diff --git a/use_case_examples/lora_finetune/gpt2_finetune_hybrid.ipynb b/use_case_examples/lora_finetune/gpt2_finetune_hybrid.ipynb index 8ee6072c43..d103253eeb 100644 --- a/use_case_examples/lora_finetune/gpt2_finetune_hybrid.ipynb +++ b/use_case_examples/lora_finetune/gpt2_finetune_hybrid.ipynb @@ -246,8 +246,8 @@ " # modules in order to get rid of the weights\n", " if (\n", " isinstance(module, Conv1D)\n", - " or include_embedding_layers\n", - " and (isinstance(module, Embedding) or \"lm_head\" in name)\n", + " or include_embedding_layers # noqa: W503\n", + " and (isinstance(module, Embedding) or \"lm_head\" in name) # noqa: W503\n", " ):\n", " remote_names.append(name)\n", "\n", @@ -397,7 +397,7 @@ "To disable this warning, you can either:\n", "\t- Avoid using `tokenizers` before the fork if possible\n", "\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n", - "Training Progress: 1%| | 1/100 [04:21<7:11:59, 261.81s/it]" + "Training Progress: 1%| | 1/100 [04:24<7:17:11, 264.97s/it]" ] }, { @@ -411,7 +411,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 2%|▏ | 2/100 [05:37<4:08:32, 152.17s/it]" + "Training Progress: 2%|▏ | 2/100 [05:41<4:12:04, 154.33s/it]" ] }, { @@ -425,7 +425,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 3%|▎ | 3/100 [06:53<3:10:17, 117.70s/it]" + "Training Progress: 3%|▎ | 3/100 [06:58<3:12:09, 118.86s/it]" ] }, { @@ -439,7 +439,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 4%|▍ | 4/100 [08:11<2:42:54, 101.82s/it]" + "Training Progress: 4%|▍ | 4/100 [08:14<2:43:19, 102.08s/it]" ] }, { @@ -453,7 +453,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 5%|▌ | 5/100 [09:29<2:27:34, 93.21s/it] " + "Training Progress: 5%|▌ | 5/100 [09:32<2:27:46, 93.33s/it] " ] }, { @@ -467,7 +467,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 6%|▌ | 6/100 [10:46<2:17:27, 87.73s/it]" + "Training Progress: 6%|▌ | 6/100 [10:49<2:17:14, 87.60s/it]" ] }, { @@ -481,7 +481,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 7%|▋ | 7/100 [12:02<2:10:11, 84.00s/it]" + "Training Progress: 7%|▋ | 7/100 [12:05<2:09:55, 83.83s/it]" ] }, { @@ -495,7 +495,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 8%|▊ | 8/100 [13:19<2:05:08, 81.62s/it]" + "Training Progress: 8%|▊ | 8/100 [13:21<2:05:04, 81.57s/it]" ] }, { @@ -509,7 +509,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 9%|▉ | 9/100 [14:36<2:01:38, 80.21s/it]" + "Training Progress: 9%|▉ | 9/100 [14:38<2:01:25, 80.06s/it]" ] }, { @@ -523,7 +523,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 10%|█ | 10/100 [15:53<1:58:45, 79.18s/it]" + "Training Progress: 10%|█ | 10/100 [15:55<1:58:29, 79.00s/it]" ] }, { @@ -537,7 +537,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 11%|█ | 11/100 [17:10<1:56:41, 78.67s/it]" + "Training Progress: 11%|█ | 11/100 [17:12<1:56:09, 78.30s/it]" ] }, { @@ -551,7 +551,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 12%|█▏ | 12/100 [18:27<1:54:34, 78.12s/it]" + "Training Progress: 12%|█▏ | 12/100 [18:29<1:54:17, 77.93s/it]" ] }, { @@ -565,7 +565,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 13%|█▎ | 13/100 [19:46<1:53:25, 78.23s/it]" + "Training Progress: 13%|█▎ | 13/100 [19:45<1:52:30, 77.59s/it]" ] }, { @@ -579,7 +579,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 14%|█▍ | 14/100 [21:04<1:52:18, 78.35s/it]" + "Training Progress: 14%|█▍ | 14/100 [21:01<1:50:33, 77.13s/it]" ] }, { @@ -593,7 +593,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 15%|█▌ | 15/100 [22:25<1:52:00, 79.07s/it]" + "Training Progress: 15%|█▌ | 15/100 [22:19<1:49:13, 77.10s/it]" ] }, { @@ -607,7 +607,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 16%|█▌ | 16/100 [23:43<1:50:10, 78.70s/it]" + "Training Progress: 16%|█▌ | 16/100 [23:35<1:47:48, 77.00s/it]" ] }, { @@ -621,7 +621,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 17%|█▋ | 17/100 [25:01<1:48:45, 78.62s/it]" + "Training Progress: 17%|█▋ | 17/100 [24:52<1:46:34, 77.04s/it]" ] }, { @@ -635,7 +635,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 18%|█▊ | 18/100 [26:20<1:47:31, 78.68s/it]" + "Training Progress: 18%|█▊ | 18/100 [26:09<1:45:12, 76.98s/it]" ] }, { @@ -649,7 +649,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 19%|█▉ | 19/100 [27:40<1:46:32, 78.93s/it]" + "Training Progress: 19%|█▉ | 19/100 [27:26<1:43:45, 76.85s/it]" ] }, { @@ -663,7 +663,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 20%|██ | 20/100 [28:58<1:44:54, 78.69s/it]" + "Training Progress: 20%|██ | 20/100 [28:43<1:42:29, 76.87s/it]" ] }, { @@ -677,7 +677,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 21%|██ | 21/100 [30:17<1:43:43, 78.78s/it]" + "Training Progress: 21%|██ | 21/100 [30:00<1:41:12, 76.86s/it]" ] }, { @@ -691,7 +691,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 22%|██▏ | 22/100 [31:34<1:41:51, 78.35s/it]" + "Training Progress: 22%|██▏ | 22/100 [31:17<1:40:02, 76.96s/it]" ] }, { @@ -705,7 +705,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 23%|██▎ | 23/100 [32:52<1:40:17, 78.15s/it]" + "Training Progress: 23%|██▎ | 23/100 [32:34<1:38:48, 77.00s/it]" ] }, { @@ -719,7 +719,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 24%|██▍ | 24/100 [34:10<1:38:58, 78.13s/it]" + "Training Progress: 24%|██▍ | 24/100 [33:51<1:37:29, 76.97s/it]" ] }, { @@ -733,7 +733,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 25%|██▌ | 25/100 [35:27<1:37:18, 77.85s/it]" + "Training Progress: 25%|██▌ | 25/100 [35:11<1:37:22, 77.90s/it]" ] }, { @@ -747,7 +747,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 26%|██▌ | 26/100 [36:46<1:36:37, 78.35s/it]" + "Training Progress: 26%|██▌ | 26/100 [36:27<1:35:37, 77.53s/it]" ] }, { @@ -761,7 +761,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 27%|██▋ | 27/100 [38:05<1:35:29, 78.49s/it]" + "Training Progress: 27%|██▋ | 27/100 [37:45<1:34:08, 77.38s/it]" ] }, { @@ -775,7 +775,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 28%|██▊ | 28/100 [39:27<1:35:25, 79.52s/it]" + "Training Progress: 28%|██▊ | 28/100 [39:01<1:32:39, 77.22s/it]" ] }, { @@ -789,7 +789,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 29%|██▉ | 29/100 [40:50<1:35:06, 80.38s/it]" + "Training Progress: 29%|██▉ | 29/100 [40:19<1:31:27, 77.29s/it]" ] }, { @@ -803,7 +803,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 30%|███ | 30/100 [42:11<1:34:06, 80.67s/it]" + "Training Progress: 30%|███ | 30/100 [41:36<1:30:12, 77.32s/it]" ] }, { @@ -817,7 +817,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 31%|███ | 31/100 [43:33<1:33:06, 80.97s/it]" + "Training Progress: 31%|███ | 31/100 [42:57<1:30:04, 78.32s/it]" ] }, { @@ -831,7 +831,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 32%|███▏ | 32/100 [44:55<1:32:06, 81.27s/it]" + "Training Progress: 32%|███▏ | 32/100 [44:11<1:27:26, 77.15s/it]" ] }, { @@ -845,7 +845,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 33%|███▎ | 33/100 [46:14<1:30:10, 80.76s/it]" + "Training Progress: 33%|███▎ | 33/100 [45:26<1:25:17, 76.38s/it]" ] }, { @@ -859,7 +859,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 34%|███▍ | 34/100 [47:33<1:28:04, 80.07s/it]" + "Training Progress: 34%|███▍ | 34/100 [46:41<1:23:31, 75.93s/it]" ] }, { @@ -873,7 +873,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 35%|███▌ | 35/100 [48:53<1:26:41, 80.02s/it]" + "Training Progress: 35%|███▌ | 35/100 [47:55<1:21:47, 75.50s/it]" ] }, { @@ -887,7 +887,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 36%|███▌ | 36/100 [50:13<1:25:34, 80.23s/it]" + "Training Progress: 36%|███▌ | 36/100 [49:10<1:20:18, 75.28s/it]" ] }, { @@ -901,7 +901,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 37%|███▋ | 37/100 [51:34<1:24:24, 80.38s/it]" + "Training Progress: 37%|███▋ | 37/100 [50:25<1:18:48, 75.05s/it]" ] }, { @@ -915,7 +915,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 38%|███▊ | 38/100 [52:53<1:22:45, 80.09s/it]" + "Training Progress: 38%|███▊ | 38/100 [51:39<1:17:26, 74.94s/it]" ] }, { @@ -929,7 +929,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 39%|███▉ | 39/100 [54:15<1:21:53, 80.55s/it]" + "Training Progress: 39%|███▉ | 39/100 [52:54<1:16:08, 74.90s/it]" ] }, { @@ -943,7 +943,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 40%|████ | 40/100 [55:36<1:20:35, 80.59s/it]" + "Training Progress: 40%|████ | 40/100 [54:10<1:15:08, 75.15s/it]" ] }, { @@ -957,7 +957,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 41%|████ | 41/100 [56:55<1:18:58, 80.32s/it]" + "Training Progress: 41%|████ | 41/100 [55:25<1:13:49, 75.08s/it]" ] }, { @@ -971,7 +971,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 42%|████▏ | 42/100 [58:18<1:18:15, 80.96s/it]" + "Training Progress: 42%|████▏ | 42/100 [56:40<1:12:39, 75.16s/it]" ] }, { @@ -985,7 +985,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 43%|████▎ | 43/100 [59:40<1:17:19, 81.40s/it]" + "Training Progress: 43%|████▎ | 43/100 [57:55<1:11:20, 75.10s/it]" ] }, { @@ -999,7 +999,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 44%|████▍ | 44/100 [1:01:00<1:15:33, 80.95s/it]" + "Training Progress: 44%|████▍ | 44/100 [59:12<1:10:35, 75.63s/it]" ] }, { @@ -1013,7 +1013,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 45%|████▌ | 45/100 [1:02:22<1:14:28, 81.24s/it]" + "Training Progress: 45%|████▌ | 45/100 [1:00:27<1:09:15, 75.56s/it]" ] }, { @@ -1027,7 +1027,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 46%|████▌ | 46/100 [1:03:42<1:12:51, 80.96s/it]" + "Training Progress: 46%|████▌ | 46/100 [1:01:42<1:07:49, 75.36s/it]" ] }, { @@ -1041,7 +1041,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 47%|████▋ | 47/100 [1:05:04<1:11:47, 81.28s/it]" + "Training Progress: 47%|████▋ | 47/100 [1:02:58<1:06:35, 75.39s/it]" ] }, { @@ -1055,7 +1055,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 48%|████▊ | 48/100 [1:06:24<1:10:04, 80.86s/it]" + "Training Progress: 48%|████▊ | 48/100 [1:04:13<1:05:26, 75.52s/it]" ] }, { @@ -1069,7 +1069,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 49%|████▉ | 49/100 [1:07:46<1:08:56, 81.11s/it]" + "Training Progress: 49%|████▉ | 49/100 [1:05:29<1:04:07, 75.44s/it]" ] }, { @@ -1083,7 +1083,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 50%|█████ | 50/100 [1:09:09<1:08:08, 81.78s/it]" + "Training Progress: 50%|█████ | 50/100 [1:06:46<1:03:14, 75.90s/it]" ] }, { @@ -1097,7 +1097,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 51%|█████ | 51/100 [1:10:32<1:06:58, 82.01s/it]" + "Training Progress: 51%|█████ | 51/100 [1:08:01<1:01:50, 75.73s/it]" ] }, { @@ -1111,7 +1111,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 52%|█████▏ | 52/100 [1:11:54<1:05:33, 81.96s/it]" + "Training Progress: 52%|█████▏ | 52/100 [1:09:16<1:00:27, 75.58s/it]" ] }, { @@ -1125,7 +1125,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 53%|█████▎ | 53/100 [1:13:15<1:04:07, 81.85s/it]" + "Training Progress: 53%|█████▎ | 53/100 [1:10:31<59:06, 75.45s/it] " ] }, { @@ -1139,7 +1139,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 54%|█████▍ | 54/100 [1:14:38<1:02:49, 81.95s/it]" + "Training Progress: 54%|█████▍ | 54/100 [1:11:46<57:44, 75.33s/it]" ] }, { @@ -1153,7 +1153,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 55%|█████▌ | 55/100 [1:15:59<1:01:19, 81.76s/it]" + "Training Progress: 55%|█████▌ | 55/100 [1:13:01<56:25, 75.24s/it]" ] }, { @@ -1167,7 +1167,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 56%|█████▌ | 56/100 [1:17:22<1:00:18, 82.24s/it]" + "Training Progress: 56%|█████▌ | 56/100 [1:14:17<55:11, 75.25s/it]" ] }, { @@ -1181,7 +1181,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 57%|█████▋ | 57/100 [1:18:42<58:30, 81.65s/it] " + "Training Progress: 57%|█████▋ | 57/100 [1:15:32<53:57, 75.28s/it]" ] }, { @@ -1195,7 +1195,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 58%|█████▊ | 58/100 [1:20:05<57:19, 81.89s/it]" + "Training Progress: 58%|█████▊ | 58/100 [1:16:47<52:38, 75.21s/it]" ] }, { @@ -1209,7 +1209,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 59%|█████▉ | 59/100 [1:21:26<55:53, 81.78s/it]" + "Training Progress: 59%|█████▉ | 59/100 [1:18:26<56:11, 82.23s/it]" ] }, { @@ -1223,7 +1223,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 60%|██████ | 60/100 [1:22:50<54:55, 82.39s/it]" + "Training Progress: 60%|██████ | 60/100 [2:35:53<16:07:46, 1451.67s/it]" ] }, { @@ -1237,7 +1237,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 61%|██████ | 61/100 [1:24:14<53:54, 82.95s/it]" + "Training Progress: 61%|██████ | 61/100 [2:37:09<11:15:17, 1038.91s/it]" ] }, { @@ -1251,7 +1251,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 62%|██████▏ | 62/100 [1:25:50<54:52, 86.65s/it]" + "Training Progress: 62%|██████▏ | 62/100 [2:38:25<7:55:01, 750.04s/it] " ] }, { @@ -1265,7 +1265,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 63%|██████▎ | 63/100 [1:27:22<54:24, 88.23s/it]" + "Training Progress: 63%|██████▎ | 63/100 [2:39:41<5:37:49, 547.83s/it]" ] }, { @@ -1279,7 +1279,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 64%|██████▍ | 64/100 [1:28:42<51:26, 85.74s/it]" + "Training Progress: 64%|██████▍ | 64/100 [2:40:56<4:03:43, 406.21s/it]" ] }, { @@ -1293,7 +1293,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 65%|██████▌ | 65/100 [1:30:01<48:52, 83.78s/it]" + "Training Progress: 65%|██████▌ | 65/100 [2:42:12<2:59:02, 306.92s/it]" ] }, { @@ -1307,7 +1307,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 66%|██████▌ | 66/100 [1:31:20<46:39, 82.33s/it]" + "Training Progress: 66%|██████▌ | 66/100 [2:43:27<2:14:35, 237.53s/it]" ] }, { @@ -1321,7 +1321,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 67%|██████▋ | 67/100 [1:32:39<44:45, 81.38s/it]" + "Training Progress: 67%|██████▋ | 67/100 [2:44:43<1:43:58, 189.05s/it]" ] }, { @@ -1335,7 +1335,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 68%|██████▊ | 68/100 [1:33:58<43:00, 80.64s/it]" + "Training Progress: 68%|██████▊ | 68/100 [2:46:00<1:22:49, 155.31s/it]" ] }, { @@ -1349,7 +1349,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 69%|██████▉ | 69/100 [1:35:17<41:27, 80.23s/it]" + "Training Progress: 69%|██████▉ | 69/100 [2:47:16<1:08:00, 131.64s/it]" ] }, { @@ -1363,7 +1363,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 70%|███████ | 70/100 [1:36:36<39:55, 79.86s/it]" + "Training Progress: 70%|███████ | 70/100 [2:48:32<57:29, 114.97s/it] " ] }, { @@ -1377,7 +1377,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 71%|███████ | 71/100 [1:37:55<38:26, 79.53s/it]" + "Training Progress: 71%|███████ | 71/100 [2:49:48<49:55, 103.30s/it]" ] }, { @@ -1391,7 +1391,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 72%|███████▏ | 72/100 [1:39:15<37:11, 79.71s/it]" + "Training Progress: 72%|███████▏ | 72/100 [2:51:05<44:25, 95.20s/it] " ] }, { @@ -1405,7 +1405,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 73%|███████▎ | 73/100 [1:40:35<35:54, 79.79s/it]" + "Training Progress: 73%|███████▎ | 73/100 [2:52:20<40:13, 89.38s/it]" ] }, { @@ -1419,7 +1419,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 74%|███████▍ | 74/100 [1:41:56<34:43, 80.13s/it]" + "Training Progress: 74%|███████▍ | 74/100 [2:53:36<36:56, 85.24s/it]" ] }, { @@ -1433,7 +1433,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 75%|███████▌ | 75/100 [1:43:17<33:27, 80.28s/it]" + "Training Progress: 75%|███████▌ | 75/100 [2:54:51<34:17, 82.29s/it]" ] }, { @@ -1447,7 +1447,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 76%|███████▌ | 76/100 [1:44:37<32:04, 80.19s/it]" + "Training Progress: 76%|███████▌ | 76/100 [2:56:07<32:05, 80.22s/it]" ] }, { @@ -1461,7 +1461,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 77%|███████▋ | 77/100 [1:45:56<30:37, 79.87s/it]" + "Training Progress: 77%|███████▋ | 77/100 [2:57:22<30:10, 78.74s/it]" ] }, { @@ -1475,7 +1475,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 78%|███████▊ | 78/100 [1:47:15<29:11, 79.62s/it]" + "Training Progress: 78%|███████▊ | 78/100 [2:58:38<28:32, 77.83s/it]" ] }, { @@ -1489,7 +1489,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 79%|███████▉ | 79/100 [1:48:34<27:51, 79.60s/it]" + "Training Progress: 79%|███████▉ | 79/100 [2:59:53<26:58, 77.09s/it]" ] }, { @@ -1503,7 +1503,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 80%|████████ | 80/100 [1:49:54<26:35, 79.76s/it]" + "Training Progress: 80%|████████ | 80/100 [3:01:09<25:33, 76.66s/it]" ] }, { @@ -1517,7 +1517,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 81%|████████ | 81/100 [1:51:14<25:16, 79.84s/it]" + "Training Progress: 81%|████████ | 81/100 [3:02:25<24:15, 76.59s/it]" ] }, { @@ -1531,7 +1531,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 82%|████████▏ | 82/100 [1:52:35<24:03, 80.21s/it]" + "Training Progress: 82%|████████▏ | 82/100 [3:03:41<22:54, 76.38s/it]" ] }, { @@ -1545,7 +1545,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 83%|████████▎ | 83/100 [1:53:55<22:41, 80.08s/it]" + "Training Progress: 83%|████████▎ | 83/100 [3:04:56<21:33, 76.09s/it]" ] }, { @@ -1559,7 +1559,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 84%|████████▍ | 84/100 [1:55:15<21:21, 80.10s/it]" + "Training Progress: 84%|████████▍ | 84/100 [3:06:12<20:16, 76.00s/it]" ] }, { @@ -1573,7 +1573,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 85%|████████▌ | 85/100 [1:56:34<19:56, 79.77s/it]" + "Training Progress: 85%|████████▌ | 85/100 [3:07:28<18:58, 75.88s/it]" ] }, { @@ -1587,7 +1587,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 86%|████████▌ | 86/100 [1:57:54<18:34, 79.60s/it]" + "Training Progress: 86%|████████▌ | 86/100 [3:08:43<17:40, 75.73s/it]" ] }, { @@ -1601,7 +1601,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 87%|████████▋ | 87/100 [1:59:13<17:14, 79.55s/it]" + "Training Progress: 87%|████████▋ | 87/100 [3:09:59<16:24, 75.74s/it]" ] }, { @@ -1615,7 +1615,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 88%|████████▊ | 88/100 [2:00:33<15:56, 79.73s/it]" + "Training Progress: 88%|████████▊ | 88/100 [3:11:15<15:10, 75.89s/it]" ] }, { @@ -1629,7 +1629,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 89%|████████▉ | 89/100 [2:01:52<14:34, 79.53s/it]" + "Training Progress: 89%|████████▉ | 89/100 [3:12:31<13:55, 75.97s/it]" ] }, { @@ -1643,7 +1643,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 90%|█████████ | 90/100 [2:03:12<13:15, 79.51s/it]" + "Training Progress: 90%|█████████ | 90/100 [3:13:47<12:39, 75.96s/it]" ] }, { @@ -1657,7 +1657,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 91%|█████████ | 91/100 [2:04:32<11:57, 79.78s/it]" + "Training Progress: 91%|█████████ | 91/100 [3:15:03<11:23, 75.96s/it]" ] }, { @@ -1671,7 +1671,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 92%|█████████▏| 92/100 [2:05:52<10:39, 79.96s/it]" + "Training Progress: 92%|█████████▏| 92/100 [3:16:19<10:07, 75.89s/it]" ] }, { @@ -1685,7 +1685,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 93%|█████████▎| 93/100 [2:07:13<09:21, 80.23s/it]" + "Training Progress: 93%|█████████▎| 93/100 [3:17:35<08:50, 75.83s/it]" ] }, { @@ -1699,7 +1699,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 94%|█████████▍| 94/100 [2:08:44<08:20, 83.37s/it]" + "Training Progress: 94%|█████████▍| 94/100 [3:18:51<07:35, 75.92s/it]" ] }, { @@ -1713,7 +1713,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 95%|█████████▌| 95/100 [2:10:20<07:15, 87.17s/it]" + "Training Progress: 95%|█████████▌| 95/100 [3:20:07<06:19, 75.97s/it]" ] }, { @@ -1727,7 +1727,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 96%|█████████▌| 96/100 [2:11:46<05:46, 86.74s/it]" + "Training Progress: 96%|█████████▌| 96/100 [3:21:23<05:04, 76.04s/it]" ] }, { @@ -1741,7 +1741,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 97%|█████████▋| 97/100 [2:13:05<04:13, 84.58s/it]" + "Training Progress: 97%|█████████▋| 97/100 [3:22:40<03:48, 76.19s/it]" ] }, { @@ -1755,7 +1755,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 98%|█████████▊| 98/100 [2:14:25<02:46, 83.18s/it]" + "Training Progress: 98%|█████████▊| 98/100 [3:23:56<02:32, 76.20s/it]" ] }, { @@ -1769,7 +1769,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 99%|█████████▉| 99/100 [2:15:45<01:22, 82.11s/it]" + "Training Progress: 99%|█████████▉| 99/100 [3:25:13<01:16, 76.43s/it]" ] }, { @@ -1783,7 +1783,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 100%|██████████| 100/100 [2:17:06<00:00, 81.94s/it]" + "Training Progress: 100%|██████████| 100/100 [3:26:29<00:00, 123.90s/it]" ] }, { @@ -1797,7 +1797,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "Training Progress: 100%|██████████| 100/100 [2:17:07<00:00, 82.28s/it]\n" + "\n" ] }, { @@ -1835,7 +1835,7 @@ }, { "cell_type": "code", - "execution_count": 18, + "execution_count": 22, "metadata": {}, "outputs": [ { @@ -1844,11 +1844,14 @@ "text": [ "What is FHE?\n", "\n", - "FHE? FHS is a groundbreaking concept that allows the use of cloud computing to help protect data and privacy while still allowing data to be\n" + "FHE is a breakthrough in computer security. It allows computations on encrypted data and store it in a database, which can be used to\n" ] } ], "source": [ + "# Seed for best reproducibility\n", + "torch.manual_seed(SEED)\n", + "\n", "prompt = \"What is FHE ?\"\n", "generated_text = generate_text(prompt, fine_tuned_model, tokenizer)\n", "print(generated_text)" @@ -1856,7 +1859,7 @@ }, { "cell_type": "code", - "execution_count": 19, + "execution_count": 23, "metadata": {}, "outputs": [ { @@ -1865,11 +1868,14 @@ "text": [ "What is FHE?\n", "\n", - "FHE is a new form of the term \"fission energy\". It is the energy of fusion of a process which is in a state\n" + "We're talking about the FH and its use of the H, the use the D, and the C, which are often used interchange\n" ] } ], "source": [ + "# Seed for best reproducibility\n", + "torch.manual_seed(SEED)\n", + "\n", "peft_model.disable_adapter_layers()\n", "\n", "prompt = \"What is FHE ?\"\n", @@ -1923,7 +1929,7 @@ }, { "cell_type": "code", - "execution_count": 22, + "execution_count": null, "metadata": {}, "outputs": [], "source": [ @@ -1938,7 +1944,7 @@ }, { "cell_type": "code", - "execution_count": 23, + "execution_count": null, "metadata": {}, "outputs": [ { @@ -1956,7 +1962,7 @@ }, { "cell_type": "code", - "execution_count": 24, + "execution_count": null, "metadata": {}, "outputs": [ {