Upload 8 files
Browse files- optimizer.pt +2 -2
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +39 -3
- training_args.bin +1 -1
optimizer.pt
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:b35b770d8d9a1d972e1ca4150bc7db5473aa0d4a013a2b6da74180a3868e4824
|
3 |
+
size 686682245
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 347081849
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18c71cd7270dbc3467f6585890ab427ab26e113ba536e770b0a3e3f985666441
|
3 |
size 347081849
|
rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14639
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ffe9257f4b5f6e7b196028f804debb7e03c6688f35197b7c41db7f1d92bb153
|
3 |
size 14639
|
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 sha256:314e7fcfa86bd8b2926804a8e8c2a2f170604f936fe430e459b9b1e7c4ade27f
|
3 |
size 627
|
trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -48,11 +48,47 @@
|
|
48 |
"learning_rate": 7.740112994350283e-06,
|
49 |
"loss": 0.9305,
|
50 |
"step": 40000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
51 |
}
|
52 |
],
|
53 |
"max_steps": 177000,
|
54 |
"num_train_epochs": 40,
|
55 |
-
"total_flos":
|
56 |
"trial_name": null,
|
57 |
"trial_params": null
|
58 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 22.598870056497177,
|
5 |
+
"global_step": 100000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
48 |
"learning_rate": 7.740112994350283e-06,
|
49 |
"loss": 0.9305,
|
50 |
"step": 40000
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 11.3,
|
54 |
+
"learning_rate": 7.175141242937854e-06,
|
55 |
+
"loss": 0.8309,
|
56 |
+
"step": 50000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 13.56,
|
60 |
+
"learning_rate": 6.610169491525424e-06,
|
61 |
+
"loss": 0.7535,
|
62 |
+
"step": 60000
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 15.82,
|
66 |
+
"learning_rate": 6.045197740112995e-06,
|
67 |
+
"loss": 0.69,
|
68 |
+
"step": 70000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 18.08,
|
72 |
+
"learning_rate": 5.480225988700565e-06,
|
73 |
+
"loss": 0.6365,
|
74 |
+
"step": 80000
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 20.34,
|
78 |
+
"learning_rate": 4.915254237288136e-06,
|
79 |
+
"loss": 0.5881,
|
80 |
+
"step": 90000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 22.6,
|
84 |
+
"learning_rate": 4.350282485875706e-06,
|
85 |
+
"loss": 0.5565,
|
86 |
+
"step": 100000
|
87 |
}
|
88 |
],
|
89 |
"max_steps": 177000,
|
90 |
"num_train_epochs": 40,
|
91 |
+
"total_flos": 1.2400055882758914e+20,
|
92 |
"trial_name": null,
|
93 |
"trial_params": null
|
94 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3643
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9bd6820ef696af4fce6112b9d1a81049c7a5afdfb484af20448230d8f0ea1024
|
3 |
size 3643
|