Upload folder using huggingface_hub
Browse files- pytorch_model.bin +1 -1
- trainer_state.json +10 -28
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3132793669
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:431cabe618b797a57de20bca78cfd1dbf4b58f9326c1e7dba5bc4121dbada186
|
3 |
size 3132793669
|
trainer_state.json
CHANGED
@@ -3,53 +3,35 @@
|
|
3 |
"best_model_checkpoint": null,
|
4 |
"epoch": 1.0,
|
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": 0.17,
|
13 |
-
"learning_rate": 1.6666666666666667e-05,
|
14 |
-
"loss": 2.1442,
|
15 |
-
"step": 500
|
16 |
-
},
|
17 |
{
|
18 |
"epoch": 0.33,
|
19 |
-
"learning_rate": 1.3333333333333333e-05,
|
20 |
-
"loss": 1.5391,
|
21 |
-
"step": 1000
|
22 |
-
},
|
23 |
-
{
|
24 |
-
"epoch": 0.5,
|
25 |
-
"learning_rate": 1e-05,
|
26 |
-
"loss": 1.3816,
|
27 |
-
"step": 1500
|
28 |
-
},
|
29 |
-
{
|
30 |
-
"epoch": 0.67,
|
31 |
"learning_rate": 6.666666666666667e-06,
|
32 |
-
"loss":
|
33 |
-
"step":
|
34 |
},
|
35 |
{
|
36 |
-
"epoch": 0.
|
37 |
"learning_rate": 3.3333333333333333e-06,
|
38 |
-
"loss": 1.
|
39 |
-
"step":
|
40 |
},
|
41 |
{
|
42 |
"epoch": 1.0,
|
43 |
"learning_rate": 0.0,
|
44 |
-
"loss": 1.
|
45 |
-
"step":
|
46 |
}
|
47 |
],
|
48 |
"logging_steps": 500,
|
49 |
-
"max_steps":
|
50 |
"num_train_epochs": 1,
|
51 |
"save_steps": 300,
|
52 |
-
"total_flos":
|
53 |
"trial_name": null,
|
54 |
"trial_params": null
|
55 |
}
|
|
|
3 |
"best_model_checkpoint": null,
|
4 |
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 1500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
{
|
12 |
"epoch": 0.33,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
"learning_rate": 6.666666666666667e-06,
|
14 |
+
"loss": 2.5374,
|
15 |
+
"step": 500
|
16 |
},
|
17 |
{
|
18 |
+
"epoch": 0.67,
|
19 |
"learning_rate": 3.3333333333333333e-06,
|
20 |
+
"loss": 1.8615,
|
21 |
+
"step": 1000
|
22 |
},
|
23 |
{
|
24 |
"epoch": 1.0,
|
25 |
"learning_rate": 0.0,
|
26 |
+
"loss": 1.7412,
|
27 |
+
"step": 1500
|
28 |
}
|
29 |
],
|
30 |
"logging_steps": 500,
|
31 |
+
"max_steps": 1500,
|
32 |
"num_train_epochs": 1,
|
33 |
"save_steps": 300,
|
34 |
+
"total_flos": 6637623662444544.0,
|
35 |
"trial_name": null,
|
36 |
"trial_params": null
|
37 |
}
|