EhsanAghazadeh
commited on
Commit
•
a5d146f
1
Parent(s):
cef209f
Wrong model fixed.
Browse files- config.json +0 -1
- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- scheduler.pt +1 -1
- trainer_state.json +16 -26
- training_args.bin +1 -1
config.json
CHANGED
@@ -14,7 +14,6 @@
|
|
14 |
"end_n_top": 5,
|
15 |
"eos_token_id": 2,
|
16 |
"ff_activation": "gelu",
|
17 |
-
"finetuning_task": "cola",
|
18 |
"initializer_range": 0.02,
|
19 |
"layer_norm_eps": 1e-12,
|
20 |
"mem_len": null,
|
|
|
14 |
"end_n_top": 5,
|
15 |
"eos_token_id": 2,
|
16 |
"ff_activation": "gelu",
|
|
|
17 |
"initializer_range": 0.02,
|
18 |
"layer_norm_eps": 1e-12,
|
19 |
"mem_len": null,
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2890816569
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d87d914a3bf8774f8c235e0e553d2c311e659dc0494699951e2b28e85d2f9b5f
|
3 |
size 2890816569
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1445440509
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:636f445ef6adb04a2982e260043d65011430f99a7840eaed41e946a338124d73
|
3 |
size 1445440509
|
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:ed1991a8d407a4fa7df45b578feeca09e4eda9d2e4f390d00392f47fd0b35b7d
|
3 |
size 623
|
trainer_state.json
CHANGED
@@ -1,40 +1,30 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
-
"best_model_checkpoint":
|
4 |
-
"epoch": 1.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
-
"epoch": 0.
|
12 |
-
"learning_rate":
|
13 |
-
"loss": 0.
|
14 |
"step": 500
|
15 |
},
|
16 |
{
|
17 |
-
"epoch": 0
|
18 |
-
"
|
19 |
-
"
|
20 |
-
"
|
21 |
-
|
22 |
-
|
23 |
-
"epoch": 1.4,
|
24 |
-
"learning_rate": 3.246024321796071e-05,
|
25 |
-
"loss": 0.6296,
|
26 |
-
"step": 1500
|
27 |
-
},
|
28 |
-
{
|
29 |
-
"epoch": 1.87,
|
30 |
-
"learning_rate": 2.6613657623947615e-05,
|
31 |
-
"loss": 0.6285,
|
32 |
-
"step": 2000
|
33 |
}
|
34 |
],
|
35 |
-
"max_steps":
|
36 |
-
"num_train_epochs":
|
37 |
-
"total_flos":
|
38 |
"trial_name": null,
|
39 |
"trial_params": null
|
40 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.6213340784507475,
|
3 |
+
"best_model_checkpoint": "test-glue/checkpoint-535",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"global_step": 535,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
+
"epoch": 0.93,
|
12 |
+
"learning_rate": 1.308411214953271e-06,
|
13 |
+
"loss": 0.227,
|
14 |
"step": 500
|
15 |
},
|
16 |
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_loss": 0.7487037777900696,
|
19 |
+
"eval_matthews_correlation": 0.6213340784507475,
|
20 |
+
"eval_runtime": 5.731,
|
21 |
+
"eval_samples_per_second": 181.993,
|
22 |
+
"step": 535
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
}
|
24 |
],
|
25 |
+
"max_steps": 535,
|
26 |
+
"num_train_epochs": 1,
|
27 |
+
"total_flos": 389100934118700.0,
|
28 |
"trial_name": null,
|
29 |
"trial_params": null
|
30 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2351
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:096f1b59c8b732a00227768a9fc6519f4f6349950e9bf5c8d5ca7dd120d59d82
|
3 |
size 2351
|