Commit
•
fecf5d8
1
Parent(s):
4e23210
Upload folder using huggingface_hub
Browse files- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +166 -0
- training_args.bin +3 -0
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9fdb85571ef33da8cec527cf805ab20b0235068b7ce57d33cfbfcd8a7258b9a
|
| 3 |
+
size 691
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c76d03ae6d839e3668b5580261ed5c5f459f0fcc1f3bf7dd1f1afb561a9b5d46
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48268bfa38645a491a5b2414c642994ca1ef111bd43d15a84cfebc5950f32a5f
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,166 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.218769043266301,
|
| 5 |
+
"global_step": 1000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.05,
|
| 12 |
+
"learning_rate": 5e-06,
|
| 13 |
+
"loss": 0.0,
|
| 14 |
+
"step": 40
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.1,
|
| 18 |
+
"learning_rate": 5e-06,
|
| 19 |
+
"loss": 1085325.8,
|
| 20 |
+
"step": 80
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.15,
|
| 24 |
+
"learning_rate": 5e-06,
|
| 25 |
+
"loss": 27.3891,
|
| 26 |
+
"step": 120
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.2,
|
| 30 |
+
"learning_rate": 5e-06,
|
| 31 |
+
"loss": 0.0,
|
| 32 |
+
"step": 160
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.24,
|
| 36 |
+
"learning_rate": 9.7985347985348e-06,
|
| 37 |
+
"loss": 43973696.0,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.29,
|
| 42 |
+
"learning_rate": 9.554334554334555e-06,
|
| 43 |
+
"loss": 308.4559,
|
| 44 |
+
"step": 240
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.34,
|
| 48 |
+
"learning_rate": 9.31013431013431e-06,
|
| 49 |
+
"loss": 0.0,
|
| 50 |
+
"step": 280
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.39,
|
| 54 |
+
"learning_rate": 9.065934065934067e-06,
|
| 55 |
+
"loss": 54291310182.4,
|
| 56 |
+
"step": 320
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.44,
|
| 60 |
+
"learning_rate": 8.821733821733822e-06,
|
| 61 |
+
"loss": 201.0815,
|
| 62 |
+
"step": 360
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.49,
|
| 66 |
+
"learning_rate": 8.577533577533578e-06,
|
| 67 |
+
"loss": 49.0666,
|
| 68 |
+
"step": 400
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.54,
|
| 72 |
+
"learning_rate": 8.333333333333334e-06,
|
| 73 |
+
"loss": 13360362.4,
|
| 74 |
+
"step": 440
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.59,
|
| 78 |
+
"learning_rate": 8.08913308913309e-06,
|
| 79 |
+
"loss": 41888.1875,
|
| 80 |
+
"step": 480
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.63,
|
| 84 |
+
"learning_rate": 7.844932844932845e-06,
|
| 85 |
+
"loss": 1587181676134.4,
|
| 86 |
+
"step": 520
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.68,
|
| 90 |
+
"learning_rate": 7.600732600732601e-06,
|
| 91 |
+
"loss": 0.0,
|
| 92 |
+
"step": 560
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.73,
|
| 96 |
+
"learning_rate": 7.3565323565323575e-06,
|
| 97 |
+
"loss": 19445940.8,
|
| 98 |
+
"step": 600
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.78,
|
| 102 |
+
"learning_rate": 7.112332112332113e-06,
|
| 103 |
+
"loss": 364.8462,
|
| 104 |
+
"step": 640
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.83,
|
| 108 |
+
"learning_rate": 6.868131868131869e-06,
|
| 109 |
+
"loss": 8510298521.6,
|
| 110 |
+
"step": 680
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.88,
|
| 114 |
+
"learning_rate": 6.623931623931624e-06,
|
| 115 |
+
"loss": 2695.5557,
|
| 116 |
+
"step": 720
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.93,
|
| 120 |
+
"learning_rate": 6.37973137973138e-06,
|
| 121 |
+
"loss": 49141020.8,
|
| 122 |
+
"step": 760
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.98,
|
| 126 |
+
"learning_rate": 6.135531135531136e-06,
|
| 127 |
+
"loss": 8376225792.0,
|
| 128 |
+
"step": 800
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.02,
|
| 132 |
+
"learning_rate": 5.891330891330892e-06,
|
| 133 |
+
"loss": 10.4181,
|
| 134 |
+
"step": 840
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.07,
|
| 138 |
+
"learning_rate": 5.647130647130648e-06,
|
| 139 |
+
"loss": 89069.3438,
|
| 140 |
+
"step": 880
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.12,
|
| 144 |
+
"learning_rate": 5.402930402930403e-06,
|
| 145 |
+
"loss": 3576579469659341.0,
|
| 146 |
+
"step": 920
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.17,
|
| 150 |
+
"learning_rate": 5.15873015873016e-06,
|
| 151 |
+
"loss": 15996842252697.6,
|
| 152 |
+
"step": 960
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.22,
|
| 156 |
+
"learning_rate": 4.914529914529915e-06,
|
| 157 |
+
"loss": 13413.2859,
|
| 158 |
+
"step": 1000
|
| 159 |
+
}
|
| 160 |
+
],
|
| 161 |
+
"max_steps": 1640,
|
| 162 |
+
"num_train_epochs": 2,
|
| 163 |
+
"total_flos": 1119188941897728.0,
|
| 164 |
+
"trial_name": null,
|
| 165 |
+
"trial_params": null
|
| 166 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f383bef34eeb858d5c8e2c1d0fafb660bee3b3dd04fbd5852c213bde868c4081
|
| 3 |
+
size 4027
|