Upload 5 files
Browse files- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +199 -0
- training_args.bin +3 -0
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3546f8492421cfd87db69cadba53bc75fa76a34bb8c3e665b8cff75ed6bcb768
|
| 3 |
+
size 671466706
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b51d5ac2b393e97636a64352df308bb0b55cf886ebbdc9b96bdf85e7a87b988e
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fbfebdb9370fa79ff3d22115617702fccac4d89b75bfb761f020050159185353
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,199 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 13.215859030837004,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 300,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.44,
|
| 13 |
+
"learning_rate": 0.0001958997722095672,
|
| 14 |
+
"loss": 2.0853,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.88,
|
| 19 |
+
"learning_rate": 0.00019134396355353076,
|
| 20 |
+
"loss": 1.3615,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 1.32,
|
| 25 |
+
"learning_rate": 0.00018678815489749431,
|
| 26 |
+
"loss": 0.9669,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 1.76,
|
| 31 |
+
"learning_rate": 0.00018223234624145787,
|
| 32 |
+
"loss": 0.812,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 2.2,
|
| 37 |
+
"learning_rate": 0.00017767653758542142,
|
| 38 |
+
"loss": 0.5919,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 2.64,
|
| 43 |
+
"learning_rate": 0.00017312072892938497,
|
| 44 |
+
"loss": 0.3963,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 3.08,
|
| 49 |
+
"learning_rate": 0.00016856492027334853,
|
| 50 |
+
"loss": 0.3623,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 3.52,
|
| 55 |
+
"learning_rate": 0.00016400911161731208,
|
| 56 |
+
"loss": 0.2111,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 3.96,
|
| 61 |
+
"learning_rate": 0.00015945330296127563,
|
| 62 |
+
"loss": 0.2065,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 4.41,
|
| 67 |
+
"learning_rate": 0.0001548974943052392,
|
| 68 |
+
"loss": 0.1298,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 4.85,
|
| 73 |
+
"learning_rate": 0.00015034168564920274,
|
| 74 |
+
"loss": 0.1439,
|
| 75 |
+
"step": 110
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 5.29,
|
| 79 |
+
"learning_rate": 0.0001457858769931663,
|
| 80 |
+
"loss": 0.1188,
|
| 81 |
+
"step": 120
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 5.73,
|
| 85 |
+
"learning_rate": 0.00014123006833712985,
|
| 86 |
+
"loss": 0.1068,
|
| 87 |
+
"step": 130
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 6.17,
|
| 91 |
+
"learning_rate": 0.0001366742596810934,
|
| 92 |
+
"loss": 0.1007,
|
| 93 |
+
"step": 140
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 6.61,
|
| 97 |
+
"learning_rate": 0.00013211845102505695,
|
| 98 |
+
"loss": 0.0901,
|
| 99 |
+
"step": 150
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 7.05,
|
| 103 |
+
"learning_rate": 0.0001275626423690205,
|
| 104 |
+
"loss": 0.0886,
|
| 105 |
+
"step": 160
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 7.49,
|
| 109 |
+
"learning_rate": 0.00012300683371298406,
|
| 110 |
+
"loss": 0.0746,
|
| 111 |
+
"step": 170
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 7.93,
|
| 115 |
+
"learning_rate": 0.0001184510250569476,
|
| 116 |
+
"loss": 0.0798,
|
| 117 |
+
"step": 180
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 8.37,
|
| 121 |
+
"learning_rate": 0.00011389521640091117,
|
| 122 |
+
"loss": 0.0655,
|
| 123 |
+
"step": 190
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 8.81,
|
| 127 |
+
"learning_rate": 0.00010933940774487472,
|
| 128 |
+
"loss": 0.068,
|
| 129 |
+
"step": 200
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 9.25,
|
| 133 |
+
"learning_rate": 0.00010478359908883827,
|
| 134 |
+
"loss": 0.0633,
|
| 135 |
+
"step": 210
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 9.69,
|
| 139 |
+
"learning_rate": 0.00010022779043280184,
|
| 140 |
+
"loss": 0.0604,
|
| 141 |
+
"step": 220
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 10.13,
|
| 145 |
+
"learning_rate": 9.567198177676538e-05,
|
| 146 |
+
"loss": 0.0642,
|
| 147 |
+
"step": 230
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 10.57,
|
| 151 |
+
"learning_rate": 9.111617312072893e-05,
|
| 152 |
+
"loss": 0.0566,
|
| 153 |
+
"step": 240
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 11.01,
|
| 157 |
+
"learning_rate": 8.656036446469249e-05,
|
| 158 |
+
"loss": 0.0578,
|
| 159 |
+
"step": 250
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 11.45,
|
| 163 |
+
"learning_rate": 8.200455580865604e-05,
|
| 164 |
+
"loss": 0.0504,
|
| 165 |
+
"step": 260
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 11.89,
|
| 169 |
+
"learning_rate": 7.74487471526196e-05,
|
| 170 |
+
"loss": 0.0606,
|
| 171 |
+
"step": 270
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 12.33,
|
| 175 |
+
"learning_rate": 7.289293849658315e-05,
|
| 176 |
+
"loss": 0.0497,
|
| 177 |
+
"step": 280
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 12.78,
|
| 181 |
+
"learning_rate": 6.83371298405467e-05,
|
| 182 |
+
"loss": 0.0524,
|
| 183 |
+
"step": 290
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 13.22,
|
| 187 |
+
"learning_rate": 6.378132118451025e-05,
|
| 188 |
+
"loss": 0.057,
|
| 189 |
+
"step": 300
|
| 190 |
+
}
|
| 191 |
+
],
|
| 192 |
+
"logging_steps": 10,
|
| 193 |
+
"max_steps": 440,
|
| 194 |
+
"num_train_epochs": 20,
|
| 195 |
+
"save_steps": 100,
|
| 196 |
+
"total_flos": 2.630622497248051e+16,
|
| 197 |
+
"trial_name": null,
|
| 198 |
+
"trial_params": null
|
| 199 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30a42c226fff79698af7c9053ac25947252e2060d78fe3833bbc53c24acc95a5
|
| 3 |
+
size 4600
|