Training in progress, step 19500
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1001681601
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac4583c45c3ac210f50688208cd349a4f7e6e5e0636db16c8567230f0f3db5df
|
3 |
size 1001681601
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 551185105
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e3162b34cf1e02db14e3b771d56efbfa85e01d42aea300367f85d835f2a94ed
|
3 |
size 551185105
|
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 sha256:6dcb84109a1941ce14497096f64f0faed6fd08117a1ea71d919e470df2c7502a
|
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 sha256:1ca9f4aea09ae0c3876f882c71c93fc9a6c2815dfdcf619df60aa03bb8fdde26
|
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": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -234,11 +234,17 @@
|
|
234 |
"learning_rate": 2.8413636363636364e-05,
|
235 |
"loss": 0.0341,
|
236 |
"step": 19000
|
|
|
|
|
|
|
|
|
|
|
|
|
237 |
}
|
238 |
],
|
239 |
"max_steps": 44000,
|
240 |
"num_train_epochs": 1,
|
241 |
-
"total_flos":
|
242 |
"trial_name": null,
|
243 |
"trial_params": null
|
244 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.2645215551154399,
|
5 |
+
"global_step": 19500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
234 |
"learning_rate": 2.8413636363636364e-05,
|
235 |
"loss": 0.0341,
|
236 |
"step": 19000
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.26,
|
240 |
+
"learning_rate": 2.7845454545454548e-05,
|
241 |
+
"loss": 0.0337,
|
242 |
+
"step": 19500
|
243 |
}
|
244 |
],
|
245 |
"max_steps": 44000,
|
246 |
"num_train_epochs": 1,
|
247 |
+
"total_flos": 2.037624324961075e+16,
|
248 |
"trial_name": null,
|
249 |
"trial_params": null
|
250 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 551185105
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e3162b34cf1e02db14e3b771d56efbfa85e01d42aea300367f85d835f2a94ed
|
3 |
size 551185105
|
runs/Oct19_12-48-30_40567d3bb726/events.out.tfevents.1666183950.40567d3bb726.23.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95fea938e705cc7d91ab4a3f8f4ccc13b9792b7a4ec726ae42c2a48a998b0d3c
|
3 |
+
size 51790
|