DazMashaly
commited on
Commit
•
f18656e
1
Parent(s):
3c94d43
Upload folder
Browse files- checkpoint-423/config.json +154 -0
- checkpoint-423/generation_config.json +248 -0
- checkpoint-423/model.safetensors +3 -0
- checkpoint-423/optimizer.pt +3 -0
- checkpoint-423/preprocessor_config.json +14 -0
- checkpoint-423/rng_state.pth +3 -0
- checkpoint-423/scheduler.pt +3 -0
- checkpoint-423/trainer_state.json +165 -0
- checkpoint-423/training_args.bin +3 -0
- checkpoint-564/config.json +154 -0
- checkpoint-564/generation_config.json +248 -0
- checkpoint-564/model.safetensors +3 -0
- checkpoint-564/optimizer.pt +3 -0
- checkpoint-564/preprocessor_config.json +14 -0
- checkpoint-564/rng_state.pth +3 -0
- checkpoint-564/scheduler.pt +3 -0
- checkpoint-564/trainer_state.json +217 -0
- checkpoint-564/training_args.bin +3 -0
- checkpoint-705/config.json +154 -0
- checkpoint-705/generation_config.json +248 -0
- checkpoint-705/model.safetensors +3 -0
- checkpoint-705/optimizer.pt +3 -0
- checkpoint-705/preprocessor_config.json +14 -0
- checkpoint-705/rng_state.pth +3 -0
- checkpoint-705/scheduler.pt +3 -0
- checkpoint-705/trainer_state.json +269 -0
- checkpoint-705/training_args.bin +3 -0
- config.json +1 -1
- model.safetensors +1 -1
- runs/Jun29_22-49-32_ac23a7b0cb5f/events.out.tfevents.1719701375.ac23a7b0cb5f.4846.0 +3 -0
- runs/Jun29_22-50-11_ac23a7b0cb5f/events.out.tfevents.1719701413.ac23a7b0cb5f.4846.1 +3 -0
- training_args.bin +1 -1
checkpoint-423/config.json
ADDED
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/content/new_downloads/checkpoint-397",
|
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": 512,
|
17 |
+
"decoder_attention_heads": 8,
|
18 |
+
"decoder_ffn_dim": 2048,
|
19 |
+
"decoder_layerdrop": 0.0,
|
20 |
+
"decoder_layers": 6,
|
21 |
+
"decoder_start_token_id": 50257,
|
22 |
+
"dropout": 0.0,
|
23 |
+
"encoder_attention_heads": 8,
|
24 |
+
"encoder_ffn_dim": 2048,
|
25 |
+
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 6,
|
27 |
+
"eos_token_id": 50257,
|
28 |
+
"forced_decoder_ids": [
|
29 |
+
[
|
30 |
+
1,
|
31 |
+
50259
|
32 |
+
],
|
33 |
+
[
|
34 |
+
2,
|
35 |
+
50359
|
36 |
+
],
|
37 |
+
[
|
38 |
+
3,
|
39 |
+
50363
|
40 |
+
]
|
41 |
+
],
|
42 |
+
"init_std": 0.02,
|
43 |
+
"is_encoder_decoder": true,
|
44 |
+
"mask_feature_length": 10,
|
45 |
+
"mask_feature_min_masks": 0,
|
46 |
+
"mask_feature_prob": 0.0,
|
47 |
+
"mask_time_length": 10,
|
48 |
+
"mask_time_min_masks": 2,
|
49 |
+
"mask_time_prob": 0.05,
|
50 |
+
"max_length": 448,
|
51 |
+
"max_source_positions": 1500,
|
52 |
+
"max_target_positions": 448,
|
53 |
+
"median_filter_width": 7,
|
54 |
+
"model_type": "whisper",
|
55 |
+
"num_hidden_layers": 6,
|
56 |
+
"num_mel_bins": 80,
|
57 |
+
"pad_token_id": 50257,
|
58 |
+
"scale_embedding": false,
|
59 |
+
"suppress_tokens": [
|
60 |
+
1,
|
61 |
+
2,
|
62 |
+
7,
|
63 |
+
8,
|
64 |
+
9,
|
65 |
+
10,
|
66 |
+
14,
|
67 |
+
25,
|
68 |
+
26,
|
69 |
+
27,
|
70 |
+
28,
|
71 |
+
29,
|
72 |
+
31,
|
73 |
+
58,
|
74 |
+
59,
|
75 |
+
60,
|
76 |
+
61,
|
77 |
+
62,
|
78 |
+
63,
|
79 |
+
90,
|
80 |
+
91,
|
81 |
+
92,
|
82 |
+
93,
|
83 |
+
359,
|
84 |
+
503,
|
85 |
+
522,
|
86 |
+
542,
|
87 |
+
873,
|
88 |
+
893,
|
89 |
+
902,
|
90 |
+
918,
|
91 |
+
922,
|
92 |
+
931,
|
93 |
+
1350,
|
94 |
+
1853,
|
95 |
+
1982,
|
96 |
+
2460,
|
97 |
+
2627,
|
98 |
+
3246,
|
99 |
+
3253,
|
100 |
+
3268,
|
101 |
+
3536,
|
102 |
+
3846,
|
103 |
+
3961,
|
104 |
+
4183,
|
105 |
+
4667,
|
106 |
+
6585,
|
107 |
+
6647,
|
108 |
+
7273,
|
109 |
+
9061,
|
110 |
+
9383,
|
111 |
+
10428,
|
112 |
+
10929,
|
113 |
+
11938,
|
114 |
+
12033,
|
115 |
+
12331,
|
116 |
+
12562,
|
117 |
+
13793,
|
118 |
+
14157,
|
119 |
+
14635,
|
120 |
+
15265,
|
121 |
+
15618,
|
122 |
+
16553,
|
123 |
+
16604,
|
124 |
+
18362,
|
125 |
+
18956,
|
126 |
+
20075,
|
127 |
+
21675,
|
128 |
+
22520,
|
129 |
+
26130,
|
130 |
+
26161,
|
131 |
+
26435,
|
132 |
+
28279,
|
133 |
+
29464,
|
134 |
+
31650,
|
135 |
+
32302,
|
136 |
+
32470,
|
137 |
+
36865,
|
138 |
+
42863,
|
139 |
+
47425,
|
140 |
+
49870,
|
141 |
+
50254,
|
142 |
+
50258,
|
143 |
+
50358,
|
144 |
+
50359,
|
145 |
+
50360,
|
146 |
+
50361,
|
147 |
+
50362
|
148 |
+
],
|
149 |
+
"torch_dtype": "float32",
|
150 |
+
"transformers_version": "4.42.3",
|
151 |
+
"use_cache": true,
|
152 |
+
"use_weighted_layer_sum": false,
|
153 |
+
"vocab_size": 51865
|
154 |
+
}
|
checkpoint-423/generation_config.json
ADDED
@@ -0,0 +1,248 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alignment_heads": [
|
3 |
+
[
|
4 |
+
3,
|
5 |
+
1
|
6 |
+
],
|
7 |
+
[
|
8 |
+
4,
|
9 |
+
2
|
10 |
+
],
|
11 |
+
[
|
12 |
+
4,
|
13 |
+
3
|
14 |
+
],
|
15 |
+
[
|
16 |
+
4,
|
17 |
+
7
|
18 |
+
],
|
19 |
+
[
|
20 |
+
5,
|
21 |
+
1
|
22 |
+
],
|
23 |
+
[
|
24 |
+
5,
|
25 |
+
2
|
26 |
+
],
|
27 |
+
[
|
28 |
+
5,
|
29 |
+
4
|
30 |
+
],
|
31 |
+
[
|
32 |
+
5,
|
33 |
+
6
|
34 |
+
]
|
35 |
+
],
|
36 |
+
"begin_suppress_tokens": [
|
37 |
+
220,
|
38 |
+
50257
|
39 |
+
],
|
40 |
+
"bos_token_id": 50257,
|
41 |
+
"decoder_start_token_id": 50258,
|
42 |
+
"eos_token_id": 50257,
|
43 |
+
"is_multilingual": true,
|
44 |
+
"lang_to_id": {
|
45 |
+
"<|af|>": 50327,
|
46 |
+
"<|am|>": 50334,
|
47 |
+
"<|ar|>": 50272,
|
48 |
+
"<|as|>": 50350,
|
49 |
+
"<|az|>": 50304,
|
50 |
+
"<|ba|>": 50355,
|
51 |
+
"<|be|>": 50330,
|
52 |
+
"<|bg|>": 50292,
|
53 |
+
"<|bn|>": 50302,
|
54 |
+
"<|bo|>": 50347,
|
55 |
+
"<|br|>": 50309,
|
56 |
+
"<|bs|>": 50315,
|
57 |
+
"<|ca|>": 50270,
|
58 |
+
"<|cs|>": 50283,
|
59 |
+
"<|cy|>": 50297,
|
60 |
+
"<|da|>": 50285,
|
61 |
+
"<|de|>": 50261,
|
62 |
+
"<|el|>": 50281,
|
63 |
+
"<|en|>": 50259,
|
64 |
+
"<|es|>": 50262,
|
65 |
+
"<|et|>": 50307,
|
66 |
+
"<|eu|>": 50310,
|
67 |
+
"<|fa|>": 50300,
|
68 |
+
"<|fi|>": 50277,
|
69 |
+
"<|fo|>": 50338,
|
70 |
+
"<|fr|>": 50265,
|
71 |
+
"<|gl|>": 50319,
|
72 |
+
"<|gu|>": 50333,
|
73 |
+
"<|haw|>": 50352,
|
74 |
+
"<|ha|>": 50354,
|
75 |
+
"<|he|>": 50279,
|
76 |
+
"<|hi|>": 50276,
|
77 |
+
"<|hr|>": 50291,
|
78 |
+
"<|ht|>": 50339,
|
79 |
+
"<|hu|>": 50286,
|
80 |
+
"<|hy|>": 50312,
|
81 |
+
"<|id|>": 50275,
|
82 |
+
"<|is|>": 50311,
|
83 |
+
"<|it|>": 50274,
|
84 |
+
"<|ja|>": 50266,
|
85 |
+
"<|jw|>": 50356,
|
86 |
+
"<|ka|>": 50329,
|
87 |
+
"<|kk|>": 50316,
|
88 |
+
"<|km|>": 50323,
|
89 |
+
"<|kn|>": 50306,
|
90 |
+
"<|ko|>": 50264,
|
91 |
+
"<|la|>": 50294,
|
92 |
+
"<|lb|>": 50345,
|
93 |
+
"<|ln|>": 50353,
|
94 |
+
"<|lo|>": 50336,
|
95 |
+
"<|lt|>": 50293,
|
96 |
+
"<|lv|>": 50301,
|
97 |
+
"<|mg|>": 50349,
|
98 |
+
"<|mi|>": 50295,
|
99 |
+
"<|mk|>": 50308,
|
100 |
+
"<|ml|>": 50296,
|
101 |
+
"<|mn|>": 50314,
|
102 |
+
"<|mr|>": 50320,
|
103 |
+
"<|ms|>": 50282,
|
104 |
+
"<|mt|>": 50343,
|
105 |
+
"<|my|>": 50346,
|
106 |
+
"<|ne|>": 50313,
|
107 |
+
"<|nl|>": 50271,
|
108 |
+
"<|nn|>": 50342,
|
109 |
+
"<|no|>": 50288,
|
110 |
+
"<|oc|>": 50328,
|
111 |
+
"<|pa|>": 50321,
|
112 |
+
"<|pl|>": 50269,
|
113 |
+
"<|ps|>": 50340,
|
114 |
+
"<|pt|>": 50267,
|
115 |
+
"<|ro|>": 50284,
|
116 |
+
"<|ru|>": 50263,
|
117 |
+
"<|sa|>": 50344,
|
118 |
+
"<|sd|>": 50332,
|
119 |
+
"<|si|>": 50322,
|
120 |
+
"<|sk|>": 50298,
|
121 |
+
"<|sl|>": 50305,
|
122 |
+
"<|sn|>": 50324,
|
123 |
+
"<|so|>": 50326,
|
124 |
+
"<|sq|>": 50317,
|
125 |
+
"<|sr|>": 50303,
|
126 |
+
"<|su|>": 50357,
|
127 |
+
"<|sv|>": 50273,
|
128 |
+
"<|sw|>": 50318,
|
129 |
+
"<|ta|>": 50287,
|
130 |
+
"<|te|>": 50299,
|
131 |
+
"<|tg|>": 50331,
|
132 |
+
"<|th|>": 50289,
|
133 |
+
"<|tk|>": 50341,
|
134 |
+
"<|tl|>": 50348,
|
135 |
+
"<|tr|>": 50268,
|
136 |
+
"<|tt|>": 50351,
|
137 |
+
"<|uk|>": 50280,
|
138 |
+
"<|ur|>": 50290,
|
139 |
+
"<|uz|>": 50337,
|
140 |
+
"<|vi|>": 50278,
|
141 |
+
"<|yi|>": 50335,
|
142 |
+
"<|yo|>": 50325,
|
143 |
+
"<|zh|>": 50260
|
144 |
+
},
|
145 |
+
"language": "arabic",
|
146 |
+
"max_initial_timestamp_index": 50,
|
147 |
+
"max_length": 448,
|
148 |
+
"no_timestamps_token_id": 50363,
|
149 |
+
"pad_token_id": 50257,
|
150 |
+
"prev_sot_token_id": 50361,
|
151 |
+
"return_timestamps": false,
|
152 |
+
"suppress_tokens": [
|
153 |
+
1,
|
154 |
+
2,
|
155 |
+
7,
|
156 |
+
8,
|
157 |
+
9,
|
158 |
+
10,
|
159 |
+
14,
|
160 |
+
25,
|
161 |
+
26,
|
162 |
+
27,
|
163 |
+
28,
|
164 |
+
29,
|
165 |
+
31,
|
166 |
+
58,
|
167 |
+
59,
|
168 |
+
60,
|
169 |
+
61,
|
170 |
+
62,
|
171 |
+
63,
|
172 |
+
90,
|
173 |
+
91,
|
174 |
+
92,
|
175 |
+
93,
|
176 |
+
359,
|
177 |
+
503,
|
178 |
+
522,
|
179 |
+
542,
|
180 |
+
873,
|
181 |
+
893,
|
182 |
+
902,
|
183 |
+
918,
|
184 |
+
922,
|
185 |
+
931,
|
186 |
+
1350,
|
187 |
+
1853,
|
188 |
+
1982,
|
189 |
+
2460,
|
190 |
+
2627,
|
191 |
+
3246,
|
192 |
+
3253,
|
193 |
+
3268,
|
194 |
+
3536,
|
195 |
+
3846,
|
196 |
+
3961,
|
197 |
+
4183,
|
198 |
+
4667,
|
199 |
+
6585,
|
200 |
+
6647,
|
201 |
+
7273,
|
202 |
+
9061,
|
203 |
+
9383,
|
204 |
+
10428,
|
205 |
+
10929,
|
206 |
+
11938,
|
207 |
+
12033,
|
208 |
+
12331,
|
209 |
+
12562,
|
210 |
+
13793,
|
211 |
+
14157,
|
212 |
+
14635,
|
213 |
+
15265,
|
214 |
+
15618,
|
215 |
+
16553,
|
216 |
+
16604,
|
217 |
+
18362,
|
218 |
+
18956,
|
219 |
+
20075,
|
220 |
+
21675,
|
221 |
+
22520,
|
222 |
+
26130,
|
223 |
+
26161,
|
224 |
+
26435,
|
225 |
+
28279,
|
226 |
+
29464,
|
227 |
+
31650,
|
228 |
+
32302,
|
229 |
+
32470,
|
230 |
+
36865,
|
231 |
+
42863,
|
232 |
+
47425,
|
233 |
+
49870,
|
234 |
+
50254,
|
235 |
+
50258,
|
236 |
+
50358,
|
237 |
+
50359,
|
238 |
+
50360,
|
239 |
+
50361,
|
240 |
+
50362
|
241 |
+
],
|
242 |
+
"task": "transcribe",
|
243 |
+
"task_to_id": {
|
244 |
+
"transcribe": 50359,
|
245 |
+
"translate": 50358
|
246 |
+
},
|
247 |
+
"transformers_version": "4.42.3"
|
248 |
+
}
|
checkpoint-423/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d64a7637d1a117afebc70192eb24c4ee65ddfa1c0ba83b5a9c98dc670e1719ab
|
3 |
+
size 290403936
|
checkpoint-423/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7dfeba2729c4fe3af211e34ffc69a5ed5d99670910f0d4a8d5f1f0f0fc4cf87f
|
3 |
+
size 574811514
|
checkpoint-423/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 |
+
}
|
checkpoint-423/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12e9371f00f02031d79a62ac07aeeef5e04cf7ff88c2de89eb5f799962d5c58f
|
3 |
+
size 14244
|
checkpoint-423/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cdaa5cc5c45cfc7ba1012bb86c331bc2c92420a61d6f29ffa5a6368bb9ddf0db
|
3 |
+
size 1064
|
checkpoint-423/trainer_state.json
ADDED
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.0,
|
3 |
+
"best_model_checkpoint": "/kaggle/working/new_downloads/checkpoint-397",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 423,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.06297229219143577,
|
13 |
+
"grad_norm": 1.4191151857376099,
|
14 |
+
"learning_rate": 6.25e-05,
|
15 |
+
"loss": 4.3195,
|
16 |
+
"step": 25
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.12594458438287154,
|
20 |
+
"grad_norm": 1.5384018421173096,
|
21 |
+
"learning_rate": 0.000125,
|
22 |
+
"loss": 4.2512,
|
23 |
+
"step": 50
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.1889168765743073,
|
27 |
+
"grad_norm": 1.5718939304351807,
|
28 |
+
"learning_rate": 0.00018749999999999998,
|
29 |
+
"loss": 4.2373,
|
30 |
+
"step": 75
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.2518891687657431,
|
34 |
+
"grad_norm": 1.4780595302581787,
|
35 |
+
"learning_rate": 0.00025,
|
36 |
+
"loss": 4.2214,
|
37 |
+
"step": 100
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.3148614609571788,
|
41 |
+
"grad_norm": 1.543885588645935,
|
42 |
+
"learning_rate": 0.00029980818414322247,
|
43 |
+
"loss": 4.2333,
|
44 |
+
"step": 125
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.3778337531486146,
|
48 |
+
"grad_norm": 1.5833216905593872,
|
49 |
+
"learning_rate": 0.000298849104859335,
|
50 |
+
"loss": 4.2375,
|
51 |
+
"step": 150
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.44080604534005036,
|
55 |
+
"grad_norm": 1.8211495876312256,
|
56 |
+
"learning_rate": 0.00029789002557544756,
|
57 |
+
"loss": 4.2227,
|
58 |
+
"step": 175
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.5037783375314862,
|
62 |
+
"grad_norm": 1.5552014112472534,
|
63 |
+
"learning_rate": 0.0002969309462915601,
|
64 |
+
"loss": 4.2426,
|
65 |
+
"step": 200
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.5667506297229219,
|
69 |
+
"grad_norm": 1.5943366289138794,
|
70 |
+
"learning_rate": 0.0002959718670076726,
|
71 |
+
"loss": 4.2254,
|
72 |
+
"step": 225
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.6297229219143576,
|
76 |
+
"grad_norm": 1.9039855003356934,
|
77 |
+
"learning_rate": 0.0002950127877237851,
|
78 |
+
"loss": 4.2428,
|
79 |
+
"step": 250
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.6926952141057935,
|
83 |
+
"grad_norm": 1.624612808227539,
|
84 |
+
"learning_rate": 0.0002940537084398977,
|
85 |
+
"loss": 4.2183,
|
86 |
+
"step": 275
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.7556675062972292,
|
90 |
+
"grad_norm": 1.5801411867141724,
|
91 |
+
"learning_rate": 0.0002930946291560102,
|
92 |
+
"loss": 4.2032,
|
93 |
+
"step": 300
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.818639798488665,
|
97 |
+
"grad_norm": 1.6559851169586182,
|
98 |
+
"learning_rate": 0.0002921355498721227,
|
99 |
+
"loss": 4.1869,
|
100 |
+
"step": 325
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.8816120906801007,
|
104 |
+
"grad_norm": 1.6399421691894531,
|
105 |
+
"learning_rate": 0.00029117647058823524,
|
106 |
+
"loss": 4.2117,
|
107 |
+
"step": 350
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.9445843828715366,
|
111 |
+
"grad_norm": 1.6710602045059204,
|
112 |
+
"learning_rate": 0.0002902173913043478,
|
113 |
+
"loss": 4.2257,
|
114 |
+
"step": 375
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 1.0,
|
118 |
+
"eval_cer": 1.0,
|
119 |
+
"eval_loss": 4.691751956939697,
|
120 |
+
"eval_runtime": 1056.28,
|
121 |
+
"eval_samples_per_second": 2.082,
|
122 |
+
"eval_steps_per_second": 0.017,
|
123 |
+
"eval_wer": 1.0,
|
124 |
+
"step": 397
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 2.8368794326241136,
|
128 |
+
"grad_norm": 1.1363143920898438,
|
129 |
+
"learning_rate": 0.00026209386281588447,
|
130 |
+
"loss": 3.967,
|
131 |
+
"step": 400
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 3.0,
|
135 |
+
"eval_cer": 1.0,
|
136 |
+
"eval_loss": 4.709719657897949,
|
137 |
+
"eval_runtime": 540.9535,
|
138 |
+
"eval_samples_per_second": 4.065,
|
139 |
+
"eval_steps_per_second": 0.017,
|
140 |
+
"eval_wer": 1.0,
|
141 |
+
"step": 423
|
142 |
+
}
|
143 |
+
],
|
144 |
+
"logging_steps": 25,
|
145 |
+
"max_steps": 2820,
|
146 |
+
"num_input_tokens_seen": 0,
|
147 |
+
"num_train_epochs": 20,
|
148 |
+
"save_steps": 500,
|
149 |
+
"stateful_callbacks": {
|
150 |
+
"TrainerControl": {
|
151 |
+
"args": {
|
152 |
+
"should_epoch_stop": false,
|
153 |
+
"should_evaluate": false,
|
154 |
+
"should_log": false,
|
155 |
+
"should_save": true,
|
156 |
+
"should_training_stop": false
|
157 |
+
},
|
158 |
+
"attributes": {}
|
159 |
+
}
|
160 |
+
},
|
161 |
+
"total_flos": 3.8935455694848e+18,
|
162 |
+
"train_batch_size": 360,
|
163 |
+
"trial_name": null,
|
164 |
+
"trial_params": null
|
165 |
+
}
|
checkpoint-423/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9aa0e436ad246aaf6463a35edf4105b71e18a4052887d3d74a658cc3acfc09f2
|
3 |
+
size 5304
|
checkpoint-564/config.json
ADDED
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/content/new_downloads/checkpoint-397",
|
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": 512,
|
17 |
+
"decoder_attention_heads": 8,
|
18 |
+
"decoder_ffn_dim": 2048,
|
19 |
+
"decoder_layerdrop": 0.0,
|
20 |
+
"decoder_layers": 6,
|
21 |
+
"decoder_start_token_id": 50257,
|
22 |
+
"dropout": 0.0,
|
23 |
+
"encoder_attention_heads": 8,
|
24 |
+
"encoder_ffn_dim": 2048,
|
25 |
+
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 6,
|
27 |
+
"eos_token_id": 50257,
|
28 |
+
"forced_decoder_ids": [
|
29 |
+
[
|
30 |
+
1,
|
31 |
+
50259
|
32 |
+
],
|
33 |
+
[
|
34 |
+
2,
|
35 |
+
50359
|
36 |
+
],
|
37 |
+
[
|
38 |
+
3,
|
39 |
+
50363
|
40 |
+
]
|
41 |
+
],
|
42 |
+
"init_std": 0.02,
|
43 |
+
"is_encoder_decoder": true,
|
44 |
+
"mask_feature_length": 10,
|
45 |
+
"mask_feature_min_masks": 0,
|
46 |
+
"mask_feature_prob": 0.0,
|
47 |
+
"mask_time_length": 10,
|
48 |
+
"mask_time_min_masks": 2,
|
49 |
+
"mask_time_prob": 0.05,
|
50 |
+
"max_length": 448,
|
51 |
+
"max_source_positions": 1500,
|
52 |
+
"max_target_positions": 448,
|
53 |
+
"median_filter_width": 7,
|
54 |
+
"model_type": "whisper",
|
55 |
+
"num_hidden_layers": 6,
|
56 |
+
"num_mel_bins": 80,
|
57 |
+
"pad_token_id": 50257,
|
58 |
+
"scale_embedding": false,
|
59 |
+
"suppress_tokens": [
|
60 |
+
1,
|
61 |
+
2,
|
62 |
+
7,
|
63 |
+
8,
|
64 |
+
9,
|
65 |
+
10,
|
66 |
+
14,
|
67 |
+
25,
|
68 |
+
26,
|
69 |
+
27,
|
70 |
+
28,
|
71 |
+
29,
|
72 |
+
31,
|
73 |
+
58,
|
74 |
+
59,
|
75 |
+
60,
|
76 |
+
61,
|
77 |
+
62,
|
78 |
+
63,
|
79 |
+
90,
|
80 |
+
91,
|
81 |
+
92,
|
82 |
+
93,
|
83 |
+
359,
|
84 |
+
503,
|
85 |
+
522,
|
86 |
+
542,
|
87 |
+
873,
|
88 |
+
893,
|
89 |
+
902,
|
90 |
+
918,
|
91 |
+
922,
|
92 |
+
931,
|
93 |
+
1350,
|
94 |
+
1853,
|
95 |
+
1982,
|
96 |
+
2460,
|
97 |
+
2627,
|
98 |
+
3246,
|
99 |
+
3253,
|
100 |
+
3268,
|
101 |
+
3536,
|
102 |
+
3846,
|
103 |
+
3961,
|
104 |
+
4183,
|
105 |
+
4667,
|
106 |
+
6585,
|
107 |
+
6647,
|
108 |
+
7273,
|
109 |
+
9061,
|
110 |
+
9383,
|
111 |
+
10428,
|
112 |
+
10929,
|
113 |
+
11938,
|
114 |
+
12033,
|
115 |
+
12331,
|
116 |
+
12562,
|
117 |
+
13793,
|
118 |
+
14157,
|
119 |
+
14635,
|
120 |
+
15265,
|
121 |
+
15618,
|
122 |
+
16553,
|
123 |
+
16604,
|
124 |
+
18362,
|
125 |
+
18956,
|
126 |
+
20075,
|
127 |
+
21675,
|
128 |
+
22520,
|
129 |
+
26130,
|
130 |
+
26161,
|
131 |
+
26435,
|
132 |
+
28279,
|
133 |
+
29464,
|
134 |
+
31650,
|
135 |
+
32302,
|
136 |
+
32470,
|
137 |
+
36865,
|
138 |
+
42863,
|
139 |
+
47425,
|
140 |
+
49870,
|
141 |
+
50254,
|
142 |
+
50258,
|
143 |
+
50358,
|
144 |
+
50359,
|
145 |
+
50360,
|
146 |
+
50361,
|
147 |
+
50362
|
148 |
+
],
|
149 |
+
"torch_dtype": "float32",
|
150 |
+
"transformers_version": "4.42.3",
|
151 |
+
"use_cache": true,
|
152 |
+
"use_weighted_layer_sum": false,
|
153 |
+
"vocab_size": 51865
|
154 |
+
}
|
checkpoint-564/generation_config.json
ADDED
@@ -0,0 +1,248 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alignment_heads": [
|
3 |
+
[
|
4 |
+
3,
|
5 |
+
1
|
6 |
+
],
|
7 |
+
[
|
8 |
+
4,
|
9 |
+
2
|
10 |
+
],
|
11 |
+
[
|
12 |
+
4,
|
13 |
+
3
|
14 |
+
],
|
15 |
+
[
|
16 |
+
4,
|
17 |
+
7
|
18 |
+
],
|
19 |
+
[
|
20 |
+
5,
|
21 |
+
1
|
22 |
+
],
|
23 |
+
[
|
24 |
+
5,
|
25 |
+
2
|
26 |
+
],
|
27 |
+
[
|
28 |
+
5,
|
29 |
+
4
|
30 |
+
],
|
31 |
+
[
|
32 |
+
5,
|
33 |
+
6
|
34 |
+
]
|
35 |
+
],
|
36 |
+
"begin_suppress_tokens": [
|
37 |
+
220,
|
38 |
+
50257
|
39 |
+
],
|
40 |
+
"bos_token_id": 50257,
|
41 |
+
"decoder_start_token_id": 50258,
|
42 |
+
"eos_token_id": 50257,
|
43 |
+
"is_multilingual": true,
|
44 |
+
"lang_to_id": {
|
45 |
+
"<|af|>": 50327,
|
46 |
+
"<|am|>": 50334,
|
47 |
+
"<|ar|>": 50272,
|
48 |
+
"<|as|>": 50350,
|
49 |
+
"<|az|>": 50304,
|
50 |
+
"<|ba|>": 50355,
|
51 |
+
"<|be|>": 50330,
|
52 |
+
"<|bg|>": 50292,
|
53 |
+
"<|bn|>": 50302,
|
54 |
+
"<|bo|>": 50347,
|
55 |
+
"<|br|>": 50309,
|
56 |
+
"<|bs|>": 50315,
|
57 |
+
"<|ca|>": 50270,
|
58 |
+
"<|cs|>": 50283,
|
59 |
+
"<|cy|>": 50297,
|
60 |
+
"<|da|>": 50285,
|
61 |
+
"<|de|>": 50261,
|
62 |
+
"<|el|>": 50281,
|
63 |
+
"<|en|>": 50259,
|
64 |
+
"<|es|>": 50262,
|
65 |
+
"<|et|>": 50307,
|
66 |
+
"<|eu|>": 50310,
|
67 |
+
"<|fa|>": 50300,
|
68 |
+
"<|fi|>": 50277,
|
69 |
+
"<|fo|>": 50338,
|
70 |
+
"<|fr|>": 50265,
|
71 |
+
"<|gl|>": 50319,
|
72 |
+
"<|gu|>": 50333,
|
73 |
+
"<|haw|>": 50352,
|
74 |
+
"<|ha|>": 50354,
|
75 |
+
"<|he|>": 50279,
|
76 |
+
"<|hi|>": 50276,
|
77 |
+
"<|hr|>": 50291,
|
78 |
+
"<|ht|>": 50339,
|
79 |
+
"<|hu|>": 50286,
|
80 |
+
"<|hy|>": 50312,
|
81 |
+
"<|id|>": 50275,
|
82 |
+
"<|is|>": 50311,
|
83 |
+
"<|it|>": 50274,
|
84 |
+
"<|ja|>": 50266,
|
85 |
+
"<|jw|>": 50356,
|
86 |
+
"<|ka|>": 50329,
|
87 |
+
"<|kk|>": 50316,
|
88 |
+
"<|km|>": 50323,
|
89 |
+
"<|kn|>": 50306,
|
90 |
+
"<|ko|>": 50264,
|
91 |
+
"<|la|>": 50294,
|
92 |
+
"<|lb|>": 50345,
|
93 |
+
"<|ln|>": 50353,
|
94 |
+
"<|lo|>": 50336,
|
95 |
+
"<|lt|>": 50293,
|
96 |
+
"<|lv|>": 50301,
|
97 |
+
"<|mg|>": 50349,
|
98 |
+
"<|mi|>": 50295,
|
99 |
+
"<|mk|>": 50308,
|
100 |
+
"<|ml|>": 50296,
|
101 |
+
"<|mn|>": 50314,
|
102 |
+
"<|mr|>": 50320,
|
103 |
+
"<|ms|>": 50282,
|
104 |
+
"<|mt|>": 50343,
|
105 |
+
"<|my|>": 50346,
|
106 |
+
"<|ne|>": 50313,
|
107 |
+
"<|nl|>": 50271,
|
108 |
+
"<|nn|>": 50342,
|
109 |
+
"<|no|>": 50288,
|
110 |
+
"<|oc|>": 50328,
|
111 |
+
"<|pa|>": 50321,
|
112 |
+
"<|pl|>": 50269,
|
113 |
+
"<|ps|>": 50340,
|
114 |
+
"<|pt|>": 50267,
|
115 |
+
"<|ro|>": 50284,
|
116 |
+
"<|ru|>": 50263,
|
117 |
+
"<|sa|>": 50344,
|
118 |
+
"<|sd|>": 50332,
|
119 |
+
"<|si|>": 50322,
|
120 |
+
"<|sk|>": 50298,
|
121 |
+
"<|sl|>": 50305,
|
122 |
+
"<|sn|>": 50324,
|
123 |
+
"<|so|>": 50326,
|
124 |
+
"<|sq|>": 50317,
|
125 |
+
"<|sr|>": 50303,
|
126 |
+
"<|su|>": 50357,
|
127 |
+
"<|sv|>": 50273,
|
128 |
+
"<|sw|>": 50318,
|
129 |
+
"<|ta|>": 50287,
|
130 |
+
"<|te|>": 50299,
|
131 |
+
"<|tg|>": 50331,
|
132 |
+
"<|th|>": 50289,
|
133 |
+
"<|tk|>": 50341,
|
134 |
+
"<|tl|>": 50348,
|
135 |
+
"<|tr|>": 50268,
|
136 |
+
"<|tt|>": 50351,
|
137 |
+
"<|uk|>": 50280,
|
138 |
+
"<|ur|>": 50290,
|
139 |
+
"<|uz|>": 50337,
|
140 |
+
"<|vi|>": 50278,
|
141 |
+
"<|yi|>": 50335,
|
142 |
+
"<|yo|>": 50325,
|
143 |
+
"<|zh|>": 50260
|
144 |
+
},
|
145 |
+
"language": "arabic",
|
146 |
+
"max_initial_timestamp_index": 50,
|
147 |
+
"max_length": 448,
|
148 |
+
"no_timestamps_token_id": 50363,
|
149 |
+
"pad_token_id": 50257,
|
150 |
+
"prev_sot_token_id": 50361,
|
151 |
+
"return_timestamps": false,
|
152 |
+
"suppress_tokens": [
|
153 |
+
1,
|
154 |
+
2,
|
155 |
+
7,
|
156 |
+
8,
|
157 |
+
9,
|
158 |
+
10,
|
159 |
+
14,
|
160 |
+
25,
|
161 |
+
26,
|
162 |
+
27,
|
163 |
+
28,
|
164 |
+
29,
|
165 |
+
31,
|
166 |
+
58,
|
167 |
+
59,
|
168 |
+
60,
|
169 |
+
61,
|
170 |
+
62,
|
171 |
+
63,
|
172 |
+
90,
|
173 |
+
91,
|
174 |
+
92,
|
175 |
+
93,
|
176 |
+
359,
|
177 |
+
503,
|
178 |
+
522,
|
179 |
+
542,
|
180 |
+
873,
|
181 |
+
893,
|
182 |
+
902,
|
183 |
+
918,
|
184 |
+
922,
|
185 |
+
931,
|
186 |
+
1350,
|
187 |
+
1853,
|
188 |
+
1982,
|
189 |
+
2460,
|
190 |
+
2627,
|
191 |
+
3246,
|
192 |
+
3253,
|
193 |
+
3268,
|
194 |
+
3536,
|
195 |
+
3846,
|
196 |
+
3961,
|
197 |
+
4183,
|
198 |
+
4667,
|
199 |
+
6585,
|
200 |
+
6647,
|
201 |
+
7273,
|
202 |
+
9061,
|
203 |
+
9383,
|
204 |
+
10428,
|
205 |
+
10929,
|
206 |
+
11938,
|
207 |
+
12033,
|
208 |
+
12331,
|
209 |
+
12562,
|
210 |
+
13793,
|
211 |
+
14157,
|
212 |
+
14635,
|
213 |
+
15265,
|
214 |
+
15618,
|
215 |
+
16553,
|
216 |
+
16604,
|
217 |
+
18362,
|
218 |
+
18956,
|
219 |
+
20075,
|
220 |
+
21675,
|
221 |
+
22520,
|
222 |
+
26130,
|
223 |
+
26161,
|
224 |
+
26435,
|
225 |
+
28279,
|
226 |
+
29464,
|
227 |
+
31650,
|
228 |
+
32302,
|
229 |
+
32470,
|
230 |
+
36865,
|
231 |
+
42863,
|
232 |
+
47425,
|
233 |
+
49870,
|
234 |
+
50254,
|
235 |
+
50258,
|
236 |
+
50358,
|
237 |
+
50359,
|
238 |
+
50360,
|
239 |
+
50361,
|
240 |
+
50362
|
241 |
+
],
|
242 |
+
"task": "transcribe",
|
243 |
+
"task_to_id": {
|
244 |
+
"transcribe": 50359,
|
245 |
+
"translate": 50358
|
246 |
+
},
|
247 |
+
"transformers_version": "4.42.3"
|
248 |
+
}
|
checkpoint-564/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fcf3866a23f5f7affe24c1a452c3aeceb224fdec1d370ae26215a9e64d5f8ef
|
3 |
+
size 290403936
|
checkpoint-564/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8aa3622a8aca9ecfa49cbb7ffe03d96c2a6dc0813d9a5b8e3169bfdde63b1ef
|
3 |
+
size 574811514
|
checkpoint-564/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 |
+
}
|
checkpoint-564/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1372c74b35b8315007da0086ce9024f7d66e5eda4d2d38456981d7482ffc070
|
3 |
+
size 14244
|
checkpoint-564/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:161135b256dea4cac0969515d349e6847e1bd9796792e573380d6f3e7c83c291
|
3 |
+
size 1064
|
checkpoint-564/trainer_state.json
ADDED
@@ -0,0 +1,217 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.0,
|
3 |
+
"best_model_checkpoint": "/kaggle/working/new_downloads/checkpoint-397",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 564,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.06297229219143577,
|
13 |
+
"grad_norm": 1.4191151857376099,
|
14 |
+
"learning_rate": 6.25e-05,
|
15 |
+
"loss": 4.3195,
|
16 |
+
"step": 25
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.12594458438287154,
|
20 |
+
"grad_norm": 1.5384018421173096,
|
21 |
+
"learning_rate": 0.000125,
|
22 |
+
"loss": 4.2512,
|
23 |
+
"step": 50
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.1889168765743073,
|
27 |
+
"grad_norm": 1.5718939304351807,
|
28 |
+
"learning_rate": 0.00018749999999999998,
|
29 |
+
"loss": 4.2373,
|
30 |
+
"step": 75
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.2518891687657431,
|
34 |
+
"grad_norm": 1.4780595302581787,
|
35 |
+
"learning_rate": 0.00025,
|
36 |
+
"loss": 4.2214,
|
37 |
+
"step": 100
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.3148614609571788,
|
41 |
+
"grad_norm": 1.543885588645935,
|
42 |
+
"learning_rate": 0.00029980818414322247,
|
43 |
+
"loss": 4.2333,
|
44 |
+
"step": 125
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.3778337531486146,
|
48 |
+
"grad_norm": 1.5833216905593872,
|
49 |
+
"learning_rate": 0.000298849104859335,
|
50 |
+
"loss": 4.2375,
|
51 |
+
"step": 150
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.44080604534005036,
|
55 |
+
"grad_norm": 1.8211495876312256,
|
56 |
+
"learning_rate": 0.00029789002557544756,
|
57 |
+
"loss": 4.2227,
|
58 |
+
"step": 175
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.5037783375314862,
|
62 |
+
"grad_norm": 1.5552014112472534,
|
63 |
+
"learning_rate": 0.0002969309462915601,
|
64 |
+
"loss": 4.2426,
|
65 |
+
"step": 200
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.5667506297229219,
|
69 |
+
"grad_norm": 1.5943366289138794,
|
70 |
+
"learning_rate": 0.0002959718670076726,
|
71 |
+
"loss": 4.2254,
|
72 |
+
"step": 225
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.6297229219143576,
|
76 |
+
"grad_norm": 1.9039855003356934,
|
77 |
+
"learning_rate": 0.0002950127877237851,
|
78 |
+
"loss": 4.2428,
|
79 |
+
"step": 250
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.6926952141057935,
|
83 |
+
"grad_norm": 1.624612808227539,
|
84 |
+
"learning_rate": 0.0002940537084398977,
|
85 |
+
"loss": 4.2183,
|
86 |
+
"step": 275
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.7556675062972292,
|
90 |
+
"grad_norm": 1.5801411867141724,
|
91 |
+
"learning_rate": 0.0002930946291560102,
|
92 |
+
"loss": 4.2032,
|
93 |
+
"step": 300
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.818639798488665,
|
97 |
+
"grad_norm": 1.6559851169586182,
|
98 |
+
"learning_rate": 0.0002921355498721227,
|
99 |
+
"loss": 4.1869,
|
100 |
+
"step": 325
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.8816120906801007,
|
104 |
+
"grad_norm": 1.6399421691894531,
|
105 |
+
"learning_rate": 0.00029117647058823524,
|
106 |
+
"loss": 4.2117,
|
107 |
+
"step": 350
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.9445843828715366,
|
111 |
+
"grad_norm": 1.6710602045059204,
|
112 |
+
"learning_rate": 0.0002902173913043478,
|
113 |
+
"loss": 4.2257,
|
114 |
+
"step": 375
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 1.0,
|
118 |
+
"eval_cer": 1.0,
|
119 |
+
"eval_loss": 4.691751956939697,
|
120 |
+
"eval_runtime": 1056.28,
|
121 |
+
"eval_samples_per_second": 2.082,
|
122 |
+
"eval_steps_per_second": 0.017,
|
123 |
+
"eval_wer": 1.0,
|
124 |
+
"step": 397
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 2.8368794326241136,
|
128 |
+
"grad_norm": 1.1363143920898438,
|
129 |
+
"learning_rate": 0.00026209386281588447,
|
130 |
+
"loss": 3.967,
|
131 |
+
"step": 400
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 3.0,
|
135 |
+
"eval_cer": 1.0,
|
136 |
+
"eval_loss": 4.709719657897949,
|
137 |
+
"eval_runtime": 540.9535,
|
138 |
+
"eval_samples_per_second": 4.065,
|
139 |
+
"eval_steps_per_second": 0.017,
|
140 |
+
"eval_wer": 1.0,
|
141 |
+
"step": 423
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 3.0141843971631204,
|
145 |
+
"grad_norm": 1.0413663387298584,
|
146 |
+
"learning_rate": 0.0002593862815884476,
|
147 |
+
"loss": 3.8784,
|
148 |
+
"step": 425
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 3.1914893617021276,
|
152 |
+
"grad_norm": 1.220971703529358,
|
153 |
+
"learning_rate": 0.0002566787003610108,
|
154 |
+
"loss": 3.7718,
|
155 |
+
"step": 450
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 3.368794326241135,
|
159 |
+
"grad_norm": 1.127140760421753,
|
160 |
+
"learning_rate": 0.000253971119133574,
|
161 |
+
"loss": 3.7725,
|
162 |
+
"step": 475
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 3.546099290780142,
|
166 |
+
"grad_norm": 1.1641333103179932,
|
167 |
+
"learning_rate": 0.00025126353790613716,
|
168 |
+
"loss": 3.778,
|
169 |
+
"step": 500
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 3.723404255319149,
|
173 |
+
"grad_norm": 1.1840986013412476,
|
174 |
+
"learning_rate": 0.00024855595667870036,
|
175 |
+
"loss": 3.7789,
|
176 |
+
"step": 525
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 3.900709219858156,
|
180 |
+
"grad_norm": 1.1780372858047485,
|
181 |
+
"learning_rate": 0.0002458483754512635,
|
182 |
+
"loss": 3.7835,
|
183 |
+
"step": 550
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 4.0,
|
187 |
+
"eval_cer": 1.0,
|
188 |
+
"eval_loss": 4.711414337158203,
|
189 |
+
"eval_runtime": 483.9002,
|
190 |
+
"eval_samples_per_second": 4.544,
|
191 |
+
"eval_steps_per_second": 0.019,
|
192 |
+
"eval_wer": 1.0,
|
193 |
+
"step": 564
|
194 |
+
}
|
195 |
+
],
|
196 |
+
"logging_steps": 25,
|
197 |
+
"max_steps": 2820,
|
198 |
+
"num_input_tokens_seen": 0,
|
199 |
+
"num_train_epochs": 20,
|
200 |
+
"save_steps": 500,
|
201 |
+
"stateful_callbacks": {
|
202 |
+
"TrainerControl": {
|
203 |
+
"args": {
|
204 |
+
"should_epoch_stop": false,
|
205 |
+
"should_evaluate": false,
|
206 |
+
"should_log": false,
|
207 |
+
"should_save": true,
|
208 |
+
"should_training_stop": false
|
209 |
+
},
|
210 |
+
"attributes": {}
|
211 |
+
}
|
212 |
+
},
|
213 |
+
"total_flos": 7.1829202747392e+18,
|
214 |
+
"train_batch_size": 360,
|
215 |
+
"trial_name": null,
|
216 |
+
"trial_params": null
|
217 |
+
}
|
checkpoint-564/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9aa0e436ad246aaf6463a35edf4105b71e18a4052887d3d74a658cc3acfc09f2
|
3 |
+
size 5304
|
checkpoint-705/config.json
ADDED
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/content/new_downloads/checkpoint-397",
|
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": 512,
|
17 |
+
"decoder_attention_heads": 8,
|
18 |
+
"decoder_ffn_dim": 2048,
|
19 |
+
"decoder_layerdrop": 0.0,
|
20 |
+
"decoder_layers": 6,
|
21 |
+
"decoder_start_token_id": 50257,
|
22 |
+
"dropout": 0.0,
|
23 |
+
"encoder_attention_heads": 8,
|
24 |
+
"encoder_ffn_dim": 2048,
|
25 |
+
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 6,
|
27 |
+
"eos_token_id": 50257,
|
28 |
+
"forced_decoder_ids": [
|
29 |
+
[
|
30 |
+
1,
|
31 |
+
50259
|
32 |
+
],
|
33 |
+
[
|
34 |
+
2,
|
35 |
+
50359
|
36 |
+
],
|
37 |
+
[
|
38 |
+
3,
|
39 |
+
50363
|
40 |
+
]
|
41 |
+
],
|
42 |
+
"init_std": 0.02,
|
43 |
+
"is_encoder_decoder": true,
|
44 |
+
"mask_feature_length": 10,
|
45 |
+
"mask_feature_min_masks": 0,
|
46 |
+
"mask_feature_prob": 0.0,
|
47 |
+
"mask_time_length": 10,
|
48 |
+
"mask_time_min_masks": 2,
|
49 |
+
"mask_time_prob": 0.05,
|
50 |
+
"max_length": 448,
|
51 |
+
"max_source_positions": 1500,
|
52 |
+
"max_target_positions": 448,
|
53 |
+
"median_filter_width": 7,
|
54 |
+
"model_type": "whisper",
|
55 |
+
"num_hidden_layers": 6,
|
56 |
+
"num_mel_bins": 80,
|
57 |
+
"pad_token_id": 50257,
|
58 |
+
"scale_embedding": false,
|
59 |
+
"suppress_tokens": [
|
60 |
+
1,
|
61 |
+
2,
|
62 |
+
7,
|
63 |
+
8,
|
64 |
+
9,
|
65 |
+
10,
|
66 |
+
14,
|
67 |
+
25,
|
68 |
+
26,
|
69 |
+
27,
|
70 |
+
28,
|
71 |
+
29,
|
72 |
+
31,
|
73 |
+
58,
|
74 |
+
59,
|
75 |
+
60,
|
76 |
+
61,
|
77 |
+
62,
|
78 |
+
63,
|
79 |
+
90,
|
80 |
+
91,
|
81 |
+
92,
|
82 |
+
93,
|
83 |
+
359,
|
84 |
+
503,
|
85 |
+
522,
|
86 |
+
542,
|
87 |
+
873,
|
88 |
+
893,
|
89 |
+
902,
|
90 |
+
918,
|
91 |
+
922,
|
92 |
+
931,
|
93 |
+
1350,
|
94 |
+
1853,
|
95 |
+
1982,
|
96 |
+
2460,
|
97 |
+
2627,
|
98 |
+
3246,
|
99 |
+
3253,
|
100 |
+
3268,
|
101 |
+
3536,
|
102 |
+
3846,
|
103 |
+
3961,
|
104 |
+
4183,
|
105 |
+
4667,
|
106 |
+
6585,
|
107 |
+
6647,
|
108 |
+
7273,
|
109 |
+
9061,
|
110 |
+
9383,
|
111 |
+
10428,
|
112 |
+
10929,
|
113 |
+
11938,
|
114 |
+
12033,
|
115 |
+
12331,
|
116 |
+
12562,
|
117 |
+
13793,
|
118 |
+
14157,
|
119 |
+
14635,
|
120 |
+
15265,
|
121 |
+
15618,
|
122 |
+
16553,
|
123 |
+
16604,
|
124 |
+
18362,
|
125 |
+
18956,
|
126 |
+
20075,
|
127 |
+
21675,
|
128 |
+
22520,
|
129 |
+
26130,
|
130 |
+
26161,
|
131 |
+
26435,
|
132 |
+
28279,
|
133 |
+
29464,
|
134 |
+
31650,
|
135 |
+
32302,
|
136 |
+
32470,
|
137 |
+
36865,
|
138 |
+
42863,
|
139 |
+
47425,
|
140 |
+
49870,
|
141 |
+
50254,
|
142 |
+
50258,
|
143 |
+
50358,
|
144 |
+
50359,
|
145 |
+
50360,
|
146 |
+
50361,
|
147 |
+
50362
|
148 |
+
],
|
149 |
+
"torch_dtype": "float32",
|
150 |
+
"transformers_version": "4.42.3",
|
151 |
+
"use_cache": true,
|
152 |
+
"use_weighted_layer_sum": false,
|
153 |
+
"vocab_size": 51865
|
154 |
+
}
|
checkpoint-705/generation_config.json
ADDED
@@ -0,0 +1,248 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alignment_heads": [
|
3 |
+
[
|
4 |
+
3,
|
5 |
+
1
|
6 |
+
],
|
7 |
+
[
|
8 |
+
4,
|
9 |
+
2
|
10 |
+
],
|
11 |
+
[
|
12 |
+
4,
|
13 |
+
3
|
14 |
+
],
|
15 |
+
[
|
16 |
+
4,
|
17 |
+
7
|
18 |
+
],
|
19 |
+
[
|
20 |
+
5,
|
21 |
+
1
|
22 |
+
],
|
23 |
+
[
|
24 |
+
5,
|
25 |
+
2
|
26 |
+
],
|
27 |
+
[
|
28 |
+
5,
|
29 |
+
4
|
30 |
+
],
|
31 |
+
[
|
32 |
+
5,
|
33 |
+
6
|
34 |
+
]
|
35 |
+
],
|
36 |
+
"begin_suppress_tokens": [
|
37 |
+
220,
|
38 |
+
50257
|
39 |
+
],
|
40 |
+
"bos_token_id": 50257,
|
41 |
+
"decoder_start_token_id": 50258,
|
42 |
+
"eos_token_id": 50257,
|
43 |
+
"is_multilingual": true,
|
44 |
+
"lang_to_id": {
|
45 |
+
"<|af|>": 50327,
|
46 |
+
"<|am|>": 50334,
|
47 |
+
"<|ar|>": 50272,
|
48 |
+
"<|as|>": 50350,
|
49 |
+
"<|az|>": 50304,
|
50 |
+
"<|ba|>": 50355,
|
51 |
+
"<|be|>": 50330,
|
52 |
+
"<|bg|>": 50292,
|
53 |
+
"<|bn|>": 50302,
|
54 |
+
"<|bo|>": 50347,
|
55 |
+
"<|br|>": 50309,
|
56 |
+
"<|bs|>": 50315,
|
57 |
+
"<|ca|>": 50270,
|
58 |
+
"<|cs|>": 50283,
|
59 |
+
"<|cy|>": 50297,
|
60 |
+
"<|da|>": 50285,
|
61 |
+
"<|de|>": 50261,
|
62 |
+
"<|el|>": 50281,
|
63 |
+
"<|en|>": 50259,
|
64 |
+
"<|es|>": 50262,
|
65 |
+
"<|et|>": 50307,
|
66 |
+
"<|eu|>": 50310,
|
67 |
+
"<|fa|>": 50300,
|
68 |
+
"<|fi|>": 50277,
|
69 |
+
"<|fo|>": 50338,
|
70 |
+
"<|fr|>": 50265,
|
71 |
+
"<|gl|>": 50319,
|
72 |
+
"<|gu|>": 50333,
|
73 |
+
"<|haw|>": 50352,
|
74 |
+
"<|ha|>": 50354,
|
75 |
+
"<|he|>": 50279,
|
76 |
+
"<|hi|>": 50276,
|
77 |
+
"<|hr|>": 50291,
|
78 |
+
"<|ht|>": 50339,
|
79 |
+
"<|hu|>": 50286,
|
80 |
+
"<|hy|>": 50312,
|
81 |
+
"<|id|>": 50275,
|
82 |
+
"<|is|>": 50311,
|
83 |
+
"<|it|>": 50274,
|
84 |
+
"<|ja|>": 50266,
|
85 |
+
"<|jw|>": 50356,
|
86 |
+
"<|ka|>": 50329,
|
87 |
+
"<|kk|>": 50316,
|
88 |
+
"<|km|>": 50323,
|
89 |
+
"<|kn|>": 50306,
|
90 |
+
"<|ko|>": 50264,
|
91 |
+
"<|la|>": 50294,
|
92 |
+
"<|lb|>": 50345,
|
93 |
+
"<|ln|>": 50353,
|
94 |
+
"<|lo|>": 50336,
|
95 |
+
"<|lt|>": 50293,
|
96 |
+
"<|lv|>": 50301,
|
97 |
+
"<|mg|>": 50349,
|
98 |
+
"<|mi|>": 50295,
|
99 |
+
"<|mk|>": 50308,
|
100 |
+
"<|ml|>": 50296,
|
101 |
+
"<|mn|>": 50314,
|
102 |
+
"<|mr|>": 50320,
|
103 |
+
"<|ms|>": 50282,
|
104 |
+
"<|mt|>": 50343,
|
105 |
+
"<|my|>": 50346,
|
106 |
+
"<|ne|>": 50313,
|
107 |
+
"<|nl|>": 50271,
|
108 |
+
"<|nn|>": 50342,
|
109 |
+
"<|no|>": 50288,
|
110 |
+
"<|oc|>": 50328,
|
111 |
+
"<|pa|>": 50321,
|
112 |
+
"<|pl|>": 50269,
|
113 |
+
"<|ps|>": 50340,
|
114 |
+
"<|pt|>": 50267,
|
115 |
+
"<|ro|>": 50284,
|
116 |
+
"<|ru|>": 50263,
|
117 |
+
"<|sa|>": 50344,
|
118 |
+
"<|sd|>": 50332,
|
119 |
+
"<|si|>": 50322,
|
120 |
+
"<|sk|>": 50298,
|
121 |
+
"<|sl|>": 50305,
|
122 |
+
"<|sn|>": 50324,
|
123 |
+
"<|so|>": 50326,
|
124 |
+
"<|sq|>": 50317,
|
125 |
+
"<|sr|>": 50303,
|
126 |
+
"<|su|>": 50357,
|
127 |
+
"<|sv|>": 50273,
|
128 |
+
"<|sw|>": 50318,
|
129 |
+
"<|ta|>": 50287,
|
130 |
+
"<|te|>": 50299,
|
131 |
+
"<|tg|>": 50331,
|
132 |
+
"<|th|>": 50289,
|
133 |
+
"<|tk|>": 50341,
|
134 |
+
"<|tl|>": 50348,
|
135 |
+
"<|tr|>": 50268,
|
136 |
+
"<|tt|>": 50351,
|
137 |
+
"<|uk|>": 50280,
|
138 |
+
"<|ur|>": 50290,
|
139 |
+
"<|uz|>": 50337,
|
140 |
+
"<|vi|>": 50278,
|
141 |
+
"<|yi|>": 50335,
|
142 |
+
"<|yo|>": 50325,
|
143 |
+
"<|zh|>": 50260
|
144 |
+
},
|
145 |
+
"language": "arabic",
|
146 |
+
"max_initial_timestamp_index": 50,
|
147 |
+
"max_length": 448,
|
148 |
+
"no_timestamps_token_id": 50363,
|
149 |
+
"pad_token_id": 50257,
|
150 |
+
"prev_sot_token_id": 50361,
|
151 |
+
"return_timestamps": false,
|
152 |
+
"suppress_tokens": [
|
153 |
+
1,
|
154 |
+
2,
|
155 |
+
7,
|
156 |
+
8,
|
157 |
+
9,
|
158 |
+
10,
|
159 |
+
14,
|
160 |
+
25,
|
161 |
+
26,
|
162 |
+
27,
|
163 |
+
28,
|
164 |
+
29,
|
165 |
+
31,
|
166 |
+
58,
|
167 |
+
59,
|
168 |
+
60,
|
169 |
+
61,
|
170 |
+
62,
|
171 |
+
63,
|
172 |
+
90,
|
173 |
+
91,
|
174 |
+
92,
|
175 |
+
93,
|
176 |
+
359,
|
177 |
+
503,
|
178 |
+
522,
|
179 |
+
542,
|
180 |
+
873,
|
181 |
+
893,
|
182 |
+
902,
|
183 |
+
918,
|
184 |
+
922,
|
185 |
+
931,
|
186 |
+
1350,
|
187 |
+
1853,
|
188 |
+
1982,
|
189 |
+
2460,
|
190 |
+
2627,
|
191 |
+
3246,
|
192 |
+
3253,
|
193 |
+
3268,
|
194 |
+
3536,
|
195 |
+
3846,
|
196 |
+
3961,
|
197 |
+
4183,
|
198 |
+
4667,
|
199 |
+
6585,
|
200 |
+
6647,
|
201 |
+
7273,
|
202 |
+
9061,
|
203 |
+
9383,
|
204 |
+
10428,
|
205 |
+
10929,
|
206 |
+
11938,
|
207 |
+
12033,
|
208 |
+
12331,
|
209 |
+
12562,
|
210 |
+
13793,
|
211 |
+
14157,
|
212 |
+
14635,
|
213 |
+
15265,
|
214 |
+
15618,
|
215 |
+
16553,
|
216 |
+
16604,
|
217 |
+
18362,
|
218 |
+
18956,
|
219 |
+
20075,
|
220 |
+
21675,
|
221 |
+
22520,
|
222 |
+
26130,
|
223 |
+
26161,
|
224 |
+
26435,
|
225 |
+
28279,
|
226 |
+
29464,
|
227 |
+
31650,
|
228 |
+
32302,
|
229 |
+
32470,
|
230 |
+
36865,
|
231 |
+
42863,
|
232 |
+
47425,
|
233 |
+
49870,
|
234 |
+
50254,
|
235 |
+
50258,
|
236 |
+
50358,
|
237 |
+
50359,
|
238 |
+
50360,
|
239 |
+
50361,
|
240 |
+
50362
|
241 |
+
],
|
242 |
+
"task": "transcribe",
|
243 |
+
"task_to_id": {
|
244 |
+
"transcribe": 50359,
|
245 |
+
"translate": 50358
|
246 |
+
},
|
247 |
+
"transformers_version": "4.42.3"
|
248 |
+
}
|
checkpoint-705/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2bc0b40dd306d9ebdca7cb50cc714760255e5ae9b4fb767d38d108bab91ce335
|
3 |
+
size 290403936
|
checkpoint-705/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a35d65a820a39260b647497c6c9a20463e239fda9c8dfcd4cbffdcfbe84c0850
|
3 |
+
size 574811514
|
checkpoint-705/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 |
+
}
|
checkpoint-705/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18f452226e27495152d820849e7268511614063bf9faa3a5fa0ab63a58bbf524
|
3 |
+
size 14244
|
checkpoint-705/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3153f9a76f415d6fab1bf4aeca182d00637b06f8680b861eb5f3c7710a020b42
|
3 |
+
size 1064
|
checkpoint-705/trainer_state.json
ADDED
@@ -0,0 +1,269 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.0,
|
3 |
+
"best_model_checkpoint": "/kaggle/working/new_downloads/checkpoint-397",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 705,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.06297229219143577,
|
13 |
+
"grad_norm": 1.4191151857376099,
|
14 |
+
"learning_rate": 6.25e-05,
|
15 |
+
"loss": 4.3195,
|
16 |
+
"step": 25
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.12594458438287154,
|
20 |
+
"grad_norm": 1.5384018421173096,
|
21 |
+
"learning_rate": 0.000125,
|
22 |
+
"loss": 4.2512,
|
23 |
+
"step": 50
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.1889168765743073,
|
27 |
+
"grad_norm": 1.5718939304351807,
|
28 |
+
"learning_rate": 0.00018749999999999998,
|
29 |
+
"loss": 4.2373,
|
30 |
+
"step": 75
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.2518891687657431,
|
34 |
+
"grad_norm": 1.4780595302581787,
|
35 |
+
"learning_rate": 0.00025,
|
36 |
+
"loss": 4.2214,
|
37 |
+
"step": 100
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.3148614609571788,
|
41 |
+
"grad_norm": 1.543885588645935,
|
42 |
+
"learning_rate": 0.00029980818414322247,
|
43 |
+
"loss": 4.2333,
|
44 |
+
"step": 125
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.3778337531486146,
|
48 |
+
"grad_norm": 1.5833216905593872,
|
49 |
+
"learning_rate": 0.000298849104859335,
|
50 |
+
"loss": 4.2375,
|
51 |
+
"step": 150
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.44080604534005036,
|
55 |
+
"grad_norm": 1.8211495876312256,
|
56 |
+
"learning_rate": 0.00029789002557544756,
|
57 |
+
"loss": 4.2227,
|
58 |
+
"step": 175
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.5037783375314862,
|
62 |
+
"grad_norm": 1.5552014112472534,
|
63 |
+
"learning_rate": 0.0002969309462915601,
|
64 |
+
"loss": 4.2426,
|
65 |
+
"step": 200
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.5667506297229219,
|
69 |
+
"grad_norm": 1.5943366289138794,
|
70 |
+
"learning_rate": 0.0002959718670076726,
|
71 |
+
"loss": 4.2254,
|
72 |
+
"step": 225
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.6297229219143576,
|
76 |
+
"grad_norm": 1.9039855003356934,
|
77 |
+
"learning_rate": 0.0002950127877237851,
|
78 |
+
"loss": 4.2428,
|
79 |
+
"step": 250
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.6926952141057935,
|
83 |
+
"grad_norm": 1.624612808227539,
|
84 |
+
"learning_rate": 0.0002940537084398977,
|
85 |
+
"loss": 4.2183,
|
86 |
+
"step": 275
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.7556675062972292,
|
90 |
+
"grad_norm": 1.5801411867141724,
|
91 |
+
"learning_rate": 0.0002930946291560102,
|
92 |
+
"loss": 4.2032,
|
93 |
+
"step": 300
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.818639798488665,
|
97 |
+
"grad_norm": 1.6559851169586182,
|
98 |
+
"learning_rate": 0.0002921355498721227,
|
99 |
+
"loss": 4.1869,
|
100 |
+
"step": 325
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.8816120906801007,
|
104 |
+
"grad_norm": 1.6399421691894531,
|
105 |
+
"learning_rate": 0.00029117647058823524,
|
106 |
+
"loss": 4.2117,
|
107 |
+
"step": 350
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.9445843828715366,
|
111 |
+
"grad_norm": 1.6710602045059204,
|
112 |
+
"learning_rate": 0.0002902173913043478,
|
113 |
+
"loss": 4.2257,
|
114 |
+
"step": 375
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 1.0,
|
118 |
+
"eval_cer": 1.0,
|
119 |
+
"eval_loss": 4.691751956939697,
|
120 |
+
"eval_runtime": 1056.28,
|
121 |
+
"eval_samples_per_second": 2.082,
|
122 |
+
"eval_steps_per_second": 0.017,
|
123 |
+
"eval_wer": 1.0,
|
124 |
+
"step": 397
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 2.8368794326241136,
|
128 |
+
"grad_norm": 1.1363143920898438,
|
129 |
+
"learning_rate": 0.00026209386281588447,
|
130 |
+
"loss": 3.967,
|
131 |
+
"step": 400
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 3.0,
|
135 |
+
"eval_cer": 1.0,
|
136 |
+
"eval_loss": 4.709719657897949,
|
137 |
+
"eval_runtime": 540.9535,
|
138 |
+
"eval_samples_per_second": 4.065,
|
139 |
+
"eval_steps_per_second": 0.017,
|
140 |
+
"eval_wer": 1.0,
|
141 |
+
"step": 423
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 3.0141843971631204,
|
145 |
+
"grad_norm": 1.0413663387298584,
|
146 |
+
"learning_rate": 0.0002593862815884476,
|
147 |
+
"loss": 3.8784,
|
148 |
+
"step": 425
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 3.1914893617021276,
|
152 |
+
"grad_norm": 1.220971703529358,
|
153 |
+
"learning_rate": 0.0002566787003610108,
|
154 |
+
"loss": 3.7718,
|
155 |
+
"step": 450
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 3.368794326241135,
|
159 |
+
"grad_norm": 1.127140760421753,
|
160 |
+
"learning_rate": 0.000253971119133574,
|
161 |
+
"loss": 3.7725,
|
162 |
+
"step": 475
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 3.546099290780142,
|
166 |
+
"grad_norm": 1.1641333103179932,
|
167 |
+
"learning_rate": 0.00025126353790613716,
|
168 |
+
"loss": 3.778,
|
169 |
+
"step": 500
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 3.723404255319149,
|
173 |
+
"grad_norm": 1.1840986013412476,
|
174 |
+
"learning_rate": 0.00024855595667870036,
|
175 |
+
"loss": 3.7789,
|
176 |
+
"step": 525
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 3.900709219858156,
|
180 |
+
"grad_norm": 1.1780372858047485,
|
181 |
+
"learning_rate": 0.0002458483754512635,
|
182 |
+
"loss": 3.7835,
|
183 |
+
"step": 550
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 4.0,
|
187 |
+
"eval_cer": 1.0,
|
188 |
+
"eval_loss": 4.711414337158203,
|
189 |
+
"eval_runtime": 483.9002,
|
190 |
+
"eval_samples_per_second": 4.544,
|
191 |
+
"eval_steps_per_second": 0.019,
|
192 |
+
"eval_wer": 1.0,
|
193 |
+
"step": 564
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 4.078014184397163,
|
197 |
+
"grad_norm": 1.278428077697754,
|
198 |
+
"learning_rate": 0.00024314079422382669,
|
199 |
+
"loss": 3.6307,
|
200 |
+
"step": 575
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 4.25531914893617,
|
204 |
+
"grad_norm": 1.5900382995605469,
|
205 |
+
"learning_rate": 0.00024043321299638986,
|
206 |
+
"loss": 3.4048,
|
207 |
+
"step": 600
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 4.432624113475177,
|
211 |
+
"grad_norm": 1.502553105354309,
|
212 |
+
"learning_rate": 0.00023772563176895306,
|
213 |
+
"loss": 3.4276,
|
214 |
+
"step": 625
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 4.609929078014185,
|
218 |
+
"grad_norm": 1.44204843044281,
|
219 |
+
"learning_rate": 0.00023501805054151624,
|
220 |
+
"loss": 3.4493,
|
221 |
+
"step": 650
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 4.787234042553192,
|
225 |
+
"grad_norm": 1.4242497682571411,
|
226 |
+
"learning_rate": 0.0002323104693140794,
|
227 |
+
"loss": 3.4718,
|
228 |
+
"step": 675
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 4.964539007092198,
|
232 |
+
"grad_norm": 1.5147054195404053,
|
233 |
+
"learning_rate": 0.00022960288808664258,
|
234 |
+
"loss": 3.4886,
|
235 |
+
"step": 700
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 5.0,
|
239 |
+
"eval_cer": 1.0,
|
240 |
+
"eval_loss": 4.814764022827148,
|
241 |
+
"eval_runtime": 484.6076,
|
242 |
+
"eval_samples_per_second": 4.538,
|
243 |
+
"eval_steps_per_second": 0.019,
|
244 |
+
"eval_wer": 1.0,
|
245 |
+
"step": 705
|
246 |
+
}
|
247 |
+
],
|
248 |
+
"logging_steps": 25,
|
249 |
+
"max_steps": 2820,
|
250 |
+
"num_input_tokens_seen": 0,
|
251 |
+
"num_train_epochs": 20,
|
252 |
+
"save_steps": 500,
|
253 |
+
"stateful_callbacks": {
|
254 |
+
"TrainerControl": {
|
255 |
+
"args": {
|
256 |
+
"should_epoch_stop": false,
|
257 |
+
"should_evaluate": false,
|
258 |
+
"should_log": false,
|
259 |
+
"should_save": true,
|
260 |
+
"should_training_stop": false
|
261 |
+
},
|
262 |
+
"attributes": {}
|
263 |
+
}
|
264 |
+
},
|
265 |
+
"total_flos": 1.04722949799936e+19,
|
266 |
+
"train_batch_size": 360,
|
267 |
+
"trial_name": null,
|
268 |
+
"trial_params": null
|
269 |
+
}
|
checkpoint-705/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9aa0e436ad246aaf6463a35edf4105b71e18a4052887d3d74a658cc3acfc09f2
|
3 |
+
size 5304
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "gelu",
|
5 |
"apply_spec_augment": false,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/content/new_downloads/checkpoint-397",
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "gelu",
|
5 |
"apply_spec_augment": false,
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 290403936
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2bc0b40dd306d9ebdca7cb50cc714760255e5ae9b4fb767d38d108bab91ce335
|
3 |
size 290403936
|
runs/Jun29_22-49-32_ac23a7b0cb5f/events.out.tfevents.1719701375.ac23a7b0cb5f.4846.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0cf4588243c3681877d13425cad5eddd0e3416693f048ea49e098b517194172
|
3 |
+
size 6651
|
runs/Jun29_22-50-11_ac23a7b0cb5f/events.out.tfevents.1719701413.ac23a7b0cb5f.4846.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae3aac84eb3ce970f150dc73332d15aed0c4677797e448ac9bec8971926ab45d
|
3 |
+
size 10489
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5304
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9aa0e436ad246aaf6463a35edf4105b71e18a4052887d3d74a658cc3acfc09f2
|
3 |
size 5304
|