Commit
•
9c1d92c
1
Parent(s):
897d711
End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.1,
|
| 3 |
+
"eval_accuracy": 0.9730941704035875,
|
| 4 |
+
"eval_loss": 0.10973779112100601,
|
| 5 |
+
"eval_runtime": 50.2397,
|
| 6 |
+
"eval_samples_per_second": 4.439,
|
| 7 |
+
"eval_steps_per_second": 2.229
|
| 8 |
+
}
|
runs/Jun29_14-08-11_dac39c8ce1f5/events.out.tfevents.1688049643.dac39c8ce1f5.29.1
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:f9d4945ecbf3d6a89f693d0ddba73005392c9ed2636eff6d0f18d6fac124370d
|
| 3 |
+
size 734
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.1,
|
| 3 |
+
"eval_accuracy": 0.9730941704035875,
|
| 4 |
+
"eval_loss": 0.10973779112100601,
|
| 5 |
+
"eval_runtime": 50.2397,
|
| 6 |
+
"eval_samples_per_second": 4.439,
|
| 7 |
+
"eval_steps_per_second": 2.229
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,223 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9090909090909091,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-finetuned-ucf101-subset-nimeshbuddhika/checkpoint-1350",
|
| 4 |
+
"epoch": 9.1,
|
| 5 |
+
"global_step": 1500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.07,
|
| 12 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 13 |
+
"loss": 2.4285,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.1,
|
| 18 |
+
"eval_accuracy": 0.20320855614973263,
|
| 19 |
+
"eval_loss": 2.118558406829834,
|
| 20 |
+
"eval_runtime": 43.6317,
|
| 21 |
+
"eval_samples_per_second": 4.286,
|
| 22 |
+
"eval_steps_per_second": 2.154,
|
| 23 |
+
"step": 150
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.03,
|
| 27 |
+
"learning_rate": 4.814814814814815e-05,
|
| 28 |
+
"loss": 1.6775,
|
| 29 |
+
"step": 200
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 1.1,
|
| 33 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 34 |
+
"loss": 0.9154,
|
| 35 |
+
"step": 300
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 1.1,
|
| 39 |
+
"eval_accuracy": 0.6042780748663101,
|
| 40 |
+
"eval_loss": 1.1913264989852905,
|
| 41 |
+
"eval_runtime": 43.6901,
|
| 42 |
+
"eval_samples_per_second": 4.28,
|
| 43 |
+
"eval_steps_per_second": 2.152,
|
| 44 |
+
"step": 300
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 2.07,
|
| 48 |
+
"learning_rate": 4.074074074074074e-05,
|
| 49 |
+
"loss": 0.4498,
|
| 50 |
+
"step": 400
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 2.1,
|
| 54 |
+
"eval_accuracy": 0.8823529411764706,
|
| 55 |
+
"eval_loss": 0.37695419788360596,
|
| 56 |
+
"eval_runtime": 43.5293,
|
| 57 |
+
"eval_samples_per_second": 4.296,
|
| 58 |
+
"eval_steps_per_second": 2.159,
|
| 59 |
+
"step": 450
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 3.03,
|
| 63 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 64 |
+
"loss": 0.3165,
|
| 65 |
+
"step": 500
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 3.1,
|
| 69 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 70 |
+
"loss": 0.3012,
|
| 71 |
+
"step": 600
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 3.1,
|
| 75 |
+
"eval_accuracy": 0.8663101604278075,
|
| 76 |
+
"eval_loss": 0.39042213559150696,
|
| 77 |
+
"eval_runtime": 33.9376,
|
| 78 |
+
"eval_samples_per_second": 5.51,
|
| 79 |
+
"eval_steps_per_second": 2.77,
|
| 80 |
+
"step": 600
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 4.07,
|
| 84 |
+
"learning_rate": 2.962962962962963e-05,
|
| 85 |
+
"loss": 0.1458,
|
| 86 |
+
"step": 700
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 4.1,
|
| 90 |
+
"eval_accuracy": 0.7967914438502673,
|
| 91 |
+
"eval_loss": 0.8938174843788147,
|
| 92 |
+
"eval_runtime": 39.5211,
|
| 93 |
+
"eval_samples_per_second": 4.732,
|
| 94 |
+
"eval_steps_per_second": 2.378,
|
| 95 |
+
"step": 750
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 5.03,
|
| 99 |
+
"learning_rate": 2.5925925925925925e-05,
|
| 100 |
+
"loss": 0.0895,
|
| 101 |
+
"step": 800
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 5.1,
|
| 105 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 106 |
+
"loss": 0.0464,
|
| 107 |
+
"step": 900
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 5.1,
|
| 111 |
+
"eval_accuracy": 0.8556149732620321,
|
| 112 |
+
"eval_loss": 0.6180762052536011,
|
| 113 |
+
"eval_runtime": 43.0074,
|
| 114 |
+
"eval_samples_per_second": 4.348,
|
| 115 |
+
"eval_steps_per_second": 2.186,
|
| 116 |
+
"step": 900
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 6.07,
|
| 120 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 121 |
+
"loss": 0.0274,
|
| 122 |
+
"step": 1000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 6.1,
|
| 126 |
+
"eval_accuracy": 0.8074866310160428,
|
| 127 |
+
"eval_loss": 0.7182068228721619,
|
| 128 |
+
"eval_runtime": 42.9074,
|
| 129 |
+
"eval_samples_per_second": 4.358,
|
| 130 |
+
"eval_steps_per_second": 2.191,
|
| 131 |
+
"step": 1050
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 7.03,
|
| 135 |
+
"learning_rate": 1.4814814814814815e-05,
|
| 136 |
+
"loss": 0.0189,
|
| 137 |
+
"step": 1100
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 7.1,
|
| 141 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 142 |
+
"loss": 0.0022,
|
| 143 |
+
"step": 1200
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 7.1,
|
| 147 |
+
"eval_accuracy": 0.8716577540106952,
|
| 148 |
+
"eval_loss": 0.45252320170402527,
|
| 149 |
+
"eval_runtime": 43.1934,
|
| 150 |
+
"eval_samples_per_second": 4.329,
|
| 151 |
+
"eval_steps_per_second": 2.176,
|
| 152 |
+
"step": 1200
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 8.07,
|
| 156 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 157 |
+
"loss": 0.0302,
|
| 158 |
+
"step": 1300
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 8.1,
|
| 162 |
+
"eval_accuracy": 0.9090909090909091,
|
| 163 |
+
"eval_loss": 0.31720033288002014,
|
| 164 |
+
"eval_runtime": 43.0746,
|
| 165 |
+
"eval_samples_per_second": 4.341,
|
| 166 |
+
"eval_steps_per_second": 2.182,
|
| 167 |
+
"step": 1350
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 9.03,
|
| 171 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 172 |
+
"loss": 0.003,
|
| 173 |
+
"step": 1400
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 9.1,
|
| 177 |
+
"learning_rate": 0.0,
|
| 178 |
+
"loss": 0.0166,
|
| 179 |
+
"step": 1500
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 9.1,
|
| 183 |
+
"eval_accuracy": 0.8983957219251337,
|
| 184 |
+
"eval_loss": 0.28981590270996094,
|
| 185 |
+
"eval_runtime": 43.1833,
|
| 186 |
+
"eval_samples_per_second": 4.33,
|
| 187 |
+
"eval_steps_per_second": 2.177,
|
| 188 |
+
"step": 1500
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 9.1,
|
| 192 |
+
"step": 1500,
|
| 193 |
+
"total_flos": 3.738527145787392e+18,
|
| 194 |
+
"train_loss": 0.4312617871661981,
|
| 195 |
+
"train_runtime": 1888.5613,
|
| 196 |
+
"train_samples_per_second": 1.589,
|
| 197 |
+
"train_steps_per_second": 0.794
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 9.1,
|
| 201 |
+
"eval_accuracy": 0.9730941704035875,
|
| 202 |
+
"eval_loss": 0.10973779112100601,
|
| 203 |
+
"eval_runtime": 51.205,
|
| 204 |
+
"eval_samples_per_second": 4.355,
|
| 205 |
+
"eval_steps_per_second": 2.187,
|
| 206 |
+
"step": 1500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 9.1,
|
| 210 |
+
"eval_accuracy": 0.9730941704035875,
|
| 211 |
+
"eval_loss": 0.10973779112100601,
|
| 212 |
+
"eval_runtime": 50.2397,
|
| 213 |
+
"eval_samples_per_second": 4.439,
|
| 214 |
+
"eval_steps_per_second": 2.229,
|
| 215 |
+
"step": 1500
|
| 216 |
+
}
|
| 217 |
+
],
|
| 218 |
+
"max_steps": 1500,
|
| 219 |
+
"num_train_epochs": 9223372036854775807,
|
| 220 |
+
"total_flos": 3.738527145787392e+18,
|
| 221 |
+
"trial_name": null,
|
| 222 |
+
"trial_params": null
|
| 223 |
+
}
|