Femboyuwu2000
commited on
Commit
•
7e3aa77
1
Parent(s):
2abae2e
Training in progress, step 5300, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13982248
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20cdefd57805f803ae76e655f7dbbf814dfbdec3e1c1f7257e45fb2a6c06eab5
|
3 |
size 13982248
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 7062522
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2db2c533e49d05568b09bae363fc3e81a696c252f9dfc839b36f0463a25f0e02
|
3 |
size 7062522
|
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 sha256:49f030e6373edf769dccea9c3f55568d6feebbe751b5ccaf17c5dd48945e66be
|
3 |
size 14244
|
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:f889ec4d2e9c550aeb9719ae7a9587413e8a6ae17e4db0aeba0b5fdab4e7fc8f
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -1855,6 +1855,13 @@
|
|
1855 |
"learning_rate": 2.589453947885745e-05,
|
1856 |
"loss": 3.5018,
|
1857 |
"step": 5280
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1858 |
}
|
1859 |
],
|
1860 |
"logging_steps": 20,
|
@@ -1862,7 +1869,7 @@
|
|
1862 |
"num_input_tokens_seen": 0,
|
1863 |
"num_train_epochs": 2,
|
1864 |
"save_steps": 20,
|
1865 |
-
"total_flos": 1.
|
1866 |
"train_batch_size": 8,
|
1867 |
"trial_name": null,
|
1868 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.424,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 5300,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1855 |
"learning_rate": 2.589453947885745e-05,
|
1856 |
"loss": 3.5018,
|
1857 |
"step": 5280
|
1858 |
+
},
|
1859 |
+
{
|
1860 |
+
"epoch": 0.42,
|
1861 |
+
"grad_norm": 34.955291748046875,
|
1862 |
+
"learning_rate": 2.5861088803056324e-05,
|
1863 |
+
"loss": 3.4988,
|
1864 |
+
"step": 5300
|
1865 |
}
|
1866 |
],
|
1867 |
"logging_steps": 20,
|
|
|
1869 |
"num_input_tokens_seen": 0,
|
1870 |
"num_train_epochs": 2,
|
1871 |
"save_steps": 20,
|
1872 |
+
"total_flos": 1.2540420947214336e+16,
|
1873 |
"train_batch_size": 8,
|
1874 |
"trial_name": null,
|
1875 |
"trial_params": null
|