Training in progress, step 1250, checkpoint
Browse files- checkpoint-1250/config.json +65 -0
- checkpoint-1250/generation_config.json +265 -0
- checkpoint-1250/model.safetensors +3 -0
- checkpoint-1250/optimizer.pt +3 -0
- checkpoint-1250/preprocessor_config.json +14 -0
- checkpoint-1250/rng_state.pth +3 -0
- checkpoint-1250/scheduler.pt +3 -0
- checkpoint-1250/trainer_state.json +461 -0
- checkpoint-1250/training_args.bin +3 -0
checkpoint-1250/config.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/kaggle/input/whisper-small-final/the-final-whisper",
|
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": 0.0,
|
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": [
|
29 |
+
[
|
30 |
+
1,
|
31 |
+
50272
|
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": 12,
|
56 |
+
"num_mel_bins": 80,
|
57 |
+
"pad_token_id": 50257,
|
58 |
+
"scale_embedding": false,
|
59 |
+
"suppress_tokens": [],
|
60 |
+
"torch_dtype": "float32",
|
61 |
+
"transformers_version": "4.40.0.dev0",
|
62 |
+
"use_cache": true,
|
63 |
+
"use_weighted_layer_sum": false,
|
64 |
+
"vocab_size": 51865
|
65 |
+
}
|
checkpoint-1250/generation_config.json
ADDED
@@ -0,0 +1,265 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alignment_heads": [
|
3 |
+
[
|
4 |
+
5,
|
5 |
+
3
|
6 |
+
],
|
7 |
+
[
|
8 |
+
5,
|
9 |
+
9
|
10 |
+
],
|
11 |
+
[
|
12 |
+
8,
|
13 |
+
0
|
14 |
+
],
|
15 |
+
[
|
16 |
+
8,
|
17 |
+
4
|
18 |
+
],
|
19 |
+
[
|
20 |
+
8,
|
21 |
+
7
|
22 |
+
],
|
23 |
+
[
|
24 |
+
8,
|
25 |
+
8
|
26 |
+
],
|
27 |
+
[
|
28 |
+
9,
|
29 |
+
0
|
30 |
+
],
|
31 |
+
[
|
32 |
+
9,
|
33 |
+
7
|
34 |
+
],
|
35 |
+
[
|
36 |
+
9,
|
37 |
+
9
|
38 |
+
],
|
39 |
+
[
|
40 |
+
10,
|
41 |
+
5
|
42 |
+
]
|
43 |
+
],
|
44 |
+
"begin_suppress_tokens": [
|
45 |
+
220,
|
46 |
+
50257
|
47 |
+
],
|
48 |
+
"bos_token_id": 50257,
|
49 |
+
"decoder_start_token_id": 50258,
|
50 |
+
"eos_token_id": 50257,
|
51 |
+
"forced_decoder_ids": [
|
52 |
+
[
|
53 |
+
1,
|
54 |
+
null
|
55 |
+
],
|
56 |
+
[
|
57 |
+
2,
|
58 |
+
50359
|
59 |
+
]
|
60 |
+
],
|
61 |
+
"is_multilingual": true,
|
62 |
+
"lang_to_id": {
|
63 |
+
"<|af|>": 50327,
|
64 |
+
"<|am|>": 50334,
|
65 |
+
"<|ar|>": 50272,
|
66 |
+
"<|as|>": 50350,
|
67 |
+
"<|az|>": 50304,
|
68 |
+
"<|ba|>": 50355,
|
69 |
+
"<|be|>": 50330,
|
70 |
+
"<|bg|>": 50292,
|
71 |
+
"<|bn|>": 50302,
|
72 |
+
"<|bo|>": 50347,
|
73 |
+
"<|br|>": 50309,
|
74 |
+
"<|bs|>": 50315,
|
75 |
+
"<|ca|>": 50270,
|
76 |
+
"<|cs|>": 50283,
|
77 |
+
"<|cy|>": 50297,
|
78 |
+
"<|da|>": 50285,
|
79 |
+
"<|de|>": 50261,
|
80 |
+
"<|el|>": 50281,
|
81 |
+
"<|en|>": 50259,
|
82 |
+
"<|es|>": 50262,
|
83 |
+
"<|et|>": 50307,
|
84 |
+
"<|eu|>": 50310,
|
85 |
+
"<|fa|>": 50300,
|
86 |
+
"<|fi|>": 50277,
|
87 |
+
"<|fo|>": 50338,
|
88 |
+
"<|fr|>": 50265,
|
89 |
+
"<|gl|>": 50319,
|
90 |
+
"<|gu|>": 50333,
|
91 |
+
"<|haw|>": 50352,
|
92 |
+
"<|ha|>": 50354,
|
93 |
+
"<|he|>": 50279,
|
94 |
+
"<|hi|>": 50276,
|
95 |
+
"<|hr|>": 50291,
|
96 |
+
"<|ht|>": 50339,
|
97 |
+
"<|hu|>": 50286,
|
98 |
+
"<|hy|>": 50312,
|
99 |
+
"<|id|>": 50275,
|
100 |
+
"<|is|>": 50311,
|
101 |
+
"<|it|>": 50274,
|
102 |
+
"<|ja|>": 50266,
|
103 |
+
"<|jw|>": 50356,
|
104 |
+
"<|ka|>": 50329,
|
105 |
+
"<|kk|>": 50316,
|
106 |
+
"<|km|>": 50323,
|
107 |
+
"<|kn|>": 50306,
|
108 |
+
"<|ko|>": 50264,
|
109 |
+
"<|la|>": 50294,
|
110 |
+
"<|lb|>": 50345,
|
111 |
+
"<|ln|>": 50353,
|
112 |
+
"<|lo|>": 50336,
|
113 |
+
"<|lt|>": 50293,
|
114 |
+
"<|lv|>": 50301,
|
115 |
+
"<|mg|>": 50349,
|
116 |
+
"<|mi|>": 50295,
|
117 |
+
"<|mk|>": 50308,
|
118 |
+
"<|ml|>": 50296,
|
119 |
+
"<|mn|>": 50314,
|
120 |
+
"<|mr|>": 50320,
|
121 |
+
"<|ms|>": 50282,
|
122 |
+
"<|mt|>": 50343,
|
123 |
+
"<|my|>": 50346,
|
124 |
+
"<|ne|>": 50313,
|
125 |
+
"<|nl|>": 50271,
|
126 |
+
"<|nn|>": 50342,
|
127 |
+
"<|no|>": 50288,
|
128 |
+
"<|oc|>": 50328,
|
129 |
+
"<|pa|>": 50321,
|
130 |
+
"<|pl|>": 50269,
|
131 |
+
"<|ps|>": 50340,
|
132 |
+
"<|pt|>": 50267,
|
133 |
+
"<|ro|>": 50284,
|
134 |
+
"<|ru|>": 50263,
|
135 |
+
"<|sa|>": 50344,
|
136 |
+
"<|sd|>": 50332,
|
137 |
+
"<|si|>": 50322,
|
138 |
+
"<|sk|>": 50298,
|
139 |
+
"<|sl|>": 50305,
|
140 |
+
"<|sn|>": 50324,
|
141 |
+
"<|so|>": 50326,
|
142 |
+
"<|sq|>": 50317,
|
143 |
+
"<|sr|>": 50303,
|
144 |
+
"<|su|>": 50357,
|
145 |
+
"<|sv|>": 50273,
|
146 |
+
"<|sw|>": 50318,
|
147 |
+
"<|ta|>": 50287,
|
148 |
+
"<|te|>": 50299,
|
149 |
+
"<|tg|>": 50331,
|
150 |
+
"<|th|>": 50289,
|
151 |
+
"<|tk|>": 50341,
|
152 |
+
"<|tl|>": 50348,
|
153 |
+
"<|tr|>": 50268,
|
154 |
+
"<|tt|>": 50351,
|
155 |
+
"<|uk|>": 50280,
|
156 |
+
"<|ur|>": 50290,
|
157 |
+
"<|uz|>": 50337,
|
158 |
+
"<|vi|>": 50278,
|
159 |
+
"<|yi|>": 50335,
|
160 |
+
"<|yo|>": 50325,
|
161 |
+
"<|zh|>": 50260
|
162 |
+
},
|
163 |
+
"language": "ar",
|
164 |
+
"max_initial_timestamp_index": 50,
|
165 |
+
"max_length": 448,
|
166 |
+
"no_timestamps_token_id": 50363,
|
167 |
+
"pad_token_id": 50257,
|
168 |
+
"prev_sot_token_id": 50361,
|
169 |
+
"return_timestamps": false,
|
170 |
+
"suppress_tokens": [
|
171 |
+
1,
|
172 |
+
2,
|
173 |
+
7,
|
174 |
+
8,
|
175 |
+
9,
|
176 |
+
10,
|
177 |
+
14,
|
178 |
+
25,
|
179 |
+
26,
|
180 |
+
27,
|
181 |
+
28,
|
182 |
+
29,
|
183 |
+
31,
|
184 |
+
58,
|
185 |
+
59,
|
186 |
+
60,
|
187 |
+
61,
|
188 |
+
62,
|
189 |
+
63,
|
190 |
+
90,
|
191 |
+
91,
|
192 |
+
92,
|
193 |
+
93,
|
194 |
+
359,
|
195 |
+
503,
|
196 |
+
522,
|
197 |
+
542,
|
198 |
+
873,
|
199 |
+
893,
|
200 |
+
902,
|
201 |
+
918,
|
202 |
+
922,
|
203 |
+
931,
|
204 |
+
1350,
|
205 |
+
1853,
|
206 |
+
1982,
|
207 |
+
2460,
|
208 |
+
2627,
|
209 |
+
3246,
|
210 |
+
3253,
|
211 |
+
3268,
|
212 |
+
3536,
|
213 |
+
3846,
|
214 |
+
3961,
|
215 |
+
4183,
|
216 |
+
4667,
|
217 |
+
6585,
|
218 |
+
6647,
|
219 |
+
7273,
|
220 |
+
9061,
|
221 |
+
9383,
|
222 |
+
10428,
|
223 |
+
10929,
|
224 |
+
11938,
|
225 |
+
12033,
|
226 |
+
12331,
|
227 |
+
12562,
|
228 |
+
13793,
|
229 |
+
14157,
|
230 |
+
14635,
|
231 |
+
15265,
|
232 |
+
15618,
|
233 |
+
16553,
|
234 |
+
16604,
|
235 |
+
18362,
|
236 |
+
18956,
|
237 |
+
20075,
|
238 |
+
21675,
|
239 |
+
22520,
|
240 |
+
26130,
|
241 |
+
26161,
|
242 |
+
26435,
|
243 |
+
28279,
|
244 |
+
29464,
|
245 |
+
31650,
|
246 |
+
32302,
|
247 |
+
32470,
|
248 |
+
36865,
|
249 |
+
42863,
|
250 |
+
47425,
|
251 |
+
49870,
|
252 |
+
50254,
|
253 |
+
50258,
|
254 |
+
50358,
|
255 |
+
50359,
|
256 |
+
50360,
|
257 |
+
50361,
|
258 |
+
50362
|
259 |
+
],
|
260 |
+
"task_to_id": {
|
261 |
+
"transcribe": 50359,
|
262 |
+
"translate": 50358
|
263 |
+
},
|
264 |
+
"transformers_version": "4.40.0.dev0"
|
265 |
+
}
|
checkpoint-1250/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50178ace38f8fc2ef57402fcbde9c9f1fe3363978f8aa0abf40f8f715e1cc6cd
|
3 |
+
size 966995080
|
checkpoint-1250/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1cb4e1cf09eb503ff3006168193ff2b4954511986f4bd847d446d54e7b8541fe
|
3 |
+
size 1925064044
|
checkpoint-1250/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-1250/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c4aad0a89b337546947fd1477d8fd0b19f1a9a5fc3d22bdbce2e59680f071c4
|
3 |
+
size 14244
|
checkpoint-1250/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64754ebacb5d3a74bce6df005ac123997cb14067455c68aa47cac2a2bf5bcbdc
|
3 |
+
size 1064
|
checkpoint-1250/trainer_state.json
ADDED
@@ -0,0 +1,461 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 14.845024469820556,
|
3 |
+
"best_model_checkpoint": "./the-final-whisper/checkpoint-1000",
|
4 |
+
"epoch": 2.059308072487644,
|
5 |
+
"eval_steps": 125,
|
6 |
+
"global_step": 1250,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.04118616144975288,
|
13 |
+
"grad_norm": 52.4793701171875,
|
14 |
+
"learning_rate": 4.2000000000000006e-07,
|
15 |
+
"loss": 2.7503,
|
16 |
+
"step": 25
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.08237232289950576,
|
20 |
+
"grad_norm": 16.525333404541016,
|
21 |
+
"learning_rate": 9.200000000000001e-07,
|
22 |
+
"loss": 2.0994,
|
23 |
+
"step": 50
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.12355848434925865,
|
27 |
+
"grad_norm": 14.271560668945312,
|
28 |
+
"learning_rate": 1.42e-06,
|
29 |
+
"loss": 1.3213,
|
30 |
+
"step": 75
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.16474464579901152,
|
34 |
+
"grad_norm": 8.628070831298828,
|
35 |
+
"learning_rate": 1.9200000000000003e-06,
|
36 |
+
"loss": 0.7342,
|
37 |
+
"step": 100
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.20593080724876442,
|
41 |
+
"grad_norm": 8.307537078857422,
|
42 |
+
"learning_rate": 2.42e-06,
|
43 |
+
"loss": 0.5674,
|
44 |
+
"step": 125
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.20593080724876442,
|
48 |
+
"eval_loss": 0.6090311408042908,
|
49 |
+
"eval_runtime": 2805.8489,
|
50 |
+
"eval_samples_per_second": 1.442,
|
51 |
+
"eval_steps_per_second": 0.18,
|
52 |
+
"eval_wer": 45.15497553017945,
|
53 |
+
"step": 125
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.2471169686985173,
|
57 |
+
"grad_norm": 6.402714729309082,
|
58 |
+
"learning_rate": 2.92e-06,
|
59 |
+
"loss": 0.4853,
|
60 |
+
"step": 150
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 0.2883031301482702,
|
64 |
+
"grad_norm": 7.138896942138672,
|
65 |
+
"learning_rate": 3.4200000000000007e-06,
|
66 |
+
"loss": 0.424,
|
67 |
+
"step": 175
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"epoch": 0.32948929159802304,
|
71 |
+
"grad_norm": 6.78637170791626,
|
72 |
+
"learning_rate": 3.920000000000001e-06,
|
73 |
+
"loss": 0.3443,
|
74 |
+
"step": 200
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.37067545304777594,
|
78 |
+
"grad_norm": 6.042959690093994,
|
79 |
+
"learning_rate": 4.42e-06,
|
80 |
+
"loss": 0.2769,
|
81 |
+
"step": 225
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.41186161449752884,
|
85 |
+
"grad_norm": 2.8671882152557373,
|
86 |
+
"learning_rate": 4.92e-06,
|
87 |
+
"loss": 0.1545,
|
88 |
+
"step": 250
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 0.41186161449752884,
|
92 |
+
"eval_loss": 0.18588024377822876,
|
93 |
+
"eval_runtime": 2810.3027,
|
94 |
+
"eval_samples_per_second": 1.439,
|
95 |
+
"eval_steps_per_second": 0.18,
|
96 |
+
"eval_wer": 30.12351433232347,
|
97 |
+
"step": 250
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 0.45304777594728174,
|
101 |
+
"grad_norm": 4.210362911224365,
|
102 |
+
"learning_rate": 5.420000000000001e-06,
|
103 |
+
"loss": 0.094,
|
104 |
+
"step": 275
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.4942339373970346,
|
108 |
+
"grad_norm": 3.7346065044403076,
|
109 |
+
"learning_rate": 5.92e-06,
|
110 |
+
"loss": 0.0858,
|
111 |
+
"step": 300
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.5354200988467874,
|
115 |
+
"grad_norm": 2.7393386363983154,
|
116 |
+
"learning_rate": 6.42e-06,
|
117 |
+
"loss": 0.0745,
|
118 |
+
"step": 325
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 0.5766062602965404,
|
122 |
+
"grad_norm": 2.8941423892974854,
|
123 |
+
"learning_rate": 6.92e-06,
|
124 |
+
"loss": 0.0631,
|
125 |
+
"step": 350
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 0.6177924217462932,
|
129 |
+
"grad_norm": 3.1176912784576416,
|
130 |
+
"learning_rate": 7.420000000000001e-06,
|
131 |
+
"loss": 0.0658,
|
132 |
+
"step": 375
|
133 |
+
},
|
134 |
+
{
|
135 |
+
"epoch": 0.6177924217462932,
|
136 |
+
"eval_loss": 0.1334521770477295,
|
137 |
+
"eval_runtime": 2821.0386,
|
138 |
+
"eval_samples_per_second": 1.434,
|
139 |
+
"eval_steps_per_second": 0.179,
|
140 |
+
"eval_wer": 22.91773479375437,
|
141 |
+
"step": 375
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.6589785831960461,
|
145 |
+
"grad_norm": 3.2934091091156006,
|
146 |
+
"learning_rate": 7.92e-06,
|
147 |
+
"loss": 0.0552,
|
148 |
+
"step": 400
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 0.700164744645799,
|
152 |
+
"grad_norm": 3.6386263370513916,
|
153 |
+
"learning_rate": 8.42e-06,
|
154 |
+
"loss": 0.0529,
|
155 |
+
"step": 425
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 0.7413509060955519,
|
159 |
+
"grad_norm": 1.1384811401367188,
|
160 |
+
"learning_rate": 8.920000000000001e-06,
|
161 |
+
"loss": 0.0418,
|
162 |
+
"step": 450
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 0.7825370675453048,
|
166 |
+
"grad_norm": 4.086984634399414,
|
167 |
+
"learning_rate": 9.42e-06,
|
168 |
+
"loss": 0.0493,
|
169 |
+
"step": 475
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 0.8237232289950577,
|
173 |
+
"grad_norm": 2.331613540649414,
|
174 |
+
"learning_rate": 9.920000000000002e-06,
|
175 |
+
"loss": 0.0378,
|
176 |
+
"step": 500
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.8237232289950577,
|
180 |
+
"eval_loss": 0.12090734392404556,
|
181 |
+
"eval_runtime": 2820.3109,
|
182 |
+
"eval_samples_per_second": 1.434,
|
183 |
+
"eval_steps_per_second": 0.179,
|
184 |
+
"eval_wer": 20.77837333954789,
|
185 |
+
"step": 500
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.8649093904448105,
|
189 |
+
"grad_norm": 2.7532379627227783,
|
190 |
+
"learning_rate": 9.58e-06,
|
191 |
+
"loss": 0.0365,
|
192 |
+
"step": 525
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.9060955518945635,
|
196 |
+
"grad_norm": 3.022937774658203,
|
197 |
+
"learning_rate": 9.080000000000001e-06,
|
198 |
+
"loss": 0.0414,
|
199 |
+
"step": 550
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.9472817133443163,
|
203 |
+
"grad_norm": 2.641817092895508,
|
204 |
+
"learning_rate": 8.580000000000001e-06,
|
205 |
+
"loss": 0.0319,
|
206 |
+
"step": 575
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.9884678747940692,
|
210 |
+
"grad_norm": 3.3846614360809326,
|
211 |
+
"learning_rate": 8.08e-06,
|
212 |
+
"loss": 0.0272,
|
213 |
+
"step": 600
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 1.029654036243822,
|
217 |
+
"grad_norm": 4.221302032470703,
|
218 |
+
"learning_rate": 7.58e-06,
|
219 |
+
"loss": 0.022,
|
220 |
+
"step": 625
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 1.029654036243822,
|
224 |
+
"eval_loss": 0.10999257117509842,
|
225 |
+
"eval_runtime": 2822.9012,
|
226 |
+
"eval_samples_per_second": 1.433,
|
227 |
+
"eval_steps_per_second": 0.179,
|
228 |
+
"eval_wer": 18.08436261943603,
|
229 |
+
"step": 625
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"epoch": 1.0708401976935749,
|
233 |
+
"grad_norm": 4.843472480773926,
|
234 |
+
"learning_rate": 7.08e-06,
|
235 |
+
"loss": 0.021,
|
236 |
+
"step": 650
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 1.112026359143328,
|
240 |
+
"grad_norm": 1.8119359016418457,
|
241 |
+
"learning_rate": 6.5800000000000005e-06,
|
242 |
+
"loss": 0.0141,
|
243 |
+
"step": 675
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 1.1532125205930808,
|
247 |
+
"grad_norm": 1.112451195716858,
|
248 |
+
"learning_rate": 6.08e-06,
|
249 |
+
"loss": 0.0148,
|
250 |
+
"step": 700
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"epoch": 1.1943986820428336,
|
254 |
+
"grad_norm": 0.6692703366279602,
|
255 |
+
"learning_rate": 5.580000000000001e-06,
|
256 |
+
"loss": 0.0126,
|
257 |
+
"step": 725
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 1.2355848434925865,
|
261 |
+
"grad_norm": 1.457305908203125,
|
262 |
+
"learning_rate": 5.0800000000000005e-06,
|
263 |
+
"loss": 0.0097,
|
264 |
+
"step": 750
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 1.2355848434925865,
|
268 |
+
"eval_loss": 0.09214470535516739,
|
269 |
+
"eval_runtime": 2819.3708,
|
270 |
+
"eval_samples_per_second": 1.435,
|
271 |
+
"eval_steps_per_second": 0.179,
|
272 |
+
"eval_wer": 15.441621999533908,
|
273 |
+
"step": 750
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 1.2767710049423393,
|
277 |
+
"grad_norm": 2.9795682430267334,
|
278 |
+
"learning_rate": 4.58e-06,
|
279 |
+
"loss": 0.0105,
|
280 |
+
"step": 775
|
281 |
+
},
|
282 |
+
{
|
283 |
+
"epoch": 1.3179571663920924,
|
284 |
+
"grad_norm": 1.0585089921951294,
|
285 |
+
"learning_rate": 4.08e-06,
|
286 |
+
"loss": 0.0083,
|
287 |
+
"step": 800
|
288 |
+
},
|
289 |
+
{
|
290 |
+
"epoch": 1.3591433278418452,
|
291 |
+
"grad_norm": 2.7793498039245605,
|
292 |
+
"learning_rate": 3.58e-06,
|
293 |
+
"loss": 0.0113,
|
294 |
+
"step": 825
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 1.400329489291598,
|
298 |
+
"grad_norm": 0.24739088118076324,
|
299 |
+
"learning_rate": 3.08e-06,
|
300 |
+
"loss": 0.0106,
|
301 |
+
"step": 850
|
302 |
+
},
|
303 |
+
{
|
304 |
+
"epoch": 1.441515650741351,
|
305 |
+
"grad_norm": 0.5349621176719666,
|
306 |
+
"learning_rate": 2.5800000000000003e-06,
|
307 |
+
"loss": 0.0078,
|
308 |
+
"step": 875
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 1.441515650741351,
|
312 |
+
"eval_loss": 0.08723945915699005,
|
313 |
+
"eval_runtime": 2823.033,
|
314 |
+
"eval_samples_per_second": 1.433,
|
315 |
+
"eval_steps_per_second": 0.179,
|
316 |
+
"eval_wer": 15.530179445350733,
|
317 |
+
"step": 875
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 1.4827018121911038,
|
321 |
+
"grad_norm": 3.1261961460113525,
|
322 |
+
"learning_rate": 2.08e-06,
|
323 |
+
"loss": 0.0098,
|
324 |
+
"step": 900
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 1.5238879736408566,
|
328 |
+
"grad_norm": 0.6137211322784424,
|
329 |
+
"learning_rate": 1.5800000000000001e-06,
|
330 |
+
"loss": 0.0092,
|
331 |
+
"step": 925
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 1.5650741350906094,
|
335 |
+
"grad_norm": 1.3198140859603882,
|
336 |
+
"learning_rate": 1.08e-06,
|
337 |
+
"loss": 0.0088,
|
338 |
+
"step": 950
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 1.6062602965403623,
|
342 |
+
"grad_norm": 0.7606719136238098,
|
343 |
+
"learning_rate": 5.800000000000001e-07,
|
344 |
+
"loss": 0.0132,
|
345 |
+
"step": 975
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 1.6474464579901154,
|
349 |
+
"grad_norm": 1.69697105884552,
|
350 |
+
"learning_rate": 8e-08,
|
351 |
+
"loss": 0.012,
|
352 |
+
"step": 1000
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 1.6474464579901154,
|
356 |
+
"eval_loss": 0.08294647186994553,
|
357 |
+
"eval_runtime": 2832.7593,
|
358 |
+
"eval_samples_per_second": 1.428,
|
359 |
+
"eval_steps_per_second": 0.179,
|
360 |
+
"eval_wer": 14.845024469820556,
|
361 |
+
"step": 1000
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 1.6886326194398682,
|
365 |
+
"grad_norm": 1.8255125284194946,
|
366 |
+
"learning_rate": 8.842222222222223e-06,
|
367 |
+
"loss": 0.0097,
|
368 |
+
"step": 1025
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 1.729818780889621,
|
372 |
+
"grad_norm": 1.6991933584213257,
|
373 |
+
"learning_rate": 8.786666666666668e-06,
|
374 |
+
"loss": 0.0128,
|
375 |
+
"step": 1050
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 1.771004942339374,
|
379 |
+
"grad_norm": 3.427128314971924,
|
380 |
+
"learning_rate": 8.73111111111111e-06,
|
381 |
+
"loss": 0.0127,
|
382 |
+
"step": 1075
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 1.812191103789127,
|
386 |
+
"grad_norm": 1.3395907878875732,
|
387 |
+
"learning_rate": 8.675555555555556e-06,
|
388 |
+
"loss": 0.0111,
|
389 |
+
"step": 1100
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 1.8533772652388798,
|
393 |
+
"grad_norm": 2.087146520614624,
|
394 |
+
"learning_rate": 8.62e-06,
|
395 |
+
"loss": 0.0098,
|
396 |
+
"step": 1125
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 1.8533772652388798,
|
400 |
+
"eval_loss": 0.09520899504423141,
|
401 |
+
"eval_runtime": 2831.8668,
|
402 |
+
"eval_samples_per_second": 1.428,
|
403 |
+
"eval_steps_per_second": 0.179,
|
404 |
+
"eval_wer": 16.11745513866232,
|
405 |
+
"step": 1125
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 1.8945634266886326,
|
409 |
+
"grad_norm": 1.362247109413147,
|
410 |
+
"learning_rate": 8.564444444444445e-06,
|
411 |
+
"loss": 0.0102,
|
412 |
+
"step": 1150
|
413 |
+
},
|
414 |
+
{
|
415 |
+
"epoch": 1.9357495881383855,
|
416 |
+
"grad_norm": 1.9441858530044556,
|
417 |
+
"learning_rate": 8.50888888888889e-06,
|
418 |
+
"loss": 0.012,
|
419 |
+
"step": 1175
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 1.9769357495881383,
|
423 |
+
"grad_norm": 1.1025640964508057,
|
424 |
+
"learning_rate": 8.453333333333334e-06,
|
425 |
+
"loss": 0.0094,
|
426 |
+
"step": 1200
|
427 |
+
},
|
428 |
+
{
|
429 |
+
"epoch": 2.018121911037891,
|
430 |
+
"grad_norm": 0.26811718940734863,
|
431 |
+
"learning_rate": 8.397777777777778e-06,
|
432 |
+
"loss": 0.0103,
|
433 |
+
"step": 1225
|
434 |
+
},
|
435 |
+
{
|
436 |
+
"epoch": 2.059308072487644,
|
437 |
+
"grad_norm": 0.3004502058029175,
|
438 |
+
"learning_rate": 8.342222222222222e-06,
|
439 |
+
"loss": 0.0038,
|
440 |
+
"step": 1250
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 2.059308072487644,
|
444 |
+
"eval_loss": 0.09276822954416275,
|
445 |
+
"eval_runtime": 2807.4549,
|
446 |
+
"eval_samples_per_second": 1.441,
|
447 |
+
"eval_steps_per_second": 0.18,
|
448 |
+
"eval_wer": 15.422978326730366,
|
449 |
+
"step": 1250
|
450 |
+
}
|
451 |
+
],
|
452 |
+
"logging_steps": 25,
|
453 |
+
"max_steps": 5000,
|
454 |
+
"num_input_tokens_seen": 0,
|
455 |
+
"num_train_epochs": 9,
|
456 |
+
"save_steps": 250,
|
457 |
+
"total_flos": 5.76939932319744e+18,
|
458 |
+
"train_batch_size": 16,
|
459 |
+
"trial_name": null,
|
460 |
+
"trial_params": null
|
461 |
+
}
|
checkpoint-1250/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1497d51f875d54500f9d78264525118a3360d64231627067c2b218bf4374fd32
|
3 |
+
size 5112
|