End of training
Browse files- last-checkpoint/config.json +0 -42
- last-checkpoint/optimizer.pt +0 -3
- last-checkpoint/preprocessor_config.json +0 -0
- last-checkpoint/pytorch_model.bin +0 -3
- last-checkpoint/rng_state.pth +0 -3
- last-checkpoint/scaler.pt +0 -3
- last-checkpoint/scheduler.pt +0 -3
- last-checkpoint/trainer_state.json +0 -265
- last-checkpoint/training_args.bin +0 -3
- pytorch_model.bin +1 -1
- runs/Dec07_18-48-23_dd70ba896431/events.out.tfevents.1670439815.dd70ba896431.112.0 +2 -2
last-checkpoint/config.json
DELETED
@@ -1,42 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "openai/whisper-small",
|
3 |
-
"activation_dropout": 0.0,
|
4 |
-
"activation_function": "gelu",
|
5 |
-
"architectures": [
|
6 |
-
"WhisperForConditionalGeneration"
|
7 |
-
],
|
8 |
-
"attention_dropout": 0.0,
|
9 |
-
"begin_suppress_tokens": [
|
10 |
-
220,
|
11 |
-
50257
|
12 |
-
],
|
13 |
-
"bos_token_id": 50257,
|
14 |
-
"d_model": 768,
|
15 |
-
"decoder_attention_heads": 12,
|
16 |
-
"decoder_ffn_dim": 3072,
|
17 |
-
"decoder_layerdrop": 0.0,
|
18 |
-
"decoder_layers": 12,
|
19 |
-
"decoder_start_token_id": 50258,
|
20 |
-
"dropout": 0.0,
|
21 |
-
"encoder_attention_heads": 12,
|
22 |
-
"encoder_ffn_dim": 3072,
|
23 |
-
"encoder_layerdrop": 0.0,
|
24 |
-
"encoder_layers": 12,
|
25 |
-
"eos_token_id": 50257,
|
26 |
-
"forced_decoder_ids": null,
|
27 |
-
"init_std": 0.02,
|
28 |
-
"is_encoder_decoder": true,
|
29 |
-
"max_length": 448,
|
30 |
-
"max_source_positions": 1500,
|
31 |
-
"max_target_positions": 448,
|
32 |
-
"model_type": "whisper",
|
33 |
-
"num_hidden_layers": 12,
|
34 |
-
"num_mel_bins": 80,
|
35 |
-
"pad_token_id": 50257,
|
36 |
-
"scale_embedding": false,
|
37 |
-
"suppress_tokens": [],
|
38 |
-
"torch_dtype": "float32",
|
39 |
-
"transformers_version": "4.26.0.dev0",
|
40 |
-
"use_cache": true,
|
41 |
-
"vocab_size": 51865
|
42 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/optimizer.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:42974957d05a50485422eecf7c1ead0ccc9611956290f23b082e7c58745b99fa
|
3 |
-
size 1934161093
|
|
|
|
|
|
|
|
last-checkpoint/preprocessor_config.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
last-checkpoint/pytorch_model.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:61df0efb760ab9346e318ac670db76c293f4bdbfc2ac41b2eb52b94540724f64
|
3 |
-
size 967102601
|
|
|
|
|
|
|
|
last-checkpoint/rng_state.pth
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:aff791f9f544d8533ff7167e47df86f312e9b0c4082f324fd67803cbe75bd7b2
|
3 |
-
size 14511
|
|
|
|
|
|
|
|
last-checkpoint/scaler.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:07ebb7f7f0feb7f78417f21615799245f76629f5c6d85f2f374397ba4f5ec1c8
|
3 |
-
size 557
|
|
|
|
|
|
|
|
last-checkpoint/scheduler.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:ebabd12e19f22f239482f83a56ceca9603374d549198524cc0a20fa45950474d
|
3 |
-
size 627
|
|
|
|
|
|
|
|
last-checkpoint/trainer_state.json
DELETED
@@ -1,265 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"best_metric": 21.574385584763643,
|
3 |
-
"best_model_checkpoint": "./whisper-small-sv-SE/checkpoint-1000",
|
4 |
-
"epoch": 2.1881838074398248,
|
5 |
-
"global_step": 1000,
|
6 |
-
"is_hyper_param_search": false,
|
7 |
-
"is_local_process_zero": true,
|
8 |
-
"is_world_process_zero": true,
|
9 |
-
"log_history": [
|
10 |
-
{
|
11 |
-
"epoch": 0.05,
|
12 |
-
"learning_rate": 4.2000000000000006e-07,
|
13 |
-
"loss": 4.131,
|
14 |
-
"step": 25
|
15 |
-
},
|
16 |
-
{
|
17 |
-
"epoch": 0.11,
|
18 |
-
"learning_rate": 9.200000000000001e-07,
|
19 |
-
"loss": 3.2463,
|
20 |
-
"step": 50
|
21 |
-
},
|
22 |
-
{
|
23 |
-
"epoch": 0.16,
|
24 |
-
"learning_rate": 1.42e-06,
|
25 |
-
"loss": 2.4008,
|
26 |
-
"step": 75
|
27 |
-
},
|
28 |
-
{
|
29 |
-
"epoch": 0.22,
|
30 |
-
"learning_rate": 1.9200000000000003e-06,
|
31 |
-
"loss": 1.508,
|
32 |
-
"step": 100
|
33 |
-
},
|
34 |
-
{
|
35 |
-
"epoch": 0.27,
|
36 |
-
"learning_rate": 2.42e-06,
|
37 |
-
"loss": 1.1038,
|
38 |
-
"step": 125
|
39 |
-
},
|
40 |
-
{
|
41 |
-
"epoch": 0.33,
|
42 |
-
"learning_rate": 2.9e-06,
|
43 |
-
"loss": 0.9943,
|
44 |
-
"step": 150
|
45 |
-
},
|
46 |
-
{
|
47 |
-
"epoch": 0.38,
|
48 |
-
"learning_rate": 3.4000000000000005e-06,
|
49 |
-
"loss": 0.9689,
|
50 |
-
"step": 175
|
51 |
-
},
|
52 |
-
{
|
53 |
-
"epoch": 0.44,
|
54 |
-
"learning_rate": 3.900000000000001e-06,
|
55 |
-
"loss": 0.8328,
|
56 |
-
"step": 200
|
57 |
-
},
|
58 |
-
{
|
59 |
-
"epoch": 0.49,
|
60 |
-
"learning_rate": 4.4e-06,
|
61 |
-
"loss": 0.7131,
|
62 |
-
"step": 225
|
63 |
-
},
|
64 |
-
{
|
65 |
-
"epoch": 0.55,
|
66 |
-
"learning_rate": 4.9000000000000005e-06,
|
67 |
-
"loss": 0.6087,
|
68 |
-
"step": 250
|
69 |
-
},
|
70 |
-
{
|
71 |
-
"epoch": 0.6,
|
72 |
-
"learning_rate": 5.400000000000001e-06,
|
73 |
-
"loss": 0.4887,
|
74 |
-
"step": 275
|
75 |
-
},
|
76 |
-
{
|
77 |
-
"epoch": 0.66,
|
78 |
-
"learning_rate": 5.9e-06,
|
79 |
-
"loss": 0.3064,
|
80 |
-
"step": 300
|
81 |
-
},
|
82 |
-
{
|
83 |
-
"epoch": 0.71,
|
84 |
-
"learning_rate": 6.4000000000000006e-06,
|
85 |
-
"loss": 0.3017,
|
86 |
-
"step": 325
|
87 |
-
},
|
88 |
-
{
|
89 |
-
"epoch": 0.77,
|
90 |
-
"learning_rate": 6.9e-06,
|
91 |
-
"loss": 0.3293,
|
92 |
-
"step": 350
|
93 |
-
},
|
94 |
-
{
|
95 |
-
"epoch": 0.82,
|
96 |
-
"learning_rate": 7.4e-06,
|
97 |
-
"loss": 0.3279,
|
98 |
-
"step": 375
|
99 |
-
},
|
100 |
-
{
|
101 |
-
"epoch": 0.88,
|
102 |
-
"learning_rate": 7.9e-06,
|
103 |
-
"loss": 0.2945,
|
104 |
-
"step": 400
|
105 |
-
},
|
106 |
-
{
|
107 |
-
"epoch": 0.93,
|
108 |
-
"learning_rate": 8.400000000000001e-06,
|
109 |
-
"loss": 0.315,
|
110 |
-
"step": 425
|
111 |
-
},
|
112 |
-
{
|
113 |
-
"epoch": 0.98,
|
114 |
-
"learning_rate": 8.900000000000001e-06,
|
115 |
-
"loss": 0.2944,
|
116 |
-
"step": 450
|
117 |
-
},
|
118 |
-
{
|
119 |
-
"epoch": 1.04,
|
120 |
-
"learning_rate": 9.4e-06,
|
121 |
-
"loss": 0.2057,
|
122 |
-
"step": 475
|
123 |
-
},
|
124 |
-
{
|
125 |
-
"epoch": 1.09,
|
126 |
-
"learning_rate": 9.9e-06,
|
127 |
-
"loss": 0.1603,
|
128 |
-
"step": 500
|
129 |
-
},
|
130 |
-
{
|
131 |
-
"epoch": 1.15,
|
132 |
-
"learning_rate": 9.942857142857145e-06,
|
133 |
-
"loss": 0.1954,
|
134 |
-
"step": 525
|
135 |
-
},
|
136 |
-
{
|
137 |
-
"epoch": 1.2,
|
138 |
-
"learning_rate": 9.871428571428572e-06,
|
139 |
-
"loss": 0.1754,
|
140 |
-
"step": 550
|
141 |
-
},
|
142 |
-
{
|
143 |
-
"epoch": 1.26,
|
144 |
-
"learning_rate": 9.800000000000001e-06,
|
145 |
-
"loss": 0.1865,
|
146 |
-
"step": 575
|
147 |
-
},
|
148 |
-
{
|
149 |
-
"epoch": 1.31,
|
150 |
-
"learning_rate": 9.72857142857143e-06,
|
151 |
-
"loss": 0.1893,
|
152 |
-
"step": 600
|
153 |
-
},
|
154 |
-
{
|
155 |
-
"epoch": 1.37,
|
156 |
-
"learning_rate": 9.657142857142859e-06,
|
157 |
-
"loss": 0.1837,
|
158 |
-
"step": 625
|
159 |
-
},
|
160 |
-
{
|
161 |
-
"epoch": 1.42,
|
162 |
-
"learning_rate": 9.585714285714286e-06,
|
163 |
-
"loss": 0.1703,
|
164 |
-
"step": 650
|
165 |
-
},
|
166 |
-
{
|
167 |
-
"epoch": 1.48,
|
168 |
-
"learning_rate": 9.514285714285715e-06,
|
169 |
-
"loss": 0.1863,
|
170 |
-
"step": 675
|
171 |
-
},
|
172 |
-
{
|
173 |
-
"epoch": 1.53,
|
174 |
-
"learning_rate": 9.442857142857144e-06,
|
175 |
-
"loss": 0.1767,
|
176 |
-
"step": 700
|
177 |
-
},
|
178 |
-
{
|
179 |
-
"epoch": 1.59,
|
180 |
-
"learning_rate": 9.371428571428572e-06,
|
181 |
-
"loss": 0.2068,
|
182 |
-
"step": 725
|
183 |
-
},
|
184 |
-
{
|
185 |
-
"epoch": 1.64,
|
186 |
-
"learning_rate": 9.3e-06,
|
187 |
-
"loss": 0.1796,
|
188 |
-
"step": 750
|
189 |
-
},
|
190 |
-
{
|
191 |
-
"epoch": 1.7,
|
192 |
-
"learning_rate": 9.22857142857143e-06,
|
193 |
-
"loss": 0.1784,
|
194 |
-
"step": 775
|
195 |
-
},
|
196 |
-
{
|
197 |
-
"epoch": 1.75,
|
198 |
-
"learning_rate": 9.157142857142857e-06,
|
199 |
-
"loss": 0.1706,
|
200 |
-
"step": 800
|
201 |
-
},
|
202 |
-
{
|
203 |
-
"epoch": 1.81,
|
204 |
-
"learning_rate": 9.085714285714286e-06,
|
205 |
-
"loss": 0.1766,
|
206 |
-
"step": 825
|
207 |
-
},
|
208 |
-
{
|
209 |
-
"epoch": 1.86,
|
210 |
-
"learning_rate": 9.014285714285715e-06,
|
211 |
-
"loss": 0.1736,
|
212 |
-
"step": 850
|
213 |
-
},
|
214 |
-
{
|
215 |
-
"epoch": 1.91,
|
216 |
-
"learning_rate": 8.942857142857142e-06,
|
217 |
-
"loss": 0.1703,
|
218 |
-
"step": 875
|
219 |
-
},
|
220 |
-
{
|
221 |
-
"epoch": 1.97,
|
222 |
-
"learning_rate": 8.871428571428571e-06,
|
223 |
-
"loss": 0.1894,
|
224 |
-
"step": 900
|
225 |
-
},
|
226 |
-
{
|
227 |
-
"epoch": 2.02,
|
228 |
-
"learning_rate": 8.8e-06,
|
229 |
-
"loss": 0.123,
|
230 |
-
"step": 925
|
231 |
-
},
|
232 |
-
{
|
233 |
-
"epoch": 2.08,
|
234 |
-
"learning_rate": 8.72857142857143e-06,
|
235 |
-
"loss": 0.0638,
|
236 |
-
"step": 950
|
237 |
-
},
|
238 |
-
{
|
239 |
-
"epoch": 2.13,
|
240 |
-
"learning_rate": 8.657142857142858e-06,
|
241 |
-
"loss": 0.0569,
|
242 |
-
"step": 975
|
243 |
-
},
|
244 |
-
{
|
245 |
-
"epoch": 2.19,
|
246 |
-
"learning_rate": 8.585714285714286e-06,
|
247 |
-
"loss": 0.0646,
|
248 |
-
"step": 1000
|
249 |
-
},
|
250 |
-
{
|
251 |
-
"epoch": 2.19,
|
252 |
-
"eval_loss": 0.2945411503314972,
|
253 |
-
"eval_runtime": 1132.8007,
|
254 |
-
"eval_samples_per_second": 4.46,
|
255 |
-
"eval_steps_per_second": 0.558,
|
256 |
-
"eval_wer": 21.574385584763643,
|
257 |
-
"step": 1000
|
258 |
-
}
|
259 |
-
],
|
260 |
-
"max_steps": 4000,
|
261 |
-
"num_train_epochs": 9,
|
262 |
-
"total_flos": 4.61505772191744e+18,
|
263 |
-
"trial_name": null,
|
264 |
-
"trial_params": null
|
265 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/training_args.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:3eefe50450ebd49f87f84b59e01b239e42692e4e5ab42e7c509a278cf825c777
|
3 |
-
size 3579
|
|
|
|
|
|
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 967102601
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9266b90ee4c8d75c93fca65e604a758148291bceb28e0d069071a63cd4cd05e
|
3 |
size 967102601
|
runs/Dec07_18-48-23_dd70ba896431/events.out.tfevents.1670439815.dd70ba896431.112.0
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 sha256:01f0b063580388cc3952496fe041ae38e9f815071fced039cabc145679d8e59c
|
3 |
+
size 30982
|