Training in progress, step 16800, checkpoint
Browse files
last-checkpoint/README.md
CHANGED
@@ -1359,6 +1359,10 @@ You can finetune this model on your own dataset.
|
|
1359 |
| 0.2916 | 16500 | 0.3065 |
|
1360 |
| 0.2924 | 16550 | 0.4003 |
|
1361 |
| 0.2933 | 16600 | 0.5295 |
|
|
|
|
|
|
|
|
|
1362 |
|
1363 |
</details>
|
1364 |
|
|
|
1359 |
| 0.2916 | 16500 | 0.3065 |
|
1360 |
| 0.2924 | 16550 | 0.4003 |
|
1361 |
| 0.2933 | 16600 | 0.5295 |
|
1362 |
+
| 0.2942 | 16650 | 0.3582 |
|
1363 |
+
| 0.2951 | 16700 | 0.3299 |
|
1364 |
+
| 0.2960 | 16750 | 0.3493 |
|
1365 |
+
| 0.2969 | 16800 | 0.2752 |
|
1366 |
|
1367 |
</details>
|
1368 |
|
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 90864192
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6e1b391f33422456061353bd355bf2435eeb4195f81389af6dbc0e8fc66d25b
|
3 |
size 90864192
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 180609210
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9de93effda738b0b5fd57692fb67723566f34b54c872aac7a9626fa31feaf70
|
3 |
size 180609210
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd3be6ab84a32000b2bae6b4e86032ac0554f86e01256b1d6d073b96f56c8ada
|
3 |
size 14244
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 988
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:caeb14c75258126c0a61054123d2b052c3f92789f4356192be834a257bdfec4c
|
3 |
size 988
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ba1c971d0e3bd3fc6e84348fd8cbae570fbf4f01d4c3efacd1f9719190d9e71
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -2,9 +2,9 @@
|
|
2 |
"best_global_step": null,
|
3 |
"best_metric": null,
|
4 |
"best_model_checkpoint": null,
|
5 |
-
"epoch": 0.
|
6 |
"eval_steps": 500,
|
7 |
-
"global_step":
|
8 |
"is_hyper_param_search": false,
|
9 |
"is_local_process_zero": true,
|
10 |
"is_world_process_zero": true,
|
@@ -2332,6 +2332,34 @@
|
|
2332 |
"learning_rate": 3.926390606899531e-05,
|
2333 |
"loss": 0.5295,
|
2334 |
"step": 16600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2335 |
}
|
2336 |
],
|
2337 |
"logging_steps": 50,
|
|
|
2 |
"best_global_step": null,
|
3 |
"best_metric": null,
|
4 |
"best_model_checkpoint": null,
|
5 |
+
"epoch": 0.2968669929847502,
|
6 |
"eval_steps": 500,
|
7 |
+
"global_step": 16800,
|
8 |
"is_hyper_param_search": false,
|
9 |
"is_local_process_zero": true,
|
10 |
"is_world_process_zero": true,
|
|
|
2332 |
"learning_rate": 3.926390606899531e-05,
|
2333 |
"loss": 0.5295,
|
2334 |
"step": 16600
|
2335 |
+
},
|
2336 |
+
{
|
2337 |
+
"epoch": 0.2942163948331007,
|
2338 |
+
"grad_norm": 1.9425716400146484,
|
2339 |
+
"learning_rate": 3.9214820050656776e-05,
|
2340 |
+
"loss": 0.3582,
|
2341 |
+
"step": 16650
|
2342 |
+
},
|
2343 |
+
{
|
2344 |
+
"epoch": 0.29509992755031716,
|
2345 |
+
"grad_norm": 3.003871440887451,
|
2346 |
+
"learning_rate": 3.9165734032318234e-05,
|
2347 |
+
"loss": 0.3299,
|
2348 |
+
"step": 16700
|
2349 |
+
},
|
2350 |
+
{
|
2351 |
+
"epoch": 0.2959834602675337,
|
2352 |
+
"grad_norm": 3.689194679260254,
|
2353 |
+
"learning_rate": 3.91166480139797e-05,
|
2354 |
+
"loss": 0.3493,
|
2355 |
+
"step": 16750
|
2356 |
+
},
|
2357 |
+
{
|
2358 |
+
"epoch": 0.2968669929847502,
|
2359 |
+
"grad_norm": 1.9439842700958252,
|
2360 |
+
"learning_rate": 3.906756199564116e-05,
|
2361 |
+
"loss": 0.2752,
|
2362 |
+
"step": 16800
|
2363 |
}
|
2364 |
],
|
2365 |
"logging_steps": 50,
|