.0,
235 "step": 500
236 }
237 ],
238 "logging_steps": 20,
239 "max_steps": 500,
240 "num_input_tokens_seen": 0,
241 "num_train_epochs": 1,
242 "save_steps": 500,
243 "stateful_callbacks": {
244 "TrainerControl": {
245 "args": {
246 "should_epoch_stop": false,
247 "should_evaluate": false,
248 "should_log": false,
249 "should_save": true,
250 "should_training_stop": true
251 },
252 "attributes": {}
253 }
254 },
255 "total_flos": 1.0414470479035392e+16,
256 "train_batch_size": 1,
257 "trial_name": null,
258 "trial_params": null
259}
260