Delete checkpoint-2000
Browse files- checkpoint-2000/config.json +0 -42
- checkpoint-2000/optimizer.pt +0 -3
- checkpoint-2000/preprocessor_config.json +0 -0
- checkpoint-2000/pytorch_model.bin +0 -3
- checkpoint-2000/rng_state.pth +0 -3
- checkpoint-2000/scaler.pt +0 -3
- checkpoint-2000/scheduler.pt +0 -3
- checkpoint-2000/trainer_state.json +0 -514
- checkpoint-2000/training_args.bin +0 -3
checkpoint-2000/config.json
DELETED
@@ -1,42 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "openai/whisper-small",
|
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": true,
|
41 |
-
"vocab_size": 51865
|
42 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/optimizer.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:62df7a0e1a4a3e28ddd03c1fb05e5f874e1f99fe7ce6590e2b995534939fcc4a
|
3 |
-
size 1934158597
|
|
|
|
|
|
|
|
checkpoint-2000/preprocessor_config.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-2000/pytorch_model.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:42f6c9c8ce011a3cd64f73e554ffad7a7eeccb1ab10f81ab3ab01e2fc88da522
|
3 |
-
size 967099139
|
|
|
|
|
|
|
|
checkpoint-2000/rng_state.pth
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:7bce841fb4dbbf6bd41053f16c84251d18e5bc5818d9dff667509985dcc60684
|
3 |
-
size 14439
|
|
|
|
|
|
|
|
checkpoint-2000/scaler.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:f1107989d62f000d9dde8f5b09650bc15f7856c9608cf33df0efca161d5c02bd
|
3 |
-
size 559
|
|
|
|
|
|
|
|
checkpoint-2000/scheduler.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:8c99784789da5872bcf0411dd2748247fdf0e8c4cf1ae88c6e57854569056aff
|
3 |
-
size 623
|
|
|
|
|
|
|
|
checkpoint-2000/trainer_state.json
DELETED
@@ -1,514 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"best_metric": 20.332876233497352,
|
3 |
-
"best_model_checkpoint": "/content/gdrive/MyDrive/Whisper_Checkpoints/checkpoint-2000",
|
4 |
-
"epoch": 2.5873221216041395,
|
5 |
-
"global_step": 2000,
|
6 |
-
"is_hyper_param_search": false,
|
7 |
-
"is_local_process_zero": true,
|
8 |
-
"is_world_process_zero": true,
|
9 |
-
"log_history": [
|
10 |
-
{
|
11 |
-
"epoch": 0.03,
|
12 |
-
"learning_rate": 4.2000000000000006e-07,
|
13 |
-
"loss": 4.2747,
|
14 |
-
"step": 25
|
15 |
-
},
|
16 |
-
{
|
17 |
-
"epoch": 0.06,
|
18 |
-
"learning_rate": 9.200000000000001e-07,
|
19 |
-
"loss": 3.4782,
|
20 |
-
"step": 50
|
21 |
-
},
|
22 |
-
{
|
23 |
-
"epoch": 0.1,
|
24 |
-
"learning_rate": 1.42e-06,
|
25 |
-
"loss": 2.4424,
|
26 |
-
"step": 75
|
27 |
-
},
|
28 |
-
{
|
29 |
-
"epoch": 0.13,
|
30 |
-
"learning_rate": 1.9200000000000003e-06,
|
31 |
-
"loss": 1.4339,
|
32 |
-
"step": 100
|
33 |
-
},
|
34 |
-
{
|
35 |
-
"epoch": 0.16,
|
36 |
-
"learning_rate": 2.42e-06,
|
37 |
-
"loss": 1.1695,
|
38 |
-
"step": 125
|
39 |
-
},
|
40 |
-
{
|
41 |
-
"epoch": 0.19,
|
42 |
-
"learning_rate": 2.92e-06,
|
43 |
-
"loss": 1.0811,
|
44 |
-
"step": 150
|
45 |
-
},
|
46 |
-
{
|
47 |
-
"epoch": 0.23,
|
48 |
-
"learning_rate": 3.4200000000000007e-06,
|
49 |
-
"loss": 0.9162,
|
50 |
-
"step": 175
|
51 |
-
},
|
52 |
-
{
|
53 |
-
"epoch": 0.26,
|
54 |
-
"learning_rate": 3.920000000000001e-06,
|
55 |
-
"loss": 0.8637,
|
56 |
-
"step": 200
|
57 |
-
},
|
58 |
-
{
|
59 |
-
"epoch": 0.29,
|
60 |
-
"learning_rate": 4.42e-06,
|
61 |
-
"loss": 0.7423,
|
62 |
-
"step": 225
|
63 |
-
},
|
64 |
-
{
|
65 |
-
"epoch": 0.32,
|
66 |
-
"learning_rate": 4.92e-06,
|
67 |
-
"loss": 0.6393,
|
68 |
-
"step": 250
|
69 |
-
},
|
70 |
-
{
|
71 |
-
"epoch": 0.36,
|
72 |
-
"learning_rate": 5.420000000000001e-06,
|
73 |
-
"loss": 0.4363,
|
74 |
-
"step": 275
|
75 |
-
},
|
76 |
-
{
|
77 |
-
"epoch": 0.39,
|
78 |
-
"learning_rate": 5.92e-06,
|
79 |
-
"loss": 0.3485,
|
80 |
-
"step": 300
|
81 |
-
},
|
82 |
-
{
|
83 |
-
"epoch": 0.42,
|
84 |
-
"learning_rate": 6.42e-06,
|
85 |
-
"loss": 0.2951,
|
86 |
-
"step": 325
|
87 |
-
},
|
88 |
-
{
|
89 |
-
"epoch": 0.45,
|
90 |
-
"learning_rate": 6.92e-06,
|
91 |
-
"loss": 0.3216,
|
92 |
-
"step": 350
|
93 |
-
},
|
94 |
-
{
|
95 |
-
"epoch": 0.49,
|
96 |
-
"learning_rate": 7.420000000000001e-06,
|
97 |
-
"loss": 0.2954,
|
98 |
-
"step": 375
|
99 |
-
},
|
100 |
-
{
|
101 |
-
"epoch": 0.52,
|
102 |
-
"learning_rate": 7.92e-06,
|
103 |
-
"loss": 0.317,
|
104 |
-
"step": 400
|
105 |
-
},
|
106 |
-
{
|
107 |
-
"epoch": 0.55,
|
108 |
-
"learning_rate": 8.42e-06,
|
109 |
-
"loss": 0.3122,
|
110 |
-
"step": 425
|
111 |
-
},
|
112 |
-
{
|
113 |
-
"epoch": 0.58,
|
114 |
-
"learning_rate": 8.920000000000001e-06,
|
115 |
-
"loss": 0.3339,
|
116 |
-
"step": 450
|
117 |
-
},
|
118 |
-
{
|
119 |
-
"epoch": 0.61,
|
120 |
-
"learning_rate": 9.42e-06,
|
121 |
-
"loss": 0.2815,
|
122 |
-
"step": 475
|
123 |
-
},
|
124 |
-
{
|
125 |
-
"epoch": 0.65,
|
126 |
-
"learning_rate": 9.920000000000002e-06,
|
127 |
-
"loss": 0.3144,
|
128 |
-
"step": 500
|
129 |
-
},
|
130 |
-
{
|
131 |
-
"epoch": 0.68,
|
132 |
-
"learning_rate": 9.940000000000001e-06,
|
133 |
-
"loss": 0.2778,
|
134 |
-
"step": 525
|
135 |
-
},
|
136 |
-
{
|
137 |
-
"epoch": 0.71,
|
138 |
-
"learning_rate": 9.86857142857143e-06,
|
139 |
-
"loss": 0.3041,
|
140 |
-
"step": 550
|
141 |
-
},
|
142 |
-
{
|
143 |
-
"epoch": 0.74,
|
144 |
-
"learning_rate": 9.797142857142858e-06,
|
145 |
-
"loss": 0.3016,
|
146 |
-
"step": 575
|
147 |
-
},
|
148 |
-
{
|
149 |
-
"epoch": 0.78,
|
150 |
-
"learning_rate": 9.725714285714287e-06,
|
151 |
-
"loss": 0.2984,
|
152 |
-
"step": 600
|
153 |
-
},
|
154 |
-
{
|
155 |
-
"epoch": 0.81,
|
156 |
-
"learning_rate": 9.654285714285716e-06,
|
157 |
-
"loss": 0.2963,
|
158 |
-
"step": 625
|
159 |
-
},
|
160 |
-
{
|
161 |
-
"epoch": 0.84,
|
162 |
-
"learning_rate": 9.582857142857143e-06,
|
163 |
-
"loss": 0.2958,
|
164 |
-
"step": 650
|
165 |
-
},
|
166 |
-
{
|
167 |
-
"epoch": 0.87,
|
168 |
-
"learning_rate": 9.511428571428572e-06,
|
169 |
-
"loss": 0.2896,
|
170 |
-
"step": 675
|
171 |
-
},
|
172 |
-
{
|
173 |
-
"epoch": 0.91,
|
174 |
-
"learning_rate": 9.440000000000001e-06,
|
175 |
-
"loss": 0.2663,
|
176 |
-
"step": 700
|
177 |
-
},
|
178 |
-
{
|
179 |
-
"epoch": 0.94,
|
180 |
-
"learning_rate": 9.368571428571428e-06,
|
181 |
-
"loss": 0.2612,
|
182 |
-
"step": 725
|
183 |
-
},
|
184 |
-
{
|
185 |
-
"epoch": 0.97,
|
186 |
-
"learning_rate": 9.297142857142857e-06,
|
187 |
-
"loss": 0.2912,
|
188 |
-
"step": 750
|
189 |
-
},
|
190 |
-
{
|
191 |
-
"epoch": 1.0,
|
192 |
-
"learning_rate": 9.225714285714286e-06,
|
193 |
-
"loss": 0.2776,
|
194 |
-
"step": 775
|
195 |
-
},
|
196 |
-
{
|
197 |
-
"epoch": 1.03,
|
198 |
-
"learning_rate": 9.154285714285715e-06,
|
199 |
-
"loss": 0.1359,
|
200 |
-
"step": 800
|
201 |
-
},
|
202 |
-
{
|
203 |
-
"epoch": 1.07,
|
204 |
-
"learning_rate": 9.082857142857143e-06,
|
205 |
-
"loss": 0.1632,
|
206 |
-
"step": 825
|
207 |
-
},
|
208 |
-
{
|
209 |
-
"epoch": 1.1,
|
210 |
-
"learning_rate": 9.011428571428572e-06,
|
211 |
-
"loss": 0.1571,
|
212 |
-
"step": 850
|
213 |
-
},
|
214 |
-
{
|
215 |
-
"epoch": 1.13,
|
216 |
-
"learning_rate": 8.94e-06,
|
217 |
-
"loss": 0.137,
|
218 |
-
"step": 875
|
219 |
-
},
|
220 |
-
{
|
221 |
-
"epoch": 1.16,
|
222 |
-
"learning_rate": 8.86857142857143e-06,
|
223 |
-
"loss": 0.1373,
|
224 |
-
"step": 900
|
225 |
-
},
|
226 |
-
{
|
227 |
-
"epoch": 1.2,
|
228 |
-
"learning_rate": 8.797142857142857e-06,
|
229 |
-
"loss": 0.145,
|
230 |
-
"step": 925
|
231 |
-
},
|
232 |
-
{
|
233 |
-
"epoch": 1.23,
|
234 |
-
"learning_rate": 8.725714285714286e-06,
|
235 |
-
"loss": 0.1627,
|
236 |
-
"step": 950
|
237 |
-
},
|
238 |
-
{
|
239 |
-
"epoch": 1.26,
|
240 |
-
"learning_rate": 8.654285714285715e-06,
|
241 |
-
"loss": 0.1561,
|
242 |
-
"step": 975
|
243 |
-
},
|
244 |
-
{
|
245 |
-
"epoch": 1.29,
|
246 |
-
"learning_rate": 8.582857142857144e-06,
|
247 |
-
"loss": 0.1321,
|
248 |
-
"step": 1000
|
249 |
-
},
|
250 |
-
{
|
251 |
-
"epoch": 1.29,
|
252 |
-
"eval_loss": 0.2980383336544037,
|
253 |
-
"eval_runtime": 1963.1004,
|
254 |
-
"eval_samples_per_second": 2.582,
|
255 |
-
"eval_steps_per_second": 0.323,
|
256 |
-
"eval_wer": 21.55629050038988,
|
257 |
-
"step": 1000
|
258 |
-
},
|
259 |
-
{
|
260 |
-
"epoch": 1.33,
|
261 |
-
"learning_rate": 8.511428571428571e-06,
|
262 |
-
"loss": 0.1477,
|
263 |
-
"step": 1025
|
264 |
-
},
|
265 |
-
{
|
266 |
-
"epoch": 1.36,
|
267 |
-
"learning_rate": 8.44e-06,
|
268 |
-
"loss": 0.1378,
|
269 |
-
"step": 1050
|
270 |
-
},
|
271 |
-
{
|
272 |
-
"epoch": 1.39,
|
273 |
-
"learning_rate": 8.36857142857143e-06,
|
274 |
-
"loss": 0.1354,
|
275 |
-
"step": 1075
|
276 |
-
},
|
277 |
-
{
|
278 |
-
"epoch": 1.42,
|
279 |
-
"learning_rate": 8.297142857142859e-06,
|
280 |
-
"loss": 0.1352,
|
281 |
-
"step": 1100
|
282 |
-
},
|
283 |
-
{
|
284 |
-
"epoch": 1.46,
|
285 |
-
"learning_rate": 8.225714285714288e-06,
|
286 |
-
"loss": 0.1456,
|
287 |
-
"step": 1125
|
288 |
-
},
|
289 |
-
{
|
290 |
-
"epoch": 1.49,
|
291 |
-
"learning_rate": 8.154285714285715e-06,
|
292 |
-
"loss": 0.1386,
|
293 |
-
"step": 1150
|
294 |
-
},
|
295 |
-
{
|
296 |
-
"epoch": 1.52,
|
297 |
-
"learning_rate": 8.082857142857144e-06,
|
298 |
-
"loss": 0.1366,
|
299 |
-
"step": 1175
|
300 |
-
},
|
301 |
-
{
|
302 |
-
"epoch": 1.55,
|
303 |
-
"learning_rate": 8.011428571428573e-06,
|
304 |
-
"loss": 0.1509,
|
305 |
-
"step": 1200
|
306 |
-
},
|
307 |
-
{
|
308 |
-
"epoch": 1.58,
|
309 |
-
"learning_rate": 7.94e-06,
|
310 |
-
"loss": 0.136,
|
311 |
-
"step": 1225
|
312 |
-
},
|
313 |
-
{
|
314 |
-
"epoch": 1.62,
|
315 |
-
"learning_rate": 7.86857142857143e-06,
|
316 |
-
"loss": 0.1488,
|
317 |
-
"step": 1250
|
318 |
-
},
|
319 |
-
{
|
320 |
-
"epoch": 1.65,
|
321 |
-
"learning_rate": 7.797142857142858e-06,
|
322 |
-
"loss": 0.1662,
|
323 |
-
"step": 1275
|
324 |
-
},
|
325 |
-
{
|
326 |
-
"epoch": 1.68,
|
327 |
-
"learning_rate": 7.725714285714286e-06,
|
328 |
-
"loss": 0.1505,
|
329 |
-
"step": 1300
|
330 |
-
},
|
331 |
-
{
|
332 |
-
"epoch": 1.71,
|
333 |
-
"learning_rate": 7.654285714285715e-06,
|
334 |
-
"loss": 0.1431,
|
335 |
-
"step": 1325
|
336 |
-
},
|
337 |
-
{
|
338 |
-
"epoch": 1.75,
|
339 |
-
"learning_rate": 7.5828571428571444e-06,
|
340 |
-
"loss": 0.1263,
|
341 |
-
"step": 1350
|
342 |
-
},
|
343 |
-
{
|
344 |
-
"epoch": 1.78,
|
345 |
-
"learning_rate": 7.511428571428572e-06,
|
346 |
-
"loss": 0.132,
|
347 |
-
"step": 1375
|
348 |
-
},
|
349 |
-
{
|
350 |
-
"epoch": 1.81,
|
351 |
-
"learning_rate": 7.440000000000001e-06,
|
352 |
-
"loss": 0.1429,
|
353 |
-
"step": 1400
|
354 |
-
},
|
355 |
-
{
|
356 |
-
"epoch": 1.84,
|
357 |
-
"learning_rate": 7.36857142857143e-06,
|
358 |
-
"loss": 0.1398,
|
359 |
-
"step": 1425
|
360 |
-
},
|
361 |
-
{
|
362 |
-
"epoch": 1.88,
|
363 |
-
"learning_rate": 7.297142857142858e-06,
|
364 |
-
"loss": 0.1467,
|
365 |
-
"step": 1450
|
366 |
-
},
|
367 |
-
{
|
368 |
-
"epoch": 1.91,
|
369 |
-
"learning_rate": 7.225714285714286e-06,
|
370 |
-
"loss": 0.146,
|
371 |
-
"step": 1475
|
372 |
-
},
|
373 |
-
{
|
374 |
-
"epoch": 1.94,
|
375 |
-
"learning_rate": 7.154285714285715e-06,
|
376 |
-
"loss": 0.1318,
|
377 |
-
"step": 1500
|
378 |
-
},
|
379 |
-
{
|
380 |
-
"epoch": 1.97,
|
381 |
-
"learning_rate": 7.082857142857143e-06,
|
382 |
-
"loss": 0.1365,
|
383 |
-
"step": 1525
|
384 |
-
},
|
385 |
-
{
|
386 |
-
"epoch": 2.01,
|
387 |
-
"learning_rate": 7.011428571428572e-06,
|
388 |
-
"loss": 0.1236,
|
389 |
-
"step": 1550
|
390 |
-
},
|
391 |
-
{
|
392 |
-
"epoch": 2.04,
|
393 |
-
"learning_rate": 6.9400000000000005e-06,
|
394 |
-
"loss": 0.049,
|
395 |
-
"step": 1575
|
396 |
-
},
|
397 |
-
{
|
398 |
-
"epoch": 2.07,
|
399 |
-
"learning_rate": 6.868571428571429e-06,
|
400 |
-
"loss": 0.0512,
|
401 |
-
"step": 1600
|
402 |
-
},
|
403 |
-
{
|
404 |
-
"epoch": 2.1,
|
405 |
-
"learning_rate": 6.797142857142858e-06,
|
406 |
-
"loss": 0.0499,
|
407 |
-
"step": 1625
|
408 |
-
},
|
409 |
-
{
|
410 |
-
"epoch": 2.13,
|
411 |
-
"learning_rate": 6.725714285714287e-06,
|
412 |
-
"loss": 0.0477,
|
413 |
-
"step": 1650
|
414 |
-
},
|
415 |
-
{
|
416 |
-
"epoch": 2.17,
|
417 |
-
"learning_rate": 6.654285714285716e-06,
|
418 |
-
"loss": 0.0539,
|
419 |
-
"step": 1675
|
420 |
-
},
|
421 |
-
{
|
422 |
-
"epoch": 2.2,
|
423 |
-
"learning_rate": 6.582857142857143e-06,
|
424 |
-
"loss": 0.0502,
|
425 |
-
"step": 1700
|
426 |
-
},
|
427 |
-
{
|
428 |
-
"epoch": 2.23,
|
429 |
-
"learning_rate": 6.511428571428572e-06,
|
430 |
-
"loss": 0.0572,
|
431 |
-
"step": 1725
|
432 |
-
},
|
433 |
-
{
|
434 |
-
"epoch": 2.26,
|
435 |
-
"learning_rate": 6.440000000000001e-06,
|
436 |
-
"loss": 0.0555,
|
437 |
-
"step": 1750
|
438 |
-
},
|
439 |
-
{
|
440 |
-
"epoch": 2.3,
|
441 |
-
"learning_rate": 6.368571428571429e-06,
|
442 |
-
"loss": 0.0568,
|
443 |
-
"step": 1775
|
444 |
-
},
|
445 |
-
{
|
446 |
-
"epoch": 2.33,
|
447 |
-
"learning_rate": 6.297142857142857e-06,
|
448 |
-
"loss": 0.053,
|
449 |
-
"step": 1800
|
450 |
-
},
|
451 |
-
{
|
452 |
-
"epoch": 2.36,
|
453 |
-
"learning_rate": 6.225714285714286e-06,
|
454 |
-
"loss": 0.0501,
|
455 |
-
"step": 1825
|
456 |
-
},
|
457 |
-
{
|
458 |
-
"epoch": 2.39,
|
459 |
-
"learning_rate": 6.1542857142857145e-06,
|
460 |
-
"loss": 0.0521,
|
461 |
-
"step": 1850
|
462 |
-
},
|
463 |
-
{
|
464 |
-
"epoch": 2.43,
|
465 |
-
"learning_rate": 6.0828571428571435e-06,
|
466 |
-
"loss": 0.0518,
|
467 |
-
"step": 1875
|
468 |
-
},
|
469 |
-
{
|
470 |
-
"epoch": 2.46,
|
471 |
-
"learning_rate": 6.011428571428572e-06,
|
472 |
-
"loss": 0.0537,
|
473 |
-
"step": 1900
|
474 |
-
},
|
475 |
-
{
|
476 |
-
"epoch": 2.49,
|
477 |
-
"learning_rate": 5.94e-06,
|
478 |
-
"loss": 0.0554,
|
479 |
-
"step": 1925
|
480 |
-
},
|
481 |
-
{
|
482 |
-
"epoch": 2.52,
|
483 |
-
"learning_rate": 5.868571428571429e-06,
|
484 |
-
"loss": 0.0515,
|
485 |
-
"step": 1950
|
486 |
-
},
|
487 |
-
{
|
488 |
-
"epoch": 2.55,
|
489 |
-
"learning_rate": 5.797142857142858e-06,
|
490 |
-
"loss": 0.0548,
|
491 |
-
"step": 1975
|
492 |
-
},
|
493 |
-
{
|
494 |
-
"epoch": 2.59,
|
495 |
-
"learning_rate": 5.725714285714287e-06,
|
496 |
-
"loss": 0.052,
|
497 |
-
"step": 2000
|
498 |
-
},
|
499 |
-
{
|
500 |
-
"epoch": 2.59,
|
501 |
-
"eval_loss": 0.2855091094970703,
|
502 |
-
"eval_runtime": 1971.7129,
|
503 |
-
"eval_samples_per_second": 2.571,
|
504 |
-
"eval_steps_per_second": 0.322,
|
505 |
-
"eval_wer": 20.332876233497352,
|
506 |
-
"step": 2000
|
507 |
-
}
|
508 |
-
],
|
509 |
-
"max_steps": 4000,
|
510 |
-
"num_train_epochs": 6,
|
511 |
-
"total_flos": 9.23011544383488e+18,
|
512 |
-
"trial_name": null,
|
513 |
-
"trial_params": null
|
514 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/training_args.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:e7e84bbacb78e09cd8ee7d524f70614635cbf5f954a28de4f50bb8ea71406a63
|
3 |
-
size 3567
|
|
|
|
|
|
|
|