haibotamiu
commited on
Commit
•
e2c69db
1
Parent(s):
262245a
Model save
Browse files- all_results.json +5 -5
- args.bin +1 -1
- train_results.json +5 -5
- trainer_state.json +9 -9
- training_args.bin +1 -1
all_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
-
"train_loss":
|
4 |
-
"train_runtime":
|
5 |
-
"train_samples":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
+
"train_loss": 4.621011098225911,
|
4 |
+
"train_runtime": 40.2046,
|
5 |
+
"train_samples": 3000,
|
6 |
+
"train_samples_per_second": 223.855,
|
7 |
+
"train_steps_per_second": 0.895
|
8 |
}
|
args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5652
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d40abfa4155cddcba82cbf65e16136b1f7f02f9059737d9f4180121e5bafbba5
|
3 |
size 5652
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
-
"train_loss":
|
4 |
-
"train_runtime":
|
5 |
-
"train_samples":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
+
"train_loss": 4.621011098225911,
|
4 |
+
"train_runtime": 40.2046,
|
5 |
+
"train_samples": 3000,
|
6 |
+
"train_samples_per_second": 223.855,
|
7 |
+
"train_steps_per_second": 0.895
|
8 |
}
|
trainer_state.json
CHANGED
@@ -3,26 +3,26 @@
|
|
3 |
"best_model_checkpoint": null,
|
4 |
"epoch": 3.0,
|
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,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 3.0,
|
13 |
-
"step":
|
14 |
-
"total_flos":
|
15 |
-
"train_loss":
|
16 |
-
"train_runtime":
|
17 |
-
"train_samples_per_second":
|
18 |
-
"train_steps_per_second":
|
19 |
}
|
20 |
],
|
21 |
"logging_steps": 500,
|
22 |
-
"max_steps":
|
23 |
"num_train_epochs": 3,
|
24 |
"save_steps": 500,
|
25 |
-
"total_flos":
|
26 |
"trial_name": null,
|
27 |
"trial_params": null
|
28 |
}
|
|
|
3 |
"best_model_checkpoint": null,
|
4 |
"epoch": 3.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 36,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 3.0,
|
13 |
+
"step": 36,
|
14 |
+
"total_flos": 881908425216000.0,
|
15 |
+
"train_loss": 4.621011098225911,
|
16 |
+
"train_runtime": 40.2046,
|
17 |
+
"train_samples_per_second": 223.855,
|
18 |
+
"train_steps_per_second": 0.895
|
19 |
}
|
20 |
],
|
21 |
"logging_steps": 500,
|
22 |
+
"max_steps": 36,
|
23 |
"num_train_epochs": 3,
|
24 |
"save_steps": 500,
|
25 |
+
"total_flos": 881908425216000.0,
|
26 |
"trial_name": null,
|
27 |
"trial_params": null
|
28 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c21a7a1d71fbc7505829b21472df420af8d762d2ec82196f32ef3365d115b7e
|
3 |
size 4664
|