Scrya commited on
Commit
4060ab3
·
1 Parent(s): a6abaeb

Training in progress, step 2000

Browse files
fine-tune-whisper-non-streaming-id-augmented.ipynb CHANGED
@@ -1058,8 +1058,8 @@
1058
  "\n",
1059
  " <div>\n",
1060
  " \n",
1061
- " <progress value='1001' max='5000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
1062
- " [1001/5000 1:06:20 < 4:25:35, 0.25 it/s, Epoch 11.49/58]\n",
1063
  " </div>\n",
1064
  " <table border=\"1\" class=\"dataframe\">\n",
1065
  " <thead>\n",
@@ -1079,6 +1079,13 @@
1079
  " <td>18.128976</td>\n",
1080
  " <td>8.464310</td>\n",
1081
  " </tr>\n",
 
 
 
 
 
 
 
1082
  " </tbody>\n",
1083
  "</table><p>"
1084
  ],
@@ -2291,6 +2298,1197 @@
2291
  "name": "stderr",
2292
  "output_type": "stream",
2293
  "text": [
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2294
  "Feature extractor saved in ./preprocessor_config.json\n"
2295
  ]
2296
  }
 
1058
  "\n",
1059
  " <div>\n",
1060
  " \n",
1061
+ " <progress value='2001' max='5000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
1062
+ " [2001/5000 2:23:52 < 3:35:50, 0.23 it/s, Epoch 22.99/58]\n",
1063
  " </div>\n",
1064
  " <table border=\"1\" class=\"dataframe\">\n",
1065
  " <thead>\n",
 
1079
  " <td>18.128976</td>\n",
1080
  " <td>8.464310</td>\n",
1081
  " </tr>\n",
1082
+ " <tr>\n",
1083
+ " <td>2000</td>\n",
1084
+ " <td>0.002100</td>\n",
1085
+ " <td>0.591579</td>\n",
1086
+ " <td>18.885721</td>\n",
1087
+ " <td>8.653769</td>\n",
1088
+ " </tr>\n",
1089
  " </tbody>\n",
1090
  "</table><p>"
1091
  ],
 
2298
  "name": "stderr",
2299
  "output_type": "stream",
2300
  "text": [
2301
+ "Feature extractor saved in ./preprocessor_config.json\n",
2302
+ "The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`, you can safely ignore this message.\n",
2303
+ "***** Running Evaluation *****\n",
2304
+ " Num examples = 1237\n",
2305
+ " Batch size = 16\n",
2306
+ "Generate config GenerationConfig {\n",
2307
+ " \"begin_suppress_tokens\": [\n",
2308
+ " 220,\n",
2309
+ " 50257\n",
2310
+ " ],\n",
2311
+ " \"bos_token_id\": 50257,\n",
2312
+ " \"decoder_start_token_id\": 50258,\n",
2313
+ " \"eos_token_id\": 50257,\n",
2314
+ " \"max_length\": 448,\n",
2315
+ " \"pad_token_id\": 50257,\n",
2316
+ " \"suppress_tokens\": [],\n",
2317
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2318
+ " \"use_cache\": false\n",
2319
+ "}\n",
2320
+ "\n",
2321
+ "Generate config GenerationConfig {\n",
2322
+ " \"begin_suppress_tokens\": [\n",
2323
+ " 220,\n",
2324
+ " 50257\n",
2325
+ " ],\n",
2326
+ " \"bos_token_id\": 50257,\n",
2327
+ " \"decoder_start_token_id\": 50258,\n",
2328
+ " \"eos_token_id\": 50257,\n",
2329
+ " \"max_length\": 448,\n",
2330
+ " \"pad_token_id\": 50257,\n",
2331
+ " \"suppress_tokens\": [],\n",
2332
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2333
+ " \"use_cache\": false\n",
2334
+ "}\n",
2335
+ "\n",
2336
+ "Generate config GenerationConfig {\n",
2337
+ " \"begin_suppress_tokens\": [\n",
2338
+ " 220,\n",
2339
+ " 50257\n",
2340
+ " ],\n",
2341
+ " \"bos_token_id\": 50257,\n",
2342
+ " \"decoder_start_token_id\": 50258,\n",
2343
+ " \"eos_token_id\": 50257,\n",
2344
+ " \"max_length\": 448,\n",
2345
+ " \"pad_token_id\": 50257,\n",
2346
+ " \"suppress_tokens\": [],\n",
2347
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2348
+ " \"use_cache\": false\n",
2349
+ "}\n",
2350
+ "\n",
2351
+ "Generate config GenerationConfig {\n",
2352
+ " \"begin_suppress_tokens\": [\n",
2353
+ " 220,\n",
2354
+ " 50257\n",
2355
+ " ],\n",
2356
+ " \"bos_token_id\": 50257,\n",
2357
+ " \"decoder_start_token_id\": 50258,\n",
2358
+ " \"eos_token_id\": 50257,\n",
2359
+ " \"max_length\": 448,\n",
2360
+ " \"pad_token_id\": 50257,\n",
2361
+ " \"suppress_tokens\": [],\n",
2362
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2363
+ " \"use_cache\": false\n",
2364
+ "}\n",
2365
+ "\n",
2366
+ "Generate config GenerationConfig {\n",
2367
+ " \"begin_suppress_tokens\": [\n",
2368
+ " 220,\n",
2369
+ " 50257\n",
2370
+ " ],\n",
2371
+ " \"bos_token_id\": 50257,\n",
2372
+ " \"decoder_start_token_id\": 50258,\n",
2373
+ " \"eos_token_id\": 50257,\n",
2374
+ " \"max_length\": 448,\n",
2375
+ " \"pad_token_id\": 50257,\n",
2376
+ " \"suppress_tokens\": [],\n",
2377
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2378
+ " \"use_cache\": false\n",
2379
+ "}\n",
2380
+ "\n",
2381
+ "Generate config GenerationConfig {\n",
2382
+ " \"begin_suppress_tokens\": [\n",
2383
+ " 220,\n",
2384
+ " 50257\n",
2385
+ " ],\n",
2386
+ " \"bos_token_id\": 50257,\n",
2387
+ " \"decoder_start_token_id\": 50258,\n",
2388
+ " \"eos_token_id\": 50257,\n",
2389
+ " \"max_length\": 448,\n",
2390
+ " \"pad_token_id\": 50257,\n",
2391
+ " \"suppress_tokens\": [],\n",
2392
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2393
+ " \"use_cache\": false\n",
2394
+ "}\n",
2395
+ "\n",
2396
+ "Generate config GenerationConfig {\n",
2397
+ " \"begin_suppress_tokens\": [\n",
2398
+ " 220,\n",
2399
+ " 50257\n",
2400
+ " ],\n",
2401
+ " \"bos_token_id\": 50257,\n",
2402
+ " \"decoder_start_token_id\": 50258,\n",
2403
+ " \"eos_token_id\": 50257,\n",
2404
+ " \"max_length\": 448,\n",
2405
+ " \"pad_token_id\": 50257,\n",
2406
+ " \"suppress_tokens\": [],\n",
2407
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2408
+ " \"use_cache\": false\n",
2409
+ "}\n",
2410
+ "\n",
2411
+ "Generate config GenerationConfig {\n",
2412
+ " \"begin_suppress_tokens\": [\n",
2413
+ " 220,\n",
2414
+ " 50257\n",
2415
+ " ],\n",
2416
+ " \"bos_token_id\": 50257,\n",
2417
+ " \"decoder_start_token_id\": 50258,\n",
2418
+ " \"eos_token_id\": 50257,\n",
2419
+ " \"max_length\": 448,\n",
2420
+ " \"pad_token_id\": 50257,\n",
2421
+ " \"suppress_tokens\": [],\n",
2422
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2423
+ " \"use_cache\": false\n",
2424
+ "}\n",
2425
+ "\n",
2426
+ "Generate config GenerationConfig {\n",
2427
+ " \"begin_suppress_tokens\": [\n",
2428
+ " 220,\n",
2429
+ " 50257\n",
2430
+ " ],\n",
2431
+ " \"bos_token_id\": 50257,\n",
2432
+ " \"decoder_start_token_id\": 50258,\n",
2433
+ " \"eos_token_id\": 50257,\n",
2434
+ " \"max_length\": 448,\n",
2435
+ " \"pad_token_id\": 50257,\n",
2436
+ " \"suppress_tokens\": [],\n",
2437
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2438
+ " \"use_cache\": false\n",
2439
+ "}\n",
2440
+ "\n",
2441
+ "Generate config GenerationConfig {\n",
2442
+ " \"begin_suppress_tokens\": [\n",
2443
+ " 220,\n",
2444
+ " 50257\n",
2445
+ " ],\n",
2446
+ " \"bos_token_id\": 50257,\n",
2447
+ " \"decoder_start_token_id\": 50258,\n",
2448
+ " \"eos_token_id\": 50257,\n",
2449
+ " \"max_length\": 448,\n",
2450
+ " \"pad_token_id\": 50257,\n",
2451
+ " \"suppress_tokens\": [],\n",
2452
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2453
+ " \"use_cache\": false\n",
2454
+ "}\n",
2455
+ "\n",
2456
+ "Generate config GenerationConfig {\n",
2457
+ " \"begin_suppress_tokens\": [\n",
2458
+ " 220,\n",
2459
+ " 50257\n",
2460
+ " ],\n",
2461
+ " \"bos_token_id\": 50257,\n",
2462
+ " \"decoder_start_token_id\": 50258,\n",
2463
+ " \"eos_token_id\": 50257,\n",
2464
+ " \"max_length\": 448,\n",
2465
+ " \"pad_token_id\": 50257,\n",
2466
+ " \"suppress_tokens\": [],\n",
2467
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2468
+ " \"use_cache\": false\n",
2469
+ "}\n",
2470
+ "\n",
2471
+ "Generate config GenerationConfig {\n",
2472
+ " \"begin_suppress_tokens\": [\n",
2473
+ " 220,\n",
2474
+ " 50257\n",
2475
+ " ],\n",
2476
+ " \"bos_token_id\": 50257,\n",
2477
+ " \"decoder_start_token_id\": 50258,\n",
2478
+ " \"eos_token_id\": 50257,\n",
2479
+ " \"max_length\": 448,\n",
2480
+ " \"pad_token_id\": 50257,\n",
2481
+ " \"suppress_tokens\": [],\n",
2482
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2483
+ " \"use_cache\": false\n",
2484
+ "}\n",
2485
+ "\n",
2486
+ "Generate config GenerationConfig {\n",
2487
+ " \"begin_suppress_tokens\": [\n",
2488
+ " 220,\n",
2489
+ " 50257\n",
2490
+ " ],\n",
2491
+ " \"bos_token_id\": 50257,\n",
2492
+ " \"decoder_start_token_id\": 50258,\n",
2493
+ " \"eos_token_id\": 50257,\n",
2494
+ " \"max_length\": 448,\n",
2495
+ " \"pad_token_id\": 50257,\n",
2496
+ " \"suppress_tokens\": [],\n",
2497
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2498
+ " \"use_cache\": false\n",
2499
+ "}\n",
2500
+ "\n",
2501
+ "Generate config GenerationConfig {\n",
2502
+ " \"begin_suppress_tokens\": [\n",
2503
+ " 220,\n",
2504
+ " 50257\n",
2505
+ " ],\n",
2506
+ " \"bos_token_id\": 50257,\n",
2507
+ " \"decoder_start_token_id\": 50258,\n",
2508
+ " \"eos_token_id\": 50257,\n",
2509
+ " \"max_length\": 448,\n",
2510
+ " \"pad_token_id\": 50257,\n",
2511
+ " \"suppress_tokens\": [],\n",
2512
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2513
+ " \"use_cache\": false\n",
2514
+ "}\n",
2515
+ "\n",
2516
+ "Generate config GenerationConfig {\n",
2517
+ " \"begin_suppress_tokens\": [\n",
2518
+ " 220,\n",
2519
+ " 50257\n",
2520
+ " ],\n",
2521
+ " \"bos_token_id\": 50257,\n",
2522
+ " \"decoder_start_token_id\": 50258,\n",
2523
+ " \"eos_token_id\": 50257,\n",
2524
+ " \"max_length\": 448,\n",
2525
+ " \"pad_token_id\": 50257,\n",
2526
+ " \"suppress_tokens\": [],\n",
2527
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2528
+ " \"use_cache\": false\n",
2529
+ "}\n",
2530
+ "\n",
2531
+ "Generate config GenerationConfig {\n",
2532
+ " \"begin_suppress_tokens\": [\n",
2533
+ " 220,\n",
2534
+ " 50257\n",
2535
+ " ],\n",
2536
+ " \"bos_token_id\": 50257,\n",
2537
+ " \"decoder_start_token_id\": 50258,\n",
2538
+ " \"eos_token_id\": 50257,\n",
2539
+ " \"max_length\": 448,\n",
2540
+ " \"pad_token_id\": 50257,\n",
2541
+ " \"suppress_tokens\": [],\n",
2542
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2543
+ " \"use_cache\": false\n",
2544
+ "}\n",
2545
+ "\n",
2546
+ "Generate config GenerationConfig {\n",
2547
+ " \"begin_suppress_tokens\": [\n",
2548
+ " 220,\n",
2549
+ " 50257\n",
2550
+ " ],\n",
2551
+ " \"bos_token_id\": 50257,\n",
2552
+ " \"decoder_start_token_id\": 50258,\n",
2553
+ " \"eos_token_id\": 50257,\n",
2554
+ " \"max_length\": 448,\n",
2555
+ " \"pad_token_id\": 50257,\n",
2556
+ " \"suppress_tokens\": [],\n",
2557
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2558
+ " \"use_cache\": false\n",
2559
+ "}\n",
2560
+ "\n",
2561
+ "Generate config GenerationConfig {\n",
2562
+ " \"begin_suppress_tokens\": [\n",
2563
+ " 220,\n",
2564
+ " 50257\n",
2565
+ " ],\n",
2566
+ " \"bos_token_id\": 50257,\n",
2567
+ " \"decoder_start_token_id\": 50258,\n",
2568
+ " \"eos_token_id\": 50257,\n",
2569
+ " \"max_length\": 448,\n",
2570
+ " \"pad_token_id\": 50257,\n",
2571
+ " \"suppress_tokens\": [],\n",
2572
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2573
+ " \"use_cache\": false\n",
2574
+ "}\n",
2575
+ "\n",
2576
+ "Generate config GenerationConfig {\n",
2577
+ " \"begin_suppress_tokens\": [\n",
2578
+ " 220,\n",
2579
+ " 50257\n",
2580
+ " ],\n",
2581
+ " \"bos_token_id\": 50257,\n",
2582
+ " \"decoder_start_token_id\": 50258,\n",
2583
+ " \"eos_token_id\": 50257,\n",
2584
+ " \"max_length\": 448,\n",
2585
+ " \"pad_token_id\": 50257,\n",
2586
+ " \"suppress_tokens\": [],\n",
2587
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2588
+ " \"use_cache\": false\n",
2589
+ "}\n",
2590
+ "\n",
2591
+ "Generate config GenerationConfig {\n",
2592
+ " \"begin_suppress_tokens\": [\n",
2593
+ " 220,\n",
2594
+ " 50257\n",
2595
+ " ],\n",
2596
+ " \"bos_token_id\": 50257,\n",
2597
+ " \"decoder_start_token_id\": 50258,\n",
2598
+ " \"eos_token_id\": 50257,\n",
2599
+ " \"max_length\": 448,\n",
2600
+ " \"pad_token_id\": 50257,\n",
2601
+ " \"suppress_tokens\": [],\n",
2602
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2603
+ " \"use_cache\": false\n",
2604
+ "}\n",
2605
+ "\n",
2606
+ "Generate config GenerationConfig {\n",
2607
+ " \"begin_suppress_tokens\": [\n",
2608
+ " 220,\n",
2609
+ " 50257\n",
2610
+ " ],\n",
2611
+ " \"bos_token_id\": 50257,\n",
2612
+ " \"decoder_start_token_id\": 50258,\n",
2613
+ " \"eos_token_id\": 50257,\n",
2614
+ " \"max_length\": 448,\n",
2615
+ " \"pad_token_id\": 50257,\n",
2616
+ " \"suppress_tokens\": [],\n",
2617
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2618
+ " \"use_cache\": false\n",
2619
+ "}\n",
2620
+ "\n",
2621
+ "Generate config GenerationConfig {\n",
2622
+ " \"begin_suppress_tokens\": [\n",
2623
+ " 220,\n",
2624
+ " 50257\n",
2625
+ " ],\n",
2626
+ " \"bos_token_id\": 50257,\n",
2627
+ " \"decoder_start_token_id\": 50258,\n",
2628
+ " \"eos_token_id\": 50257,\n",
2629
+ " \"max_length\": 448,\n",
2630
+ " \"pad_token_id\": 50257,\n",
2631
+ " \"suppress_tokens\": [],\n",
2632
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2633
+ " \"use_cache\": false\n",
2634
+ "}\n",
2635
+ "\n",
2636
+ "Generate config GenerationConfig {\n",
2637
+ " \"begin_suppress_tokens\": [\n",
2638
+ " 220,\n",
2639
+ " 50257\n",
2640
+ " ],\n",
2641
+ " \"bos_token_id\": 50257,\n",
2642
+ " \"decoder_start_token_id\": 50258,\n",
2643
+ " \"eos_token_id\": 50257,\n",
2644
+ " \"max_length\": 448,\n",
2645
+ " \"pad_token_id\": 50257,\n",
2646
+ " \"suppress_tokens\": [],\n",
2647
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2648
+ " \"use_cache\": false\n",
2649
+ "}\n",
2650
+ "\n",
2651
+ "Generate config GenerationConfig {\n",
2652
+ " \"begin_suppress_tokens\": [\n",
2653
+ " 220,\n",
2654
+ " 50257\n",
2655
+ " ],\n",
2656
+ " \"bos_token_id\": 50257,\n",
2657
+ " \"decoder_start_token_id\": 50258,\n",
2658
+ " \"eos_token_id\": 50257,\n",
2659
+ " \"max_length\": 448,\n",
2660
+ " \"pad_token_id\": 50257,\n",
2661
+ " \"suppress_tokens\": [],\n",
2662
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2663
+ " \"use_cache\": false\n",
2664
+ "}\n",
2665
+ "\n",
2666
+ "Generate config GenerationConfig {\n",
2667
+ " \"begin_suppress_tokens\": [\n",
2668
+ " 220,\n",
2669
+ " 50257\n",
2670
+ " ],\n",
2671
+ " \"bos_token_id\": 50257,\n",
2672
+ " \"decoder_start_token_id\": 50258,\n",
2673
+ " \"eos_token_id\": 50257,\n",
2674
+ " \"max_length\": 448,\n",
2675
+ " \"pad_token_id\": 50257,\n",
2676
+ " \"suppress_tokens\": [],\n",
2677
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2678
+ " \"use_cache\": false\n",
2679
+ "}\n",
2680
+ "\n",
2681
+ "Generate config GenerationConfig {\n",
2682
+ " \"begin_suppress_tokens\": [\n",
2683
+ " 220,\n",
2684
+ " 50257\n",
2685
+ " ],\n",
2686
+ " \"bos_token_id\": 50257,\n",
2687
+ " \"decoder_start_token_id\": 50258,\n",
2688
+ " \"eos_token_id\": 50257,\n",
2689
+ " \"max_length\": 448,\n",
2690
+ " \"pad_token_id\": 50257,\n",
2691
+ " \"suppress_tokens\": [],\n",
2692
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2693
+ " \"use_cache\": false\n",
2694
+ "}\n",
2695
+ "\n"
2696
+ ]
2697
+ },
2698
+ {
2699
+ "name": "stderr",
2700
+ "output_type": "stream",
2701
+ "text": [
2702
+ "Generate config GenerationConfig {\n",
2703
+ " \"begin_suppress_tokens\": [\n",
2704
+ " 220,\n",
2705
+ " 50257\n",
2706
+ " ],\n",
2707
+ " \"bos_token_id\": 50257,\n",
2708
+ " \"decoder_start_token_id\": 50258,\n",
2709
+ " \"eos_token_id\": 50257,\n",
2710
+ " \"max_length\": 448,\n",
2711
+ " \"pad_token_id\": 50257,\n",
2712
+ " \"suppress_tokens\": [],\n",
2713
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2714
+ " \"use_cache\": false\n",
2715
+ "}\n",
2716
+ "\n",
2717
+ "Generate config GenerationConfig {\n",
2718
+ " \"begin_suppress_tokens\": [\n",
2719
+ " 220,\n",
2720
+ " 50257\n",
2721
+ " ],\n",
2722
+ " \"bos_token_id\": 50257,\n",
2723
+ " \"decoder_start_token_id\": 50258,\n",
2724
+ " \"eos_token_id\": 50257,\n",
2725
+ " \"max_length\": 448,\n",
2726
+ " \"pad_token_id\": 50257,\n",
2727
+ " \"suppress_tokens\": [],\n",
2728
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2729
+ " \"use_cache\": false\n",
2730
+ "}\n",
2731
+ "\n",
2732
+ "Generate config GenerationConfig {\n",
2733
+ " \"begin_suppress_tokens\": [\n",
2734
+ " 220,\n",
2735
+ " 50257\n",
2736
+ " ],\n",
2737
+ " \"bos_token_id\": 50257,\n",
2738
+ " \"decoder_start_token_id\": 50258,\n",
2739
+ " \"eos_token_id\": 50257,\n",
2740
+ " \"max_length\": 448,\n",
2741
+ " \"pad_token_id\": 50257,\n",
2742
+ " \"suppress_tokens\": [],\n",
2743
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2744
+ " \"use_cache\": false\n",
2745
+ "}\n",
2746
+ "\n",
2747
+ "Generate config GenerationConfig {\n",
2748
+ " \"begin_suppress_tokens\": [\n",
2749
+ " 220,\n",
2750
+ " 50257\n",
2751
+ " ],\n",
2752
+ " \"bos_token_id\": 50257,\n",
2753
+ " \"decoder_start_token_id\": 50258,\n",
2754
+ " \"eos_token_id\": 50257,\n",
2755
+ " \"max_length\": 448,\n",
2756
+ " \"pad_token_id\": 50257,\n",
2757
+ " \"suppress_tokens\": [],\n",
2758
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2759
+ " \"use_cache\": false\n",
2760
+ "}\n",
2761
+ "\n",
2762
+ "Generate config GenerationConfig {\n",
2763
+ " \"begin_suppress_tokens\": [\n",
2764
+ " 220,\n",
2765
+ " 50257\n",
2766
+ " ],\n",
2767
+ " \"bos_token_id\": 50257,\n",
2768
+ " \"decoder_start_token_id\": 50258,\n",
2769
+ " \"eos_token_id\": 50257,\n",
2770
+ " \"max_length\": 448,\n",
2771
+ " \"pad_token_id\": 50257,\n",
2772
+ " \"suppress_tokens\": [],\n",
2773
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2774
+ " \"use_cache\": false\n",
2775
+ "}\n",
2776
+ "\n",
2777
+ "Generate config GenerationConfig {\n",
2778
+ " \"begin_suppress_tokens\": [\n",
2779
+ " 220,\n",
2780
+ " 50257\n",
2781
+ " ],\n",
2782
+ " \"bos_token_id\": 50257,\n",
2783
+ " \"decoder_start_token_id\": 50258,\n",
2784
+ " \"eos_token_id\": 50257,\n",
2785
+ " \"max_length\": 448,\n",
2786
+ " \"pad_token_id\": 50257,\n",
2787
+ " \"suppress_tokens\": [],\n",
2788
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2789
+ " \"use_cache\": false\n",
2790
+ "}\n",
2791
+ "\n",
2792
+ "Generate config GenerationConfig {\n",
2793
+ " \"begin_suppress_tokens\": [\n",
2794
+ " 220,\n",
2795
+ " 50257\n",
2796
+ " ],\n",
2797
+ " \"bos_token_id\": 50257,\n",
2798
+ " \"decoder_start_token_id\": 50258,\n",
2799
+ " \"eos_token_id\": 50257,\n",
2800
+ " \"max_length\": 448,\n",
2801
+ " \"pad_token_id\": 50257,\n",
2802
+ " \"suppress_tokens\": [],\n",
2803
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2804
+ " \"use_cache\": false\n",
2805
+ "}\n",
2806
+ "\n",
2807
+ "Generate config GenerationConfig {\n",
2808
+ " \"begin_suppress_tokens\": [\n",
2809
+ " 220,\n",
2810
+ " 50257\n",
2811
+ " ],\n",
2812
+ " \"bos_token_id\": 50257,\n",
2813
+ " \"decoder_start_token_id\": 50258,\n",
2814
+ " \"eos_token_id\": 50257,\n",
2815
+ " \"max_length\": 448,\n",
2816
+ " \"pad_token_id\": 50257,\n",
2817
+ " \"suppress_tokens\": [],\n",
2818
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2819
+ " \"use_cache\": false\n",
2820
+ "}\n",
2821
+ "\n",
2822
+ "Generate config GenerationConfig {\n",
2823
+ " \"begin_suppress_tokens\": [\n",
2824
+ " 220,\n",
2825
+ " 50257\n",
2826
+ " ],\n",
2827
+ " \"bos_token_id\": 50257,\n",
2828
+ " \"decoder_start_token_id\": 50258,\n",
2829
+ " \"eos_token_id\": 50257,\n",
2830
+ " \"max_length\": 448,\n",
2831
+ " \"pad_token_id\": 50257,\n",
2832
+ " \"suppress_tokens\": [],\n",
2833
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2834
+ " \"use_cache\": false\n",
2835
+ "}\n",
2836
+ "\n",
2837
+ "Generate config GenerationConfig {\n",
2838
+ " \"begin_suppress_tokens\": [\n",
2839
+ " 220,\n",
2840
+ " 50257\n",
2841
+ " ],\n",
2842
+ " \"bos_token_id\": 50257,\n",
2843
+ " \"decoder_start_token_id\": 50258,\n",
2844
+ " \"eos_token_id\": 50257,\n",
2845
+ " \"max_length\": 448,\n",
2846
+ " \"pad_token_id\": 50257,\n",
2847
+ " \"suppress_tokens\": [],\n",
2848
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2849
+ " \"use_cache\": false\n",
2850
+ "}\n",
2851
+ "\n",
2852
+ "Generate config GenerationConfig {\n",
2853
+ " \"begin_suppress_tokens\": [\n",
2854
+ " 220,\n",
2855
+ " 50257\n",
2856
+ " ],\n",
2857
+ " \"bos_token_id\": 50257,\n",
2858
+ " \"decoder_start_token_id\": 50258,\n",
2859
+ " \"eos_token_id\": 50257,\n",
2860
+ " \"max_length\": 448,\n",
2861
+ " \"pad_token_id\": 50257,\n",
2862
+ " \"suppress_tokens\": [],\n",
2863
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2864
+ " \"use_cache\": false\n",
2865
+ "}\n",
2866
+ "\n",
2867
+ "Generate config GenerationConfig {\n",
2868
+ " \"begin_suppress_tokens\": [\n",
2869
+ " 220,\n",
2870
+ " 50257\n",
2871
+ " ],\n",
2872
+ " \"bos_token_id\": 50257,\n",
2873
+ " \"decoder_start_token_id\": 50258,\n",
2874
+ " \"eos_token_id\": 50257,\n",
2875
+ " \"max_length\": 448,\n",
2876
+ " \"pad_token_id\": 50257,\n",
2877
+ " \"suppress_tokens\": [],\n",
2878
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2879
+ " \"use_cache\": false\n",
2880
+ "}\n",
2881
+ "\n",
2882
+ "Generate config GenerationConfig {\n",
2883
+ " \"begin_suppress_tokens\": [\n",
2884
+ " 220,\n",
2885
+ " 50257\n",
2886
+ " ],\n",
2887
+ " \"bos_token_id\": 50257,\n",
2888
+ " \"decoder_start_token_id\": 50258,\n",
2889
+ " \"eos_token_id\": 50257,\n",
2890
+ " \"max_length\": 448,\n",
2891
+ " \"pad_token_id\": 50257,\n",
2892
+ " \"suppress_tokens\": [],\n",
2893
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2894
+ " \"use_cache\": false\n",
2895
+ "}\n",
2896
+ "\n",
2897
+ "Generate config GenerationConfig {\n",
2898
+ " \"begin_suppress_tokens\": [\n",
2899
+ " 220,\n",
2900
+ " 50257\n",
2901
+ " ],\n",
2902
+ " \"bos_token_id\": 50257,\n",
2903
+ " \"decoder_start_token_id\": 50258,\n",
2904
+ " \"eos_token_id\": 50257,\n",
2905
+ " \"max_length\": 448,\n",
2906
+ " \"pad_token_id\": 50257,\n",
2907
+ " \"suppress_tokens\": [],\n",
2908
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2909
+ " \"use_cache\": false\n",
2910
+ "}\n",
2911
+ "\n",
2912
+ "Generate config GenerationConfig {\n",
2913
+ " \"begin_suppress_tokens\": [\n",
2914
+ " 220,\n",
2915
+ " 50257\n",
2916
+ " ],\n",
2917
+ " \"bos_token_id\": 50257,\n",
2918
+ " \"decoder_start_token_id\": 50258,\n",
2919
+ " \"eos_token_id\": 50257,\n",
2920
+ " \"max_length\": 448,\n",
2921
+ " \"pad_token_id\": 50257,\n",
2922
+ " \"suppress_tokens\": [],\n",
2923
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2924
+ " \"use_cache\": false\n",
2925
+ "}\n",
2926
+ "\n",
2927
+ "Generate config GenerationConfig {\n",
2928
+ " \"begin_suppress_tokens\": [\n",
2929
+ " 220,\n",
2930
+ " 50257\n",
2931
+ " ],\n",
2932
+ " \"bos_token_id\": 50257,\n",
2933
+ " \"decoder_start_token_id\": 50258,\n",
2934
+ " \"eos_token_id\": 50257,\n",
2935
+ " \"max_length\": 448,\n",
2936
+ " \"pad_token_id\": 50257,\n",
2937
+ " \"suppress_tokens\": [],\n",
2938
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2939
+ " \"use_cache\": false\n",
2940
+ "}\n",
2941
+ "\n",
2942
+ "Generate config GenerationConfig {\n",
2943
+ " \"begin_suppress_tokens\": [\n",
2944
+ " 220,\n",
2945
+ " 50257\n",
2946
+ " ],\n",
2947
+ " \"bos_token_id\": 50257,\n",
2948
+ " \"decoder_start_token_id\": 50258,\n",
2949
+ " \"eos_token_id\": 50257,\n",
2950
+ " \"max_length\": 448,\n",
2951
+ " \"pad_token_id\": 50257,\n",
2952
+ " \"suppress_tokens\": [],\n",
2953
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2954
+ " \"use_cache\": false\n",
2955
+ "}\n",
2956
+ "\n",
2957
+ "Generate config GenerationConfig {\n",
2958
+ " \"begin_suppress_tokens\": [\n",
2959
+ " 220,\n",
2960
+ " 50257\n",
2961
+ " ],\n",
2962
+ " \"bos_token_id\": 50257,\n",
2963
+ " \"decoder_start_token_id\": 50258,\n",
2964
+ " \"eos_token_id\": 50257,\n",
2965
+ " \"max_length\": 448,\n",
2966
+ " \"pad_token_id\": 50257,\n",
2967
+ " \"suppress_tokens\": [],\n",
2968
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2969
+ " \"use_cache\": false\n",
2970
+ "}\n",
2971
+ "\n",
2972
+ "Generate config GenerationConfig {\n",
2973
+ " \"begin_suppress_tokens\": [\n",
2974
+ " 220,\n",
2975
+ " 50257\n",
2976
+ " ],\n",
2977
+ " \"bos_token_id\": 50257,\n",
2978
+ " \"decoder_start_token_id\": 50258,\n",
2979
+ " \"eos_token_id\": 50257,\n",
2980
+ " \"max_length\": 448,\n",
2981
+ " \"pad_token_id\": 50257,\n",
2982
+ " \"suppress_tokens\": [],\n",
2983
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2984
+ " \"use_cache\": false\n",
2985
+ "}\n",
2986
+ "\n",
2987
+ "Generate config GenerationConfig {\n",
2988
+ " \"begin_suppress_tokens\": [\n",
2989
+ " 220,\n",
2990
+ " 50257\n",
2991
+ " ],\n",
2992
+ " \"bos_token_id\": 50257,\n",
2993
+ " \"decoder_start_token_id\": 50258,\n",
2994
+ " \"eos_token_id\": 50257,\n",
2995
+ " \"max_length\": 448,\n",
2996
+ " \"pad_token_id\": 50257,\n",
2997
+ " \"suppress_tokens\": [],\n",
2998
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
2999
+ " \"use_cache\": false\n",
3000
+ "}\n",
3001
+ "\n",
3002
+ "Generate config GenerationConfig {\n",
3003
+ " \"begin_suppress_tokens\": [\n",
3004
+ " 220,\n",
3005
+ " 50257\n",
3006
+ " ],\n",
3007
+ " \"bos_token_id\": 50257,\n",
3008
+ " \"decoder_start_token_id\": 50258,\n",
3009
+ " \"eos_token_id\": 50257,\n",
3010
+ " \"max_length\": 448,\n",
3011
+ " \"pad_token_id\": 50257,\n",
3012
+ " \"suppress_tokens\": [],\n",
3013
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3014
+ " \"use_cache\": false\n",
3015
+ "}\n",
3016
+ "\n",
3017
+ "Generate config GenerationConfig {\n",
3018
+ " \"begin_suppress_tokens\": [\n",
3019
+ " 220,\n",
3020
+ " 50257\n",
3021
+ " ],\n",
3022
+ " \"bos_token_id\": 50257,\n",
3023
+ " \"decoder_start_token_id\": 50258,\n",
3024
+ " \"eos_token_id\": 50257,\n",
3025
+ " \"max_length\": 448,\n",
3026
+ " \"pad_token_id\": 50257,\n",
3027
+ " \"suppress_tokens\": [],\n",
3028
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3029
+ " \"use_cache\": false\n",
3030
+ "}\n",
3031
+ "\n",
3032
+ "Generate config GenerationConfig {\n",
3033
+ " \"begin_suppress_tokens\": [\n",
3034
+ " 220,\n",
3035
+ " 50257\n",
3036
+ " ],\n",
3037
+ " \"bos_token_id\": 50257,\n",
3038
+ " \"decoder_start_token_id\": 50258,\n",
3039
+ " \"eos_token_id\": 50257,\n",
3040
+ " \"max_length\": 448,\n",
3041
+ " \"pad_token_id\": 50257,\n",
3042
+ " \"suppress_tokens\": [],\n",
3043
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3044
+ " \"use_cache\": false\n",
3045
+ "}\n",
3046
+ "\n",
3047
+ "Generate config GenerationConfig {\n",
3048
+ " \"begin_suppress_tokens\": [\n",
3049
+ " 220,\n",
3050
+ " 50257\n",
3051
+ " ],\n",
3052
+ " \"bos_token_id\": 50257,\n",
3053
+ " \"decoder_start_token_id\": 50258,\n",
3054
+ " \"eos_token_id\": 50257,\n",
3055
+ " \"max_length\": 448,\n",
3056
+ " \"pad_token_id\": 50257,\n",
3057
+ " \"suppress_tokens\": [],\n",
3058
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3059
+ " \"use_cache\": false\n",
3060
+ "}\n",
3061
+ "\n",
3062
+ "Generate config GenerationConfig {\n",
3063
+ " \"begin_suppress_tokens\": [\n",
3064
+ " 220,\n",
3065
+ " 50257\n",
3066
+ " ],\n",
3067
+ " \"bos_token_id\": 50257,\n",
3068
+ " \"decoder_start_token_id\": 50258,\n",
3069
+ " \"eos_token_id\": 50257,\n",
3070
+ " \"max_length\": 448,\n",
3071
+ " \"pad_token_id\": 50257,\n",
3072
+ " \"suppress_tokens\": [],\n",
3073
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3074
+ " \"use_cache\": false\n",
3075
+ "}\n",
3076
+ "\n",
3077
+ "Generate config GenerationConfig {\n",
3078
+ " \"begin_suppress_tokens\": [\n",
3079
+ " 220,\n",
3080
+ " 50257\n",
3081
+ " ],\n",
3082
+ " \"bos_token_id\": 50257,\n",
3083
+ " \"decoder_start_token_id\": 50258,\n",
3084
+ " \"eos_token_id\": 50257,\n",
3085
+ " \"max_length\": 448,\n",
3086
+ " \"pad_token_id\": 50257,\n",
3087
+ " \"suppress_tokens\": [],\n",
3088
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3089
+ " \"use_cache\": false\n",
3090
+ "}\n",
3091
+ "\n",
3092
+ "Generate config GenerationConfig {\n",
3093
+ " \"begin_suppress_tokens\": [\n",
3094
+ " 220,\n",
3095
+ " 50257\n",
3096
+ " ],\n",
3097
+ " \"bos_token_id\": 50257,\n",
3098
+ " \"decoder_start_token_id\": 50258,\n",
3099
+ " \"eos_token_id\": 50257,\n",
3100
+ " \"max_length\": 448,\n",
3101
+ " \"pad_token_id\": 50257,\n",
3102
+ " \"suppress_tokens\": [],\n",
3103
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3104
+ " \"use_cache\": false\n",
3105
+ "}\n",
3106
+ "\n"
3107
+ ]
3108
+ },
3109
+ {
3110
+ "name": "stderr",
3111
+ "output_type": "stream",
3112
+ "text": [
3113
+ "Generate config GenerationConfig {\n",
3114
+ " \"begin_suppress_tokens\": [\n",
3115
+ " 220,\n",
3116
+ " 50257\n",
3117
+ " ],\n",
3118
+ " \"bos_token_id\": 50257,\n",
3119
+ " \"decoder_start_token_id\": 50258,\n",
3120
+ " \"eos_token_id\": 50257,\n",
3121
+ " \"max_length\": 448,\n",
3122
+ " \"pad_token_id\": 50257,\n",
3123
+ " \"suppress_tokens\": [],\n",
3124
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3125
+ " \"use_cache\": false\n",
3126
+ "}\n",
3127
+ "\n",
3128
+ "Generate config GenerationConfig {\n",
3129
+ " \"begin_suppress_tokens\": [\n",
3130
+ " 220,\n",
3131
+ " 50257\n",
3132
+ " ],\n",
3133
+ " \"bos_token_id\": 50257,\n",
3134
+ " \"decoder_start_token_id\": 50258,\n",
3135
+ " \"eos_token_id\": 50257,\n",
3136
+ " \"max_length\": 448,\n",
3137
+ " \"pad_token_id\": 50257,\n",
3138
+ " \"suppress_tokens\": [],\n",
3139
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3140
+ " \"use_cache\": false\n",
3141
+ "}\n",
3142
+ "\n",
3143
+ "Generate config GenerationConfig {\n",
3144
+ " \"begin_suppress_tokens\": [\n",
3145
+ " 220,\n",
3146
+ " 50257\n",
3147
+ " ],\n",
3148
+ " \"bos_token_id\": 50257,\n",
3149
+ " \"decoder_start_token_id\": 50258,\n",
3150
+ " \"eos_token_id\": 50257,\n",
3151
+ " \"max_length\": 448,\n",
3152
+ " \"pad_token_id\": 50257,\n",
3153
+ " \"suppress_tokens\": [],\n",
3154
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3155
+ " \"use_cache\": false\n",
3156
+ "}\n",
3157
+ "\n",
3158
+ "Generate config GenerationConfig {\n",
3159
+ " \"begin_suppress_tokens\": [\n",
3160
+ " 220,\n",
3161
+ " 50257\n",
3162
+ " ],\n",
3163
+ " \"bos_token_id\": 50257,\n",
3164
+ " \"decoder_start_token_id\": 50258,\n",
3165
+ " \"eos_token_id\": 50257,\n",
3166
+ " \"max_length\": 448,\n",
3167
+ " \"pad_token_id\": 50257,\n",
3168
+ " \"suppress_tokens\": [],\n",
3169
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3170
+ " \"use_cache\": false\n",
3171
+ "}\n",
3172
+ "\n",
3173
+ "Generate config GenerationConfig {\n",
3174
+ " \"begin_suppress_tokens\": [\n",
3175
+ " 220,\n",
3176
+ " 50257\n",
3177
+ " ],\n",
3178
+ " \"bos_token_id\": 50257,\n",
3179
+ " \"decoder_start_token_id\": 50258,\n",
3180
+ " \"eos_token_id\": 50257,\n",
3181
+ " \"max_length\": 448,\n",
3182
+ " \"pad_token_id\": 50257,\n",
3183
+ " \"suppress_tokens\": [],\n",
3184
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3185
+ " \"use_cache\": false\n",
3186
+ "}\n",
3187
+ "\n",
3188
+ "Generate config GenerationConfig {\n",
3189
+ " \"begin_suppress_tokens\": [\n",
3190
+ " 220,\n",
3191
+ " 50257\n",
3192
+ " ],\n",
3193
+ " \"bos_token_id\": 50257,\n",
3194
+ " \"decoder_start_token_id\": 50258,\n",
3195
+ " \"eos_token_id\": 50257,\n",
3196
+ " \"max_length\": 448,\n",
3197
+ " \"pad_token_id\": 50257,\n",
3198
+ " \"suppress_tokens\": [],\n",
3199
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3200
+ " \"use_cache\": false\n",
3201
+ "}\n",
3202
+ "\n",
3203
+ "Generate config GenerationConfig {\n",
3204
+ " \"begin_suppress_tokens\": [\n",
3205
+ " 220,\n",
3206
+ " 50257\n",
3207
+ " ],\n",
3208
+ " \"bos_token_id\": 50257,\n",
3209
+ " \"decoder_start_token_id\": 50258,\n",
3210
+ " \"eos_token_id\": 50257,\n",
3211
+ " \"max_length\": 448,\n",
3212
+ " \"pad_token_id\": 50257,\n",
3213
+ " \"suppress_tokens\": [],\n",
3214
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3215
+ " \"use_cache\": false\n",
3216
+ "}\n",
3217
+ "\n",
3218
+ "Generate config GenerationConfig {\n",
3219
+ " \"begin_suppress_tokens\": [\n",
3220
+ " 220,\n",
3221
+ " 50257\n",
3222
+ " ],\n",
3223
+ " \"bos_token_id\": 50257,\n",
3224
+ " \"decoder_start_token_id\": 50258,\n",
3225
+ " \"eos_token_id\": 50257,\n",
3226
+ " \"max_length\": 448,\n",
3227
+ " \"pad_token_id\": 50257,\n",
3228
+ " \"suppress_tokens\": [],\n",
3229
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3230
+ " \"use_cache\": false\n",
3231
+ "}\n",
3232
+ "\n",
3233
+ "Generate config GenerationConfig {\n",
3234
+ " \"begin_suppress_tokens\": [\n",
3235
+ " 220,\n",
3236
+ " 50257\n",
3237
+ " ],\n",
3238
+ " \"bos_token_id\": 50257,\n",
3239
+ " \"decoder_start_token_id\": 50258,\n",
3240
+ " \"eos_token_id\": 50257,\n",
3241
+ " \"max_length\": 448,\n",
3242
+ " \"pad_token_id\": 50257,\n",
3243
+ " \"suppress_tokens\": [],\n",
3244
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3245
+ " \"use_cache\": false\n",
3246
+ "}\n",
3247
+ "\n",
3248
+ "Generate config GenerationConfig {\n",
3249
+ " \"begin_suppress_tokens\": [\n",
3250
+ " 220,\n",
3251
+ " 50257\n",
3252
+ " ],\n",
3253
+ " \"bos_token_id\": 50257,\n",
3254
+ " \"decoder_start_token_id\": 50258,\n",
3255
+ " \"eos_token_id\": 50257,\n",
3256
+ " \"max_length\": 448,\n",
3257
+ " \"pad_token_id\": 50257,\n",
3258
+ " \"suppress_tokens\": [],\n",
3259
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3260
+ " \"use_cache\": false\n",
3261
+ "}\n",
3262
+ "\n",
3263
+ "Generate config GenerationConfig {\n",
3264
+ " \"begin_suppress_tokens\": [\n",
3265
+ " 220,\n",
3266
+ " 50257\n",
3267
+ " ],\n",
3268
+ " \"bos_token_id\": 50257,\n",
3269
+ " \"decoder_start_token_id\": 50258,\n",
3270
+ " \"eos_token_id\": 50257,\n",
3271
+ " \"max_length\": 448,\n",
3272
+ " \"pad_token_id\": 50257,\n",
3273
+ " \"suppress_tokens\": [],\n",
3274
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3275
+ " \"use_cache\": false\n",
3276
+ "}\n",
3277
+ "\n",
3278
+ "Generate config GenerationConfig {\n",
3279
+ " \"begin_suppress_tokens\": [\n",
3280
+ " 220,\n",
3281
+ " 50257\n",
3282
+ " ],\n",
3283
+ " \"bos_token_id\": 50257,\n",
3284
+ " \"decoder_start_token_id\": 50258,\n",
3285
+ " \"eos_token_id\": 50257,\n",
3286
+ " \"max_length\": 448,\n",
3287
+ " \"pad_token_id\": 50257,\n",
3288
+ " \"suppress_tokens\": [],\n",
3289
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3290
+ " \"use_cache\": false\n",
3291
+ "}\n",
3292
+ "\n",
3293
+ "Generate config GenerationConfig {\n",
3294
+ " \"begin_suppress_tokens\": [\n",
3295
+ " 220,\n",
3296
+ " 50257\n",
3297
+ " ],\n",
3298
+ " \"bos_token_id\": 50257,\n",
3299
+ " \"decoder_start_token_id\": 50258,\n",
3300
+ " \"eos_token_id\": 50257,\n",
3301
+ " \"max_length\": 448,\n",
3302
+ " \"pad_token_id\": 50257,\n",
3303
+ " \"suppress_tokens\": [],\n",
3304
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3305
+ " \"use_cache\": false\n",
3306
+ "}\n",
3307
+ "\n",
3308
+ "Generate config GenerationConfig {\n",
3309
+ " \"begin_suppress_tokens\": [\n",
3310
+ " 220,\n",
3311
+ " 50257\n",
3312
+ " ],\n",
3313
+ " \"bos_token_id\": 50257,\n",
3314
+ " \"decoder_start_token_id\": 50258,\n",
3315
+ " \"eos_token_id\": 50257,\n",
3316
+ " \"max_length\": 448,\n",
3317
+ " \"pad_token_id\": 50257,\n",
3318
+ " \"suppress_tokens\": [],\n",
3319
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3320
+ " \"use_cache\": false\n",
3321
+ "}\n",
3322
+ "\n",
3323
+ "Generate config GenerationConfig {\n",
3324
+ " \"begin_suppress_tokens\": [\n",
3325
+ " 220,\n",
3326
+ " 50257\n",
3327
+ " ],\n",
3328
+ " \"bos_token_id\": 50257,\n",
3329
+ " \"decoder_start_token_id\": 50258,\n",
3330
+ " \"eos_token_id\": 50257,\n",
3331
+ " \"max_length\": 448,\n",
3332
+ " \"pad_token_id\": 50257,\n",
3333
+ " \"suppress_tokens\": [],\n",
3334
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3335
+ " \"use_cache\": false\n",
3336
+ "}\n",
3337
+ "\n",
3338
+ "Generate config GenerationConfig {\n",
3339
+ " \"begin_suppress_tokens\": [\n",
3340
+ " 220,\n",
3341
+ " 50257\n",
3342
+ " ],\n",
3343
+ " \"bos_token_id\": 50257,\n",
3344
+ " \"decoder_start_token_id\": 50258,\n",
3345
+ " \"eos_token_id\": 50257,\n",
3346
+ " \"max_length\": 448,\n",
3347
+ " \"pad_token_id\": 50257,\n",
3348
+ " \"suppress_tokens\": [],\n",
3349
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3350
+ " \"use_cache\": false\n",
3351
+ "}\n",
3352
+ "\n",
3353
+ "Generate config GenerationConfig {\n",
3354
+ " \"begin_suppress_tokens\": [\n",
3355
+ " 220,\n",
3356
+ " 50257\n",
3357
+ " ],\n",
3358
+ " \"bos_token_id\": 50257,\n",
3359
+ " \"decoder_start_token_id\": 50258,\n",
3360
+ " \"eos_token_id\": 50257,\n",
3361
+ " \"max_length\": 448,\n",
3362
+ " \"pad_token_id\": 50257,\n",
3363
+ " \"suppress_tokens\": [],\n",
3364
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3365
+ " \"use_cache\": false\n",
3366
+ "}\n",
3367
+ "\n",
3368
+ "Generate config GenerationConfig {\n",
3369
+ " \"begin_suppress_tokens\": [\n",
3370
+ " 220,\n",
3371
+ " 50257\n",
3372
+ " ],\n",
3373
+ " \"bos_token_id\": 50257,\n",
3374
+ " \"decoder_start_token_id\": 50258,\n",
3375
+ " \"eos_token_id\": 50257,\n",
3376
+ " \"max_length\": 448,\n",
3377
+ " \"pad_token_id\": 50257,\n",
3378
+ " \"suppress_tokens\": [],\n",
3379
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3380
+ " \"use_cache\": false\n",
3381
+ "}\n",
3382
+ "\n",
3383
+ "Generate config GenerationConfig {\n",
3384
+ " \"begin_suppress_tokens\": [\n",
3385
+ " 220,\n",
3386
+ " 50257\n",
3387
+ " ],\n",
3388
+ " \"bos_token_id\": 50257,\n",
3389
+ " \"decoder_start_token_id\": 50258,\n",
3390
+ " \"eos_token_id\": 50257,\n",
3391
+ " \"max_length\": 448,\n",
3392
+ " \"pad_token_id\": 50257,\n",
3393
+ " \"suppress_tokens\": [],\n",
3394
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3395
+ " \"use_cache\": false\n",
3396
+ "}\n",
3397
+ "\n",
3398
+ "Generate config GenerationConfig {\n",
3399
+ " \"begin_suppress_tokens\": [\n",
3400
+ " 220,\n",
3401
+ " 50257\n",
3402
+ " ],\n",
3403
+ " \"bos_token_id\": 50257,\n",
3404
+ " \"decoder_start_token_id\": 50258,\n",
3405
+ " \"eos_token_id\": 50257,\n",
3406
+ " \"max_length\": 448,\n",
3407
+ " \"pad_token_id\": 50257,\n",
3408
+ " \"suppress_tokens\": [],\n",
3409
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3410
+ " \"use_cache\": false\n",
3411
+ "}\n",
3412
+ "\n",
3413
+ "Generate config GenerationConfig {\n",
3414
+ " \"begin_suppress_tokens\": [\n",
3415
+ " 220,\n",
3416
+ " 50257\n",
3417
+ " ],\n",
3418
+ " \"bos_token_id\": 50257,\n",
3419
+ " \"decoder_start_token_id\": 50258,\n",
3420
+ " \"eos_token_id\": 50257,\n",
3421
+ " \"max_length\": 448,\n",
3422
+ " \"pad_token_id\": 50257,\n",
3423
+ " \"suppress_tokens\": [],\n",
3424
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3425
+ " \"use_cache\": false\n",
3426
+ "}\n",
3427
+ "\n",
3428
+ "Generate config GenerationConfig {\n",
3429
+ " \"begin_suppress_tokens\": [\n",
3430
+ " 220,\n",
3431
+ " 50257\n",
3432
+ " ],\n",
3433
+ " \"bos_token_id\": 50257,\n",
3434
+ " \"decoder_start_token_id\": 50258,\n",
3435
+ " \"eos_token_id\": 50257,\n",
3436
+ " \"max_length\": 448,\n",
3437
+ " \"pad_token_id\": 50257,\n",
3438
+ " \"suppress_tokens\": [],\n",
3439
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3440
+ " \"use_cache\": false\n",
3441
+ "}\n",
3442
+ "\n",
3443
+ "Generate config GenerationConfig {\n",
3444
+ " \"begin_suppress_tokens\": [\n",
3445
+ " 220,\n",
3446
+ " 50257\n",
3447
+ " ],\n",
3448
+ " \"bos_token_id\": 50257,\n",
3449
+ " \"decoder_start_token_id\": 50258,\n",
3450
+ " \"eos_token_id\": 50257,\n",
3451
+ " \"max_length\": 448,\n",
3452
+ " \"pad_token_id\": 50257,\n",
3453
+ " \"suppress_tokens\": [],\n",
3454
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3455
+ " \"use_cache\": false\n",
3456
+ "}\n",
3457
+ "\n",
3458
+ "Generate config GenerationConfig {\n",
3459
+ " \"begin_suppress_tokens\": [\n",
3460
+ " 220,\n",
3461
+ " 50257\n",
3462
+ " ],\n",
3463
+ " \"bos_token_id\": 50257,\n",
3464
+ " \"decoder_start_token_id\": 50258,\n",
3465
+ " \"eos_token_id\": 50257,\n",
3466
+ " \"max_length\": 448,\n",
3467
+ " \"pad_token_id\": 50257,\n",
3468
+ " \"suppress_tokens\": [],\n",
3469
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3470
+ " \"use_cache\": false\n",
3471
+ "}\n",
3472
+ "\n",
3473
+ "Generate config GenerationConfig {\n",
3474
+ " \"begin_suppress_tokens\": [\n",
3475
+ " 220,\n",
3476
+ " 50257\n",
3477
+ " ],\n",
3478
+ " \"bos_token_id\": 50257,\n",
3479
+ " \"decoder_start_token_id\": 50258,\n",
3480
+ " \"eos_token_id\": 50257,\n",
3481
+ " \"max_length\": 448,\n",
3482
+ " \"pad_token_id\": 50257,\n",
3483
+ " \"suppress_tokens\": [],\n",
3484
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3485
+ " \"use_cache\": false\n",
3486
+ "}\n",
3487
+ "\n",
3488
+ "Saving model checkpoint to ./checkpoint-2000\n",
3489
+ "Configuration saved in ./checkpoint-2000/config.json\n",
3490
+ "Model weights saved in ./checkpoint-2000/pytorch_model.bin\n",
3491
+ "Feature extractor saved in ./checkpoint-2000/preprocessor_config.json\n",
3492
  "Feature extractor saved in ./preprocessor_config.json\n"
3493
  ]
3494
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:04a4c5aa4fd868f15c45ea43819bf1a6d4e1cd9a54087bf4c7e3542040491896
3
  size 3055754841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18820e99e5a7c711d06d1dd09f04bb3b52f42be904581fb0717f6ae03ad63279
3
  size 3055754841
runs/Dec18_13-16-20_150-136-94-223/events.out.tfevents.1671369384.150-136-94-223.188704.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91d5c1e008fca368c38df82e9c94653dc1219462e0d29b6e634a51da2fe160f3
3
- size 10920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ab8e7c32a8f4eda61bd1d92319aa3291260ea54e824d21a1fbcabb9eeec4e3a
3
+ size 17565