Upload 9 files
Browse files- config.json +51 -0
- generation_config.json +221 -0
- preprocessor_config.json +14 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- trainer_state.json +532 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "openai/whisper-small",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"apply_spec_augment": false,
|
6 |
+
"architectures": [
|
7 |
+
"WhisperForConditionalGeneration"
|
8 |
+
],
|
9 |
+
"attention_dropout": 0.0,
|
10 |
+
"begin_suppress_tokens": [
|
11 |
+
220,
|
12 |
+
50257
|
13 |
+
],
|
14 |
+
"bos_token_id": 50257,
|
15 |
+
"classifier_proj_size": 256,
|
16 |
+
"d_model": 768,
|
17 |
+
"decoder_attention_heads": 12,
|
18 |
+
"decoder_ffn_dim": 3072,
|
19 |
+
"decoder_layerdrop": 0.0,
|
20 |
+
"decoder_layers": 12,
|
21 |
+
"decoder_start_token_id": 50258,
|
22 |
+
"dropout": 0.2,
|
23 |
+
"encoder_attention_heads": 12,
|
24 |
+
"encoder_ffn_dim": 3072,
|
25 |
+
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 12,
|
27 |
+
"eos_token_id": 50257,
|
28 |
+
"forced_decoder_ids": null,
|
29 |
+
"init_std": 0.02,
|
30 |
+
"is_encoder_decoder": true,
|
31 |
+
"mask_feature_length": 10,
|
32 |
+
"mask_feature_min_masks": 0,
|
33 |
+
"mask_feature_prob": 0.0,
|
34 |
+
"mask_time_length": 10,
|
35 |
+
"mask_time_min_masks": 2,
|
36 |
+
"mask_time_prob": 0.05,
|
37 |
+
"max_length": 448,
|
38 |
+
"max_source_positions": 1500,
|
39 |
+
"max_target_positions": 448,
|
40 |
+
"model_type": "whisper",
|
41 |
+
"num_hidden_layers": 12,
|
42 |
+
"num_mel_bins": 80,
|
43 |
+
"pad_token_id": 50257,
|
44 |
+
"scale_embedding": false,
|
45 |
+
"suppress_tokens": [],
|
46 |
+
"torch_dtype": "float32",
|
47 |
+
"transformers_version": "4.29.2",
|
48 |
+
"use_cache": true,
|
49 |
+
"use_weighted_layer_sum": false,
|
50 |
+
"vocab_size": 51865
|
51 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,221 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"begin_suppress_tokens": [
|
3 |
+
220,
|
4 |
+
50257
|
5 |
+
],
|
6 |
+
"bos_token_id": 50257,
|
7 |
+
"decoder_start_token_id": 50258,
|
8 |
+
"eos_token_id": 50257,
|
9 |
+
"forced_decoder_ids": [
|
10 |
+
[
|
11 |
+
1,
|
12 |
+
null
|
13 |
+
],
|
14 |
+
[
|
15 |
+
2,
|
16 |
+
50359
|
17 |
+
]
|
18 |
+
],
|
19 |
+
"is_multilingual": true,
|
20 |
+
"lang_to_id": {
|
21 |
+
"<|af|>": 50327,
|
22 |
+
"<|am|>": 50334,
|
23 |
+
"<|ar|>": 50272,
|
24 |
+
"<|as|>": 50350,
|
25 |
+
"<|az|>": 50304,
|
26 |
+
"<|ba|>": 50355,
|
27 |
+
"<|be|>": 50330,
|
28 |
+
"<|bg|>": 50292,
|
29 |
+
"<|bn|>": 50302,
|
30 |
+
"<|bo|>": 50347,
|
31 |
+
"<|br|>": 50309,
|
32 |
+
"<|bs|>": 50315,
|
33 |
+
"<|ca|>": 50270,
|
34 |
+
"<|cs|>": 50283,
|
35 |
+
"<|cy|>": 50297,
|
36 |
+
"<|da|>": 50285,
|
37 |
+
"<|de|>": 50261,
|
38 |
+
"<|el|>": 50281,
|
39 |
+
"<|en|>": 50259,
|
40 |
+
"<|es|>": 50262,
|
41 |
+
"<|et|>": 50307,
|
42 |
+
"<|eu|>": 50310,
|
43 |
+
"<|fa|>": 50300,
|
44 |
+
"<|fi|>": 50277,
|
45 |
+
"<|fo|>": 50338,
|
46 |
+
"<|fr|>": 50265,
|
47 |
+
"<|gl|>": 50319,
|
48 |
+
"<|gu|>": 50333,
|
49 |
+
"<|haw|>": 50352,
|
50 |
+
"<|ha|>": 50354,
|
51 |
+
"<|he|>": 50279,
|
52 |
+
"<|hi|>": 50276,
|
53 |
+
"<|hr|>": 50291,
|
54 |
+
"<|ht|>": 50339,
|
55 |
+
"<|hu|>": 50286,
|
56 |
+
"<|hy|>": 50312,
|
57 |
+
"<|id|>": 50275,
|
58 |
+
"<|is|>": 50311,
|
59 |
+
"<|it|>": 50274,
|
60 |
+
"<|ja|>": 50266,
|
61 |
+
"<|jw|>": 50356,
|
62 |
+
"<|ka|>": 50329,
|
63 |
+
"<|kk|>": 50316,
|
64 |
+
"<|km|>": 50323,
|
65 |
+
"<|kn|>": 50306,
|
66 |
+
"<|ko|>": 50264,
|
67 |
+
"<|la|>": 50294,
|
68 |
+
"<|lb|>": 50345,
|
69 |
+
"<|ln|>": 50353,
|
70 |
+
"<|lo|>": 50336,
|
71 |
+
"<|lt|>": 50293,
|
72 |
+
"<|lv|>": 50301,
|
73 |
+
"<|mg|>": 50349,
|
74 |
+
"<|mi|>": 50295,
|
75 |
+
"<|mk|>": 50308,
|
76 |
+
"<|ml|>": 50296,
|
77 |
+
"<|mn|>": 50314,
|
78 |
+
"<|mr|>": 50320,
|
79 |
+
"<|ms|>": 50282,
|
80 |
+
"<|mt|>": 50343,
|
81 |
+
"<|my|>": 50346,
|
82 |
+
"<|ne|>": 50313,
|
83 |
+
"<|nl|>": 50271,
|
84 |
+
"<|nn|>": 50342,
|
85 |
+
"<|no|>": 50288,
|
86 |
+
"<|oc|>": 50328,
|
87 |
+
"<|pa|>": 50321,
|
88 |
+
"<|pl|>": 50269,
|
89 |
+
"<|ps|>": 50340,
|
90 |
+
"<|pt|>": 50267,
|
91 |
+
"<|ro|>": 50284,
|
92 |
+
"<|ru|>": 50263,
|
93 |
+
"<|sa|>": 50344,
|
94 |
+
"<|sd|>": 50332,
|
95 |
+
"<|si|>": 50322,
|
96 |
+
"<|sk|>": 50298,
|
97 |
+
"<|sl|>": 50305,
|
98 |
+
"<|sn|>": 50324,
|
99 |
+
"<|so|>": 50326,
|
100 |
+
"<|sq|>": 50317,
|
101 |
+
"<|sr|>": 50303,
|
102 |
+
"<|su|>": 50357,
|
103 |
+
"<|sv|>": 50273,
|
104 |
+
"<|sw|>": 50318,
|
105 |
+
"<|ta|>": 50287,
|
106 |
+
"<|te|>": 50299,
|
107 |
+
"<|tg|>": 50331,
|
108 |
+
"<|th|>": 50289,
|
109 |
+
"<|tk|>": 50341,
|
110 |
+
"<|tl|>": 50348,
|
111 |
+
"<|tr|>": 50268,
|
112 |
+
"<|tt|>": 50351,
|
113 |
+
"<|uk|>": 50280,
|
114 |
+
"<|ur|>": 50290,
|
115 |
+
"<|uz|>": 50337,
|
116 |
+
"<|vi|>": 50278,
|
117 |
+
"<|yi|>": 50335,
|
118 |
+
"<|yo|>": 50325,
|
119 |
+
"<|zh|>": 50260
|
120 |
+
},
|
121 |
+
"max_initial_timestamp_index": 1,
|
122 |
+
"max_length": 448,
|
123 |
+
"no_timestamps_token_id": 50363,
|
124 |
+
"pad_token_id": 50257,
|
125 |
+
"return_timestamps": false,
|
126 |
+
"suppress_tokens": [
|
127 |
+
1,
|
128 |
+
2,
|
129 |
+
7,
|
130 |
+
8,
|
131 |
+
9,
|
132 |
+
10,
|
133 |
+
14,
|
134 |
+
25,
|
135 |
+
26,
|
136 |
+
27,
|
137 |
+
28,
|
138 |
+
29,
|
139 |
+
31,
|
140 |
+
58,
|
141 |
+
59,
|
142 |
+
60,
|
143 |
+
61,
|
144 |
+
62,
|
145 |
+
63,
|
146 |
+
90,
|
147 |
+
91,
|
148 |
+
92,
|
149 |
+
93,
|
150 |
+
359,
|
151 |
+
503,
|
152 |
+
522,
|
153 |
+
542,
|
154 |
+
873,
|
155 |
+
893,
|
156 |
+
902,
|
157 |
+
918,
|
158 |
+
922,
|
159 |
+
931,
|
160 |
+
1350,
|
161 |
+
1853,
|
162 |
+
1982,
|
163 |
+
2460,
|
164 |
+
2627,
|
165 |
+
3246,
|
166 |
+
3253,
|
167 |
+
3268,
|
168 |
+
3536,
|
169 |
+
3846,
|
170 |
+
3961,
|
171 |
+
4183,
|
172 |
+
4667,
|
173 |
+
6585,
|
174 |
+
6647,
|
175 |
+
7273,
|
176 |
+
9061,
|
177 |
+
9383,
|
178 |
+
10428,
|
179 |
+
10929,
|
180 |
+
11938,
|
181 |
+
12033,
|
182 |
+
12331,
|
183 |
+
12562,
|
184 |
+
13793,
|
185 |
+
14157,
|
186 |
+
14635,
|
187 |
+
15265,
|
188 |
+
15618,
|
189 |
+
16553,
|
190 |
+
16604,
|
191 |
+
18362,
|
192 |
+
18956,
|
193 |
+
20075,
|
194 |
+
21675,
|
195 |
+
22520,
|
196 |
+
26130,
|
197 |
+
26161,
|
198 |
+
26435,
|
199 |
+
28279,
|
200 |
+
29464,
|
201 |
+
31650,
|
202 |
+
32302,
|
203 |
+
32470,
|
204 |
+
36865,
|
205 |
+
42863,
|
206 |
+
47425,
|
207 |
+
49870,
|
208 |
+
50254,
|
209 |
+
50258,
|
210 |
+
50358,
|
211 |
+
50359,
|
212 |
+
50360,
|
213 |
+
50361,
|
214 |
+
50362
|
215 |
+
],
|
216 |
+
"task_to_id": {
|
217 |
+
"transcribe": 50359,
|
218 |
+
"translate": 50358
|
219 |
+
},
|
220 |
+
"transformers_version": "4.29.2"
|
221 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"chunk_length": 30,
|
3 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
4 |
+
"feature_size": 80,
|
5 |
+
"hop_length": 160,
|
6 |
+
"n_fft": 400,
|
7 |
+
"n_samples": 480000,
|
8 |
+
"nb_max_frames": 3000,
|
9 |
+
"padding_side": "right",
|
10 |
+
"padding_value": 0.0,
|
11 |
+
"processor_class": "WhisperProcessor",
|
12 |
+
"return_attention_mask": false,
|
13 |
+
"sampling_rate": 16000
|
14 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16e7e4d89493a3d5e33b8179503244474870a7043824b6ccc71dc51d01ac1866
|
3 |
+
size 967102601
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ada9178d028a2373fdd3b913873fced3d801e1d2cf3d2b6f9c688be030c5c8c
|
3 |
+
size 14575
|
scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:126c7813b564874318d5262c302443132103b6afa14382e69880ad35212bfede
|
3 |
+
size 557
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce92434c038f1d8b984e555cbdcca200be124e5a5c23f3963c6cef175d4d8c86
|
3 |
+
size 627
|
trainer_state.json
ADDED
@@ -0,0 +1,532 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 23.978183729793663,
|
3 |
+
"best_model_checkpoint": "./openai/whisper-small-gom-LDC-v1.non-repeating/checkpoint-2000",
|
4 |
+
"epoch": 2.73972602739726,
|
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": 0.03,
|
12 |
+
"learning_rate": 3.52e-07,
|
13 |
+
"loss": 2.5215,
|
14 |
+
"step": 25
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.07,
|
18 |
+
"learning_rate": 7.52e-07,
|
19 |
+
"loss": 2.0216,
|
20 |
+
"step": 50
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.1,
|
24 |
+
"learning_rate": 1.152e-06,
|
25 |
+
"loss": 1.5534,
|
26 |
+
"step": 75
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.14,
|
30 |
+
"learning_rate": 1.552e-06,
|
31 |
+
"loss": 1.1894,
|
32 |
+
"step": 100
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.17,
|
36 |
+
"learning_rate": 1.9519999999999997e-06,
|
37 |
+
"loss": 0.9816,
|
38 |
+
"step": 125
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.21,
|
42 |
+
"learning_rate": 2.3519999999999997e-06,
|
43 |
+
"loss": 0.9194,
|
44 |
+
"step": 150
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.24,
|
48 |
+
"learning_rate": 2.7519999999999997e-06,
|
49 |
+
"loss": 0.8616,
|
50 |
+
"step": 175
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.27,
|
54 |
+
"learning_rate": 3.152e-06,
|
55 |
+
"loss": 0.7917,
|
56 |
+
"step": 200
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.31,
|
60 |
+
"learning_rate": 3.552e-06,
|
61 |
+
"loss": 0.7533,
|
62 |
+
"step": 225
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.34,
|
66 |
+
"learning_rate": 3.952e-06,
|
67 |
+
"loss": 0.6568,
|
68 |
+
"step": 250
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.38,
|
72 |
+
"learning_rate": 4.352e-06,
|
73 |
+
"loss": 0.6336,
|
74 |
+
"step": 275
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.41,
|
78 |
+
"learning_rate": 4.7519999999999996e-06,
|
79 |
+
"loss": 0.6031,
|
80 |
+
"step": 300
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.45,
|
84 |
+
"learning_rate": 5.152e-06,
|
85 |
+
"loss": 0.5941,
|
86 |
+
"step": 325
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.48,
|
90 |
+
"learning_rate": 5.5519999999999995e-06,
|
91 |
+
"loss": 0.5556,
|
92 |
+
"step": 350
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.51,
|
96 |
+
"learning_rate": 5.952e-06,
|
97 |
+
"loss": 0.4818,
|
98 |
+
"step": 375
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.55,
|
102 |
+
"learning_rate": 6.352e-06,
|
103 |
+
"loss": 0.4068,
|
104 |
+
"step": 400
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.58,
|
108 |
+
"learning_rate": 6.751999999999999e-06,
|
109 |
+
"loss": 0.3764,
|
110 |
+
"step": 425
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.62,
|
114 |
+
"learning_rate": 7.1519999999999995e-06,
|
115 |
+
"loss": 0.3416,
|
116 |
+
"step": 450
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.65,
|
120 |
+
"learning_rate": 7.551999999999999e-06,
|
121 |
+
"loss": 0.321,
|
122 |
+
"step": 475
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.68,
|
126 |
+
"learning_rate": 7.952e-06,
|
127 |
+
"loss": 0.2987,
|
128 |
+
"step": 500
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.68,
|
132 |
+
"eval_loss": 0.3088768422603607,
|
133 |
+
"eval_runtime": 1198.5779,
|
134 |
+
"eval_samples_per_second": 1.73,
|
135 |
+
"eval_steps_per_second": 0.217,
|
136 |
+
"eval_wer": 54.862662636351686,
|
137 |
+
"step": 500
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 0.72,
|
141 |
+
"learning_rate": 7.89585798816568e-06,
|
142 |
+
"loss": 0.2955,
|
143 |
+
"step": 525
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.75,
|
147 |
+
"learning_rate": 7.777514792899408e-06,
|
148 |
+
"loss": 0.3082,
|
149 |
+
"step": 550
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.79,
|
153 |
+
"learning_rate": 7.659171597633136e-06,
|
154 |
+
"loss": 0.25,
|
155 |
+
"step": 575
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 0.82,
|
159 |
+
"learning_rate": 7.540828402366864e-06,
|
160 |
+
"loss": 0.2989,
|
161 |
+
"step": 600
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 0.86,
|
165 |
+
"learning_rate": 7.422485207100592e-06,
|
166 |
+
"loss": 0.2643,
|
167 |
+
"step": 625
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 0.89,
|
171 |
+
"learning_rate": 7.30414201183432e-06,
|
172 |
+
"loss": 0.2576,
|
173 |
+
"step": 650
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 0.92,
|
177 |
+
"learning_rate": 7.185798816568046e-06,
|
178 |
+
"loss": 0.2646,
|
179 |
+
"step": 675
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 0.96,
|
183 |
+
"learning_rate": 7.0674556213017745e-06,
|
184 |
+
"loss": 0.2231,
|
185 |
+
"step": 700
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.99,
|
189 |
+
"learning_rate": 6.949112426035503e-06,
|
190 |
+
"loss": 0.2104,
|
191 |
+
"step": 725
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 1.03,
|
195 |
+
"learning_rate": 6.83076923076923e-06,
|
196 |
+
"loss": 0.1716,
|
197 |
+
"step": 750
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 1.06,
|
201 |
+
"learning_rate": 6.712426035502958e-06,
|
202 |
+
"loss": 0.1727,
|
203 |
+
"step": 775
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 1.1,
|
207 |
+
"learning_rate": 6.594082840236686e-06,
|
208 |
+
"loss": 0.155,
|
209 |
+
"step": 800
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 1.13,
|
213 |
+
"learning_rate": 6.475739644970413e-06,
|
214 |
+
"loss": 0.2016,
|
215 |
+
"step": 825
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 1.16,
|
219 |
+
"learning_rate": 6.3573964497041415e-06,
|
220 |
+
"loss": 0.1728,
|
221 |
+
"step": 850
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 1.2,
|
225 |
+
"learning_rate": 6.23905325443787e-06,
|
226 |
+
"loss": 0.1752,
|
227 |
+
"step": 875
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 1.23,
|
231 |
+
"learning_rate": 6.120710059171597e-06,
|
232 |
+
"loss": 0.1408,
|
233 |
+
"step": 900
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 1.27,
|
237 |
+
"learning_rate": 6.002366863905325e-06,
|
238 |
+
"loss": 0.1729,
|
239 |
+
"step": 925
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 1.3,
|
243 |
+
"learning_rate": 5.884023668639053e-06,
|
244 |
+
"loss": 0.1163,
|
245 |
+
"step": 950
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"epoch": 1.34,
|
249 |
+
"learning_rate": 5.76568047337278e-06,
|
250 |
+
"loss": 0.1382,
|
251 |
+
"step": 975
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 1.37,
|
255 |
+
"learning_rate": 5.6473372781065085e-06,
|
256 |
+
"loss": 0.1506,
|
257 |
+
"step": 1000
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 1.37,
|
261 |
+
"eval_loss": 0.1685582995414734,
|
262 |
+
"eval_runtime": 1145.8994,
|
263 |
+
"eval_samples_per_second": 1.81,
|
264 |
+
"eval_steps_per_second": 0.227,
|
265 |
+
"eval_wer": 35.832566697332105,
|
266 |
+
"step": 1000
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 1.4,
|
270 |
+
"learning_rate": 5.528994082840237e-06,
|
271 |
+
"loss": 0.1395,
|
272 |
+
"step": 1025
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 1.44,
|
276 |
+
"learning_rate": 5.410650887573964e-06,
|
277 |
+
"loss": 0.1616,
|
278 |
+
"step": 1050
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 1.47,
|
282 |
+
"learning_rate": 5.292307692307692e-06,
|
283 |
+
"loss": 0.1542,
|
284 |
+
"step": 1075
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 1.51,
|
288 |
+
"learning_rate": 5.17396449704142e-06,
|
289 |
+
"loss": 0.1315,
|
290 |
+
"step": 1100
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 1.54,
|
294 |
+
"learning_rate": 5.055621301775148e-06,
|
295 |
+
"loss": 0.114,
|
296 |
+
"step": 1125
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 1.58,
|
300 |
+
"learning_rate": 4.9372781065088755e-06,
|
301 |
+
"loss": 0.1127,
|
302 |
+
"step": 1150
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 1.61,
|
306 |
+
"learning_rate": 4.818934911242604e-06,
|
307 |
+
"loss": 0.1258,
|
308 |
+
"step": 1175
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 1.64,
|
312 |
+
"learning_rate": 4.700591715976332e-06,
|
313 |
+
"loss": 0.1195,
|
314 |
+
"step": 1200
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 1.68,
|
318 |
+
"learning_rate": 4.582248520710059e-06,
|
319 |
+
"loss": 0.1189,
|
320 |
+
"step": 1225
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 1.71,
|
324 |
+
"learning_rate": 4.463905325443787e-06,
|
325 |
+
"loss": 0.1496,
|
326 |
+
"step": 1250
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 1.75,
|
330 |
+
"learning_rate": 4.345562130177515e-06,
|
331 |
+
"loss": 0.1282,
|
332 |
+
"step": 1275
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 1.78,
|
336 |
+
"learning_rate": 4.2272189349112425e-06,
|
337 |
+
"loss": 0.1212,
|
338 |
+
"step": 1300
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 1.82,
|
342 |
+
"learning_rate": 4.108875739644971e-06,
|
343 |
+
"loss": 0.1013,
|
344 |
+
"step": 1325
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 1.85,
|
348 |
+
"learning_rate": 3.990532544378698e-06,
|
349 |
+
"loss": 0.1151,
|
350 |
+
"step": 1350
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 1.88,
|
354 |
+
"learning_rate": 3.872189349112426e-06,
|
355 |
+
"loss": 0.1096,
|
356 |
+
"step": 1375
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 1.92,
|
360 |
+
"learning_rate": 3.7538461538461537e-06,
|
361 |
+
"loss": 0.1127,
|
362 |
+
"step": 1400
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 1.95,
|
366 |
+
"learning_rate": 3.6355029585798814e-06,
|
367 |
+
"loss": 0.0894,
|
368 |
+
"step": 1425
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 1.99,
|
372 |
+
"learning_rate": 3.5171597633136095e-06,
|
373 |
+
"loss": 0.095,
|
374 |
+
"step": 1450
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 2.02,
|
378 |
+
"learning_rate": 3.3988165680473372e-06,
|
379 |
+
"loss": 0.0865,
|
380 |
+
"step": 1475
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 2.05,
|
384 |
+
"learning_rate": 3.280473372781065e-06,
|
385 |
+
"loss": 0.0669,
|
386 |
+
"step": 1500
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 2.05,
|
390 |
+
"eval_loss": 0.1228846088051796,
|
391 |
+
"eval_runtime": 1086.3387,
|
392 |
+
"eval_samples_per_second": 1.909,
|
393 |
+
"eval_steps_per_second": 0.239,
|
394 |
+
"eval_wer": 25.535550006571167,
|
395 |
+
"step": 1500
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 2.09,
|
399 |
+
"learning_rate": 3.162130177514793e-06,
|
400 |
+
"loss": 0.0664,
|
401 |
+
"step": 1525
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 2.12,
|
405 |
+
"learning_rate": 3.0437869822485203e-06,
|
406 |
+
"loss": 0.0908,
|
407 |
+
"step": 1550
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"epoch": 2.16,
|
411 |
+
"learning_rate": 2.9254437869822484e-06,
|
412 |
+
"loss": 0.0796,
|
413 |
+
"step": 1575
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 2.19,
|
417 |
+
"learning_rate": 2.807100591715976e-06,
|
418 |
+
"loss": 0.0595,
|
419 |
+
"step": 1600
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 2.23,
|
423 |
+
"learning_rate": 2.688757396449704e-06,
|
424 |
+
"loss": 0.0717,
|
425 |
+
"step": 1625
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 2.26,
|
429 |
+
"learning_rate": 2.570414201183432e-06,
|
430 |
+
"loss": 0.0519,
|
431 |
+
"step": 1650
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 2.29,
|
435 |
+
"learning_rate": 2.4520710059171596e-06,
|
436 |
+
"loss": 0.0612,
|
437 |
+
"step": 1675
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 2.33,
|
441 |
+
"learning_rate": 2.3337278106508873e-06,
|
442 |
+
"loss": 0.0756,
|
443 |
+
"step": 1700
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 2.36,
|
447 |
+
"learning_rate": 2.2153846153846154e-06,
|
448 |
+
"loss": 0.0775,
|
449 |
+
"step": 1725
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 2.4,
|
453 |
+
"learning_rate": 2.097041420118343e-06,
|
454 |
+
"loss": 0.0676,
|
455 |
+
"step": 1750
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 2.43,
|
459 |
+
"learning_rate": 1.978698224852071e-06,
|
460 |
+
"loss": 0.0764,
|
461 |
+
"step": 1775
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 2.47,
|
465 |
+
"learning_rate": 1.860355029585799e-06,
|
466 |
+
"loss": 0.0677,
|
467 |
+
"step": 1800
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 2.5,
|
471 |
+
"learning_rate": 1.7420118343195264e-06,
|
472 |
+
"loss": 0.0576,
|
473 |
+
"step": 1825
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 2.53,
|
477 |
+
"learning_rate": 1.6236686390532543e-06,
|
478 |
+
"loss": 0.0557,
|
479 |
+
"step": 1850
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 2.57,
|
483 |
+
"learning_rate": 1.5053254437869822e-06,
|
484 |
+
"loss": 0.0558,
|
485 |
+
"step": 1875
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 2.6,
|
489 |
+
"learning_rate": 1.38698224852071e-06,
|
490 |
+
"loss": 0.0644,
|
491 |
+
"step": 1900
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 2.64,
|
495 |
+
"learning_rate": 1.2686390532544378e-06,
|
496 |
+
"loss": 0.0775,
|
497 |
+
"step": 1925
|
498 |
+
},
|
499 |
+
{
|
500 |
+
"epoch": 2.67,
|
501 |
+
"learning_rate": 1.1502958579881657e-06,
|
502 |
+
"loss": 0.0665,
|
503 |
+
"step": 1950
|
504 |
+
},
|
505 |
+
{
|
506 |
+
"epoch": 2.71,
|
507 |
+
"learning_rate": 1.0319526627218936e-06,
|
508 |
+
"loss": 0.0657,
|
509 |
+
"step": 1975
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 2.74,
|
513 |
+
"learning_rate": 9.136094674556213e-07,
|
514 |
+
"loss": 0.0613,
|
515 |
+
"step": 2000
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 2.74,
|
519 |
+
"eval_loss": 0.10533993691205978,
|
520 |
+
"eval_runtime": 1099.5879,
|
521 |
+
"eval_samples_per_second": 1.886,
|
522 |
+
"eval_steps_per_second": 0.236,
|
523 |
+
"eval_wer": 23.978183729793663,
|
524 |
+
"step": 2000
|
525 |
+
}
|
526 |
+
],
|
527 |
+
"max_steps": 2190,
|
528 |
+
"num_train_epochs": 3,
|
529 |
+
"total_flos": 9.23242412703744e+18,
|
530 |
+
"trial_name": null,
|
531 |
+
"trial_params": null
|
532 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7306eb694da5987d660a0524687b1782eb70852b951d163177d4919edca73bcc
|
3 |
+
size 4155
|