End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.194871794871795,
|
| 3 |
+
"eval_accuracy": 0.8874172185430463,
|
| 4 |
+
"eval_loss": 0.38032299280166626,
|
| 5 |
+
"eval_runtime": 51.2971,
|
| 6 |
+
"eval_samples_per_second": 2.944,
|
| 7 |
+
"eval_steps_per_second": 0.741
|
| 8 |
+
}
|
runs/May01_17-58-26_f9a9d4427412/events.out.tfevents.1714588618.f9a9d4427412.2055.1
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 sha256:25de17f0718b4a7e5fbcbb245ec1f6ded2ef53fcd253649dfe4ae9c1b15a487a
|
| 3 |
+
size 734
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.194871794871795,
|
| 3 |
+
"eval_accuracy": 0.8874172185430463,
|
| 4 |
+
"eval_loss": 0.38032299280166626,
|
| 5 |
+
"eval_runtime": 51.2971,
|
| 6 |
+
"eval_samples_per_second": 2.944,
|
| 7 |
+
"eval_steps_per_second": 0.741
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,639 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8561643835616438,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-finetuned-kinetics-finetuned-dcsass-shoplifting-subset/checkpoint-780",
|
| 4 |
+
"epoch": 4.194871794871795,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 780,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01282051282051282,
|
| 13 |
+
"grad_norm": 6.756944179534912,
|
| 14 |
+
"learning_rate": 6.41025641025641e-06,
|
| 15 |
+
"loss": 0.7103,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.02564102564102564,
|
| 20 |
+
"grad_norm": 7.49935245513916,
|
| 21 |
+
"learning_rate": 1.282051282051282e-05,
|
| 22 |
+
"loss": 0.5933,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.038461538461538464,
|
| 27 |
+
"grad_norm": 8.1102294921875,
|
| 28 |
+
"learning_rate": 1.923076923076923e-05,
|
| 29 |
+
"loss": 0.391,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.05128205128205128,
|
| 34 |
+
"grad_norm": 14.223252296447754,
|
| 35 |
+
"learning_rate": 2.564102564102564e-05,
|
| 36 |
+
"loss": 0.5162,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.0641025641025641,
|
| 41 |
+
"grad_norm": 10.161632537841797,
|
| 42 |
+
"learning_rate": 3.205128205128206e-05,
|
| 43 |
+
"loss": 0.5433,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.07692307692307693,
|
| 48 |
+
"grad_norm": 7.198577404022217,
|
| 49 |
+
"learning_rate": 3.846153846153846e-05,
|
| 50 |
+
"loss": 0.7253,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.08974358974358974,
|
| 55 |
+
"grad_norm": 15.455668449401855,
|
| 56 |
+
"learning_rate": 4.4871794871794874e-05,
|
| 57 |
+
"loss": 0.6042,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.10256410256410256,
|
| 62 |
+
"grad_norm": 5.9158935546875,
|
| 63 |
+
"learning_rate": 4.985754985754986e-05,
|
| 64 |
+
"loss": 0.4834,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.11538461538461539,
|
| 69 |
+
"grad_norm": 13.751437187194824,
|
| 70 |
+
"learning_rate": 4.9145299145299147e-05,
|
| 71 |
+
"loss": 0.6672,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.1282051282051282,
|
| 76 |
+
"grad_norm": 6.230504989624023,
|
| 77 |
+
"learning_rate": 4.8433048433048433e-05,
|
| 78 |
+
"loss": 0.561,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.14102564102564102,
|
| 83 |
+
"grad_norm": 0.061720337718725204,
|
| 84 |
+
"learning_rate": 4.772079772079772e-05,
|
| 85 |
+
"loss": 0.4631,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.15384615384615385,
|
| 90 |
+
"grad_norm": 14.445475578308105,
|
| 91 |
+
"learning_rate": 4.700854700854701e-05,
|
| 92 |
+
"loss": 0.5993,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.16666666666666666,
|
| 97 |
+
"grad_norm": 5.024906158447266,
|
| 98 |
+
"learning_rate": 4.62962962962963e-05,
|
| 99 |
+
"loss": 0.6052,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.1794871794871795,
|
| 104 |
+
"grad_norm": 5.089183807373047,
|
| 105 |
+
"learning_rate": 4.558404558404559e-05,
|
| 106 |
+
"loss": 0.5345,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.19230769230769232,
|
| 111 |
+
"grad_norm": 0.20361727476119995,
|
| 112 |
+
"learning_rate": 4.4871794871794874e-05,
|
| 113 |
+
"loss": 0.3314,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.2012820512820513,
|
| 118 |
+
"eval_accuracy": 0.821917808219178,
|
| 119 |
+
"eval_loss": 0.6146280169487,
|
| 120 |
+
"eval_runtime": 86.3385,
|
| 121 |
+
"eval_samples_per_second": 1.691,
|
| 122 |
+
"eval_steps_per_second": 0.429,
|
| 123 |
+
"step": 157
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.0038461538461538,
|
| 127 |
+
"grad_norm": 0.9299275875091553,
|
| 128 |
+
"learning_rate": 4.415954415954416e-05,
|
| 129 |
+
"loss": 0.5923,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.0166666666666666,
|
| 134 |
+
"grad_norm": 1.9701108932495117,
|
| 135 |
+
"learning_rate": 4.344729344729345e-05,
|
| 136 |
+
"loss": 0.6272,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.0294871794871794,
|
| 141 |
+
"grad_norm": 7.168660640716553,
|
| 142 |
+
"learning_rate": 4.2735042735042735e-05,
|
| 143 |
+
"loss": 0.3787,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.0423076923076924,
|
| 148 |
+
"grad_norm": 17.313304901123047,
|
| 149 |
+
"learning_rate": 4.202279202279202e-05,
|
| 150 |
+
"loss": 0.4095,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.0551282051282052,
|
| 155 |
+
"grad_norm": 3.225602865219116,
|
| 156 |
+
"learning_rate": 4.131054131054131e-05,
|
| 157 |
+
"loss": 0.4833,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.067948717948718,
|
| 162 |
+
"grad_norm": 11.712457656860352,
|
| 163 |
+
"learning_rate": 4.05982905982906e-05,
|
| 164 |
+
"loss": 0.6347,
|
| 165 |
+
"step": 210
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.0807692307692307,
|
| 169 |
+
"grad_norm": 15.161521911621094,
|
| 170 |
+
"learning_rate": 3.988603988603989e-05,
|
| 171 |
+
"loss": 0.4419,
|
| 172 |
+
"step": 220
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.0935897435897437,
|
| 176 |
+
"grad_norm": 11.030887603759766,
|
| 177 |
+
"learning_rate": 3.9173789173789176e-05,
|
| 178 |
+
"loss": 0.5758,
|
| 179 |
+
"step": 230
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.1064102564102565,
|
| 183 |
+
"grad_norm": 5.54761266708374,
|
| 184 |
+
"learning_rate": 3.846153846153846e-05,
|
| 185 |
+
"loss": 0.6464,
|
| 186 |
+
"step": 240
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.1192307692307693,
|
| 190 |
+
"grad_norm": 8.304089546203613,
|
| 191 |
+
"learning_rate": 3.774928774928775e-05,
|
| 192 |
+
"loss": 0.3947,
|
| 193 |
+
"step": 250
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.132051282051282,
|
| 197 |
+
"grad_norm": 0.35803475975990295,
|
| 198 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 199 |
+
"loss": 0.4621,
|
| 200 |
+
"step": 260
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.1448717948717948,
|
| 204 |
+
"grad_norm": 19.831405639648438,
|
| 205 |
+
"learning_rate": 3.6324786324786323e-05,
|
| 206 |
+
"loss": 0.8061,
|
| 207 |
+
"step": 270
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.1576923076923076,
|
| 211 |
+
"grad_norm": 0.5348687767982483,
|
| 212 |
+
"learning_rate": 3.561253561253561e-05,
|
| 213 |
+
"loss": 0.4076,
|
| 214 |
+
"step": 280
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.1705128205128206,
|
| 218 |
+
"grad_norm": 6.216036796569824,
|
| 219 |
+
"learning_rate": 3.4900284900284904e-05,
|
| 220 |
+
"loss": 0.403,
|
| 221 |
+
"step": 290
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.1833333333333333,
|
| 225 |
+
"grad_norm": 1.6393040418624878,
|
| 226 |
+
"learning_rate": 3.418803418803419e-05,
|
| 227 |
+
"loss": 0.4308,
|
| 228 |
+
"step": 300
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.1961538461538461,
|
| 232 |
+
"grad_norm": 5.89309549331665,
|
| 233 |
+
"learning_rate": 3.347578347578348e-05,
|
| 234 |
+
"loss": 0.3263,
|
| 235 |
+
"step": 310
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 1.2012820512820512,
|
| 239 |
+
"eval_accuracy": 0.8287671232876712,
|
| 240 |
+
"eval_loss": 0.6184389591217041,
|
| 241 |
+
"eval_runtime": 44.0336,
|
| 242 |
+
"eval_samples_per_second": 3.316,
|
| 243 |
+
"eval_steps_per_second": 0.84,
|
| 244 |
+
"step": 314
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.0076923076923077,
|
| 248 |
+
"grad_norm": 8.897279739379883,
|
| 249 |
+
"learning_rate": 3.2763532763532764e-05,
|
| 250 |
+
"loss": 0.736,
|
| 251 |
+
"step": 320
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 2.0205128205128204,
|
| 255 |
+
"grad_norm": 11.958976745605469,
|
| 256 |
+
"learning_rate": 3.205128205128206e-05,
|
| 257 |
+
"loss": 0.0545,
|
| 258 |
+
"step": 330
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 2.033333333333333,
|
| 262 |
+
"grad_norm": 0.10042566061019897,
|
| 263 |
+
"learning_rate": 3.133903133903134e-05,
|
| 264 |
+
"loss": 0.3544,
|
| 265 |
+
"step": 340
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 2.046153846153846,
|
| 269 |
+
"grad_norm": 3.468107223510742,
|
| 270 |
+
"learning_rate": 3.0626780626780625e-05,
|
| 271 |
+
"loss": 0.4753,
|
| 272 |
+
"step": 350
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.0589743589743588,
|
| 276 |
+
"grad_norm": 0.6979026794433594,
|
| 277 |
+
"learning_rate": 2.9914529914529915e-05,
|
| 278 |
+
"loss": 0.1313,
|
| 279 |
+
"step": 360
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.071794871794872,
|
| 283 |
+
"grad_norm": 3.0566658973693848,
|
| 284 |
+
"learning_rate": 2.9202279202279202e-05,
|
| 285 |
+
"loss": 0.5758,
|
| 286 |
+
"step": 370
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 2.0846153846153848,
|
| 290 |
+
"grad_norm": 0.26063987612724304,
|
| 291 |
+
"learning_rate": 2.8490028490028492e-05,
|
| 292 |
+
"loss": 0.2311,
|
| 293 |
+
"step": 380
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 2.0974358974358975,
|
| 297 |
+
"grad_norm": 3.1704676151275635,
|
| 298 |
+
"learning_rate": 2.777777777777778e-05,
|
| 299 |
+
"loss": 0.3121,
|
| 300 |
+
"step": 390
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 2.1102564102564103,
|
| 304 |
+
"grad_norm": 0.06660736352205276,
|
| 305 |
+
"learning_rate": 2.706552706552707e-05,
|
| 306 |
+
"loss": 0.2649,
|
| 307 |
+
"step": 400
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 2.123076923076923,
|
| 311 |
+
"grad_norm": 0.8849107027053833,
|
| 312 |
+
"learning_rate": 2.6353276353276356e-05,
|
| 313 |
+
"loss": 0.4632,
|
| 314 |
+
"step": 410
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.135897435897436,
|
| 318 |
+
"grad_norm": 16.48140525817871,
|
| 319 |
+
"learning_rate": 2.564102564102564e-05,
|
| 320 |
+
"loss": 0.5191,
|
| 321 |
+
"step": 420
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.1487179487179486,
|
| 325 |
+
"grad_norm": 2.628391742706299,
|
| 326 |
+
"learning_rate": 2.492877492877493e-05,
|
| 327 |
+
"loss": 0.405,
|
| 328 |
+
"step": 430
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 2.1615384615384614,
|
| 332 |
+
"grad_norm": 1.1029433012008667,
|
| 333 |
+
"learning_rate": 2.4216524216524217e-05,
|
| 334 |
+
"loss": 0.3149,
|
| 335 |
+
"step": 440
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 2.174358974358974,
|
| 339 |
+
"grad_norm": 8.070186614990234,
|
| 340 |
+
"learning_rate": 2.3504273504273504e-05,
|
| 341 |
+
"loss": 0.5851,
|
| 342 |
+
"step": 450
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 2.1871794871794874,
|
| 346 |
+
"grad_norm": 12.600333213806152,
|
| 347 |
+
"learning_rate": 2.2792022792022794e-05,
|
| 348 |
+
"loss": 0.3032,
|
| 349 |
+
"step": 460
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 2.2,
|
| 353 |
+
"grad_norm": 1.988337755203247,
|
| 354 |
+
"learning_rate": 2.207977207977208e-05,
|
| 355 |
+
"loss": 0.6332,
|
| 356 |
+
"step": 470
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 2.2012820512820515,
|
| 360 |
+
"eval_accuracy": 0.8424657534246576,
|
| 361 |
+
"eval_loss": 0.4275156855583191,
|
| 362 |
+
"eval_runtime": 44.8316,
|
| 363 |
+
"eval_samples_per_second": 3.257,
|
| 364 |
+
"eval_steps_per_second": 0.825,
|
| 365 |
+
"step": 471
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 3.0115384615384615,
|
| 369 |
+
"grad_norm": 0.7842563986778259,
|
| 370 |
+
"learning_rate": 2.1367521367521368e-05,
|
| 371 |
+
"loss": 0.2056,
|
| 372 |
+
"step": 480
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 3.0243589743589743,
|
| 376 |
+
"grad_norm": 9.073537826538086,
|
| 377 |
+
"learning_rate": 2.0655270655270654e-05,
|
| 378 |
+
"loss": 0.2923,
|
| 379 |
+
"step": 490
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 3.037179487179487,
|
| 383 |
+
"grad_norm": 9.187246322631836,
|
| 384 |
+
"learning_rate": 1.9943019943019945e-05,
|
| 385 |
+
"loss": 0.2992,
|
| 386 |
+
"step": 500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 3.05,
|
| 390 |
+
"grad_norm": 20.043611526489258,
|
| 391 |
+
"learning_rate": 1.923076923076923e-05,
|
| 392 |
+
"loss": 0.5296,
|
| 393 |
+
"step": 510
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 3.0628205128205126,
|
| 397 |
+
"grad_norm": 28.867929458618164,
|
| 398 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 399 |
+
"loss": 0.1522,
|
| 400 |
+
"step": 520
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 3.075641025641026,
|
| 404 |
+
"grad_norm": 13.749585151672363,
|
| 405 |
+
"learning_rate": 1.7806267806267805e-05,
|
| 406 |
+
"loss": 0.5946,
|
| 407 |
+
"step": 530
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 3.0884615384615386,
|
| 411 |
+
"grad_norm": 3.9784131050109863,
|
| 412 |
+
"learning_rate": 1.7094017094017095e-05,
|
| 413 |
+
"loss": 0.7594,
|
| 414 |
+
"step": 540
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 3.1012820512820514,
|
| 418 |
+
"grad_norm": 0.4377283453941345,
|
| 419 |
+
"learning_rate": 1.6381766381766382e-05,
|
| 420 |
+
"loss": 0.0527,
|
| 421 |
+
"step": 550
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 3.114102564102564,
|
| 425 |
+
"grad_norm": 0.44730284810066223,
|
| 426 |
+
"learning_rate": 1.566951566951567e-05,
|
| 427 |
+
"loss": 0.3361,
|
| 428 |
+
"step": 560
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 3.126923076923077,
|
| 432 |
+
"grad_norm": 2.1688125133514404,
|
| 433 |
+
"learning_rate": 1.4957264957264958e-05,
|
| 434 |
+
"loss": 0.4073,
|
| 435 |
+
"step": 570
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 3.1397435897435897,
|
| 439 |
+
"grad_norm": 6.609060287475586,
|
| 440 |
+
"learning_rate": 1.4245014245014246e-05,
|
| 441 |
+
"loss": 0.5241,
|
| 442 |
+
"step": 580
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 3.1525641025641025,
|
| 446 |
+
"grad_norm": 18.088504791259766,
|
| 447 |
+
"learning_rate": 1.3532763532763535e-05,
|
| 448 |
+
"loss": 0.1817,
|
| 449 |
+
"step": 590
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 3.1653846153846152,
|
| 453 |
+
"grad_norm": 3.1018402576446533,
|
| 454 |
+
"learning_rate": 1.282051282051282e-05,
|
| 455 |
+
"loss": 0.1476,
|
| 456 |
+
"step": 600
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 3.178205128205128,
|
| 460 |
+
"grad_norm": 0.2694937586784363,
|
| 461 |
+
"learning_rate": 1.2108262108262108e-05,
|
| 462 |
+
"loss": 0.1166,
|
| 463 |
+
"step": 610
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 3.1910256410256412,
|
| 467 |
+
"grad_norm": 0.2130882292985916,
|
| 468 |
+
"learning_rate": 1.1396011396011397e-05,
|
| 469 |
+
"loss": 0.0405,
|
| 470 |
+
"step": 620
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 3.2012820512820515,
|
| 474 |
+
"eval_accuracy": 0.8424657534246576,
|
| 475 |
+
"eval_loss": 0.76870197057724,
|
| 476 |
+
"eval_runtime": 44.2253,
|
| 477 |
+
"eval_samples_per_second": 3.301,
|
| 478 |
+
"eval_steps_per_second": 0.837,
|
| 479 |
+
"step": 628
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 4.0025641025641026,
|
| 483 |
+
"grad_norm": 37.76756286621094,
|
| 484 |
+
"learning_rate": 1.0683760683760684e-05,
|
| 485 |
+
"loss": 0.4644,
|
| 486 |
+
"step": 630
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 4.015384615384615,
|
| 490 |
+
"grad_norm": 0.223415806889534,
|
| 491 |
+
"learning_rate": 9.971509971509972e-06,
|
| 492 |
+
"loss": 0.5616,
|
| 493 |
+
"step": 640
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 4.028205128205128,
|
| 497 |
+
"grad_norm": 0.11729208379983902,
|
| 498 |
+
"learning_rate": 9.259259259259259e-06,
|
| 499 |
+
"loss": 0.0667,
|
| 500 |
+
"step": 650
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 4.041025641025641,
|
| 504 |
+
"grad_norm": 3.586672782897949,
|
| 505 |
+
"learning_rate": 8.547008547008548e-06,
|
| 506 |
+
"loss": 0.1252,
|
| 507 |
+
"step": 660
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 4.053846153846154,
|
| 511 |
+
"grad_norm": 20.754961013793945,
|
| 512 |
+
"learning_rate": 7.834757834757835e-06,
|
| 513 |
+
"loss": 0.2335,
|
| 514 |
+
"step": 670
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 4.066666666666666,
|
| 518 |
+
"grad_norm": 1.776369571685791,
|
| 519 |
+
"learning_rate": 7.122507122507123e-06,
|
| 520 |
+
"loss": 0.1772,
|
| 521 |
+
"step": 680
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 4.079487179487179,
|
| 525 |
+
"grad_norm": 0.9859512448310852,
|
| 526 |
+
"learning_rate": 6.41025641025641e-06,
|
| 527 |
+
"loss": 0.1654,
|
| 528 |
+
"step": 690
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 4.092307692307692,
|
| 532 |
+
"grad_norm": 9.265326499938965,
|
| 533 |
+
"learning_rate": 5.6980056980056985e-06,
|
| 534 |
+
"loss": 0.1738,
|
| 535 |
+
"step": 700
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 4.105128205128205,
|
| 539 |
+
"grad_norm": 17.748327255249023,
|
| 540 |
+
"learning_rate": 4.985754985754986e-06,
|
| 541 |
+
"loss": 0.3303,
|
| 542 |
+
"step": 710
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 4.1179487179487175,
|
| 546 |
+
"grad_norm": 0.5790041089057922,
|
| 547 |
+
"learning_rate": 4.273504273504274e-06,
|
| 548 |
+
"loss": 0.2181,
|
| 549 |
+
"step": 720
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 4.130769230769231,
|
| 553 |
+
"grad_norm": 0.2577972710132599,
|
| 554 |
+
"learning_rate": 3.5612535612535615e-06,
|
| 555 |
+
"loss": 0.0101,
|
| 556 |
+
"step": 730
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 4.143589743589744,
|
| 560 |
+
"grad_norm": 27.089906692504883,
|
| 561 |
+
"learning_rate": 2.8490028490028492e-06,
|
| 562 |
+
"loss": 0.1569,
|
| 563 |
+
"step": 740
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 4.156410256410257,
|
| 567 |
+
"grad_norm": 0.044243063777685165,
|
| 568 |
+
"learning_rate": 2.136752136752137e-06,
|
| 569 |
+
"loss": 0.1688,
|
| 570 |
+
"step": 750
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 4.1692307692307695,
|
| 574 |
+
"grad_norm": 13.373856544494629,
|
| 575 |
+
"learning_rate": 1.4245014245014246e-06,
|
| 576 |
+
"loss": 0.0592,
|
| 577 |
+
"step": 760
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 4.182051282051282,
|
| 581 |
+
"grad_norm": 3.7931740283966064,
|
| 582 |
+
"learning_rate": 7.122507122507123e-07,
|
| 583 |
+
"loss": 0.2266,
|
| 584 |
+
"step": 770
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 4.194871794871795,
|
| 588 |
+
"grad_norm": 6.501523971557617,
|
| 589 |
+
"learning_rate": 0.0,
|
| 590 |
+
"loss": 0.1579,
|
| 591 |
+
"step": 780
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 4.194871794871795,
|
| 595 |
+
"eval_accuracy": 0.8561643835616438,
|
| 596 |
+
"eval_loss": 0.5852294564247131,
|
| 597 |
+
"eval_runtime": 44.3219,
|
| 598 |
+
"eval_samples_per_second": 3.294,
|
| 599 |
+
"eval_steps_per_second": 0.835,
|
| 600 |
+
"step": 780
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 4.194871794871795,
|
| 604 |
+
"step": 780,
|
| 605 |
+
"total_flos": 3.8777530024360673e+18,
|
| 606 |
+
"train_loss": 0.3928673116060404,
|
| 607 |
+
"train_runtime": 2196.6027,
|
| 608 |
+
"train_samples_per_second": 1.42,
|
| 609 |
+
"train_steps_per_second": 0.355
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 4.194871794871795,
|
| 613 |
+
"eval_accuracy": 0.8874172185430463,
|
| 614 |
+
"eval_loss": 0.3803229033946991,
|
| 615 |
+
"eval_runtime": 88.7221,
|
| 616 |
+
"eval_samples_per_second": 1.702,
|
| 617 |
+
"eval_steps_per_second": 0.428,
|
| 618 |
+
"step": 780
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 4.194871794871795,
|
| 622 |
+
"eval_accuracy": 0.8874172185430463,
|
| 623 |
+
"eval_loss": 0.38032299280166626,
|
| 624 |
+
"eval_runtime": 51.2971,
|
| 625 |
+
"eval_samples_per_second": 2.944,
|
| 626 |
+
"eval_steps_per_second": 0.741,
|
| 627 |
+
"step": 780
|
| 628 |
+
}
|
| 629 |
+
],
|
| 630 |
+
"logging_steps": 10,
|
| 631 |
+
"max_steps": 780,
|
| 632 |
+
"num_input_tokens_seen": 0,
|
| 633 |
+
"num_train_epochs": 9223372036854775807,
|
| 634 |
+
"save_steps": 500,
|
| 635 |
+
"total_flos": 3.8777530024360673e+18,
|
| 636 |
+
"train_batch_size": 4,
|
| 637 |
+
"trial_name": null,
|
| 638 |
+
"trial_params": null
|
| 639 |
+
}
|