Delete checkpoint-1000
Browse files- checkpoint-1000/config.json +0 -42
- checkpoint-1000/optimizer.pt +0 -3
- checkpoint-1000/preprocessor_config.json +0 -0
- checkpoint-1000/pytorch_model.bin +0 -3
- checkpoint-1000/rng_state.pth +0 -3
- checkpoint-1000/scaler.pt +0 -3
- checkpoint-1000/scheduler.pt +0 -3
- checkpoint-1000/trainer_state.json +0 -265
- checkpoint-1000/training_args.bin +0 -3
checkpoint-1000/config.json
DELETED
@@ -1,42 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "./lab2_id2223",
|
3 |
-
"activation_dropout": 0.0,
|
4 |
-
"activation_function": "gelu",
|
5 |
-
"architectures": [
|
6 |
-
"WhisperForConditionalGeneration"
|
7 |
-
],
|
8 |
-
"attention_dropout": 0.0,
|
9 |
-
"begin_suppress_tokens": [
|
10 |
-
220,
|
11 |
-
50257
|
12 |
-
],
|
13 |
-
"bos_token_id": 50257,
|
14 |
-
"d_model": 768,
|
15 |
-
"decoder_attention_heads": 12,
|
16 |
-
"decoder_ffn_dim": 3072,
|
17 |
-
"decoder_layerdrop": 0.0,
|
18 |
-
"decoder_layers": 12,
|
19 |
-
"decoder_start_token_id": 50258,
|
20 |
-
"dropout": 0.0,
|
21 |
-
"encoder_attention_heads": 12,
|
22 |
-
"encoder_ffn_dim": 3072,
|
23 |
-
"encoder_layerdrop": 0.0,
|
24 |
-
"encoder_layers": 12,
|
25 |
-
"eos_token_id": 50257,
|
26 |
-
"forced_decoder_ids": null,
|
27 |
-
"init_std": 0.02,
|
28 |
-
"is_encoder_decoder": true,
|
29 |
-
"max_length": 448,
|
30 |
-
"max_source_positions": 1500,
|
31 |
-
"max_target_positions": 448,
|
32 |
-
"model_type": "whisper",
|
33 |
-
"num_hidden_layers": 12,
|
34 |
-
"num_mel_bins": 80,
|
35 |
-
"pad_token_id": 50257,
|
36 |
-
"scale_embedding": false,
|
37 |
-
"suppress_tokens": [],
|
38 |
-
"torch_dtype": "float32",
|
39 |
-
"transformers_version": "4.26.0.dev0",
|
40 |
-
"use_cache": false,
|
41 |
-
"vocab_size": 51865
|
42 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1000/optimizer.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:0f20721c0b9a7c610299c984d7dad194d61ca3133df7d98f7c7d332d3160aae6
|
3 |
-
size 1934158597
|
|
|
|
|
|
|
|
checkpoint-1000/preprocessor_config.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1000/pytorch_model.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:cf08a6aa6026dbc8abee5e5743f086376cc3678ad79ebe2e9e116332be05fad5
|
3 |
-
size 967099139
|
|
|
|
|
|
|
|
checkpoint-1000/rng_state.pth
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:f90fbf33b1469b721a0c185b0fe40c4526548689d54f89e04165027e4c386af1
|
3 |
-
size 14439
|
|
|
|
|
|
|
|
checkpoint-1000/scaler.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:0f1d2dbe61bd26117d1189de7cf832428e092f6b72e3a39185250270a9584a00
|
3 |
-
size 559
|
|
|
|
|
|
|
|
checkpoint-1000/scheduler.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:4d80191163bb665448e3d3769a1ef2c2dd2e2bd83464efbee56ee7d4eec97725
|
3 |
-
size 623
|
|
|
|
|
|
|
|
checkpoint-1000/trainer_state.json
DELETED
@@ -1,265 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"best_metric": 20.41339024938216,
|
3 |
-
"best_model_checkpoint": "./lab2_id2223/checkpoint-1000",
|
4 |
-
"epoch": 1.2936610608020698,
|
5 |
-
"global_step": 1000,
|
6 |
-
"is_hyper_param_search": false,
|
7 |
-
"is_local_process_zero": true,
|
8 |
-
"is_world_process_zero": true,
|
9 |
-
"log_history": [
|
10 |
-
{
|
11 |
-
"epoch": 0.03,
|
12 |
-
"learning_rate": 4.800000000000001e-07,
|
13 |
-
"loss": 0.2225,
|
14 |
-
"step": 25
|
15 |
-
},
|
16 |
-
{
|
17 |
-
"epoch": 0.06,
|
18 |
-
"learning_rate": 9.800000000000001e-07,
|
19 |
-
"loss": 0.2081,
|
20 |
-
"step": 50
|
21 |
-
},
|
22 |
-
{
|
23 |
-
"epoch": 0.1,
|
24 |
-
"learning_rate": 1.48e-06,
|
25 |
-
"loss": 0.1992,
|
26 |
-
"step": 75
|
27 |
-
},
|
28 |
-
{
|
29 |
-
"epoch": 0.13,
|
30 |
-
"learning_rate": 1.98e-06,
|
31 |
-
"loss": 0.2014,
|
32 |
-
"step": 100
|
33 |
-
},
|
34 |
-
{
|
35 |
-
"epoch": 0.16,
|
36 |
-
"learning_rate": 2.4800000000000004e-06,
|
37 |
-
"loss": 0.1914,
|
38 |
-
"step": 125
|
39 |
-
},
|
40 |
-
{
|
41 |
-
"epoch": 0.19,
|
42 |
-
"learning_rate": 2.9800000000000003e-06,
|
43 |
-
"loss": 0.1978,
|
44 |
-
"step": 150
|
45 |
-
},
|
46 |
-
{
|
47 |
-
"epoch": 0.23,
|
48 |
-
"learning_rate": 3.48e-06,
|
49 |
-
"loss": 0.1988,
|
50 |
-
"step": 175
|
51 |
-
},
|
52 |
-
{
|
53 |
-
"epoch": 0.26,
|
54 |
-
"learning_rate": 3.980000000000001e-06,
|
55 |
-
"loss": 0.2153,
|
56 |
-
"step": 200
|
57 |
-
},
|
58 |
-
{
|
59 |
-
"epoch": 0.29,
|
60 |
-
"learning_rate": 4.48e-06,
|
61 |
-
"loss": 0.1907,
|
62 |
-
"step": 225
|
63 |
-
},
|
64 |
-
{
|
65 |
-
"epoch": 0.32,
|
66 |
-
"learning_rate": 4.980000000000001e-06,
|
67 |
-
"loss": 0.1976,
|
68 |
-
"step": 250
|
69 |
-
},
|
70 |
-
{
|
71 |
-
"epoch": 0.36,
|
72 |
-
"learning_rate": 5.480000000000001e-06,
|
73 |
-
"loss": 0.2256,
|
74 |
-
"step": 275
|
75 |
-
},
|
76 |
-
{
|
77 |
-
"epoch": 0.39,
|
78 |
-
"learning_rate": 5.98e-06,
|
79 |
-
"loss": 0.1805,
|
80 |
-
"step": 300
|
81 |
-
},
|
82 |
-
{
|
83 |
-
"epoch": 0.42,
|
84 |
-
"learning_rate": 6.480000000000001e-06,
|
85 |
-
"loss": 0.2144,
|
86 |
-
"step": 325
|
87 |
-
},
|
88 |
-
{
|
89 |
-
"epoch": 0.45,
|
90 |
-
"learning_rate": 6.98e-06,
|
91 |
-
"loss": 0.195,
|
92 |
-
"step": 350
|
93 |
-
},
|
94 |
-
{
|
95 |
-
"epoch": 0.49,
|
96 |
-
"learning_rate": 7.48e-06,
|
97 |
-
"loss": 0.2053,
|
98 |
-
"step": 375
|
99 |
-
},
|
100 |
-
{
|
101 |
-
"epoch": 0.52,
|
102 |
-
"learning_rate": 7.980000000000002e-06,
|
103 |
-
"loss": 0.2157,
|
104 |
-
"step": 400
|
105 |
-
},
|
106 |
-
{
|
107 |
-
"epoch": 0.55,
|
108 |
-
"learning_rate": 8.48e-06,
|
109 |
-
"loss": 0.2062,
|
110 |
-
"step": 425
|
111 |
-
},
|
112 |
-
{
|
113 |
-
"epoch": 0.58,
|
114 |
-
"learning_rate": 8.96e-06,
|
115 |
-
"loss": 0.1979,
|
116 |
-
"step": 450
|
117 |
-
},
|
118 |
-
{
|
119 |
-
"epoch": 0.61,
|
120 |
-
"learning_rate": 9.460000000000001e-06,
|
121 |
-
"loss": 0.1868,
|
122 |
-
"step": 475
|
123 |
-
},
|
124 |
-
{
|
125 |
-
"epoch": 0.65,
|
126 |
-
"learning_rate": 9.960000000000001e-06,
|
127 |
-
"loss": 0.2211,
|
128 |
-
"step": 500
|
129 |
-
},
|
130 |
-
{
|
131 |
-
"epoch": 0.68,
|
132 |
-
"learning_rate": 9.934285714285715e-06,
|
133 |
-
"loss": 0.2049,
|
134 |
-
"step": 525
|
135 |
-
},
|
136 |
-
{
|
137 |
-
"epoch": 0.71,
|
138 |
-
"learning_rate": 9.862857142857144e-06,
|
139 |
-
"loss": 0.1989,
|
140 |
-
"step": 550
|
141 |
-
},
|
142 |
-
{
|
143 |
-
"epoch": 0.74,
|
144 |
-
"learning_rate": 9.791428571428571e-06,
|
145 |
-
"loss": 0.2127,
|
146 |
-
"step": 575
|
147 |
-
},
|
148 |
-
{
|
149 |
-
"epoch": 0.78,
|
150 |
-
"learning_rate": 9.72e-06,
|
151 |
-
"loss": 0.2261,
|
152 |
-
"step": 600
|
153 |
-
},
|
154 |
-
{
|
155 |
-
"epoch": 0.81,
|
156 |
-
"learning_rate": 9.648571428571429e-06,
|
157 |
-
"loss": 0.2081,
|
158 |
-
"step": 625
|
159 |
-
},
|
160 |
-
{
|
161 |
-
"epoch": 0.84,
|
162 |
-
"learning_rate": 9.577142857142858e-06,
|
163 |
-
"loss": 0.2281,
|
164 |
-
"step": 650
|
165 |
-
},
|
166 |
-
{
|
167 |
-
"epoch": 0.87,
|
168 |
-
"learning_rate": 9.505714285714287e-06,
|
169 |
-
"loss": 0.204,
|
170 |
-
"step": 675
|
171 |
-
},
|
172 |
-
{
|
173 |
-
"epoch": 0.91,
|
174 |
-
"learning_rate": 9.434285714285714e-06,
|
175 |
-
"loss": 0.2053,
|
176 |
-
"step": 700
|
177 |
-
},
|
178 |
-
{
|
179 |
-
"epoch": 0.94,
|
180 |
-
"learning_rate": 9.362857142857143e-06,
|
181 |
-
"loss": 0.2208,
|
182 |
-
"step": 725
|
183 |
-
},
|
184 |
-
{
|
185 |
-
"epoch": 0.97,
|
186 |
-
"learning_rate": 9.291428571428572e-06,
|
187 |
-
"loss": 0.2076,
|
188 |
-
"step": 750
|
189 |
-
},
|
190 |
-
{
|
191 |
-
"epoch": 1.0,
|
192 |
-
"learning_rate": 9.220000000000002e-06,
|
193 |
-
"loss": 0.1941,
|
194 |
-
"step": 775
|
195 |
-
},
|
196 |
-
{
|
197 |
-
"epoch": 1.03,
|
198 |
-
"learning_rate": 9.148571428571429e-06,
|
199 |
-
"loss": 0.0949,
|
200 |
-
"step": 800
|
201 |
-
},
|
202 |
-
{
|
203 |
-
"epoch": 1.07,
|
204 |
-
"learning_rate": 9.077142857142858e-06,
|
205 |
-
"loss": 0.1011,
|
206 |
-
"step": 825
|
207 |
-
},
|
208 |
-
{
|
209 |
-
"epoch": 1.1,
|
210 |
-
"learning_rate": 9.005714285714287e-06,
|
211 |
-
"loss": 0.1078,
|
212 |
-
"step": 850
|
213 |
-
},
|
214 |
-
{
|
215 |
-
"epoch": 1.13,
|
216 |
-
"learning_rate": 8.934285714285716e-06,
|
217 |
-
"loss": 0.0956,
|
218 |
-
"step": 875
|
219 |
-
},
|
220 |
-
{
|
221 |
-
"epoch": 1.16,
|
222 |
-
"learning_rate": 8.862857142857143e-06,
|
223 |
-
"loss": 0.1093,
|
224 |
-
"step": 900
|
225 |
-
},
|
226 |
-
{
|
227 |
-
"epoch": 1.2,
|
228 |
-
"learning_rate": 8.791428571428572e-06,
|
229 |
-
"loss": 0.1133,
|
230 |
-
"step": 925
|
231 |
-
},
|
232 |
-
{
|
233 |
-
"epoch": 1.23,
|
234 |
-
"learning_rate": 8.720000000000001e-06,
|
235 |
-
"loss": 0.1128,
|
236 |
-
"step": 950
|
237 |
-
},
|
238 |
-
{
|
239 |
-
"epoch": 1.26,
|
240 |
-
"learning_rate": 8.64857142857143e-06,
|
241 |
-
"loss": 0.1068,
|
242 |
-
"step": 975
|
243 |
-
},
|
244 |
-
{
|
245 |
-
"epoch": 1.29,
|
246 |
-
"learning_rate": 8.577142857142858e-06,
|
247 |
-
"loss": 0.1015,
|
248 |
-
"step": 1000
|
249 |
-
},
|
250 |
-
{
|
251 |
-
"epoch": 1.29,
|
252 |
-
"eval_loss": 0.2880099415779114,
|
253 |
-
"eval_runtime": 2234.5268,
|
254 |
-
"eval_samples_per_second": 1.343,
|
255 |
-
"eval_steps_per_second": 0.168,
|
256 |
-
"eval_wer": 20.41339024938216,
|
257 |
-
"step": 1000
|
258 |
-
}
|
259 |
-
],
|
260 |
-
"max_steps": 4000,
|
261 |
-
"num_train_epochs": 6,
|
262 |
-
"total_flos": 4.61505772191744e+18,
|
263 |
-
"trial_name": null,
|
264 |
-
"trial_params": null
|
265 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1000/training_args.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:b2f1eb1dbb07bf3ca34b6535b0daafae64c8f7caae6fd1291115311f4aa808a8
|
3 |
-
size 3567
|
|
|
|
|
|
|
|