End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0625,
|
| 3 |
+
"eval_accuracy": 0.15853658536585366,
|
| 4 |
+
"eval_loss": 2.5910537242889404,
|
| 5 |
+
"eval_runtime": 70.209,
|
| 6 |
+
"eval_samples_per_second": 1.168,
|
| 7 |
+
"eval_steps_per_second": 0.299
|
| 8 |
+
}
|
runs/Jan27_13-55-12_0e39fed15667/events.out.tfevents.1737988433.0e39fed15667.404.2
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:e785eb03feb43ad987b7a0c0d0af7ef56269e4fcdb64d9bbb795d4e8ba9c9bf3
|
| 3 |
+
size 734
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0625,
|
| 3 |
+
"eval_accuracy": 0.15853658536585366,
|
| 4 |
+
"eval_loss": 2.5910537242889404,
|
| 5 |
+
"eval_runtime": 70.209,
|
| 6 |
+
"eval_samples_per_second": 1.168,
|
| 7 |
+
"eval_steps_per_second": 0.299
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,404 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.09375,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-finetuned-NOSTRO-Nuovo-subset/checkpoint-280",
|
| 4 |
+
"epoch": 3.0625,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 448,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.022321428571428572,
|
| 13 |
+
"grad_norm": 10.661712646484375,
|
| 14 |
+
"learning_rate": 0.004888392857142857,
|
| 15 |
+
"loss": 3.7577,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.044642857142857144,
|
| 20 |
+
"grad_norm": 11.643506050109863,
|
| 21 |
+
"learning_rate": 0.004776785714285714,
|
| 22 |
+
"loss": 3.8846,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.06696428571428571,
|
| 27 |
+
"grad_norm": 6.997533321380615,
|
| 28 |
+
"learning_rate": 0.004665178571428572,
|
| 29 |
+
"loss": 3.5104,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.08928571428571429,
|
| 34 |
+
"grad_norm": 3.857959270477295,
|
| 35 |
+
"learning_rate": 0.0045535714285714285,
|
| 36 |
+
"loss": 3.0997,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.11160714285714286,
|
| 41 |
+
"grad_norm": 7.694955348968506,
|
| 42 |
+
"learning_rate": 0.004441964285714285,
|
| 43 |
+
"loss": 3.0891,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.13392857142857142,
|
| 48 |
+
"grad_norm": 6.335569858551025,
|
| 49 |
+
"learning_rate": 0.004330357142857143,
|
| 50 |
+
"loss": 3.1063,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.15625,
|
| 55 |
+
"grad_norm": 6.71449089050293,
|
| 56 |
+
"learning_rate": 0.00421875,
|
| 57 |
+
"loss": 2.9859,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.17857142857142858,
|
| 62 |
+
"grad_norm": 3.177128553390503,
|
| 63 |
+
"learning_rate": 0.004107142857142857,
|
| 64 |
+
"loss": 3.0683,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.20089285714285715,
|
| 69 |
+
"grad_norm": 3.323209285736084,
|
| 70 |
+
"learning_rate": 0.0039955357142857145,
|
| 71 |
+
"loss": 2.7508,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.22321428571428573,
|
| 76 |
+
"grad_norm": 3.6122429370880127,
|
| 77 |
+
"learning_rate": 0.0038839285714285716,
|
| 78 |
+
"loss": 2.6113,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.24553571428571427,
|
| 83 |
+
"grad_norm": 2.3688178062438965,
|
| 84 |
+
"learning_rate": 0.0037723214285714287,
|
| 85 |
+
"loss": 1.987,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.26785714285714285,
|
| 90 |
+
"grad_norm": 4.9541215896606445,
|
| 91 |
+
"learning_rate": 0.0036607142857142854,
|
| 92 |
+
"loss": 3.0538,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.29017857142857145,
|
| 97 |
+
"grad_norm": 2.793215751647949,
|
| 98 |
+
"learning_rate": 0.003549107142857143,
|
| 99 |
+
"loss": 2.9083,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.3125,
|
| 104 |
+
"grad_norm": 2.4145069122314453,
|
| 105 |
+
"learning_rate": 0.0034375,
|
| 106 |
+
"loss": 2.8766,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.3125,
|
| 111 |
+
"eval_accuracy": 0.0625,
|
| 112 |
+
"eval_loss": 2.7276196479797363,
|
| 113 |
+
"eval_runtime": 43.9026,
|
| 114 |
+
"eval_samples_per_second": 1.458,
|
| 115 |
+
"eval_steps_per_second": 0.364,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.0223214285714286,
|
| 120 |
+
"grad_norm": 3.8258724212646484,
|
| 121 |
+
"learning_rate": 0.003325892857142857,
|
| 122 |
+
"loss": 2.7419,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.0446428571428572,
|
| 127 |
+
"grad_norm": 2.8611817359924316,
|
| 128 |
+
"learning_rate": 0.0032142857142857147,
|
| 129 |
+
"loss": 2.9858,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.0669642857142858,
|
| 134 |
+
"grad_norm": 1.5673381090164185,
|
| 135 |
+
"learning_rate": 0.0031026785714285718,
|
| 136 |
+
"loss": 2.7431,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.0892857142857142,
|
| 141 |
+
"grad_norm": 1.6212363243103027,
|
| 142 |
+
"learning_rate": 0.0029910714285714284,
|
| 143 |
+
"loss": 2.6825,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.1116071428571428,
|
| 148 |
+
"grad_norm": 2.7107715606689453,
|
| 149 |
+
"learning_rate": 0.0028794642857142855,
|
| 150 |
+
"loss": 2.4267,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.1339285714285714,
|
| 155 |
+
"grad_norm": 2.5624172687530518,
|
| 156 |
+
"learning_rate": 0.002767857142857143,
|
| 157 |
+
"loss": 2.4435,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.15625,
|
| 162 |
+
"grad_norm": 1.173656940460205,
|
| 163 |
+
"learning_rate": 0.00265625,
|
| 164 |
+
"loss": 2.8848,
|
| 165 |
+
"step": 210
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.1785714285714286,
|
| 169 |
+
"grad_norm": 1.2296289205551147,
|
| 170 |
+
"learning_rate": 0.002544642857142857,
|
| 171 |
+
"loss": 2.7724,
|
| 172 |
+
"step": 220
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.2008928571428572,
|
| 176 |
+
"grad_norm": 1.0573370456695557,
|
| 177 |
+
"learning_rate": 0.0024330357142857144,
|
| 178 |
+
"loss": 2.7356,
|
| 179 |
+
"step": 230
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.2232142857142858,
|
| 183 |
+
"grad_norm": 0.9930482506752014,
|
| 184 |
+
"learning_rate": 0.0023214285714285715,
|
| 185 |
+
"loss": 2.5956,
|
| 186 |
+
"step": 240
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.2455357142857142,
|
| 190 |
+
"grad_norm": 0.8850785493850708,
|
| 191 |
+
"learning_rate": 0.0022098214285714286,
|
| 192 |
+
"loss": 2.6961,
|
| 193 |
+
"step": 250
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.2678571428571428,
|
| 197 |
+
"grad_norm": 1.2825168371200562,
|
| 198 |
+
"learning_rate": 0.0020982142857142857,
|
| 199 |
+
"loss": 2.6601,
|
| 200 |
+
"step": 260
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.2901785714285714,
|
| 204 |
+
"grad_norm": 1.7537394762039185,
|
| 205 |
+
"learning_rate": 0.001986607142857143,
|
| 206 |
+
"loss": 2.5393,
|
| 207 |
+
"step": 270
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.3125,
|
| 211 |
+
"grad_norm": 1.3740110397338867,
|
| 212 |
+
"learning_rate": 0.001875,
|
| 213 |
+
"loss": 2.719,
|
| 214 |
+
"step": 280
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.3125,
|
| 218 |
+
"eval_accuracy": 0.09375,
|
| 219 |
+
"eval_loss": 2.659668445587158,
|
| 220 |
+
"eval_runtime": 44.7095,
|
| 221 |
+
"eval_samples_per_second": 1.431,
|
| 222 |
+
"eval_steps_per_second": 0.358,
|
| 223 |
+
"step": 280
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.0223214285714284,
|
| 227 |
+
"grad_norm": 1.630075216293335,
|
| 228 |
+
"learning_rate": 0.0017633928571428573,
|
| 229 |
+
"loss": 2.6041,
|
| 230 |
+
"step": 290
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.044642857142857,
|
| 234 |
+
"grad_norm": 1.299541711807251,
|
| 235 |
+
"learning_rate": 0.0016517857142857144,
|
| 236 |
+
"loss": 2.5322,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.0669642857142856,
|
| 241 |
+
"grad_norm": 1.2279021739959717,
|
| 242 |
+
"learning_rate": 0.0015401785714285715,
|
| 243 |
+
"loss": 2.7214,
|
| 244 |
+
"step": 310
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.0892857142857144,
|
| 248 |
+
"grad_norm": 0.823603630065918,
|
| 249 |
+
"learning_rate": 0.0014285714285714286,
|
| 250 |
+
"loss": 2.5328,
|
| 251 |
+
"step": 320
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 2.111607142857143,
|
| 255 |
+
"grad_norm": 1.4392638206481934,
|
| 256 |
+
"learning_rate": 0.0013169642857142857,
|
| 257 |
+
"loss": 2.6212,
|
| 258 |
+
"step": 330
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 2.1339285714285716,
|
| 262 |
+
"grad_norm": 1.9096788167953491,
|
| 263 |
+
"learning_rate": 0.001205357142857143,
|
| 264 |
+
"loss": 2.6821,
|
| 265 |
+
"step": 340
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 2.15625,
|
| 269 |
+
"grad_norm": 1.3150078058242798,
|
| 270 |
+
"learning_rate": 0.00109375,
|
| 271 |
+
"loss": 2.4551,
|
| 272 |
+
"step": 350
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.1785714285714284,
|
| 276 |
+
"grad_norm": 1.3114469051361084,
|
| 277 |
+
"learning_rate": 0.0009821428571428572,
|
| 278 |
+
"loss": 2.5904,
|
| 279 |
+
"step": 360
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.200892857142857,
|
| 283 |
+
"grad_norm": 1.3170655965805054,
|
| 284 |
+
"learning_rate": 0.0008705357142857143,
|
| 285 |
+
"loss": 2.5248,
|
| 286 |
+
"step": 370
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 2.2232142857142856,
|
| 290 |
+
"grad_norm": 1.2158620357513428,
|
| 291 |
+
"learning_rate": 0.0007589285714285714,
|
| 292 |
+
"loss": 2.6605,
|
| 293 |
+
"step": 380
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 2.2455357142857144,
|
| 297 |
+
"grad_norm": 1.0650196075439453,
|
| 298 |
+
"learning_rate": 0.0006473214285714286,
|
| 299 |
+
"loss": 2.7011,
|
| 300 |
+
"step": 390
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 2.267857142857143,
|
| 304 |
+
"grad_norm": 0.740188479423523,
|
| 305 |
+
"learning_rate": 0.0005357142857142857,
|
| 306 |
+
"loss": 2.6101,
|
| 307 |
+
"step": 400
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 2.2901785714285716,
|
| 311 |
+
"grad_norm": 0.9205682873725891,
|
| 312 |
+
"learning_rate": 0.0004241071428571429,
|
| 313 |
+
"loss": 2.5906,
|
| 314 |
+
"step": 410
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.3125,
|
| 318 |
+
"grad_norm": 0.952158510684967,
|
| 319 |
+
"learning_rate": 0.0003125,
|
| 320 |
+
"loss": 2.6488,
|
| 321 |
+
"step": 420
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.3125,
|
| 325 |
+
"eval_accuracy": 0.09375,
|
| 326 |
+
"eval_loss": 2.63785719871521,
|
| 327 |
+
"eval_runtime": 45.7954,
|
| 328 |
+
"eval_samples_per_second": 1.398,
|
| 329 |
+
"eval_steps_per_second": 0.349,
|
| 330 |
+
"step": 420
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 3.0223214285714284,
|
| 334 |
+
"grad_norm": 0.751361608505249,
|
| 335 |
+
"learning_rate": 0.00020089285714285717,
|
| 336 |
+
"loss": 2.5654,
|
| 337 |
+
"step": 430
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 3.044642857142857,
|
| 341 |
+
"grad_norm": 1.7467005252838135,
|
| 342 |
+
"learning_rate": 8.928571428571429e-05,
|
| 343 |
+
"loss": 2.573,
|
| 344 |
+
"step": 440
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 3.0625,
|
| 348 |
+
"eval_accuracy": 0.09375,
|
| 349 |
+
"eval_loss": 2.6362757682800293,
|
| 350 |
+
"eval_runtime": 46.9191,
|
| 351 |
+
"eval_samples_per_second": 1.364,
|
| 352 |
+
"eval_steps_per_second": 0.341,
|
| 353 |
+
"step": 448
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 3.0625,
|
| 357 |
+
"step": 448,
|
| 358 |
+
"total_flos": 2.2294481154124677e+18,
|
| 359 |
+
"train_loss": 2.7684556926999773,
|
| 360 |
+
"train_runtime": 2238.8021,
|
| 361 |
+
"train_samples_per_second": 0.8,
|
| 362 |
+
"train_steps_per_second": 0.2
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 3.0625,
|
| 366 |
+
"eval_accuracy": 0.15853658536585366,
|
| 367 |
+
"eval_loss": 2.5910537242889404,
|
| 368 |
+
"eval_runtime": 69.9547,
|
| 369 |
+
"eval_samples_per_second": 1.172,
|
| 370 |
+
"eval_steps_per_second": 0.3,
|
| 371 |
+
"step": 448
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 3.0625,
|
| 375 |
+
"eval_accuracy": 0.15853658536585366,
|
| 376 |
+
"eval_loss": 2.5910537242889404,
|
| 377 |
+
"eval_runtime": 70.209,
|
| 378 |
+
"eval_samples_per_second": 1.168,
|
| 379 |
+
"eval_steps_per_second": 0.299,
|
| 380 |
+
"step": 448
|
| 381 |
+
}
|
| 382 |
+
],
|
| 383 |
+
"logging_steps": 10,
|
| 384 |
+
"max_steps": 448,
|
| 385 |
+
"num_input_tokens_seen": 0,
|
| 386 |
+
"num_train_epochs": 9223372036854775807,
|
| 387 |
+
"save_steps": 500,
|
| 388 |
+
"stateful_callbacks": {
|
| 389 |
+
"TrainerControl": {
|
| 390 |
+
"args": {
|
| 391 |
+
"should_epoch_stop": false,
|
| 392 |
+
"should_evaluate": false,
|
| 393 |
+
"should_log": false,
|
| 394 |
+
"should_save": true,
|
| 395 |
+
"should_training_stop": true
|
| 396 |
+
},
|
| 397 |
+
"attributes": {}
|
| 398 |
+
}
|
| 399 |
+
},
|
| 400 |
+
"total_flos": 2.2294481154124677e+18,
|
| 401 |
+
"train_batch_size": 4,
|
| 402 |
+
"trial_name": null,
|
| 403 |
+
"trial_params": null
|
| 404 |
+
}
|