Commit
•
f7b4f22
1
Parent(s):
b340b65
Model save
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.084745762711865,
|
| 3 |
+
"eval_accuracy": 0.6756505576208178,
|
| 4 |
+
"eval_loss": 0.8754490613937378,
|
| 5 |
+
"eval_runtime": 924.3,
|
| 6 |
+
"eval_samples_per_second": 1.164,
|
| 7 |
+
"eval_steps_per_second": 0.146
|
| 8 |
+
}
|
runs/Jul18_08-57-27_ca2cf26ddc4c/events.out.tfevents.1721308071.ca2cf26ddc4c.35.1
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2889fab40549be1b01a2467a9442493719f17b6f42c9fb6e68b9a9e7420a15d0
|
| 3 |
+
size 734
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.084745762711865,
|
| 3 |
+
"eval_accuracy": 0.6756505576208178,
|
| 4 |
+
"eval_loss": 0.8754490613937378,
|
| 5 |
+
"eval_runtime": 924.3,
|
| 6 |
+
"eval_samples_per_second": 1.164,
|
| 7 |
+
"eval_steps_per_second": 0.146
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,353 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.793597304128054,
|
| 3 |
+
"best_model_checkpoint": "MCG-NJU/videomae-base-finetuned-TikHaram/checkpoint-120",
|
| 4 |
+
"epoch": 9.084745762711865,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 295,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03389830508474576,
|
| 13 |
+
"grad_norm": 5.0345001220703125,
|
| 14 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 15 |
+
"loss": 1.3726,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06779661016949153,
|
| 20 |
+
"grad_norm": 6.756855487823486,
|
| 21 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 22 |
+
"loss": 1.3354,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.1016949152542373,
|
| 27 |
+
"grad_norm": 10.93206787109375,
|
| 28 |
+
"learning_rate": 5e-05,
|
| 29 |
+
"loss": 1.1179,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.1016949152542373,
|
| 34 |
+
"eval_accuracy": 0.6857624262847515,
|
| 35 |
+
"eval_loss": 0.9409521222114563,
|
| 36 |
+
"eval_runtime": 1237.8509,
|
| 37 |
+
"eval_samples_per_second": 0.959,
|
| 38 |
+
"eval_steps_per_second": 0.12,
|
| 39 |
+
"step": 30
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.0338983050847457,
|
| 43 |
+
"grad_norm": 7.3327813148498535,
|
| 44 |
+
"learning_rate": 4.811320754716982e-05,
|
| 45 |
+
"loss": 0.8248,
|
| 46 |
+
"step": 40
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 1.0677966101694916,
|
| 50 |
+
"grad_norm": 10.208086967468262,
|
| 51 |
+
"learning_rate": 4.6226415094339625e-05,
|
| 52 |
+
"loss": 0.759,
|
| 53 |
+
"step": 50
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 1.1016949152542372,
|
| 57 |
+
"grad_norm": 2.690416097640991,
|
| 58 |
+
"learning_rate": 4.433962264150944e-05,
|
| 59 |
+
"loss": 0.6162,
|
| 60 |
+
"step": 60
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.1016949152542372,
|
| 64 |
+
"eval_accuracy": 0.7497893850042123,
|
| 65 |
+
"eval_loss": 0.6875647902488708,
|
| 66 |
+
"eval_runtime": 1167.6728,
|
| 67 |
+
"eval_samples_per_second": 1.017,
|
| 68 |
+
"eval_steps_per_second": 0.128,
|
| 69 |
+
"step": 60
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 2.0338983050847457,
|
| 73 |
+
"grad_norm": 8.078776359558105,
|
| 74 |
+
"learning_rate": 4.245283018867925e-05,
|
| 75 |
+
"loss": 0.5685,
|
| 76 |
+
"step": 70
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 2.0677966101694913,
|
| 80 |
+
"grad_norm": 4.468865871429443,
|
| 81 |
+
"learning_rate": 4.0566037735849064e-05,
|
| 82 |
+
"loss": 0.4638,
|
| 83 |
+
"step": 80
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 2.1016949152542375,
|
| 87 |
+
"grad_norm": 4.634223937988281,
|
| 88 |
+
"learning_rate": 3.867924528301887e-05,
|
| 89 |
+
"loss": 0.5604,
|
| 90 |
+
"step": 90
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 2.1016949152542375,
|
| 94 |
+
"eval_accuracy": 0.7363100252737995,
|
| 95 |
+
"eval_loss": 0.6748067140579224,
|
| 96 |
+
"eval_runtime": 1179.8147,
|
| 97 |
+
"eval_samples_per_second": 1.006,
|
| 98 |
+
"eval_steps_per_second": 0.126,
|
| 99 |
+
"step": 90
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 3.0338983050847457,
|
| 103 |
+
"grad_norm": 1.432814359664917,
|
| 104 |
+
"learning_rate": 3.679245283018868e-05,
|
| 105 |
+
"loss": 0.4324,
|
| 106 |
+
"step": 100
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 3.0677966101694913,
|
| 110 |
+
"grad_norm": 8.20600700378418,
|
| 111 |
+
"learning_rate": 3.490566037735849e-05,
|
| 112 |
+
"loss": 0.3613,
|
| 113 |
+
"step": 110
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 3.1016949152542375,
|
| 117 |
+
"grad_norm": 5.8781514167785645,
|
| 118 |
+
"learning_rate": 3.30188679245283e-05,
|
| 119 |
+
"loss": 0.3628,
|
| 120 |
+
"step": 120
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 3.1016949152542375,
|
| 124 |
+
"eval_accuracy": 0.793597304128054,
|
| 125 |
+
"eval_loss": 0.6228342056274414,
|
| 126 |
+
"eval_runtime": 1039.6898,
|
| 127 |
+
"eval_samples_per_second": 1.142,
|
| 128 |
+
"eval_steps_per_second": 0.143,
|
| 129 |
+
"step": 120
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 4.033898305084746,
|
| 133 |
+
"grad_norm": 5.754726886749268,
|
| 134 |
+
"learning_rate": 3.113207547169811e-05,
|
| 135 |
+
"loss": 0.2648,
|
| 136 |
+
"step": 130
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 4.067796610169491,
|
| 140 |
+
"grad_norm": 4.939706325531006,
|
| 141 |
+
"learning_rate": 2.9245283018867926e-05,
|
| 142 |
+
"loss": 0.2436,
|
| 143 |
+
"step": 140
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 4.101694915254237,
|
| 147 |
+
"grad_norm": 1.7757413387298584,
|
| 148 |
+
"learning_rate": 2.7358490566037738e-05,
|
| 149 |
+
"loss": 0.2861,
|
| 150 |
+
"step": 150
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 4.101694915254237,
|
| 154 |
+
"eval_accuracy": 0.7422072451558551,
|
| 155 |
+
"eval_loss": 0.7411791682243347,
|
| 156 |
+
"eval_runtime": 1006.166,
|
| 157 |
+
"eval_samples_per_second": 1.18,
|
| 158 |
+
"eval_steps_per_second": 0.148,
|
| 159 |
+
"step": 150
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 5.033898305084746,
|
| 163 |
+
"grad_norm": 9.85596752166748,
|
| 164 |
+
"learning_rate": 2.547169811320755e-05,
|
| 165 |
+
"loss": 0.1681,
|
| 166 |
+
"step": 160
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 5.067796610169491,
|
| 170 |
+
"grad_norm": 5.040333271026611,
|
| 171 |
+
"learning_rate": 2.358490566037736e-05,
|
| 172 |
+
"loss": 0.3501,
|
| 173 |
+
"step": 170
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 5.101694915254237,
|
| 177 |
+
"grad_norm": 7.130555629730225,
|
| 178 |
+
"learning_rate": 2.1698113207547172e-05,
|
| 179 |
+
"loss": 0.213,
|
| 180 |
+
"step": 180
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 5.101694915254237,
|
| 184 |
+
"eval_accuracy": 0.7666385846672283,
|
| 185 |
+
"eval_loss": 0.6355797052383423,
|
| 186 |
+
"eval_runtime": 1155.5919,
|
| 187 |
+
"eval_samples_per_second": 1.027,
|
| 188 |
+
"eval_steps_per_second": 0.129,
|
| 189 |
+
"step": 180
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 6.033898305084746,
|
| 193 |
+
"grad_norm": 3.2904608249664307,
|
| 194 |
+
"learning_rate": 1.9811320754716984e-05,
|
| 195 |
+
"loss": 0.1472,
|
| 196 |
+
"step": 190
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 6.067796610169491,
|
| 200 |
+
"grad_norm": 2.7492494583129883,
|
| 201 |
+
"learning_rate": 1.7924528301886792e-05,
|
| 202 |
+
"loss": 0.1845,
|
| 203 |
+
"step": 200
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 6.101694915254237,
|
| 207 |
+
"grad_norm": 1.3256348371505737,
|
| 208 |
+
"learning_rate": 1.6037735849056604e-05,
|
| 209 |
+
"loss": 0.1428,
|
| 210 |
+
"step": 210
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 6.101694915254237,
|
| 214 |
+
"eval_accuracy": 0.7590564448188711,
|
| 215 |
+
"eval_loss": 0.6791483163833618,
|
| 216 |
+
"eval_runtime": 1101.1588,
|
| 217 |
+
"eval_samples_per_second": 1.078,
|
| 218 |
+
"eval_steps_per_second": 0.135,
|
| 219 |
+
"step": 210
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 7.033898305084746,
|
| 223 |
+
"grad_norm": 1.3044459819793701,
|
| 224 |
+
"learning_rate": 1.4150943396226415e-05,
|
| 225 |
+
"loss": 0.1269,
|
| 226 |
+
"step": 220
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 7.067796610169491,
|
| 230 |
+
"grad_norm": 1.1943762302398682,
|
| 231 |
+
"learning_rate": 1.2264150943396227e-05,
|
| 232 |
+
"loss": 0.057,
|
| 233 |
+
"step": 230
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 7.101694915254237,
|
| 237 |
+
"grad_norm": 20.165433883666992,
|
| 238 |
+
"learning_rate": 1.0377358490566038e-05,
|
| 239 |
+
"loss": 0.1536,
|
| 240 |
+
"step": 240
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 7.101694915254237,
|
| 244 |
+
"eval_accuracy": 0.7523167649536647,
|
| 245 |
+
"eval_loss": 0.7612273097038269,
|
| 246 |
+
"eval_runtime": 1207.276,
|
| 247 |
+
"eval_samples_per_second": 0.983,
|
| 248 |
+
"eval_steps_per_second": 0.123,
|
| 249 |
+
"step": 240
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 8.033898305084746,
|
| 253 |
+
"grad_norm": 0.7759658694267273,
|
| 254 |
+
"learning_rate": 8.49056603773585e-06,
|
| 255 |
+
"loss": 0.0919,
|
| 256 |
+
"step": 250
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 8.067796610169491,
|
| 260 |
+
"grad_norm": 0.4191964268684387,
|
| 261 |
+
"learning_rate": 6.60377358490566e-06,
|
| 262 |
+
"loss": 0.2008,
|
| 263 |
+
"step": 260
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 8.101694915254237,
|
| 267 |
+
"grad_norm": 0.7120205760002136,
|
| 268 |
+
"learning_rate": 4.716981132075472e-06,
|
| 269 |
+
"loss": 0.1594,
|
| 270 |
+
"step": 270
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 8.101694915254237,
|
| 274 |
+
"eval_accuracy": 0.7624262847514743,
|
| 275 |
+
"eval_loss": 0.7678460478782654,
|
| 276 |
+
"eval_runtime": 1195.7328,
|
| 277 |
+
"eval_samples_per_second": 0.993,
|
| 278 |
+
"eval_steps_per_second": 0.125,
|
| 279 |
+
"step": 270
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 9.033898305084746,
|
| 283 |
+
"grad_norm": 3.204578161239624,
|
| 284 |
+
"learning_rate": 2.830188679245283e-06,
|
| 285 |
+
"loss": 0.1085,
|
| 286 |
+
"step": 280
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 9.067796610169491,
|
| 290 |
+
"grad_norm": 2.541273355484009,
|
| 291 |
+
"learning_rate": 9.433962264150943e-07,
|
| 292 |
+
"loss": 0.1056,
|
| 293 |
+
"step": 290
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 9.084745762711865,
|
| 297 |
+
"eval_accuracy": 0.7657961246840775,
|
| 298 |
+
"eval_loss": 0.7785321474075317,
|
| 299 |
+
"eval_runtime": 1147.1184,
|
| 300 |
+
"eval_samples_per_second": 1.035,
|
| 301 |
+
"eval_steps_per_second": 0.13,
|
| 302 |
+
"step": 295
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 9.084745762711865,
|
| 306 |
+
"step": 295,
|
| 307 |
+
"total_flos": 2.8959057571998597e+18,
|
| 308 |
+
"train_loss": 0.4020373065592879,
|
| 309 |
+
"train_runtime": 14069.0887,
|
| 310 |
+
"train_samples_per_second": 0.168,
|
| 311 |
+
"train_steps_per_second": 0.021
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 9.084745762711865,
|
| 315 |
+
"eval_accuracy": 0.6756505576208178,
|
| 316 |
+
"eval_loss": 0.875449001789093,
|
| 317 |
+
"eval_runtime": 932.4911,
|
| 318 |
+
"eval_samples_per_second": 1.154,
|
| 319 |
+
"eval_steps_per_second": 0.145,
|
| 320 |
+
"step": 295
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 9.084745762711865,
|
| 324 |
+
"eval_accuracy": 0.6756505576208178,
|
| 325 |
+
"eval_loss": 0.8754490613937378,
|
| 326 |
+
"eval_runtime": 924.3,
|
| 327 |
+
"eval_samples_per_second": 1.164,
|
| 328 |
+
"eval_steps_per_second": 0.146,
|
| 329 |
+
"step": 295
|
| 330 |
+
}
|
| 331 |
+
],
|
| 332 |
+
"logging_steps": 10,
|
| 333 |
+
"max_steps": 295,
|
| 334 |
+
"num_input_tokens_seen": 0,
|
| 335 |
+
"num_train_epochs": 9223372036854775807,
|
| 336 |
+
"save_steps": 500,
|
| 337 |
+
"stateful_callbacks": {
|
| 338 |
+
"TrainerControl": {
|
| 339 |
+
"args": {
|
| 340 |
+
"should_epoch_stop": false,
|
| 341 |
+
"should_evaluate": false,
|
| 342 |
+
"should_log": false,
|
| 343 |
+
"should_save": true,
|
| 344 |
+
"should_training_stop": true
|
| 345 |
+
},
|
| 346 |
+
"attributes": {}
|
| 347 |
+
}
|
| 348 |
+
},
|
| 349 |
+
"total_flos": 2.8959057571998597e+18,
|
| 350 |
+
"train_batch_size": 8,
|
| 351 |
+
"trial_name": null,
|
| 352 |
+
"trial_params": null
|
| 353 |
+
}
|