Upload folder using huggingface_hub
Browse files
checkpoint-810/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac048c08c0be562ede9aa236e8c85c8cffe4f8653c8243696e417ee80a44de51
|
| 3 |
+
size 6020469052
|
checkpoint-810/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:116fdb28ffb5f13786af2d6ddfbcf542af5575a50a791aa846652c8635be179e
|
| 3 |
+
size 460681594
|
checkpoint-810/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0959e23e1122ccf0546cf64dcc6b1f11129516f4d5ec4bcbf3af19d588633b63
|
| 3 |
+
size 14308
|
checkpoint-810/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12902b5d135404c4085f65898232340add1dbf39fadba96cae7c04a980e3d2ef
|
| 3 |
+
size 1064
|
checkpoint-810/trainer_state.json
ADDED
|
@@ -0,0 +1,459 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 810,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.07901234567901234,
|
| 13 |
+
"grad_norm": 1.3167223930358887,
|
| 14 |
+
"learning_rate": 3.1683168316831685e-06,
|
| 15 |
+
"loss": 8.0693,
|
| 16 |
+
"step": 16
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.1580246913580247,
|
| 20 |
+
"grad_norm": 1.3907195329666138,
|
| 21 |
+
"learning_rate": 6.336633663366337e-06,
|
| 22 |
+
"loss": 8.0604,
|
| 23 |
+
"step": 32
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.23703703703703705,
|
| 27 |
+
"grad_norm": 1.4589389562606812,
|
| 28 |
+
"learning_rate": 9.504950495049505e-06,
|
| 29 |
+
"loss": 8.014,
|
| 30 |
+
"step": 48
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.3160493827160494,
|
| 34 |
+
"grad_norm": 1.3790431022644043,
|
| 35 |
+
"learning_rate": 1.2673267326732674e-05,
|
| 36 |
+
"loss": 8.0335,
|
| 37 |
+
"step": 64
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.3950617283950617,
|
| 41 |
+
"grad_norm": 1.4199501276016235,
|
| 42 |
+
"learning_rate": 1.5841584158415843e-05,
|
| 43 |
+
"loss": 8.0402,
|
| 44 |
+
"step": 80
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.4740740740740741,
|
| 48 |
+
"grad_norm": 1.4907445907592773,
|
| 49 |
+
"learning_rate": 1.900990099009901e-05,
|
| 50 |
+
"loss": 8.0092,
|
| 51 |
+
"step": 96
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.5530864197530864,
|
| 55 |
+
"grad_norm": 1.5364277362823486,
|
| 56 |
+
"learning_rate": 1.999277438119978e-05,
|
| 57 |
+
"loss": 8.0424,
|
| 58 |
+
"step": 112
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.6320987654320988,
|
| 62 |
+
"grad_norm": 1.511999249458313,
|
| 63 |
+
"learning_rate": 1.995649347969019e-05,
|
| 64 |
+
"loss": 8.0508,
|
| 65 |
+
"step": 128
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.7111111111111111,
|
| 69 |
+
"grad_norm": 1.4422956705093384,
|
| 70 |
+
"learning_rate": 1.9889775168565942e-05,
|
| 71 |
+
"loss": 8.0349,
|
| 72 |
+
"step": 144
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.7901234567901234,
|
| 76 |
+
"grad_norm": 1.335660457611084,
|
| 77 |
+
"learning_rate": 1.9792823408445173e-05,
|
| 78 |
+
"loss": 8.0217,
|
| 79 |
+
"step": 160
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.8691358024691358,
|
| 83 |
+
"grad_norm": 1.4929100275039673,
|
| 84 |
+
"learning_rate": 1.966593458484168e-05,
|
| 85 |
+
"loss": 8.0288,
|
| 86 |
+
"step": 176
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.9481481481481482,
|
| 90 |
+
"grad_norm": 1.4001775979995728,
|
| 91 |
+
"learning_rate": 1.9509496602102253e-05,
|
| 92 |
+
"loss": 7.988,
|
| 93 |
+
"step": 192
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.9975308641975309,
|
| 97 |
+
"eval_bleu": 0.06908982865992942,
|
| 98 |
+
"eval_cap_loss": 2.4894158536312627,
|
| 99 |
+
"eval_con_loss": 2.0581045664992987,
|
| 100 |
+
"eval_loss": 6.605625005329356,
|
| 101 |
+
"step": 202
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.9975308641975309,
|
| 105 |
+
"eval_bleu": 0.06908982865992942,
|
| 106 |
+
"eval_cap_loss": 2.4894158536312627,
|
| 107 |
+
"eval_con_loss": 2.0581045664992987,
|
| 108 |
+
"eval_loss": 6.605625005329356,
|
| 109 |
+
"eval_runtime": 79.8535,
|
| 110 |
+
"eval_samples_per_second": 10.131,
|
| 111 |
+
"eval_steps_per_second": 1.277,
|
| 112 |
+
"step": 202
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 1.0271604938271606,
|
| 116 |
+
"grad_norm": 1.6348539590835571,
|
| 117 |
+
"learning_rate": 1.932398769756714e-05,
|
| 118 |
+
"loss": 7.9169,
|
| 119 |
+
"step": 208
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.106172839506173,
|
| 123 |
+
"grad_norm": 1.468509316444397,
|
| 124 |
+
"learning_rate": 1.9109974979578852e-05,
|
| 125 |
+
"loss": 7.9217,
|
| 126 |
+
"step": 224
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 1.1851851851851851,
|
| 130 |
+
"grad_norm": 1.390411376953125,
|
| 131 |
+
"learning_rate": 1.8868112693808664e-05,
|
| 132 |
+
"loss": 7.9302,
|
| 133 |
+
"step": 240
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 1.2641975308641975,
|
| 137 |
+
"grad_norm": 1.302958369255066,
|
| 138 |
+
"learning_rate": 1.8599140223200716e-05,
|
| 139 |
+
"loss": 7.968,
|
| 140 |
+
"step": 256
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.34320987654321,
|
| 144 |
+
"grad_norm": 1.465013861656189,
|
| 145 |
+
"learning_rate": 1.8303879827647977e-05,
|
| 146 |
+
"loss": 7.9389,
|
| 147 |
+
"step": 272
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.4222222222222223,
|
| 151 |
+
"grad_norm": 1.5777554512023926,
|
| 152 |
+
"learning_rate": 1.798323413030997e-05,
|
| 153 |
+
"loss": 7.9274,
|
| 154 |
+
"step": 288
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.5012345679012347,
|
| 158 |
+
"grad_norm": 1.3084310293197632,
|
| 159 |
+
"learning_rate": 1.76381833582567e-05,
|
| 160 |
+
"loss": 7.9272,
|
| 161 |
+
"step": 304
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.5802469135802468,
|
| 165 |
+
"grad_norm": 1.4037538766860962,
|
| 166 |
+
"learning_rate": 1.7269782345874204e-05,
|
| 167 |
+
"loss": 7.9136,
|
| 168 |
+
"step": 320
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.6592592592592592,
|
| 172 |
+
"grad_norm": 1.439072608947754,
|
| 173 |
+
"learning_rate": 1.6879157310192537e-05,
|
| 174 |
+
"loss": 7.9144,
|
| 175 |
+
"step": 336
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 1.7382716049382716,
|
| 179 |
+
"grad_norm": 1.4771238565444946,
|
| 180 |
+
"learning_rate": 1.6467502407993995e-05,
|
| 181 |
+
"loss": 7.9181,
|
| 182 |
+
"step": 352
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.817283950617284,
|
| 186 |
+
"grad_norm": 1.3906282186508179,
|
| 187 |
+
"learning_rate": 1.6036076085226813e-05,
|
| 188 |
+
"loss": 7.9348,
|
| 189 |
+
"step": 368
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.8962962962962964,
|
| 193 |
+
"grad_norm": 1.3744033575057983,
|
| 194 |
+
"learning_rate": 1.5586197229884185e-05,
|
| 195 |
+
"loss": 7.9507,
|
| 196 |
+
"step": 384
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.9753086419753085,
|
| 200 |
+
"grad_norm": 1.4868050813674927,
|
| 201 |
+
"learning_rate": 1.5119241140109466e-05,
|
| 202 |
+
"loss": 7.9345,
|
| 203 |
+
"step": 400
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 2.0,
|
| 207 |
+
"eval_bleu": 0.06595043107624254,
|
| 208 |
+
"eval_cap_loss": 2.4300825864660975,
|
| 209 |
+
"eval_con_loss": 2.058166358985153,
|
| 210 |
+
"eval_loss": 6.546415304436403,
|
| 211 |
+
"step": 405
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 2.0,
|
| 215 |
+
"eval_bleu": 0.06595043107624254,
|
| 216 |
+
"eval_cap_loss": 2.4300825864660975,
|
| 217 |
+
"eval_con_loss": 2.058166358985153,
|
| 218 |
+
"eval_loss": 6.546415304436403,
|
| 219 |
+
"eval_runtime": 79.4214,
|
| 220 |
+
"eval_samples_per_second": 10.186,
|
| 221 |
+
"eval_steps_per_second": 1.284,
|
| 222 |
+
"step": 405
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 2.054320987654321,
|
| 226 |
+
"grad_norm": 1.4153790473937988,
|
| 227 |
+
"learning_rate": 1.4636635319853274e-05,
|
| 228 |
+
"loss": 7.8805,
|
| 229 |
+
"step": 416
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 2.1333333333333333,
|
| 233 |
+
"grad_norm": 1.3386727571487427,
|
| 234 |
+
"learning_rate": 1.4139855114935253e-05,
|
| 235 |
+
"loss": 7.8973,
|
| 236 |
+
"step": 432
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.212345679012346,
|
| 240 |
+
"grad_norm": 1.4466866254806519,
|
| 241 |
+
"learning_rate": 1.3630419202851287e-05,
|
| 242 |
+
"loss": 7.9001,
|
| 243 |
+
"step": 448
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 2.291358024691358,
|
| 247 |
+
"grad_norm": 1.2998391389846802,
|
| 248 |
+
"learning_rate": 1.3109884950114007e-05,
|
| 249 |
+
"loss": 7.9096,
|
| 250 |
+
"step": 464
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 2.3703703703703702,
|
| 254 |
+
"grad_norm": 1.4705991744995117,
|
| 255 |
+
"learning_rate": 1.2579843651319382e-05,
|
| 256 |
+
"loss": 7.8773,
|
| 257 |
+
"step": 480
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 2.449382716049383,
|
| 261 |
+
"grad_norm": 1.3855006694793701,
|
| 262 |
+
"learning_rate": 1.2041915664493763e-05,
|
| 263 |
+
"loss": 7.8633,
|
| 264 |
+
"step": 496
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 2.528395061728395,
|
| 268 |
+
"grad_norm": 1.3997694253921509,
|
| 269 |
+
"learning_rate": 1.1497745457592817e-05,
|
| 270 |
+
"loss": 7.8597,
|
| 271 |
+
"step": 512
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 2.6074074074074076,
|
| 275 |
+
"grad_norm": 1.343112826347351,
|
| 276 |
+
"learning_rate": 1.0948996581295437e-05,
|
| 277 |
+
"loss": 7.8755,
|
| 278 |
+
"step": 528
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.68641975308642,
|
| 282 |
+
"grad_norm": 1.5445497035980225,
|
| 283 |
+
"learning_rate": 1.0397346583460972e-05,
|
| 284 |
+
"loss": 7.8874,
|
| 285 |
+
"step": 544
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.765432098765432,
|
| 289 |
+
"grad_norm": 1.466723918914795,
|
| 290 |
+
"learning_rate": 9.844481880796492e-06,
|
| 291 |
+
"loss": 7.9148,
|
| 292 |
+
"step": 560
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 2.8444444444444446,
|
| 296 |
+
"grad_norm": 1.3584568500518799,
|
| 297 |
+
"learning_rate": 9.292092603411642e-06,
|
| 298 |
+
"loss": 7.85,
|
| 299 |
+
"step": 576
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 2.9234567901234567,
|
| 303 |
+
"grad_norm": 1.4116945266723633,
|
| 304 |
+
"learning_rate": 8.741867428021447e-06,
|
| 305 |
+
"loss": 7.8632,
|
| 306 |
+
"step": 592
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 2.9975308641975307,
|
| 310 |
+
"eval_bleu": 0.0721711700240195,
|
| 311 |
+
"eval_cap_loss": 2.4210135878301133,
|
| 312 |
+
"eval_con_loss": 2.0581733035106287,
|
| 313 |
+
"eval_loss": 6.537360193682652,
|
| 314 |
+
"step": 607
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.9975308641975307,
|
| 318 |
+
"eval_bleu": 0.0721711700240195,
|
| 319 |
+
"eval_cap_loss": 2.4210135878301133,
|
| 320 |
+
"eval_con_loss": 2.0581733035106287,
|
| 321 |
+
"eval_loss": 6.537360193682652,
|
| 322 |
+
"eval_runtime": 81.5985,
|
| 323 |
+
"eval_samples_per_second": 9.914,
|
| 324 |
+
"eval_steps_per_second": 1.25,
|
| 325 |
+
"step": 607
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 3.0024691358024693,
|
| 329 |
+
"grad_norm": 1.864071249961853,
|
| 330 |
+
"learning_rate": 8.195488415592238e-06,
|
| 331 |
+
"loss": 7.8348,
|
| 332 |
+
"step": 608
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 3.0814814814814815,
|
| 336 |
+
"grad_norm": 1.5261914730072021,
|
| 337 |
+
"learning_rate": 7.654625869212147e-06,
|
| 338 |
+
"loss": 7.8239,
|
| 339 |
+
"step": 624
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 3.1604938271604937,
|
| 343 |
+
"grad_norm": 1.5600097179412842,
|
| 344 |
+
"learning_rate": 7.120933227905971e-06,
|
| 345 |
+
"loss": 7.8729,
|
| 346 |
+
"step": 640
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 3.2395061728395063,
|
| 350 |
+
"grad_norm": 1.521858811378479,
|
| 351 |
+
"learning_rate": 6.59604201200412e-06,
|
| 352 |
+
"loss": 7.8826,
|
| 353 |
+
"step": 656
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 3.3185185185185184,
|
| 357 |
+
"grad_norm": 1.453940749168396,
|
| 358 |
+
"learning_rate": 6.081556835517955e-06,
|
| 359 |
+
"loss": 7.8802,
|
| 360 |
+
"step": 672
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 3.397530864197531,
|
| 364 |
+
"grad_norm": 1.476491928100586,
|
| 365 |
+
"learning_rate": 5.579050500768837e-06,
|
| 366 |
+
"loss": 7.8213,
|
| 367 |
+
"step": 688
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 3.476543209876543,
|
| 371 |
+
"grad_norm": 1.4222908020019531,
|
| 372 |
+
"learning_rate": 5.090059190266779e-06,
|
| 373 |
+
"loss": 7.8651,
|
| 374 |
+
"step": 704
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 3.5555555555555554,
|
| 378 |
+
"grad_norm": 1.498777151107788,
|
| 379 |
+
"learning_rate": 4.616077770537453e-06,
|
| 380 |
+
"loss": 7.8873,
|
| 381 |
+
"step": 720
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 3.634567901234568,
|
| 385 |
+
"grad_norm": 1.4121512174606323,
|
| 386 |
+
"learning_rate": 4.158555222253772e-06,
|
| 387 |
+
"loss": 7.8258,
|
| 388 |
+
"step": 736
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 3.71358024691358,
|
| 392 |
+
"grad_norm": 1.5000683069229126,
|
| 393 |
+
"learning_rate": 3.718890210642442e-06,
|
| 394 |
+
"loss": 7.8599,
|
| 395 |
+
"step": 752
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 3.7925925925925927,
|
| 399 |
+
"grad_norm": 1.630094051361084,
|
| 400 |
+
"learning_rate": 3.2984268097069284e-06,
|
| 401 |
+
"loss": 7.8903,
|
| 402 |
+
"step": 768
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 3.871604938271605,
|
| 406 |
+
"grad_norm": 1.6297024488449097,
|
| 407 |
+
"learning_rate": 2.898450393337977e-06,
|
| 408 |
+
"loss": 7.8535,
|
| 409 |
+
"step": 784
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 3.950617283950617,
|
| 413 |
+
"grad_norm": 1.6124980449676514,
|
| 414 |
+
"learning_rate": 2.5201837058728506e-06,
|
| 415 |
+
"loss": 7.8592,
|
| 416 |
+
"step": 800
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 4.0,
|
| 420 |
+
"eval_bleu": 0.06875532122288064,
|
| 421 |
+
"eval_cap_loss": 2.4062162719520868,
|
| 422 |
+
"eval_con_loss": 2.0580918672038058,
|
| 423 |
+
"eval_loss": 6.522400014540729,
|
| 424 |
+
"step": 810
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 4.0,
|
| 428 |
+
"eval_bleu": 0.06875532122288064,
|
| 429 |
+
"eval_cap_loss": 2.4062162719520868,
|
| 430 |
+
"eval_con_loss": 2.0580918672038058,
|
| 431 |
+
"eval_loss": 6.522400014540729,
|
| 432 |
+
"eval_runtime": 82.4788,
|
| 433 |
+
"eval_samples_per_second": 9.809,
|
| 434 |
+
"eval_steps_per_second": 1.237,
|
| 435 |
+
"step": 810
|
| 436 |
+
}
|
| 437 |
+
],
|
| 438 |
+
"logging_steps": 16,
|
| 439 |
+
"max_steps": 1010,
|
| 440 |
+
"num_input_tokens_seen": 0,
|
| 441 |
+
"num_train_epochs": 5,
|
| 442 |
+
"save_steps": 500,
|
| 443 |
+
"stateful_callbacks": {
|
| 444 |
+
"TrainerControl": {
|
| 445 |
+
"args": {
|
| 446 |
+
"should_epoch_stop": false,
|
| 447 |
+
"should_evaluate": false,
|
| 448 |
+
"should_log": false,
|
| 449 |
+
"should_save": true,
|
| 450 |
+
"should_training_stop": false
|
| 451 |
+
},
|
| 452 |
+
"attributes": {}
|
| 453 |
+
}
|
| 454 |
+
},
|
| 455 |
+
"total_flos": 0.0,
|
| 456 |
+
"train_batch_size": 16,
|
| 457 |
+
"trial_name": null,
|
| 458 |
+
"trial_params": null
|
| 459 |
+
}
|
checkpoint-810/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27dd50b12e8a8125c1ae97fdb89079032fd83cd34fcb149fee2dea4a9480ffdd
|
| 3 |
+
size 5176
|