mprzibilla
commited on
Commit
·
c5157ab
1
Parent(s):
187b52a
Training in progress, step 966
Browse files- config.json +1 -1
- last-checkpoint/config.json +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +17 -161
- last-checkpoint/training_args.bin +1 -1
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_dropout": 0.0,
|
4 |
"adapter_kernel_size": 3,
|
5 |
"adapter_stride": 2,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-base",
|
3 |
"activation_dropout": 0.0,
|
4 |
"adapter_kernel_size": 3,
|
5 |
"adapter_stride": 2,
|
last-checkpoint/config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_dropout": 0.0,
|
4 |
"adapter_kernel_size": 3,
|
5 |
"adapter_stride": 2,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-base",
|
3 |
"activation_dropout": 0.0,
|
4 |
"adapter_kernel_size": 3,
|
5 |
"adapter_stride": 2,
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 721655813
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7567e004a17417ef275a07f548a3b4b0136d86a6f6fbc460fe7a00e8c92e176
|
3 |
size 721655813
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377643361
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d66fa657a50991872bc901a1c0198c9fb6e1bcb0d43ff142305c507ed6b19f9
|
3 |
size 377643361
|
last-checkpoint/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 sha256:0241d9ff59634311ca32c5d58432d6e8c7f4246dfff2c1d17474efe0b6db05b2
|
3 |
size 14639
|
last-checkpoint/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 sha256:9a061dfc849fc3685649d3640ca3a6cc0e1f90ea854e09609154ff160b30cd36
|
3 |
size 557
|
last-checkpoint/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 sha256:1e3243e5fb6ee708dceb6e1201f700c07a2c1478b84476c82eecb6733b837f1f
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,176 +1,32 @@
|
|
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,
|
9 |
"log_history": [
|
10 |
{
|
11 |
-
"epoch":
|
12 |
-
"learning_rate": 9.
|
13 |
-
"loss":
|
14 |
-
"step":
|
15 |
},
|
16 |
{
|
17 |
-
"epoch":
|
18 |
-
"eval_cer": 0
|
19 |
-
"eval_loss":
|
20 |
-
"eval_runtime": 7.
|
21 |
-
"eval_samples_per_second":
|
22 |
-
"eval_steps_per_second": 3.
|
23 |
-
"eval_wer": 0
|
24 |
-
"step":
|
25 |
-
},
|
26 |
-
{
|
27 |
-
"epoch": 30.0,
|
28 |
-
"learning_rate": 8.422796120736624e-05,
|
29 |
-
"loss": 0.1585,
|
30 |
-
"step": 9660
|
31 |
-
},
|
32 |
-
{
|
33 |
-
"epoch": 30.0,
|
34 |
-
"eval_cer": 0.5670995670995671,
|
35 |
-
"eval_loss": 5.317575931549072,
|
36 |
-
"eval_runtime": 7.589,
|
37 |
-
"eval_samples_per_second": 27.672,
|
38 |
-
"eval_steps_per_second": 3.558,
|
39 |
-
"eval_wer": 0.9666666666666667,
|
40 |
-
"step": 9660
|
41 |
-
},
|
42 |
-
{
|
43 |
-
"epoch": 45.0,
|
44 |
-
"learning_rate": 7.370600414078676e-05,
|
45 |
-
"loss": 0.0948,
|
46 |
-
"step": 14490
|
47 |
-
},
|
48 |
-
{
|
49 |
-
"epoch": 45.0,
|
50 |
-
"eval_cer": 0.5437229437229437,
|
51 |
-
"eval_loss": 6.589183330535889,
|
52 |
-
"eval_runtime": 8.194,
|
53 |
-
"eval_samples_per_second": 25.629,
|
54 |
-
"eval_steps_per_second": 3.295,
|
55 |
-
"eval_wer": 0.9619047619047619,
|
56 |
-
"step": 14490
|
57 |
-
},
|
58 |
-
{
|
59 |
-
"epoch": 60.0,
|
60 |
-
"learning_rate": 6.318404707420727e-05,
|
61 |
-
"loss": 0.0768,
|
62 |
-
"step": 19320
|
63 |
-
},
|
64 |
-
{
|
65 |
-
"epoch": 60.0,
|
66 |
-
"eval_cer": 0.5627705627705628,
|
67 |
-
"eval_loss": 6.671819686889648,
|
68 |
-
"eval_runtime": 7.9228,
|
69 |
-
"eval_samples_per_second": 26.506,
|
70 |
-
"eval_steps_per_second": 3.408,
|
71 |
-
"eval_wer": 0.9571428571428572,
|
72 |
-
"step": 19320
|
73 |
-
},
|
74 |
-
{
|
75 |
-
"epoch": 75.0,
|
76 |
-
"learning_rate": 5.2659910646180674e-05,
|
77 |
-
"loss": 0.0525,
|
78 |
-
"step": 24150
|
79 |
-
},
|
80 |
-
{
|
81 |
-
"epoch": 75.0,
|
82 |
-
"eval_cer": 0.567965367965368,
|
83 |
-
"eval_loss": 7.230055809020996,
|
84 |
-
"eval_runtime": 7.8858,
|
85 |
-
"eval_samples_per_second": 26.63,
|
86 |
-
"eval_steps_per_second": 3.424,
|
87 |
-
"eval_wer": 0.9428571428571428,
|
88 |
-
"step": 24150
|
89 |
-
},
|
90 |
-
{
|
91 |
-
"epoch": 90.0,
|
92 |
-
"learning_rate": 4.214013294104828e-05,
|
93 |
-
"loss": 0.0397,
|
94 |
-
"step": 28980
|
95 |
-
},
|
96 |
-
{
|
97 |
-
"epoch": 90.0,
|
98 |
-
"eval_cer": 0.5688311688311688,
|
99 |
-
"eval_loss": 7.58466100692749,
|
100 |
-
"eval_runtime": 7.879,
|
101 |
-
"eval_samples_per_second": 26.653,
|
102 |
-
"eval_steps_per_second": 3.427,
|
103 |
-
"eval_wer": 0.9761904761904762,
|
104 |
-
"step": 28980
|
105 |
-
},
|
106 |
-
{
|
107 |
-
"epoch": 105.0,
|
108 |
-
"learning_rate": 3.162035523591588e-05,
|
109 |
-
"loss": 0.0369,
|
110 |
-
"step": 33810
|
111 |
-
},
|
112 |
-
{
|
113 |
-
"epoch": 105.0,
|
114 |
-
"eval_cer": 0.6233766233766234,
|
115 |
-
"eval_loss": 9.481943130493164,
|
116 |
-
"eval_runtime": 8.2617,
|
117 |
-
"eval_samples_per_second": 25.418,
|
118 |
-
"eval_steps_per_second": 3.268,
|
119 |
-
"eval_wer": 0.9666666666666667,
|
120 |
-
"step": 33810
|
121 |
-
},
|
122 |
-
{
|
123 |
-
"epoch": 120.0,
|
124 |
-
"learning_rate": 2.1094039446442195e-05,
|
125 |
-
"loss": 0.0181,
|
126 |
-
"step": 38640
|
127 |
-
},
|
128 |
-
{
|
129 |
-
"epoch": 120.0,
|
130 |
-
"eval_cer": 0.6095238095238096,
|
131 |
-
"eval_loss": 10.403050422668457,
|
132 |
-
"eval_runtime": 8.1478,
|
133 |
-
"eval_samples_per_second": 25.774,
|
134 |
-
"eval_steps_per_second": 3.314,
|
135 |
-
"eval_wer": 0.9380952380952381,
|
136 |
-
"step": 38640
|
137 |
-
},
|
138 |
-
{
|
139 |
-
"epoch": 135.0,
|
140 |
-
"learning_rate": 1.05720823798627e-05,
|
141 |
-
"loss": 0.012,
|
142 |
-
"step": 43470
|
143 |
-
},
|
144 |
-
{
|
145 |
-
"epoch": 135.0,
|
146 |
-
"eval_cer": 0.5497835497835498,
|
147 |
-
"eval_loss": 9.08182144165039,
|
148 |
-
"eval_runtime": 8.12,
|
149 |
-
"eval_samples_per_second": 25.862,
|
150 |
-
"eval_steps_per_second": 3.325,
|
151 |
-
"eval_wer": 0.9285714285714286,
|
152 |
-
"step": 43470
|
153 |
-
},
|
154 |
-
{
|
155 |
-
"epoch": 150.0,
|
156 |
-
"learning_rate": 4.7945951836112025e-08,
|
157 |
-
"loss": 0.0051,
|
158 |
-
"step": 48300
|
159 |
-
},
|
160 |
-
{
|
161 |
-
"epoch": 150.0,
|
162 |
-
"eval_cer": 0.5575757575757576,
|
163 |
-
"eval_loss": 8.305272102355957,
|
164 |
-
"eval_runtime": 7.8878,
|
165 |
-
"eval_samples_per_second": 26.623,
|
166 |
-
"eval_steps_per_second": 3.423,
|
167 |
-
"eval_wer": 0.9476190476190476,
|
168 |
-
"step": 48300
|
169 |
}
|
170 |
],
|
171 |
-
"max_steps":
|
172 |
-
"num_train_epochs":
|
173 |
-
"total_flos":
|
174 |
"trial_name": null,
|
175 |
"trial_params": null
|
176 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"global_step": 966,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
+
"epoch": 3.0,
|
12 |
+
"learning_rate": 9.480222294867605e-05,
|
13 |
+
"loss": 15.1064,
|
14 |
+
"step": 966
|
15 |
},
|
16 |
{
|
17 |
+
"epoch": 3.0,
|
18 |
+
"eval_cer": 1.0,
|
19 |
+
"eval_loss": 3.2236688137054443,
|
20 |
+
"eval_runtime": 7.4535,
|
21 |
+
"eval_samples_per_second": 28.175,
|
22 |
+
"eval_steps_per_second": 3.622,
|
23 |
+
"eval_wer": 1.0,
|
24 |
+
"step": 966
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
}
|
26 |
],
|
27 |
+
"max_steps": 9660,
|
28 |
+
"num_train_epochs": 30,
|
29 |
+
"total_flos": 7.16555055956832e+17,
|
30 |
"trial_name": null,
|
31 |
"trial_params": null
|
32 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3387
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7f61ae3d00288f98fe3d9d9cd08b9a2aed15609675f8311c05cf368df4913e8
|
3 |
size 3387
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377643361
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d66fa657a50991872bc901a1c0198c9fb6e1bcb0d43ff142305c507ed6b19f9
|
3 |
size 377643361
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3387
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7f61ae3d00288f98fe3d9d9cd08b9a2aed15609675f8311c05cf368df4913e8
|
3 |
size 3387
|