End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.25,
|
| 3 |
+
"eval_accuracy": 0.832258064516129,
|
| 4 |
+
"eval_loss": 0.48749518394470215,
|
| 5 |
+
"eval_runtime": 67.3551,
|
| 6 |
+
"eval_samples_per_second": 2.301,
|
| 7 |
+
"eval_steps_per_second": 1.158
|
| 8 |
+
}
|
runs/Apr17_07-34-06_8125ea423e91/events.out.tfevents.1713341739.8125ea423e91.6322.2
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:aa09fd5652fd7d60e521bf6b9046c2896c3a505e84c5104c6911f1f670d79375
|
| 3 |
+
size 734
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.25,
|
| 3 |
+
"eval_accuracy": 0.832258064516129,
|
| 4 |
+
"eval_loss": 0.48749518394470215,
|
| 5 |
+
"eval_runtime": 67.3551,
|
| 6 |
+
"eval_samples_per_second": 2.301,
|
| 7 |
+
"eval_steps_per_second": 1.158
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,504 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8285714285714286,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-450",
|
| 4 |
+
"epoch": 3.25,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 600,
|
| 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": 14.608237266540527,
|
| 14 |
+
"learning_rate": 8.333333333333334e-06,
|
| 15 |
+
"loss": 2.2453,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03,
|
| 20 |
+
"grad_norm": 36.968116760253906,
|
| 21 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 22 |
+
"loss": 2.3136,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.05,
|
| 27 |
+
"grad_norm": 17.145219802856445,
|
| 28 |
+
"learning_rate": 2.5e-05,
|
| 29 |
+
"loss": 2.42,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.07,
|
| 34 |
+
"grad_norm": 20.452388763427734,
|
| 35 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 36 |
+
"loss": 2.3047,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.08,
|
| 41 |
+
"grad_norm": 15.896721839904785,
|
| 42 |
+
"learning_rate": 4.166666666666667e-05,
|
| 43 |
+
"loss": 2.2122,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1,
|
| 48 |
+
"grad_norm": 14.993762969970703,
|
| 49 |
+
"learning_rate": 5e-05,
|
| 50 |
+
"loss": 2.2581,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.12,
|
| 55 |
+
"grad_norm": 16.3026065826416,
|
| 56 |
+
"learning_rate": 4.9074074074074075e-05,
|
| 57 |
+
"loss": 2.0639,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.13,
|
| 62 |
+
"grad_norm": 13.365699768066406,
|
| 63 |
+
"learning_rate": 4.814814814814815e-05,
|
| 64 |
+
"loss": 2.1623,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.15,
|
| 69 |
+
"grad_norm": 15.710684776306152,
|
| 70 |
+
"learning_rate": 4.722222222222222e-05,
|
| 71 |
+
"loss": 2.0486,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.17,
|
| 76 |
+
"grad_norm": 20.03302001953125,
|
| 77 |
+
"learning_rate": 4.62962962962963e-05,
|
| 78 |
+
"loss": 1.9578,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.18,
|
| 83 |
+
"grad_norm": 17.960296630859375,
|
| 84 |
+
"learning_rate": 4.5370370370370374e-05,
|
| 85 |
+
"loss": 1.952,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.2,
|
| 90 |
+
"grad_norm": 15.012153625488281,
|
| 91 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 92 |
+
"loss": 1.623,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.22,
|
| 97 |
+
"grad_norm": 18.308734893798828,
|
| 98 |
+
"learning_rate": 4.351851851851852e-05,
|
| 99 |
+
"loss": 1.7624,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.23,
|
| 104 |
+
"grad_norm": 14.50885009765625,
|
| 105 |
+
"learning_rate": 4.259259259259259e-05,
|
| 106 |
+
"loss": 1.2651,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.25,
|
| 111 |
+
"grad_norm": 24.735700607299805,
|
| 112 |
+
"learning_rate": 4.166666666666667e-05,
|
| 113 |
+
"loss": 1.3279,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.25,
|
| 118 |
+
"eval_accuracy": 0.42857142857142855,
|
| 119 |
+
"eval_loss": 1.2386213541030884,
|
| 120 |
+
"eval_runtime": 29.1642,
|
| 121 |
+
"eval_samples_per_second": 2.4,
|
| 122 |
+
"eval_steps_per_second": 1.2,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.02,
|
| 127 |
+
"grad_norm": 17.132925033569336,
|
| 128 |
+
"learning_rate": 4.074074074074074e-05,
|
| 129 |
+
"loss": 1.3581,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.03,
|
| 134 |
+
"grad_norm": 21.23714828491211,
|
| 135 |
+
"learning_rate": 3.981481481481482e-05,
|
| 136 |
+
"loss": 1.1455,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.05,
|
| 141 |
+
"grad_norm": 18.7020206451416,
|
| 142 |
+
"learning_rate": 3.888888888888889e-05,
|
| 143 |
+
"loss": 1.1061,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.07,
|
| 148 |
+
"grad_norm": 14.506175994873047,
|
| 149 |
+
"learning_rate": 3.7962962962962964e-05,
|
| 150 |
+
"loss": 1.1518,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.08,
|
| 155 |
+
"grad_norm": 29.114465713500977,
|
| 156 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 157 |
+
"loss": 0.9828,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.1,
|
| 162 |
+
"grad_norm": 10.247823715209961,
|
| 163 |
+
"learning_rate": 3.611111111111111e-05,
|
| 164 |
+
"loss": 1.003,
|
| 165 |
+
"step": 210
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.12,
|
| 169 |
+
"grad_norm": 8.87232780456543,
|
| 170 |
+
"learning_rate": 3.518518518518519e-05,
|
| 171 |
+
"loss": 0.5946,
|
| 172 |
+
"step": 220
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.13,
|
| 176 |
+
"grad_norm": 160.70228576660156,
|
| 177 |
+
"learning_rate": 3.425925925925926e-05,
|
| 178 |
+
"loss": 1.1998,
|
| 179 |
+
"step": 230
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.15,
|
| 183 |
+
"grad_norm": 12.714564323425293,
|
| 184 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 185 |
+
"loss": 0.9956,
|
| 186 |
+
"step": 240
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.17,
|
| 190 |
+
"grad_norm": 3.044830560684204,
|
| 191 |
+
"learning_rate": 3.240740740740741e-05,
|
| 192 |
+
"loss": 0.5824,
|
| 193 |
+
"step": 250
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.18,
|
| 197 |
+
"grad_norm": 0.5050694346427917,
|
| 198 |
+
"learning_rate": 3.148148148148148e-05,
|
| 199 |
+
"loss": 0.5335,
|
| 200 |
+
"step": 260
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.2,
|
| 204 |
+
"grad_norm": 16.457557678222656,
|
| 205 |
+
"learning_rate": 3.055555555555556e-05,
|
| 206 |
+
"loss": 0.7113,
|
| 207 |
+
"step": 270
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.22,
|
| 211 |
+
"grad_norm": 16.745141983032227,
|
| 212 |
+
"learning_rate": 2.962962962962963e-05,
|
| 213 |
+
"loss": 0.397,
|
| 214 |
+
"step": 280
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.23,
|
| 218 |
+
"grad_norm": 4.463345050811768,
|
| 219 |
+
"learning_rate": 2.8703703703703706e-05,
|
| 220 |
+
"loss": 0.7122,
|
| 221 |
+
"step": 290
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.25,
|
| 225 |
+
"grad_norm": 12.840511322021484,
|
| 226 |
+
"learning_rate": 2.777777777777778e-05,
|
| 227 |
+
"loss": 0.4469,
|
| 228 |
+
"step": 300
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.25,
|
| 232 |
+
"eval_accuracy": 0.7857142857142857,
|
| 233 |
+
"eval_loss": 0.46059101819992065,
|
| 234 |
+
"eval_runtime": 29.3265,
|
| 235 |
+
"eval_samples_per_second": 2.387,
|
| 236 |
+
"eval_steps_per_second": 1.193,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.02,
|
| 241 |
+
"grad_norm": 25.240575790405273,
|
| 242 |
+
"learning_rate": 2.6851851851851855e-05,
|
| 243 |
+
"loss": 0.6132,
|
| 244 |
+
"step": 310
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.03,
|
| 248 |
+
"grad_norm": 3.6886823177337646,
|
| 249 |
+
"learning_rate": 2.5925925925925925e-05,
|
| 250 |
+
"loss": 0.3257,
|
| 251 |
+
"step": 320
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 2.05,
|
| 255 |
+
"grad_norm": 7.413472652435303,
|
| 256 |
+
"learning_rate": 2.5e-05,
|
| 257 |
+
"loss": 0.3551,
|
| 258 |
+
"step": 330
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 2.07,
|
| 262 |
+
"grad_norm": 0.6936644911766052,
|
| 263 |
+
"learning_rate": 2.4074074074074074e-05,
|
| 264 |
+
"loss": 0.2338,
|
| 265 |
+
"step": 340
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 2.08,
|
| 269 |
+
"grad_norm": 0.7576755285263062,
|
| 270 |
+
"learning_rate": 2.314814814814815e-05,
|
| 271 |
+
"loss": 0.2495,
|
| 272 |
+
"step": 350
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.1,
|
| 276 |
+
"grad_norm": 2.146125078201294,
|
| 277 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 278 |
+
"loss": 0.4222,
|
| 279 |
+
"step": 360
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.12,
|
| 283 |
+
"grad_norm": 48.200714111328125,
|
| 284 |
+
"learning_rate": 2.1296296296296296e-05,
|
| 285 |
+
"loss": 0.6491,
|
| 286 |
+
"step": 370
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 2.13,
|
| 290 |
+
"grad_norm": 0.2533012628555298,
|
| 291 |
+
"learning_rate": 2.037037037037037e-05,
|
| 292 |
+
"loss": 0.3478,
|
| 293 |
+
"step": 380
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 2.15,
|
| 297 |
+
"grad_norm": 3.1355950832366943,
|
| 298 |
+
"learning_rate": 1.9444444444444445e-05,
|
| 299 |
+
"loss": 0.3471,
|
| 300 |
+
"step": 390
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 2.17,
|
| 304 |
+
"grad_norm": 32.68257522583008,
|
| 305 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 306 |
+
"loss": 0.3896,
|
| 307 |
+
"step": 400
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 2.18,
|
| 311 |
+
"grad_norm": 40.63040542602539,
|
| 312 |
+
"learning_rate": 1.7592592592592595e-05,
|
| 313 |
+
"loss": 0.423,
|
| 314 |
+
"step": 410
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.2,
|
| 318 |
+
"grad_norm": 11.917498588562012,
|
| 319 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 320 |
+
"loss": 0.7307,
|
| 321 |
+
"step": 420
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.22,
|
| 325 |
+
"grad_norm": 0.4221107065677643,
|
| 326 |
+
"learning_rate": 1.574074074074074e-05,
|
| 327 |
+
"loss": 0.327,
|
| 328 |
+
"step": 430
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 2.23,
|
| 332 |
+
"grad_norm": 0.340420126914978,
|
| 333 |
+
"learning_rate": 1.4814814814814815e-05,
|
| 334 |
+
"loss": 0.4035,
|
| 335 |
+
"step": 440
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 2.25,
|
| 339 |
+
"grad_norm": 0.12714390456676483,
|
| 340 |
+
"learning_rate": 1.388888888888889e-05,
|
| 341 |
+
"loss": 0.2142,
|
| 342 |
+
"step": 450
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 2.25,
|
| 346 |
+
"eval_accuracy": 0.8285714285714286,
|
| 347 |
+
"eval_loss": 0.38029590249061584,
|
| 348 |
+
"eval_runtime": 29.2401,
|
| 349 |
+
"eval_samples_per_second": 2.394,
|
| 350 |
+
"eval_steps_per_second": 1.197,
|
| 351 |
+
"step": 450
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 3.02,
|
| 355 |
+
"grad_norm": 0.8629240393638611,
|
| 356 |
+
"learning_rate": 1.2962962962962962e-05,
|
| 357 |
+
"loss": 0.1078,
|
| 358 |
+
"step": 460
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 3.03,
|
| 362 |
+
"grad_norm": 0.08954589068889618,
|
| 363 |
+
"learning_rate": 1.2037037037037037e-05,
|
| 364 |
+
"loss": 0.238,
|
| 365 |
+
"step": 470
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 3.05,
|
| 369 |
+
"grad_norm": 0.12774558365345,
|
| 370 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 371 |
+
"loss": 0.0945,
|
| 372 |
+
"step": 480
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 3.07,
|
| 376 |
+
"grad_norm": 0.49261391162872314,
|
| 377 |
+
"learning_rate": 1.0185185185185185e-05,
|
| 378 |
+
"loss": 0.2428,
|
| 379 |
+
"step": 490
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 3.08,
|
| 383 |
+
"grad_norm": 0.0893869623541832,
|
| 384 |
+
"learning_rate": 9.259259259259259e-06,
|
| 385 |
+
"loss": 0.2159,
|
| 386 |
+
"step": 500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 3.1,
|
| 390 |
+
"grad_norm": 3.983721971511841,
|
| 391 |
+
"learning_rate": 8.333333333333334e-06,
|
| 392 |
+
"loss": 0.39,
|
| 393 |
+
"step": 510
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 3.12,
|
| 397 |
+
"grad_norm": 0.7854453325271606,
|
| 398 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 399 |
+
"loss": 0.2665,
|
| 400 |
+
"step": 520
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 3.13,
|
| 404 |
+
"grad_norm": 2.8955111503601074,
|
| 405 |
+
"learning_rate": 6.481481481481481e-06,
|
| 406 |
+
"loss": 0.0859,
|
| 407 |
+
"step": 530
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 3.15,
|
| 411 |
+
"grad_norm": 15.494441032409668,
|
| 412 |
+
"learning_rate": 5.555555555555556e-06,
|
| 413 |
+
"loss": 0.1552,
|
| 414 |
+
"step": 540
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 3.17,
|
| 418 |
+
"grad_norm": 0.1666683405637741,
|
| 419 |
+
"learning_rate": 4.6296296296296296e-06,
|
| 420 |
+
"loss": 0.0635,
|
| 421 |
+
"step": 550
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 3.18,
|
| 425 |
+
"grad_norm": 0.389921635389328,
|
| 426 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 427 |
+
"loss": 0.3509,
|
| 428 |
+
"step": 560
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 3.2,
|
| 432 |
+
"grad_norm": 0.4067876636981964,
|
| 433 |
+
"learning_rate": 2.777777777777778e-06,
|
| 434 |
+
"loss": 0.1328,
|
| 435 |
+
"step": 570
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 3.22,
|
| 439 |
+
"grad_norm": 0.7461154460906982,
|
| 440 |
+
"learning_rate": 1.8518518518518519e-06,
|
| 441 |
+
"loss": 0.3664,
|
| 442 |
+
"step": 580
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 3.23,
|
| 446 |
+
"grad_norm": 8.207443237304688,
|
| 447 |
+
"learning_rate": 9.259259259259259e-07,
|
| 448 |
+
"loss": 0.0469,
|
| 449 |
+
"step": 590
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 3.25,
|
| 453 |
+
"grad_norm": 0.5032423138618469,
|
| 454 |
+
"learning_rate": 0.0,
|
| 455 |
+
"loss": 0.0459,
|
| 456 |
+
"step": 600
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 3.25,
|
| 460 |
+
"eval_accuracy": 0.8285714285714286,
|
| 461 |
+
"eval_loss": 0.3240524232387543,
|
| 462 |
+
"eval_runtime": 29.9304,
|
| 463 |
+
"eval_samples_per_second": 2.339,
|
| 464 |
+
"eval_steps_per_second": 1.169,
|
| 465 |
+
"step": 600
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 3.25,
|
| 469 |
+
"step": 600,
|
| 470 |
+
"total_flos": 1.495384188125184e+18,
|
| 471 |
+
"train_loss": 0.8612027465800445,
|
| 472 |
+
"train_runtime": 1212.3004,
|
| 473 |
+
"train_samples_per_second": 0.99,
|
| 474 |
+
"train_steps_per_second": 0.495
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 3.25,
|
| 478 |
+
"eval_accuracy": 0.832258064516129,
|
| 479 |
+
"eval_loss": 0.48749518394470215,
|
| 480 |
+
"eval_runtime": 67.379,
|
| 481 |
+
"eval_samples_per_second": 2.3,
|
| 482 |
+
"eval_steps_per_second": 1.158,
|
| 483 |
+
"step": 600
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 3.25,
|
| 487 |
+
"eval_accuracy": 0.832258064516129,
|
| 488 |
+
"eval_loss": 0.48749518394470215,
|
| 489 |
+
"eval_runtime": 67.3551,
|
| 490 |
+
"eval_samples_per_second": 2.301,
|
| 491 |
+
"eval_steps_per_second": 1.158,
|
| 492 |
+
"step": 600
|
| 493 |
+
}
|
| 494 |
+
],
|
| 495 |
+
"logging_steps": 10,
|
| 496 |
+
"max_steps": 600,
|
| 497 |
+
"num_input_tokens_seen": 0,
|
| 498 |
+
"num_train_epochs": 9223372036854775807,
|
| 499 |
+
"save_steps": 500,
|
| 500 |
+
"total_flos": 1.495384188125184e+18,
|
| 501 |
+
"train_batch_size": 2,
|
| 502 |
+
"trial_name": null,
|
| 503 |
+
"trial_params": null
|
| 504 |
+
}
|