Upload 9 files
Browse files- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scaler.pt +1 -1
- scheduler.pt +1 -1
- trainer_state.json +54 -54
- 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 2490594117
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b6d4d7630b4d191f4e60f7290221bb7b841c866908affb66c3acb430d72b52b
|
3 |
size 2490594117
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262168365
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b0001be4bcbd360b155ff6b09197534e32acf1ad9d35f43b70b6045b9156c67
|
3 |
size 1262168365
|
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 sha256:7c1299279db2fbc4f7c5ae0b3d9988647a93090b85d0673f16c255280a4e8e1c
|
3 |
size 14639
|
scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c904deb17584498a1a86bb508e6bbd68684aa572ee60c23f77b77d0b8129fa4d
|
3 |
size 557
|
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 sha256:54ac577c49911bc9457ae001e29dcf4084465a3c73435eba449acf103e171f5e
|
3 |
size 627
|
trainer_state.json
CHANGED
@@ -1,112 +1,112 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"global_step": 2000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
-
"epoch": 1.
|
12 |
-
"learning_rate": 9.
|
13 |
-
"loss": 0.
|
14 |
"step": 150
|
15 |
},
|
16 |
{
|
17 |
-
"epoch": 2.
|
18 |
-
"learning_rate": 9.
|
19 |
-
"loss": 0.
|
20 |
"step": 300
|
21 |
},
|
22 |
{
|
23 |
-
"epoch": 3.
|
24 |
-
"learning_rate": 9.
|
25 |
-
"loss": 0.
|
26 |
"step": 450
|
27 |
},
|
28 |
{
|
29 |
-
"epoch":
|
30 |
-
"learning_rate": 9.
|
31 |
-
"loss": 0.
|
32 |
"step": 600
|
33 |
},
|
34 |
{
|
35 |
-
"epoch":
|
36 |
-
"learning_rate": 9.
|
37 |
-
"loss": 0.
|
38 |
"step": 750
|
39 |
},
|
40 |
{
|
41 |
-
"epoch":
|
42 |
-
"learning_rate": 9.
|
43 |
-
"loss": 0.
|
44 |
"step": 900
|
45 |
},
|
46 |
{
|
47 |
-
"epoch":
|
48 |
-
"eval_loss": 0.
|
49 |
-
"eval_runtime":
|
50 |
-
"eval_samples_per_second": 9.
|
51 |
-
"eval_steps_per_second": 1.
|
52 |
-
"eval_wer": 0.
|
53 |
"step": 1000
|
54 |
},
|
55 |
{
|
56 |
-
"epoch":
|
57 |
-
"learning_rate": 9.
|
58 |
-
"loss": 0.
|
59 |
"step": 1050
|
60 |
},
|
61 |
{
|
62 |
-
"epoch":
|
63 |
-
"learning_rate": 9.
|
64 |
-
"loss": 0.
|
65 |
"step": 1200
|
66 |
},
|
67 |
{
|
68 |
-
"epoch":
|
69 |
-
"learning_rate": 9.
|
70 |
-
"loss": 0.
|
71 |
"step": 1350
|
72 |
},
|
73 |
{
|
74 |
-
"epoch":
|
75 |
-
"learning_rate": 9.
|
76 |
-
"loss": 0.
|
77 |
"step": 1500
|
78 |
},
|
79 |
{
|
80 |
-
"epoch":
|
81 |
-
"learning_rate": 9.
|
82 |
-
"loss": 0.
|
83 |
"step": 1650
|
84 |
},
|
85 |
{
|
86 |
-
"epoch":
|
87 |
-
"learning_rate": 9.
|
88 |
-
"loss": 0.
|
89 |
"step": 1800
|
90 |
},
|
91 |
{
|
92 |
-
"epoch":
|
93 |
-
"learning_rate": 9.
|
94 |
-
"loss": 0.
|
95 |
"step": 1950
|
96 |
},
|
97 |
{
|
98 |
-
"epoch":
|
99 |
-
"eval_loss": 0.
|
100 |
-
"eval_runtime":
|
101 |
-
"eval_samples_per_second":
|
102 |
-
"eval_steps_per_second": 2.
|
103 |
-
"eval_wer": 0.
|
104 |
"step": 2000
|
105 |
}
|
106 |
],
|
107 |
-
"max_steps":
|
108 |
"num_train_epochs": 10000,
|
109 |
-
"total_flos":
|
110 |
"trial_name": null,
|
111 |
"trial_params": null
|
112 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 17.54207650273224,
|
5 |
"global_step": 2000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
+
"epoch": 1.31,
|
12 |
+
"learning_rate": 9.99957013773138e-06,
|
13 |
+
"loss": 0.029,
|
14 |
"step": 150
|
15 |
},
|
16 |
{
|
17 |
+
"epoch": 2.63,
|
18 |
+
"learning_rate": 9.998254232827442e-06,
|
19 |
+
"loss": 0.0249,
|
20 |
"step": 300
|
21 |
},
|
22 |
{
|
23 |
+
"epoch": 3.94,
|
24 |
+
"learning_rate": 9.996938327923503e-06,
|
25 |
+
"loss": 0.0239,
|
26 |
"step": 450
|
27 |
},
|
28 |
{
|
29 |
+
"epoch": 5.26,
|
30 |
+
"learning_rate": 9.995622423019565e-06,
|
31 |
+
"loss": 0.0223,
|
32 |
"step": 600
|
33 |
},
|
34 |
{
|
35 |
+
"epoch": 6.58,
|
36 |
+
"learning_rate": 9.994306518115625e-06,
|
37 |
+
"loss": 0.0219,
|
38 |
"step": 750
|
39 |
},
|
40 |
{
|
41 |
+
"epoch": 7.89,
|
42 |
+
"learning_rate": 9.992990613211686e-06,
|
43 |
+
"loss": 0.0215,
|
44 |
"step": 900
|
45 |
},
|
46 |
{
|
47 |
+
"epoch": 8.77,
|
48 |
+
"eval_loss": 0.21139128506183624,
|
49 |
+
"eval_runtime": 432.0782,
|
50 |
+
"eval_samples_per_second": 9.443,
|
51 |
+
"eval_steps_per_second": 1.18,
|
52 |
+
"eval_wer": 0.1666585139167441,
|
53 |
"step": 1000
|
54 |
},
|
55 |
{
|
56 |
+
"epoch": 9.21,
|
57 |
+
"learning_rate": 9.991674708307746e-06,
|
58 |
+
"loss": 0.0207,
|
59 |
"step": 1050
|
60 |
},
|
61 |
{
|
62 |
+
"epoch": 10.52,
|
63 |
+
"learning_rate": 9.990358803403808e-06,
|
64 |
+
"loss": 0.0209,
|
65 |
"step": 1200
|
66 |
},
|
67 |
{
|
68 |
+
"epoch": 11.84,
|
69 |
+
"learning_rate": 9.989042898499869e-06,
|
70 |
+
"loss": 0.0193,
|
71 |
"step": 1350
|
72 |
},
|
73 |
{
|
74 |
+
"epoch": 13.16,
|
75 |
+
"learning_rate": 9.98772699359593e-06,
|
76 |
+
"loss": 0.02,
|
77 |
"step": 1500
|
78 |
},
|
79 |
{
|
80 |
+
"epoch": 14.47,
|
81 |
+
"learning_rate": 9.986411088691991e-06,
|
82 |
+
"loss": 0.0191,
|
83 |
"step": 1650
|
84 |
},
|
85 |
{
|
86 |
+
"epoch": 15.79,
|
87 |
+
"learning_rate": 9.985095183788054e-06,
|
88 |
+
"loss": 0.0189,
|
89 |
"step": 1800
|
90 |
},
|
91 |
{
|
92 |
+
"epoch": 17.1,
|
93 |
+
"learning_rate": 9.983779278884114e-06,
|
94 |
+
"loss": 0.0185,
|
95 |
"step": 1950
|
96 |
},
|
97 |
{
|
98 |
+
"epoch": 17.54,
|
99 |
+
"eval_loss": 0.2301694005727768,
|
100 |
+
"eval_runtime": 231.0348,
|
101 |
+
"eval_samples_per_second": 17.66,
|
102 |
+
"eval_steps_per_second": 2.207,
|
103 |
+
"eval_wer": 0.16558235092696766,
|
104 |
"step": 2000
|
105 |
}
|
106 |
],
|
107 |
+
"max_steps": 1140000,
|
108 |
"num_train_epochs": 10000,
|
109 |
+
"total_flos": 5.692337203030269e+19,
|
110 |
"trial_name": null,
|
111 |
"trial_params": null
|
112 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3323
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38fe6647c74d4bfa083d20aefd98944f22f415066e1f9f366d882e66134054bf
|
3 |
size 3323
|