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/trainer_state.json +0 -271
- last-checkpoint/training_args.bin +0 -3
- last-checkpoint/scheduler.pt → runs/Dec05_22-37-41_05c47fdab07a/1670283836.0597272/events.out.tfevents.1670283836.05c47fdab07a.2690.4 +2 -2
- runs/Dec05_22-37-41_05c47fdab07a/events.out.tfevents.1670279904.05c47fdab07a.2690.2 +2 -2
last-checkpoint/config.json
DELETED
@@ -1,42 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "openai/whisper-base",
|
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": 512,
|
15 |
-
"decoder_attention_heads": 8,
|
16 |
-
"decoder_ffn_dim": 2048,
|
17 |
-
"decoder_layerdrop": 0.0,
|
18 |
-
"decoder_layers": 6,
|
19 |
-
"decoder_start_token_id": 50258,
|
20 |
-
"dropout": 0.0,
|
21 |
-
"encoder_attention_heads": 8,
|
22 |
-
"encoder_ffn_dim": 2048,
|
23 |
-
"encoder_layerdrop": 0.0,
|
24 |
-
"encoder_layers": 6,
|
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": 6,
|
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 sha256:89a66c1835f50b06db8d93840108ad741bf2f0bf722b6e0b20ba7853b7e143c9
|
3 |
-
size 580893677
|
|
|
|
|
|
|
|
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 sha256:24e090d26376f03e58d16136c1cc20da443e41493bde4b928d9c055caed661a6
|
3 |
-
size 290456599
|
|
|
|
|
|
|
|
last-checkpoint/rng_state.pth
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:896f38e8c69947dbf7af0d02524d4bdc9f5a477b7cdadcfdfe70c83cd9da1e27
|
3 |
-
size 14503
|
|
|
|
|
|
|
|
last-checkpoint/scaler.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:58f96f786c2d0e1a1f52eb98d62260f6dd2be07fb14a2357ee4427872e88c840
|
3 |
-
size 559
|
|
|
|
|
|
|
|
last-checkpoint/trainer_state.json
DELETED
@@ -1,271 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"best_metric": 34.55136995509666,
|
3 |
-
"best_model_checkpoint": "drive/MyDrive/whisper-base-sv/checkpoint-2000",
|
4 |
-
"epoch": 2.5873221216041395,
|
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": 0.06,
|
12 |
-
"learning_rate": 9.400000000000001e-07,
|
13 |
-
"loss": 2.5457,
|
14 |
-
"step": 50
|
15 |
-
},
|
16 |
-
{
|
17 |
-
"epoch": 0.13,
|
18 |
-
"learning_rate": 1.9200000000000003e-06,
|
19 |
-
"loss": 1.8539,
|
20 |
-
"step": 100
|
21 |
-
},
|
22 |
-
{
|
23 |
-
"epoch": 0.19,
|
24 |
-
"learning_rate": 2.92e-06,
|
25 |
-
"loss": 0.9435,
|
26 |
-
"step": 150
|
27 |
-
},
|
28 |
-
{
|
29 |
-
"epoch": 0.26,
|
30 |
-
"learning_rate": 3.920000000000001e-06,
|
31 |
-
"loss": 0.6976,
|
32 |
-
"step": 200
|
33 |
-
},
|
34 |
-
{
|
35 |
-
"epoch": 0.32,
|
36 |
-
"learning_rate": 4.92e-06,
|
37 |
-
"loss": 0.6091,
|
38 |
-
"step": 250
|
39 |
-
},
|
40 |
-
{
|
41 |
-
"epoch": 0.32,
|
42 |
-
"eval_loss": 0.6114889979362488,
|
43 |
-
"eval_runtime": 1063.3892,
|
44 |
-
"eval_samples_per_second": 4.767,
|
45 |
-
"eval_steps_per_second": 0.596,
|
46 |
-
"eval_wer": 42.31668952165847,
|
47 |
-
"step": 250
|
48 |
-
},
|
49 |
-
{
|
50 |
-
"epoch": 0.39,
|
51 |
-
"learning_rate": 5.92e-06,
|
52 |
-
"loss": 0.5908,
|
53 |
-
"step": 300
|
54 |
-
},
|
55 |
-
{
|
56 |
-
"epoch": 0.45,
|
57 |
-
"learning_rate": 6.92e-06,
|
58 |
-
"loss": 0.5695,
|
59 |
-
"step": 350
|
60 |
-
},
|
61 |
-
{
|
62 |
-
"epoch": 0.52,
|
63 |
-
"learning_rate": 7.92e-06,
|
64 |
-
"loss": 0.5481,
|
65 |
-
"step": 400
|
66 |
-
},
|
67 |
-
{
|
68 |
-
"epoch": 0.58,
|
69 |
-
"learning_rate": 8.920000000000001e-06,
|
70 |
-
"loss": 0.536,
|
71 |
-
"step": 450
|
72 |
-
},
|
73 |
-
{
|
74 |
-
"epoch": 0.65,
|
75 |
-
"learning_rate": 9.920000000000002e-06,
|
76 |
-
"loss": 0.5032,
|
77 |
-
"step": 500
|
78 |
-
},
|
79 |
-
{
|
80 |
-
"epoch": 0.65,
|
81 |
-
"eval_loss": 0.5396197438240051,
|
82 |
-
"eval_runtime": 1082.4366,
|
83 |
-
"eval_samples_per_second": 4.683,
|
84 |
-
"eval_steps_per_second": 0.586,
|
85 |
-
"eval_wer": 39.05245892823533,
|
86 |
-
"step": 500
|
87 |
-
},
|
88 |
-
{
|
89 |
-
"epoch": 0.71,
|
90 |
-
"learning_rate": 9.86857142857143e-06,
|
91 |
-
"loss": 0.5107,
|
92 |
-
"step": 550
|
93 |
-
},
|
94 |
-
{
|
95 |
-
"epoch": 0.78,
|
96 |
-
"learning_rate": 9.725714285714287e-06,
|
97 |
-
"loss": 0.5179,
|
98 |
-
"step": 600
|
99 |
-
},
|
100 |
-
{
|
101 |
-
"epoch": 0.84,
|
102 |
-
"learning_rate": 9.582857142857143e-06,
|
103 |
-
"loss": 0.507,
|
104 |
-
"step": 650
|
105 |
-
},
|
106 |
-
{
|
107 |
-
"epoch": 0.91,
|
108 |
-
"learning_rate": 9.440000000000001e-06,
|
109 |
-
"loss": 0.4837,
|
110 |
-
"step": 700
|
111 |
-
},
|
112 |
-
{
|
113 |
-
"epoch": 0.97,
|
114 |
-
"learning_rate": 9.297142857142857e-06,
|
115 |
-
"loss": 0.4776,
|
116 |
-
"step": 750
|
117 |
-
},
|
118 |
-
{
|
119 |
-
"epoch": 0.97,
|
120 |
-
"eval_loss": 0.5054066181182861,
|
121 |
-
"eval_runtime": 1083.7563,
|
122 |
-
"eval_samples_per_second": 4.677,
|
123 |
-
"eval_steps_per_second": 0.585,
|
124 |
-
"eval_wer": 37.20254900379124,
|
125 |
-
"step": 750
|
126 |
-
},
|
127 |
-
{
|
128 |
-
"epoch": 1.03,
|
129 |
-
"learning_rate": 9.154285714285715e-06,
|
130 |
-
"loss": 0.3998,
|
131 |
-
"step": 800
|
132 |
-
},
|
133 |
-
{
|
134 |
-
"epoch": 1.1,
|
135 |
-
"learning_rate": 9.011428571428572e-06,
|
136 |
-
"loss": 0.3516,
|
137 |
-
"step": 850
|
138 |
-
},
|
139 |
-
{
|
140 |
-
"epoch": 1.16,
|
141 |
-
"learning_rate": 8.86857142857143e-06,
|
142 |
-
"loss": 0.3336,
|
143 |
-
"step": 900
|
144 |
-
},
|
145 |
-
{
|
146 |
-
"epoch": 1.23,
|
147 |
-
"learning_rate": 8.725714285714286e-06,
|
148 |
-
"loss": 0.3486,
|
149 |
-
"step": 950
|
150 |
-
},
|
151 |
-
{
|
152 |
-
"epoch": 1.29,
|
153 |
-
"learning_rate": 8.582857142857144e-06,
|
154 |
-
"loss": 0.3391,
|
155 |
-
"step": 1000
|
156 |
-
},
|
157 |
-
{
|
158 |
-
"epoch": 1.29,
|
159 |
-
"eval_loss": 0.4857306182384491,
|
160 |
-
"eval_runtime": 1083.0435,
|
161 |
-
"eval_samples_per_second": 4.68,
|
162 |
-
"eval_steps_per_second": 0.585,
|
163 |
-
"eval_wer": 35.86620418918556,
|
164 |
-
"step": 1000
|
165 |
-
},
|
166 |
-
{
|
167 |
-
"epoch": 1.36,
|
168 |
-
"learning_rate": 8.44e-06,
|
169 |
-
"loss": 0.3365,
|
170 |
-
"step": 1050
|
171 |
-
},
|
172 |
-
{
|
173 |
-
"epoch": 1.42,
|
174 |
-
"learning_rate": 8.297142857142859e-06,
|
175 |
-
"loss": 0.3378,
|
176 |
-
"step": 1100
|
177 |
-
},
|
178 |
-
{
|
179 |
-
"epoch": 1.49,
|
180 |
-
"learning_rate": 8.154285714285715e-06,
|
181 |
-
"loss": 0.328,
|
182 |
-
"step": 1150
|
183 |
-
},
|
184 |
-
{
|
185 |
-
"epoch": 1.55,
|
186 |
-
"learning_rate": 8.011428571428573e-06,
|
187 |
-
"loss": 0.3432,
|
188 |
-
"step": 1200
|
189 |
-
},
|
190 |
-
{
|
191 |
-
"epoch": 1.62,
|
192 |
-
"learning_rate": 7.86857142857143e-06,
|
193 |
-
"loss": 0.335,
|
194 |
-
"step": 1250
|
195 |
-
},
|
196 |
-
{
|
197 |
-
"epoch": 1.62,
|
198 |
-
"eval_loss": 0.4708064794540405,
|
199 |
-
"eval_runtime": 1085.5679,
|
200 |
-
"eval_samples_per_second": 4.669,
|
201 |
-
"eval_steps_per_second": 0.584,
|
202 |
-
"eval_wer": 35.80705009276438,
|
203 |
-
"step": 1250
|
204 |
-
},
|
205 |
-
{
|
206 |
-
"epoch": 1.68,
|
207 |
-
"learning_rate": 7.725714285714286e-06,
|
208 |
-
"loss": 0.3286,
|
209 |
-
"step": 1300
|
210 |
-
},
|
211 |
-
{
|
212 |
-
"epoch": 1.75,
|
213 |
-
"learning_rate": 7.5828571428571444e-06,
|
214 |
-
"loss": 0.3185,
|
215 |
-
"step": 1350
|
216 |
-
},
|
217 |
-
{
|
218 |
-
"epoch": 1.81,
|
219 |
-
"learning_rate": 7.440000000000001e-06,
|
220 |
-
"loss": 0.3337,
|
221 |
-
"step": 1400
|
222 |
-
},
|
223 |
-
{
|
224 |
-
"epoch": 1.88,
|
225 |
-
"learning_rate": 7.297142857142858e-06,
|
226 |
-
"loss": 0.3045,
|
227 |
-
"step": 1450
|
228 |
-
},
|
229 |
-
{
|
230 |
-
"epoch": 1.94,
|
231 |
-
"learning_rate": 7.154285714285715e-06,
|
232 |
-
"loss": 0.3239,
|
233 |
-
"step": 1500
|
234 |
-
},
|
235 |
-
{
|
236 |
-
"epoch": 1.94,
|
237 |
-
"eval_loss": 0.45699021220207214,
|
238 |
-
"eval_runtime": 1186.6678,
|
239 |
-
"eval_samples_per_second": 4.272,
|
240 |
-
"eval_steps_per_second": 0.534,
|
241 |
-
"eval_wer": 34.75303164744158,
|
242 |
-
"step": 1500
|
243 |
-
},
|
244 |
-
{
|
245 |
-
"epoch": 2.26,
|
246 |
-
"learning_rate": 6.440000000000001e-06,
|
247 |
-
"loss": 0.2205,
|
248 |
-
"step": 1750
|
249 |
-
},
|
250 |
-
{
|
251 |
-
"epoch": 2.59,
|
252 |
-
"learning_rate": 5.725714285714287e-06,
|
253 |
-
"loss": 0.1952,
|
254 |
-
"step": 2000
|
255 |
-
},
|
256 |
-
{
|
257 |
-
"epoch": 2.59,
|
258 |
-
"eval_loss": 0.4576089084148407,
|
259 |
-
"eval_runtime": 1097.6955,
|
260 |
-
"eval_samples_per_second": 4.618,
|
261 |
-
"eval_steps_per_second": 0.578,
|
262 |
-
"eval_wer": 34.55136995509666,
|
263 |
-
"step": 2000
|
264 |
-
}
|
265 |
-
],
|
266 |
-
"max_steps": 4000,
|
267 |
-
"num_train_epochs": 6,
|
268 |
-
"total_flos": 2.07448211718144e+18,
|
269 |
-
"trial_name": null,
|
270 |
-
"trial_params": null
|
271 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/training_args.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:52eb34a8abd73966c93dcde076fa52c8c1b8f56e31a4b5a3012ed8d10bcd8015
|
3 |
-
size 3567
|
|
|
|
|
|
|
|
last-checkpoint/scheduler.pt → runs/Dec05_22-37-41_05c47fdab07a/1670283836.0597272/events.out.tfevents.1670283836.05c47fdab07a.2690.4
RENAMED
@@ -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 sha256:5495afeba9d0fa54bb7ba97624c5f62343c5a42bd929f68f1b514c62dd7e2521
|
3 |
+
size 5789
|
runs/Dec05_22-37-41_05c47fdab07a/events.out.tfevents.1670279904.05c47fdab07a.2690.2
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:dbb4b1f169f7d687606ad24eb9d7a5888eb4508b37553e0d565cbfc0ec6e4c25
|
3 |
+
size 9122
|