Training in progress, epoch 0
Browse files- all_results.json +4 -0
- model.safetensors +1 -1
- runs/Apr03_17-14-31_10780645e8b2/events.out.tfevents.1712164516.10780645e8b2.34.0 +2 -2
- runs/Apr03_18-05-01_10780645e8b2/events.out.tfevents.1712167513.10780645e8b2.34.1 +3 -0
- runs/Apr03_18-06-07_10780645e8b2/events.out.tfevents.1712167572.10780645e8b2.34.2 +3 -0
- test_results.json +4 -0
- trainer_state.json +375 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eval_accuracy": 1.0,
|
| 3 |
+
"eval_loss": 0.026988975703716278
|
| 4 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 344937328
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c1e9a183f3ff2c021fd8ecffad20a43686e2fe6273821fe7740fd0ea5924b03
|
| 3 |
size 344937328
|
runs/Apr03_17-14-31_10780645e8b2/events.out.tfevents.1712164516.10780645e8b2.34.0
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 sha256:8590c3540909b9ff769645e5ed5c661191ffded18f4747466600e5b1544882c8
|
| 3 |
+
size 16085
|
runs/Apr03_18-05-01_10780645e8b2/events.out.tfevents.1712167513.10780645e8b2.34.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a15d707ab55513e1948e0f7b8cd8cc8bf4c8d7986fd0a4f916bb8f3a502ad7e
|
| 3 |
+
size 5009
|
runs/Apr03_18-06-07_10780645e8b2/events.out.tfevents.1712167572.10780645e8b2.34.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1dfb667ce55c4c3c4371cc9c6fffc4e54faf28832772f3e300193857f96c9027
|
| 3 |
+
size 11282
|
test_results.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eval_accuracy": 1.0,
|
| 3 |
+
"eval_loss": 0.026988975703716278
|
| 4 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,375 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-finetuned-ssv2-finetuned-traffic-dataset-mae/checkpoint-168",
|
| 4 |
+
"epoch": 7.011160714285714,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 397,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
+
"grad_norm": 14.671374320983887,
|
| 14 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 15 |
+
"loss": 0.7193,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.04,
|
| 20 |
+
"grad_norm": 7.1641387939453125,
|
| 21 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 22 |
+
"loss": 0.5298,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.07,
|
| 27 |
+
"grad_norm": 3.540851354598999,
|
| 28 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 29 |
+
"loss": 0.3106,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.09,
|
| 34 |
+
"grad_norm": 1.9156169891357422,
|
| 35 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 36 |
+
"loss": 0.8657,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.11,
|
| 41 |
+
"grad_norm": 2.8788669109344482,
|
| 42 |
+
"learning_rate": 4.937965260545906e-05,
|
| 43 |
+
"loss": 0.6144,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.12,
|
| 48 |
+
"eval_accuracy": 0.8571428571428571,
|
| 49 |
+
"eval_loss": 0.27961549162864685,
|
| 50 |
+
"eval_runtime": 24.2905,
|
| 51 |
+
"eval_samples_per_second": 0.576,
|
| 52 |
+
"eval_steps_per_second": 0.288,
|
| 53 |
+
"step": 56
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 1.01,
|
| 57 |
+
"grad_norm": 16.718944549560547,
|
| 58 |
+
"learning_rate": 4.8138957816377175e-05,
|
| 59 |
+
"loss": 0.4883,
|
| 60 |
+
"step": 60
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.03,
|
| 64 |
+
"grad_norm": 0.7438091039657593,
|
| 65 |
+
"learning_rate": 4.689826302729529e-05,
|
| 66 |
+
"loss": 0.236,
|
| 67 |
+
"step": 70
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 1.05,
|
| 71 |
+
"grad_norm": 1.806220293045044,
|
| 72 |
+
"learning_rate": 4.56575682382134e-05,
|
| 73 |
+
"loss": 0.4257,
|
| 74 |
+
"step": 80
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.08,
|
| 78 |
+
"grad_norm": 4.333924293518066,
|
| 79 |
+
"learning_rate": 4.441687344913151e-05,
|
| 80 |
+
"loss": 0.169,
|
| 81 |
+
"step": 90
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.1,
|
| 85 |
+
"grad_norm": 3.9030086994171143,
|
| 86 |
+
"learning_rate": 4.317617866004963e-05,
|
| 87 |
+
"loss": 0.313,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.12,
|
| 92 |
+
"grad_norm": 0.010061407461762428,
|
| 93 |
+
"learning_rate": 4.1935483870967746e-05,
|
| 94 |
+
"loss": 0.0637,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.12,
|
| 99 |
+
"eval_accuracy": 0.9285714285714286,
|
| 100 |
+
"eval_loss": 0.11744929850101471,
|
| 101 |
+
"eval_runtime": 24.0323,
|
| 102 |
+
"eval_samples_per_second": 0.583,
|
| 103 |
+
"eval_steps_per_second": 0.291,
|
| 104 |
+
"step": 112
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.02,
|
| 108 |
+
"grad_norm": 0.009479613974690437,
|
| 109 |
+
"learning_rate": 4.069478908188586e-05,
|
| 110 |
+
"loss": 0.2538,
|
| 111 |
+
"step": 120
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.04,
|
| 115 |
+
"grad_norm": 0.21475882828235626,
|
| 116 |
+
"learning_rate": 3.945409429280397e-05,
|
| 117 |
+
"loss": 0.1613,
|
| 118 |
+
"step": 130
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 2.06,
|
| 122 |
+
"grad_norm": 0.05664811283349991,
|
| 123 |
+
"learning_rate": 3.8213399503722084e-05,
|
| 124 |
+
"loss": 0.5442,
|
| 125 |
+
"step": 140
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 2.08,
|
| 129 |
+
"grad_norm": 1.2033185958862305,
|
| 130 |
+
"learning_rate": 3.69727047146402e-05,
|
| 131 |
+
"loss": 0.737,
|
| 132 |
+
"step": 150
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 2.11,
|
| 136 |
+
"grad_norm": 0.01298306230455637,
|
| 137 |
+
"learning_rate": 3.573200992555831e-05,
|
| 138 |
+
"loss": 0.4911,
|
| 139 |
+
"step": 160
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 2.12,
|
| 143 |
+
"eval_accuracy": 1.0,
|
| 144 |
+
"eval_loss": 0.028704656288027763,
|
| 145 |
+
"eval_runtime": 20.2796,
|
| 146 |
+
"eval_samples_per_second": 0.69,
|
| 147 |
+
"eval_steps_per_second": 0.345,
|
| 148 |
+
"step": 168
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 3.0,
|
| 152 |
+
"grad_norm": 0.12567199766635895,
|
| 153 |
+
"learning_rate": 3.449131513647643e-05,
|
| 154 |
+
"loss": 0.267,
|
| 155 |
+
"step": 170
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 3.03,
|
| 159 |
+
"grad_norm": 0.3274080753326416,
|
| 160 |
+
"learning_rate": 3.325062034739454e-05,
|
| 161 |
+
"loss": 0.2982,
|
| 162 |
+
"step": 180
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 3.05,
|
| 166 |
+
"grad_norm": 5.183434963226318,
|
| 167 |
+
"learning_rate": 3.200992555831266e-05,
|
| 168 |
+
"loss": 0.2744,
|
| 169 |
+
"step": 190
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 3.07,
|
| 173 |
+
"grad_norm": 0.20806659758090973,
|
| 174 |
+
"learning_rate": 3.0769230769230774e-05,
|
| 175 |
+
"loss": 0.0124,
|
| 176 |
+
"step": 200
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 3.09,
|
| 180 |
+
"grad_norm": 0.04709279537200928,
|
| 181 |
+
"learning_rate": 2.9528535980148887e-05,
|
| 182 |
+
"loss": 0.0025,
|
| 183 |
+
"step": 210
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 3.12,
|
| 187 |
+
"grad_norm": 0.0054036942310631275,
|
| 188 |
+
"learning_rate": 2.8287841191067e-05,
|
| 189 |
+
"loss": 0.3625,
|
| 190 |
+
"step": 220
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 3.12,
|
| 194 |
+
"eval_accuracy": 1.0,
|
| 195 |
+
"eval_loss": 0.08213090896606445,
|
| 196 |
+
"eval_runtime": 24.8422,
|
| 197 |
+
"eval_samples_per_second": 0.564,
|
| 198 |
+
"eval_steps_per_second": 0.282,
|
| 199 |
+
"step": 224
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 4.01,
|
| 203 |
+
"grad_norm": 0.09801805019378662,
|
| 204 |
+
"learning_rate": 2.7047146401985113e-05,
|
| 205 |
+
"loss": 0.0082,
|
| 206 |
+
"step": 230
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 4.04,
|
| 210 |
+
"grad_norm": 0.009371934458613396,
|
| 211 |
+
"learning_rate": 2.5806451612903226e-05,
|
| 212 |
+
"loss": 0.2331,
|
| 213 |
+
"step": 240
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 4.06,
|
| 217 |
+
"grad_norm": 0.33655962347984314,
|
| 218 |
+
"learning_rate": 2.4565756823821338e-05,
|
| 219 |
+
"loss": 0.1461,
|
| 220 |
+
"step": 250
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 4.08,
|
| 224 |
+
"grad_norm": 0.009524806402623653,
|
| 225 |
+
"learning_rate": 2.3325062034739454e-05,
|
| 226 |
+
"loss": 0.3265,
|
| 227 |
+
"step": 260
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 4.1,
|
| 231 |
+
"grad_norm": 0.0037162320222705603,
|
| 232 |
+
"learning_rate": 2.208436724565757e-05,
|
| 233 |
+
"loss": 0.001,
|
| 234 |
+
"step": 270
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 4.12,
|
| 238 |
+
"grad_norm": 0.005654833745211363,
|
| 239 |
+
"learning_rate": 2.0843672456575683e-05,
|
| 240 |
+
"loss": 0.1472,
|
| 241 |
+
"step": 280
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 4.12,
|
| 245 |
+
"eval_accuracy": 0.8571428571428571,
|
| 246 |
+
"eval_loss": 0.27267220616340637,
|
| 247 |
+
"eval_runtime": 24.1835,
|
| 248 |
+
"eval_samples_per_second": 0.579,
|
| 249 |
+
"eval_steps_per_second": 0.289,
|
| 250 |
+
"step": 280
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 5.02,
|
| 254 |
+
"grad_norm": 1.0853424072265625,
|
| 255 |
+
"learning_rate": 1.9602977667493796e-05,
|
| 256 |
+
"loss": 0.0061,
|
| 257 |
+
"step": 290
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 5.04,
|
| 261 |
+
"grad_norm": 0.10893365740776062,
|
| 262 |
+
"learning_rate": 1.8362282878411912e-05,
|
| 263 |
+
"loss": 0.0329,
|
| 264 |
+
"step": 300
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 5.07,
|
| 268 |
+
"grad_norm": 0.003927825018763542,
|
| 269 |
+
"learning_rate": 1.7121588089330025e-05,
|
| 270 |
+
"loss": 0.0124,
|
| 271 |
+
"step": 310
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 5.09,
|
| 275 |
+
"grad_norm": 0.03731616213917732,
|
| 276 |
+
"learning_rate": 1.588089330024814e-05,
|
| 277 |
+
"loss": 0.1577,
|
| 278 |
+
"step": 320
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 5.11,
|
| 282 |
+
"grad_norm": 0.027107276022434235,
|
| 283 |
+
"learning_rate": 1.4640198511166252e-05,
|
| 284 |
+
"loss": 0.0068,
|
| 285 |
+
"step": 330
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 5.12,
|
| 289 |
+
"eval_accuracy": 0.7142857142857143,
|
| 290 |
+
"eval_loss": 1.524235486984253,
|
| 291 |
+
"eval_runtime": 22.5747,
|
| 292 |
+
"eval_samples_per_second": 0.62,
|
| 293 |
+
"eval_steps_per_second": 0.31,
|
| 294 |
+
"step": 336
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 6.01,
|
| 298 |
+
"grad_norm": 0.015361560508608818,
|
| 299 |
+
"learning_rate": 1.3399503722084367e-05,
|
| 300 |
+
"loss": 0.0155,
|
| 301 |
+
"step": 340
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 6.03,
|
| 305 |
+
"grad_norm": 0.009546751156449318,
|
| 306 |
+
"learning_rate": 1.2158808933002481e-05,
|
| 307 |
+
"loss": 0.2251,
|
| 308 |
+
"step": 350
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 6.05,
|
| 312 |
+
"grad_norm": 0.00286727212369442,
|
| 313 |
+
"learning_rate": 1.0918114143920596e-05,
|
| 314 |
+
"loss": 0.0003,
|
| 315 |
+
"step": 360
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 6.08,
|
| 319 |
+
"grad_norm": 0.006020919419825077,
|
| 320 |
+
"learning_rate": 9.67741935483871e-06,
|
| 321 |
+
"loss": 0.0016,
|
| 322 |
+
"step": 370
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 6.1,
|
| 326 |
+
"grad_norm": 0.0052633825689554214,
|
| 327 |
+
"learning_rate": 8.436724565756825e-06,
|
| 328 |
+
"loss": 0.2976,
|
| 329 |
+
"step": 380
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 6.12,
|
| 333 |
+
"grad_norm": 0.006017320789396763,
|
| 334 |
+
"learning_rate": 7.1960297766749385e-06,
|
| 335 |
+
"loss": 0.0009,
|
| 336 |
+
"step": 390
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 6.12,
|
| 340 |
+
"eval_accuracy": 0.8571428571428571,
|
| 341 |
+
"eval_loss": 0.7878251671791077,
|
| 342 |
+
"eval_runtime": 24.9105,
|
| 343 |
+
"eval_samples_per_second": 0.562,
|
| 344 |
+
"eval_steps_per_second": 0.281,
|
| 345 |
+
"step": 392
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 7.01,
|
| 349 |
+
"eval_accuracy": 1.0,
|
| 350 |
+
"eval_loss": 0.026988975703716278,
|
| 351 |
+
"eval_runtime": 5.8255,
|
| 352 |
+
"eval_samples_per_second": 0.687,
|
| 353 |
+
"eval_steps_per_second": 0.343,
|
| 354 |
+
"step": 397
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 7.01,
|
| 358 |
+
"eval_accuracy": 1.0,
|
| 359 |
+
"eval_loss": 0.026988975703716278,
|
| 360 |
+
"eval_runtime": 5.8152,
|
| 361 |
+
"eval_samples_per_second": 0.688,
|
| 362 |
+
"eval_steps_per_second": 0.344,
|
| 363 |
+
"step": 397
|
| 364 |
+
}
|
| 365 |
+
],
|
| 366 |
+
"logging_steps": 10,
|
| 367 |
+
"max_steps": 448,
|
| 368 |
+
"num_input_tokens_seen": 0,
|
| 369 |
+
"num_train_epochs": 9223372036854775807,
|
| 370 |
+
"save_steps": 500,
|
| 371 |
+
"total_flos": 9.769146381458473e+17,
|
| 372 |
+
"train_batch_size": 2,
|
| 373 |
+
"trial_name": null,
|
| 374 |
+
"trial_params": null
|
| 375 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4603
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16f5fa2564098f96e5682c8a35add41f758740348ad73695d0bc952c8ef30e17
|
| 3 |
size 4603
|