Training in progress, step 195000
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/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +62 -2
- 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 402588883
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c7a1217516f1c133d24bb3d4b01300aff582a81619d3d1116de482975832802
|
3 |
size 402588883
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201355195
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f20459a36d3d3a9cac8bb27dfd1c8133b9a775102f7d6624b00ef85ce8d11be2
|
3 |
size 201355195
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f51296829618cd3aac8b758ff1127e9862fd5e8cd0fd7abc8577a9160e237c7
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84dfd6945eb41b1cb519fcc4c855e9281eff7b5093625da74b060011b1ad4afd
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1e6eb189ca420ecc378796eb05160bf008f874b12982cf52f2ce307ad2df17d
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:adc5617711a0cbdd1d1b3afd0601fc8e48a4056ca4765e9ca0a7b78f79204ba7
|
3 |
size 14503
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a8b406f5f7aba898aebadaf3677cc3576d4f65c3fcd2a972307877861c6b081
|
3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4ecbc1c4a1b52f43722a40d7cfcf0cbe0e1616aac22cceabe9c1c72c5a195ea
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 3.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -2286,6 +2286,66 @@
|
|
2286 |
"learning_rate": 0.00010580020382426679,
|
2287 |
"loss": 0.3376,
|
2288 |
"step": 190000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2289 |
}
|
2290 |
],
|
2291 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.3191462200321697,
|
5 |
+
"global_step": 195000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
2286 |
"learning_rate": 0.00010580020382426679,
|
2287 |
"loss": 0.3376,
|
2288 |
"step": 190000
|
2289 |
+
},
|
2290 |
+
{
|
2291 |
+
"epoch": 3.24,
|
2292 |
+
"learning_rate": 0.00010559564750360856,
|
2293 |
+
"loss": 0.3375,
|
2294 |
+
"step": 190500
|
2295 |
+
},
|
2296 |
+
{
|
2297 |
+
"epoch": 3.25,
|
2298 |
+
"learning_rate": 0.00010539083856424286,
|
2299 |
+
"loss": 0.3372,
|
2300 |
+
"step": 191000
|
2301 |
+
},
|
2302 |
+
{
|
2303 |
+
"epoch": 3.26,
|
2304 |
+
"learning_rate": 0.00010518618939537595,
|
2305 |
+
"loss": 0.337,
|
2306 |
+
"step": 191500
|
2307 |
+
},
|
2308 |
+
{
|
2309 |
+
"epoch": 3.27,
|
2310 |
+
"learning_rate": 0.00010498088178033872,
|
2311 |
+
"loss": 0.3367,
|
2312 |
+
"step": 192000
|
2313 |
+
},
|
2314 |
+
{
|
2315 |
+
"epoch": 3.28,
|
2316 |
+
"learning_rate": 0.0001047753276140835,
|
2317 |
+
"loss": 0.3368,
|
2318 |
+
"step": 192500
|
2319 |
+
},
|
2320 |
+
{
|
2321 |
+
"epoch": 3.29,
|
2322 |
+
"learning_rate": 0.00010456952892534694,
|
2323 |
+
"loss": 0.3367,
|
2324 |
+
"step": 193000
|
2325 |
+
},
|
2326 |
+
{
|
2327 |
+
"epoch": 3.29,
|
2328 |
+
"learning_rate": 0.00010436348774527898,
|
2329 |
+
"loss": 0.3364,
|
2330 |
+
"step": 193500
|
2331 |
+
},
|
2332 |
+
{
|
2333 |
+
"epoch": 3.3,
|
2334 |
+
"learning_rate": 0.00010415720610742296,
|
2335 |
+
"loss": 0.3366,
|
2336 |
+
"step": 194000
|
2337 |
+
},
|
2338 |
+
{
|
2339 |
+
"epoch": 3.31,
|
2340 |
+
"learning_rate": 0.00010395068604769528,
|
2341 |
+
"loss": 0.3365,
|
2342 |
+
"step": 194500
|
2343 |
+
},
|
2344 |
+
{
|
2345 |
+
"epoch": 3.32,
|
2346 |
+
"learning_rate": 0.00010374392960436561,
|
2347 |
+
"loss": 0.3369,
|
2348 |
+
"step": 195000
|
2349 |
}
|
2350 |
],
|
2351 |
"max_steps": 500000,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201355195
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f20459a36d3d3a9cac8bb27dfd1c8133b9a775102f7d6624b00ef85ce8d11be2
|
3 |
size 201355195
|