Training in progress, step 7200
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +19 -3
- pytorch_model.bin +1 -1
- runs/Jun20_22-52-08_0a0be1aa5e93/events.out.tfevents.1687302809.0a0be1aa5e93.956.0 +2 -2
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2117841669
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4c0e7f95a4986c179237cc591ea7cfa702fad485214a9db8a39a082ce293eb4
|
3 |
size 2117841669
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2268278205
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68b9ab7b6afa22bcac956f98ba4a14682abc53843dbe887ff9a1e9e1440360a9
|
3 |
size 2268278205
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7947e5c962bdbf6d34661d6159dc8e96f804acec4e8c7431025af2a92505e915
|
3 |
size 14575
|
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 sha256:79dcc3b925349af6933565c76d95924262be4b310b1e8e5d1a64b4d5e8847c8a
|
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": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -254,11 +254,27 @@
|
|
254 |
"eval_samples_per_second": 202.307,
|
255 |
"eval_steps_per_second": 0.791,
|
256 |
"step": 6800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
257 |
}
|
258 |
],
|
259 |
"max_steps": 953000,
|
260 |
"num_train_epochs": 100,
|
261 |
-
"total_flos":
|
262 |
"trial_name": null,
|
263 |
"trial_params": null
|
264 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.7555089192025184,
|
5 |
+
"global_step": 7200,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
254 |
"eval_samples_per_second": 202.307,
|
255 |
"eval_steps_per_second": 0.791,
|
256 |
"step": 6800
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 0.73,
|
260 |
+
"learning_rate": 9.926715634837356e-06,
|
261 |
+
"loss": 0.6948,
|
262 |
+
"step": 7000
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 0.76,
|
266 |
+
"eval_accuracy": 0.8761897032566512,
|
267 |
+
"eval_f1": 0.8771094350236266,
|
268 |
+
"eval_loss": 0.6797441840171814,
|
269 |
+
"eval_runtime": 670.6385,
|
270 |
+
"eval_samples_per_second": 202.103,
|
271 |
+
"eval_steps_per_second": 0.79,
|
272 |
+
"step": 7200
|
273 |
}
|
274 |
],
|
275 |
"max_steps": 953000,
|
276 |
"num_train_epochs": 100,
|
277 |
+
"total_flos": 3.023326846706688e+17,
|
278 |
"trial_name": null,
|
279 |
"trial_params": null
|
280 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2268278205
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68b9ab7b6afa22bcac956f98ba4a14682abc53843dbe887ff9a1e9e1440360a9
|
3 |
size 2268278205
|
runs/Jun20_22-52-08_0a0be1aa5e93/events.out.tfevents.1687302809.0a0be1aa5e93.956.0
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 sha256:6a398bfa757f868f4f675d35a74fb4a4906748cac0ac5ceb5b19126403e36c17
|
3 |
+
size 6299
|