Training in progress, step 610000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +123 -3
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 893441093
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34fa3fbc162567eded2c54001cc8f21167119645a7ad5d9438d4d6580d7e0aaf
|
| 3 |
size 893441093
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 449450757
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb7fc5d60355a8dfd752019852cdb15ae9d272ab89ceb9fe9acfccaaa3393cce
|
| 3 |
size 449450757
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14583
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd344a2f09d330c943a3dd3d04668fe450de22ee225e64c890f4722c7155791f
|
| 3 |
size 14583
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14583
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7587b2027544c125ad8875c396124abeaa8b26e560f514a758d79f5c77d1245e
|
| 3 |
size 14583
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14583
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b98e6e4730ae83aa0bbaf43b6a70f2dbea908df991dba53b4ba6b61ef5a4bc51
|
| 3 |
size 14583
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14583
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fae6c192050786077eb0c3ad856996ecc90d4abf868828c40917e34e278ddf8
|
| 3 |
size 14583
|
last-checkpoint/rng_state_4.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14583
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04edc224f8d5fe4b319f5145ba3be953f45d1403c8d037fe0f2d7e1df55860c5
|
| 3 |
size 14583
|
last-checkpoint/rng_state_5.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14583
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fd673ae46299e38ec0092baeee3dfcef9b18e2fdce8cd906ed6e5311b6eb2f0
|
| 3 |
size 14583
|
last-checkpoint/rng_state_6.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14583
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba46334d5cfb098826b8bc46bdfd08caddd05dd0a2ad976845aaf16ed9488107
|
| 3 |
size 14583
|
last-checkpoint/rng_state_7.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14583
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:071dfcafc848e779fb2959117671810686f513947ddff515a5f53d88a149a7ef
|
| 3 |
size 14583
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1451fdba239492a726627053577a5d97726556e48bcec30f5b94d6df5305247b
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 1.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -7206,11 +7206,131 @@
|
|
| 7206 |
"learning_rate": 6.281601590014407e-05,
|
| 7207 |
"loss": 0.3039,
|
| 7208 |
"step": 600000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7209 |
}
|
| 7210 |
],
|
| 7211 |
"max_steps": 1000000,
|
| 7212 |
"num_train_epochs": 2,
|
| 7213 |
-
"total_flos": 4.
|
| 7214 |
"trial_name": null,
|
| 7215 |
"trial_params": null
|
| 7216 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.2194195562912054,
|
| 5 |
+
"global_step": 610000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 7206 |
"learning_rate": 6.281601590014407e-05,
|
| 7207 |
"loss": 0.3039,
|
| 7208 |
"step": 600000
|
| 7209 |
+
},
|
| 7210 |
+
{
|
| 7211 |
+
"epoch": 1.2,
|
| 7212 |
+
"learning_rate": 6.270383825577923e-05,
|
| 7213 |
+
"loss": 0.3039,
|
| 7214 |
+
"step": 600500
|
| 7215 |
+
},
|
| 7216 |
+
{
|
| 7217 |
+
"epoch": 1.2,
|
| 7218 |
+
"learning_rate": 6.259170789846017e-05,
|
| 7219 |
+
"loss": 0.3034,
|
| 7220 |
+
"step": 601000
|
| 7221 |
+
},
|
| 7222 |
+
{
|
| 7223 |
+
"epoch": 1.2,
|
| 7224 |
+
"learning_rate": 6.247962513474697e-05,
|
| 7225 |
+
"loss": 0.3039,
|
| 7226 |
+
"step": 601500
|
| 7227 |
+
},
|
| 7228 |
+
{
|
| 7229 |
+
"epoch": 1.2,
|
| 7230 |
+
"learning_rate": 6.236759027106965e-05,
|
| 7231 |
+
"loss": 0.3035,
|
| 7232 |
+
"step": 602000
|
| 7233 |
+
},
|
| 7234 |
+
{
|
| 7235 |
+
"epoch": 1.2,
|
| 7236 |
+
"learning_rate": 6.225560361372722e-05,
|
| 7237 |
+
"loss": 0.3034,
|
| 7238 |
+
"step": 602500
|
| 7239 |
+
},
|
| 7240 |
+
{
|
| 7241 |
+
"epoch": 1.21,
|
| 7242 |
+
"learning_rate": 6.214366546888694e-05,
|
| 7243 |
+
"loss": 0.3045,
|
| 7244 |
+
"step": 603000
|
| 7245 |
+
},
|
| 7246 |
+
{
|
| 7247 |
+
"epoch": 1.21,
|
| 7248 |
+
"learning_rate": 6.203177614258345e-05,
|
| 7249 |
+
"loss": 0.3031,
|
| 7250 |
+
"step": 603500
|
| 7251 |
+
},
|
| 7252 |
+
{
|
| 7253 |
+
"epoch": 1.21,
|
| 7254 |
+
"learning_rate": 6.191993594071785e-05,
|
| 7255 |
+
"loss": 0.3039,
|
| 7256 |
+
"step": 604000
|
| 7257 |
+
},
|
| 7258 |
+
{
|
| 7259 |
+
"epoch": 1.21,
|
| 7260 |
+
"learning_rate": 6.180814516905701e-05,
|
| 7261 |
+
"loss": 0.3068,
|
| 7262 |
+
"step": 604500
|
| 7263 |
+
},
|
| 7264 |
+
{
|
| 7265 |
+
"epoch": 1.21,
|
| 7266 |
+
"learning_rate": 6.169640413323262e-05,
|
| 7267 |
+
"loss": 0.3035,
|
| 7268 |
+
"step": 605000
|
| 7269 |
+
},
|
| 7270 |
+
{
|
| 7271 |
+
"epoch": 1.21,
|
| 7272 |
+
"learning_rate": 6.158471313874041e-05,
|
| 7273 |
+
"loss": 0.3027,
|
| 7274 |
+
"step": 605500
|
| 7275 |
+
},
|
| 7276 |
+
{
|
| 7277 |
+
"epoch": 1.21,
|
| 7278 |
+
"learning_rate": 6.147307249093929e-05,
|
| 7279 |
+
"loss": 0.3039,
|
| 7280 |
+
"step": 606000
|
| 7281 |
+
},
|
| 7282 |
+
{
|
| 7283 |
+
"epoch": 1.21,
|
| 7284 |
+
"learning_rate": 6.136148249505053e-05,
|
| 7285 |
+
"loss": 0.3037,
|
| 7286 |
+
"step": 606500
|
| 7287 |
+
},
|
| 7288 |
+
{
|
| 7289 |
+
"epoch": 1.21,
|
| 7290 |
+
"learning_rate": 6.124994345615693e-05,
|
| 7291 |
+
"loss": 0.3034,
|
| 7292 |
+
"step": 607000
|
| 7293 |
+
},
|
| 7294 |
+
{
|
| 7295 |
+
"epoch": 1.21,
|
| 7296 |
+
"learning_rate": 6.113845567920194e-05,
|
| 7297 |
+
"loss": 0.3033,
|
| 7298 |
+
"step": 607500
|
| 7299 |
+
},
|
| 7300 |
+
{
|
| 7301 |
+
"epoch": 1.22,
|
| 7302 |
+
"learning_rate": 6.102701946898891e-05,
|
| 7303 |
+
"loss": 0.3041,
|
| 7304 |
+
"step": 608000
|
| 7305 |
+
},
|
| 7306 |
+
{
|
| 7307 |
+
"epoch": 1.22,
|
| 7308 |
+
"learning_rate": 6.0915635130180154e-05,
|
| 7309 |
+
"loss": 0.3027,
|
| 7310 |
+
"step": 608500
|
| 7311 |
+
},
|
| 7312 |
+
{
|
| 7313 |
+
"epoch": 1.22,
|
| 7314 |
+
"learning_rate": 6.0804302967296225e-05,
|
| 7315 |
+
"loss": 0.3028,
|
| 7316 |
+
"step": 609000
|
| 7317 |
+
},
|
| 7318 |
+
{
|
| 7319 |
+
"epoch": 1.22,
|
| 7320 |
+
"learning_rate": 6.0693023284715e-05,
|
| 7321 |
+
"loss": 0.3031,
|
| 7322 |
+
"step": 609500
|
| 7323 |
+
},
|
| 7324 |
+
{
|
| 7325 |
+
"epoch": 1.22,
|
| 7326 |
+
"learning_rate": 6.058179638667089e-05,
|
| 7327 |
+
"loss": 0.3027,
|
| 7328 |
+
"step": 610000
|
| 7329 |
}
|
| 7330 |
],
|
| 7331 |
"max_steps": 1000000,
|
| 7332 |
"num_train_epochs": 2,
|
| 7333 |
+
"total_flos": 4.124028700869167e+22,
|
| 7334 |
"trial_name": null,
|
| 7335 |
"trial_params": null
|
| 7336 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 449450757
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb7fc5d60355a8dfd752019852cdb15ae9d272ab89ceb9fe9acfccaaa3393cce
|
| 3 |
size 449450757
|