Training in progress, step 500

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 152,
+  "<s>": 151
+}

config.json

@@ -104,6 +104,6 @@
   "torch_dtype": "float32",
   "transformers_version": "4.43.1",
   "use_weighted_layer_sum": false,
-  "vocab_size": 151,
+  "vocab_size": 153,
   "xvector_output_dim": 512
 }

indicwav2vec_trainwtagsv2_MUCS_warmup500_s300shuff100_2604812.out

@@ -0,0 +1,759 @@
+wandb: Currently logged in as: priyanshi-pal (priyanshipal). Use `wandb login --relogin` to force relogin
+wandb: wandb version 0.18.0 is available!  To upgrade, please run:
+wandb:  $ pip install wandb --upgrade
+wandb: Tracking run with wandb version 0.17.6
+wandb: Run data is saved locally in /scratch/elec/t405-puhe/p/palp3/MUCS/wandb/run-20240915_194917-g83rt34t
+wandb: Run `wandb offline` to turn off syncing.
+wandb: Syncing run retrainwithtagsv2_indicw2v_ad0_3_hd_02_featd_0_3_lr6e-4_warmup500_s300_shuff100
+wandb: ⭐️ View project at https://wandb.ai/priyanshipal/huggingface
+wandb: 🚀 View run at https://wandb.ai/priyanshipal/huggingface/runs/g83rt34t
+/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/training_args.py:1525: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of 🤗 Transformers. Use `eval_strategy` instead
+  warnings.warn(
+09/15/2024 19:49:21 - WARNING - __main__ - device: cuda:0, n_gpu: 116-bits training: False
+/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/models/auto/configuration_auto.py:957: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
+  warnings.warn(
+/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/configuration_utils.py:364: UserWarning: Passing `gradient_checkpointing` to a config initialization is deprecated and will be removed in v5 Transformers. Using `model.gradient_checkpointing_enable()` instead, or if you are using the `Trainer` API, pass `gradient_checkpointing=True` in your `TrainingArguments`.
+  warnings.warn(
+/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/models/auto/feature_extraction_auto.py:329: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
+  warnings.warn(
+/scratch/elec/puhe/p/palp3/MUCS/finetune_script_wtags_partdata.py:509: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
+  state_dict = torch.load(f"{model_args.model_name_or_path}/pytorch_model.bin")
+Some weights of the model checkpoint at /m/triton/scratch/elec/puhe/p/palp3/MUCS/indicwav2vec-hindi were not used when initializing Wav2Vec2ForCTC: ['wav2vec2.encoder.pos_conv_embed.conv.weight_g', 'wav2vec2.encoder.pos_conv_embed.conv.weight_v']
+- This IS expected if you are initializing Wav2Vec2ForCTC from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
+- This IS NOT expected if you are initializing Wav2Vec2ForCTC from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
+Some weights of Wav2Vec2ForCTC were not initialized from the model checkpoint at /m/triton/scratch/elec/puhe/p/palp3/MUCS/indicwav2vec-hindi and are newly initialized: ['lm_head.bias', 'lm_head.weight', 'wav2vec2.encoder.pos_conv_embed.conv.parametrizations.weight.original0', 'wav2vec2.encoder.pos_conv_embed.conv.parametrizations.weight.original1']
+You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
+max_steps is given, it will override any value given in num_train_epochs
+Wav2Vec2CTCTokenizer(name_or_path='', vocab_size=151, model_max_length=1000000000000000019884624838656, is_fast=False, padding_side='right', truncation_side='right', special_tokens={'bos_token': '<s>', 'eos_token': '</s>', 'unk_token': '[UNK]', 'pad_token': '[PAD]'}, clean_up_tokenization_spaces=True),  added_tokens_decoder={
+	149: AddedToken("[UNK]", rstrip=True, lstrip=True, single_word=False, normalized=False, special=False),
+	150: AddedToken("[PAD]", rstrip=True, lstrip=True, single_word=False, normalized=False, special=False),
+	151: AddedToken("<s>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	152: AddedToken("</s>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+}
+CHECK MODEL PARAMS Wav2Vec2ForCTC(
+  (wav2vec2): Wav2Vec2Model(
+    (feature_extractor): Wav2Vec2FeatureEncoder(
+      (conv_layers): ModuleList(
+        (0): Wav2Vec2LayerNormConvLayer(
+          (conv): Conv1d(1, 512, kernel_size=(10,), stride=(5,))
+          (layer_norm): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+          (activation): GELUActivation()
+        )
+        (1-4): 4 x Wav2Vec2LayerNormConvLayer(
+          (conv): Conv1d(512, 512, kernel_size=(3,), stride=(2,))
+          (layer_norm): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+          (activation): GELUActivation()
+        )
+        (5-6): 2 x Wav2Vec2LayerNormConvLayer(
+          (conv): Conv1d(512, 512, kernel_size=(2,), stride=(2,))
+          (layer_norm): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+          (activation): GELUActivation()
+        )
+      )
+    )
+    (feature_projection): Wav2Vec2FeatureProjection(
+      (layer_norm): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+      (projection): Linear(in_features=512, out_features=1024, bias=True)
+      (dropout): Dropout(p=0.3, inplace=False)
+    )
+    (encoder): Wav2Vec2EncoderStableLayerNorm(
+      (pos_conv_embed): Wav2Vec2PositionalConvEmbedding(
+        (conv): ParametrizedConv1d(
+          1024, 1024, kernel_size=(128,), stride=(1,), padding=(64,), groups=16
+          (parametrizations): ModuleDict(
+            (weight): ParametrizationList(
+              (0): _WeightNorm()
+            )
+          )
+        )
+        (padding): Wav2Vec2SamePadLayer()
+        (activation): GELUActivation()
+      )
+      (layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
+      (dropout): Dropout(p=0.2, inplace=False)
+      (layers): ModuleList(
+        (0-23): 24 x Wav2Vec2EncoderLayerStableLayerNorm(
+          (attention): Wav2Vec2SdpaAttention(
+            (k_proj): Linear(in_features=1024, out_features=1024, bias=True)
+            (v_proj): Linear(in_features=1024, out_features=1024, bias=True)
+            (q_proj): Linear(in_features=1024, out_features=1024, bias=True)
+            (out_proj): Linear(in_features=1024, out_features=1024, bias=True)
+          )
+          (dropout): Dropout(p=0.2, inplace=False)
+          (layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
+          (feed_forward): Wav2Vec2FeedForward(
+            (intermediate_dropout): Dropout(p=0.0, inplace=False)
+            (intermediate_dense): Linear(in_features=1024, out_features=4096, bias=True)
+            (intermediate_act_fn): GELUActivation()
+            (output_dense): Linear(in_features=4096, out_features=1024, bias=True)
+            (output_dropout): Dropout(p=0.2, inplace=False)
+          )
+          (final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
+        )
+      )
+    )
+  )
+  (dropout): Dropout(p=0.0, inplace=False)
+  (lm_head): Linear(in_features=1024, out_features=153, bias=True)
+)
+
  0%|          | 0/5000 [00:00<?, ?it/s]/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.
+  warnings.warn(
+/scratch/work/palp3/myenv/lib/python3.11/site-packages/torch/_dynamo/eval_frame.py:600: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants.
+  return fn(*args, **kwargs)
+/scratch/work/palp3/myenv/lib/python3.11/site-packages/torch/utils/checkpoint.py:295: FutureWarning: `torch.cpu.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cpu', args...)` instead.
+  with torch.enable_grad(), device_autocast_ctx, torch.cpu.amp.autocast(**ctx.cpu_autocast_kwargs):  # type: ignore[attr-defined]
+
  0%|          | 1/5000 [00:29<40:18:00, 29.02s/it]
                                                   
  0%|          | 1/5000 [00:29<40:18:00, 29.02s/it]
  0%|          | 2/5000 [00:37<23:19:44, 16.80s/it]
                                                   
  0%|          | 2/5000 [00:37<23:19:44, 16.80s/it]
  0%|          | 3/5000 [00:44<17:11:59, 12.39s/it]
                                                   
  0%|          | 3/5000 [00:44<17:11:59, 12.39s/it]
  0%|          | 4/5000 [00:50<13:57:56, 10.06s/it]
                                                   
  0%|          | 4/5000 [00:50<13:57:56, 10.06s/it]
  0%|          | 5/5000 [00:56<11:57:47,  8.62s/it]
                                                   
  0%|          | 5/5000 [00:56<11:57:47,  8.62s/it]
  0%|          | 6/5000 [01:02<10:40:40,  7.70s/it]
                                                   
  0%|          | 6/5000 [01:02<10:40:40,  7.70s/it]
  0%|          | 7/5000 [01:08<9:37:29,  6.94s/it] 
                                                  
  0%|          | 7/5000 [01:08<9:37:29,  6.94s/it]
  0%|          | 8/5000 [01:13<8:55:38,  6.44s/it]
                                                  
  0%|          | 8/5000 [01:13<8:55:38,  6.44s/it]
  0%|          | 9/5000 [01:18<8:18:48,  6.00s/it]
                                                  
  0%|          | 9/5000 [01:18<8:18:48,  6.00s/it]
  0%|          | 10/5000 [01:23<7:45:40,  5.60s/it]
                                                   
  0%|          | 10/5000 [01:23<7:45:40,  5.60s/it]
  0%|          | 11/5000 [01:28<7:23:07,  5.33s/it]
                                                   
  0%|          | 11/5000 [01:28<7:23:07,  5.33s/it]
  0%|          | 12/5000 [01:32<7:04:45,  5.11s/it]
                                                   
  0%|          | 12/5000 [01:32<7:04:45,  5.11s/it]
  0%|          | 13/5000 [01:36<6:39:23,  4.81s/it]
                                                   
  0%|          | 13/5000 [01:36<6:39:23,  4.81s/it]
  0%|          | 14/5000 [01:40<6:21:49,  4.59s/it]
                                                   
  0%|          | 14/5000 [01:40<6:21:49,  4.59s/it]
  0%|          | 15/5000 [01:44<6:09:14,  4.44s/it]
                                                   
  0%|          | 15/5000 [01:45<6:09:14,  4.44s/it]
  0%|          | 16/5000 [01:49<6:00:43,  4.34s/it]
                                                   
  0%|          | 16/5000 [01:49<6:00:43,  4.34s/it]
  0%|          | 17/5000 [01:53<5:54:11,  4.26s/it]
                                                   
  0%|          | 17/5000 [01:53<5:54:11,  4.26s/it]
  0%|          | 18/5000 [01:57<5:46:37,  4.17s/it]
                                                   
  0%|          | 18/5000 [01:57<5:46:37,  4.17s/it]
  0%|          | 19/5000 [02:00<5:29:26,  3.97s/it]
                                                   
  0%|          | 19/5000 [02:00<5:29:26,  3.97s/it]
  0%|          | 20/5000 [02:04<5:17:04,  3.82s/it]
                                                   
  0%|          | 20/5000 [02:04<5:17:04,  3.82s/it]
  0%|          | 21/5000 [02:07<5:08:53,  3.72s/it]
                                                   
  0%|          | 21/5000 [02:07<5:08:53,  3.72s/it]
  0%|          | 22/5000 [02:11<5:02:43,  3.65s/it]
                                                   
  0%|          | 22/5000 [02:11<5:02:43,  3.65s/it]
  0%|          | 23/5000 [02:14<4:58:09,  3.59s/it]
                                                   
  0%|          | 23/5000 [02:14<4:58:09,  3.59s/it]
  0%|          | 24/5000 [02:17<4:53:07,  3.53s/it]
                                                   
  0%|          | 24/5000 [02:17<4:53:07,  3.53s/it]
  0%|          | 25/5000 [02:20<4:40:47,  3.39s/it]
                                                   
  0%|          | 25/5000 [02:21<4:40:47,  3.39s/it]
  1%|          | 26/5000 [02:23<4:28:32,  3.24s/it]
                                                   
  1%|          | 26/5000 [02:23<4:28:32,  3.24s/it]
  1%|          | 27/5000 [02:26<4:20:26,  3.14s/it]
                                                   
  1%|          | 27/5000 [02:26<4:20:26,  3.14s/it]
  1%|          | 28/5000 [02:29<4:14:25,  3.07s/it]
                                                   
  1%|          | 28/5000 [02:29<4:14:25,  3.07s/it]
  1%|          | 29/5000 [02:32<4:10:13,  3.02s/it]
                                                   
  1%|          | 29/5000 [02:32<4:10:13,  3.02s/it]
  1%|          | 30/5000 [02:35<4:07:35,  2.99s/it]
                                                   
  1%|          | 30/5000 [02:35<4:07:35,  2.99s/it]
  1%|          | 31/5000 [02:38<4:05:17,  2.96s/it]
                                                   
  1%|          | 31/5000 [02:38<4:05:17,  2.96s/it]
  1%|          | 32/5000 [02:41<4:02:49,  2.93s/it]
                                                   
  1%|          | 32/5000 [02:41<4:02:49,  2.93s/it]
  1%|          | 33/5000 [02:43<3:52:45,  2.81s/it]
                                                   
  1%|          | 33/5000 [02:43<3:52:45,  2.81s/it]
  1%|          | 34/5000 [02:46<3:40:59,  2.67s/it]
                                                   
  1%|          | 34/5000 [02:46<3:40:59,  2.67s/it]
  1%|          | 35/5000 [02:48<3:32:36,  2.57s/it]
                                                   
  1%|          | 35/5000 [02:48<3:32:36,  2.57s/it]
  1%|          | 36/5000 [02:50<3:27:01,  2.50s/it]
                                                   
  1%|          | 36/5000 [02:50<3:27:01,  2.50s/it]
  1%|          | 37/5000 [02:53<3:23:48,  2.46s/it]
                                                   
  1%|          | 37/5000 [02:53<3:23:48,  2.46s/it]
  1%|          | 38/5000 [02:55<3:20:45,  2.43s/it]
                                                   
  1%|          | 38/5000 [02:55<3:20:45,  2.43s/it]
  1%|          | 39/5000 [02:57<3:19:09,  2.41s/it]
                                                   
  1%|          | 39/5000 [02:57<3:19:09,  2.41s/it]
  1%|          | 40/5000 [03:00<3:16:32,  2.38s/it]
                                                   
  1%|          | 40/5000 [03:00<3:16:32,  2.38s/it]
  1%|          | 41/5000 [03:02<3:06:39,  2.26s/it]
                                                   
  1%|          | 41/5000 [03:02<3:06:39,  2.26s/it]
  1%|          | 42/5000 [03:03<2:54:05,  2.11s/it]
                                                   
  1%|          | 42/5000 [03:03<2:54:05,  2.11s/it]
  1%|          | 43/5000 [03:05<2:45:18,  2.00s/it]
                                                   
  1%|          | 43/5000 [03:05<2:45:18,  2.00s/it]
  1%|          | 44/5000 [03:07<2:39:10,  1.93s/it]
                                                   
  1%|          | 44/5000 [03:07<2:39:10,  1.93s/it]
  1%|          | 45/5000 [03:09<2:34:53,  1.88s/it]
                                                   
  1%|          | 45/5000 [03:09<2:34:53,  1.88s/it]
  1%|          | 46/5000 [03:10<2:31:36,  1.84s/it]
                                                   
  1%|          | 46/5000 [03:10<2:31:36,  1.84s/it]
  1%|          | 47/5000 [03:12<2:26:21,  1.77s/it]
                                                   
  1%|          | 47/5000 [03:12<2:26:21,  1.77s/it]
  1%|          | 48/5000 [03:13<2:12:05,  1.60s/it]
                                                   
  1%|          | 48/5000 [03:13<2:12:05,  1.60s/it]
  1%|          | 49/5000 [03:14<2:02:16,  1.48s/it]
                                                   
  1%|          | 49/5000 [03:15<2:02:16,  1.48s/it]
  1%|          | 50/5000 [03:18<2:44:51,  2.00s/it]
                                                   
  1%|          | 50/5000 [03:18<2:44:51,  2.00s/it]
  1%|          | 51/5000 [03:34<8:36:31,  6.26s/it]
                                                   
  1%|          | 51/5000 [03:34<8:36:31,  6.26s/it]
  1%|          | 52/5000 [03:43<9:46:07,  7.11s/it]
                                                   
  1%|          | 52/5000 [03:43<9:46:07,  7.11s/it]
  1%|          | 53/5000 [03:51<10:03:31,  7.32s/it]
                                                    
  1%|          | 53/5000 [03:51<10:03:31,  7.32s/it]
  1%|          | 54/5000 [03:58<9:52:33,  7.19s/it] 
                                                   
  1%|          | 54/5000 [03:58<9:52:33,  7.19s/it]
  1%|          | 55/5000 [04:04<9:35:40,  6.98s/it]
                                                   
  1%|          | 55/5000 [04:04<9:35:40,  6.98s/it]
  1%|          | 56/5000 [04:10<9:09:54,  6.67s/it]
                                                   
  1%|          | 56/5000 [04:10<9:09:54,  6.67s/it]
  1%|          | 57/5000 [04:16<8:42:59,  6.35s/it]
                                                   
  1%|          | 57/5000 [04:16<8:42:59,  6.35s/it]
  1%|          | 58/5000 [04:21<8:19:26,  6.06s/it]
                                                   
  1%|          | 58/5000 [04:21<8:19:26,  6.06s/it]
  1%|          | 59/5000 [04:26<7:52:24,  5.74s/it]
                                                   
  1%|          | 59/5000 [04:26<7:52:24,  5.74s/it]
  1%|          | 60/5000 [04:31<7:27:01,  5.43s/it]
                                                   
  1%|          | 60/5000 [04:31<7:27:01,  5.43s/it]
  1%|          | 61/5000 [04:36<7:09:13,  5.21s/it]
                                                   
  1%|          | 61/5000 [04:36<7:09:13,  5.21s/it]
  1%|          | 62/5000 [04:40<6:47:20,  4.95s/it]
                                                   
  1%|          | 62/5000 [04:40<6:47:20,  4.95s/it]
  1%|▏         | 63/5000 [04:44<6:26:34,  4.70s/it]
                                                   
  1%|▏         | 63/5000 [04:44<6:26:34,  4.70s/it]
  1%|▏         | 64/5000 [04:48<6:12:16,  4.53s/it]
                                                   
  1%|▏         | 64/5000 [04:48<6:12:16,  4.53s/it]
  1%|▏         | 65/5000 [04:52<6:02:02,  4.40s/it]
                                                   
  1%|▏         | 65/5000 [04:52<6:02:02,  4.40s/it]
  1%|▏         | 66/5000 [04:56<5:56:16,  4.33s/it]
                                                   
  1%|▏         | 66/5000 [04:56<5:56:16,  4.33s/it]
  1%|▏         | 67/5000 [05:00<5:49:42,  4.25s/it]
                                                   
  1%|▏         | 67/5000 [05:00<5:49:42,  4.25s/it]
  1%|▏         | 68/5000 [05:04<5:36:05,  4.09s/it]
                                                   
  1%|▏         | 68/5000 [05:04<5:36:05,  4.09s/it]
  1%|▏         | 69/5000 [05:08<5:21:05,  3.91s/it]
                                                   
  1%|▏         | 69/5000 [05:08<5:21:05,  3.91s/it]
  1%|▏         | 70/5000 [05:11<5:10:13,  3.78s/it]
                                                   
  1%|▏         | 70/5000 [05:11<5:10:13,  3.78s/it]
  1%|▏         | 71/5000 [05:15<5:02:22,  3.68s/it]
                                                   
  1%|▏         | 71/5000 [05:15<5:02:22,  3.68s/it]
  1%|▏         | 72/5000 [05:18<4:57:31,  3.62s/it]
                                                   
  1%|▏         | 72/5000 [05:18<4:57:31,  3.62s/it]
  1%|▏         | 73/5000 [05:22<4:54:11,  3.58s/it]
                                                   
  1%|▏         | 73/5000 [05:22<4:54:11,  3.58s/it]
  1%|▏         | 74/5000 [05:25<4:48:19,  3.51s/it]
                                                   
  1%|▏         | 74/5000 [05:25<4:48:19,  3.51s/it]
  2%|▏         | 75/5000 [05:28<4:32:54,  3.32s/it]
                                                   
  2%|▏         | 75/5000 [05:28<4:32:54,  3.32s/it]
  2%|▏         | 76/5000 [05:31<4:22:10,  3.19s/it]
                                                   
  2%|▏         | 76/5000 [05:31<4:22:10,  3.19s/it]
  2%|▏         | 77/5000 [05:34<4:14:46,  3.11s/it]
                                                   
  2%|▏         | 77/5000 [05:34<4:14:46,  3.11s/it]
  2%|▏         | 78/5000 [05:36<4:09:24,  3.04s/it]
                                                   
  2%|▏         | 78/5000 [05:36<4:09:24,  3.04s/it]
  2%|▏         | 79/5000 [05:39<4:06:06,  3.00s/it]
                                                   
  2%|▏         | 79/5000 [05:39<4:06:06,  3.00s/it]
  2%|▏         | 80/5000 [05:42<4:03:53,  2.97s/it]
                                                   
  2%|▏         | 80/5000 [05:42<4:03:53,  2.97s/it]
  2%|▏         | 81/5000 [05:45<4:02:14,  2.95s/it]
                                                   
  2%|▏         | 81/5000 [05:45<4:02:14,  2.95s/it]
  2%|▏         | 82/5000 [05:48<4:00:09,  2.93s/it]
                                                   
  2%|▏         | 82/5000 [05:48<4:00:09,  2.93s/it]
  2%|▏         | 83/5000 [05:51<3:50:27,  2.81s/it]
                                                   
  2%|▏         | 83/5000 [05:51<3:50:27,  2.81s/it]
  2%|▏         | 84/5000 [05:53<3:38:44,  2.67s/it]
                                                   
  2%|▏         | 84/5000 [05:53<3:38:44,  2.67s/it]
  2%|▏         | 85/5000 [05:55<3:30:25,  2.57s/it]
                                                   
  2%|▏         | 85/5000 [05:55<3:30:25,  2.57s/it]
  2%|▏         | 86/5000 [05:58<3:24:40,  2.50s/it]
                                                   
  2%|▏         | 86/5000 [05:58<3:24:40,  2.50s/it]
  2%|▏         | 87/5000 [06:00<3:20:40,  2.45s/it]
                                                   
  2%|▏         | 87/5000 [06:00<3:20:40,  2.45s/it]
  2%|▏         | 88/5000 [06:02<3:18:13,  2.42s/it]
                                                   
  2%|▏         | 88/5000 [06:02<3:18:13,  2.42s/it]
  2%|▏         | 89/5000 [06:05<3:16:04,  2.40s/it]
                                                   
  2%|▏         | 89/5000 [06:05<3:16:04,  2.40s/it]
  2%|▏         | 90/5000 [06:07<3:14:09,  2.37s/it]
                                                   
  2%|▏         | 90/5000 [06:07<3:14:09,  2.37s/it]
  2%|▏         | 91/5000 [06:09<3:04:04,  2.25s/it]
                                                   
  2%|▏         | 91/5000 [06:09<3:04:04,  2.25s/it]
  2%|▏         | 92/5000 [06:11<2:51:48,  2.10s/it]
                                                   
  2%|▏         | 92/5000 [06:11<2:51:48,  2.10s/it]
  2%|▏         | 93/5000 [06:12<2:43:14,  2.00s/it]
                                                   
  2%|▏         | 93/5000 [06:12<2:43:14,  2.00s/it]
  2%|▏         | 94/5000 [06:14<2:37:10,  1.92s/it]
                                                   
  2%|▏         | 94/5000 [06:14<2:37:10,  1.92s/it]
  2%|▏         | 95/5000 [06:16<2:33:11,  1.87s/it]
                                                   
  2%|▏         | 95/5000 [06:16<2:33:11,  1.87s/it]
  2%|▏         | 96/5000 [06:18<2:30:32,  1.84s/it]
                                                   
  2%|▏         | 96/5000 [06:18<2:30:32,  1.84s/it]
  2%|▏         | 97/5000 [06:19<2:25:12,  1.78s/it]
                                                   
  2%|▏         | 97/5000 [06:19<2:25:12,  1.78s/it]
  2%|▏         | 98/5000 [06:21<2:10:59,  1.60s/it]
                                                   
  2%|▏         | 98/5000 [06:21<2:10:59,  1.60s/it]
  2%|▏         | 99/5000 [06:22<2:01:03,  1.48s/it]
                                                   
  2%|▏         | 99/5000 [06:22<2:01:03,  1.48s/it]
  2%|▏         | 100/5000 [06:25<2:44:15,  2.01s/it]
                                                    
  2%|▏         | 100/5000 [06:25<2:44:15,  2.01s/it]{'loss': 53.3154, 'grad_norm': 79.69747924804688, 'learning_rate': 1.2e-06, 'epoch': 0.0}
+{'loss': 34.361, 'grad_norm': 24.41111946105957, 'learning_rate': 2.4e-06, 'epoch': 0.0}
+{'loss': 30.4549, 'grad_norm': 36.592803955078125, 'learning_rate': 3.6e-06, 'epoch': 0.0}
+{'loss': 23.957, 'grad_norm': 15.393040657043457, 'learning_rate': 4.8e-06, 'epoch': 0.01}
+{'loss': 23.1553, 'grad_norm': 16.698022842407227, 'learning_rate': 5.999999999999999e-06, 'epoch': 0.01}
+{'loss': 23.6211, 'grad_norm': 15.845901489257812, 'learning_rate': 7.2e-06, 'epoch': 0.01}
+{'loss': 23.8485, 'grad_norm': 16.488929748535156, 'learning_rate': 8.4e-06, 'epoch': 0.01}
+{'loss': 22.1915, 'grad_norm': 14.807597160339355, 'learning_rate': 9.6e-06, 'epoch': 0.01}
+{'loss': 19.4207, 'grad_norm': 15.219635009765625, 'learning_rate': 1.0799999999999998e-05, 'epoch': 0.01}
+{'loss': 20.869, 'grad_norm': 14.109861373901367, 'learning_rate': 1.1999999999999999e-05, 'epoch': 0.02}
+{'loss': 20.723, 'grad_norm': 15.45991325378418, 'learning_rate': 1.3199999999999997e-05, 'epoch': 0.02}
+{'loss': 20.1225, 'grad_norm': 14.389110565185547, 'learning_rate': 1.44e-05, 'epoch': 0.02}
+{'loss': 19.3834, 'grad_norm': 13.629838943481445, 'learning_rate': 1.5599999999999996e-05, 'epoch': 0.02}
+{'loss': 19.8481, 'grad_norm': 14.719141006469727, 'learning_rate': 1.68e-05, 'epoch': 0.02}
+{'loss': 18.9288, 'grad_norm': 13.934913635253906, 'learning_rate': 1.7999999999999997e-05, 'epoch': 0.02}
+{'loss': 17.2817, 'grad_norm': 13.111680030822754, 'learning_rate': 1.92e-05, 'epoch': 0.03}
+{'loss': 16.5192, 'grad_norm': 40.639015197753906, 'learning_rate': 2.04e-05, 'epoch': 0.03}
+{'loss': 17.0874, 'grad_norm': 13.131857872009277, 'learning_rate': 2.1599999999999996e-05, 'epoch': 0.03}
+{'loss': 18.3955, 'grad_norm': 14.969550132751465, 'learning_rate': 2.28e-05, 'epoch': 0.03}
+{'loss': 16.4885, 'grad_norm': 12.997845649719238, 'learning_rate': 2.3999999999999997e-05, 'epoch': 0.03}
+{'loss': 16.4608, 'grad_norm': 13.298186302185059, 'learning_rate': 2.52e-05, 'epoch': 0.03}
+{'loss': 18.4918, 'grad_norm': 17.314250946044922, 'learning_rate': 2.6399999999999995e-05, 'epoch': 0.04}
+{'loss': 16.9535, 'grad_norm': 14.80049991607666, 'learning_rate': 2.7599999999999997e-05, 'epoch': 0.04}
+{'loss': 16.5916, 'grad_norm': 15.080041885375977, 'learning_rate': 2.88e-05, 'epoch': 0.04}
+{'loss': 17.0922, 'grad_norm': 15.787080764770508, 'learning_rate': 2.9999999999999997e-05, 'epoch': 0.04}
+{'loss': 17.6368, 'grad_norm': 17.13389015197754, 'learning_rate': 3.119999999999999e-05, 'epoch': 0.04}
+{'loss': 14.6459, 'grad_norm': 13.813786506652832, 'learning_rate': 3.2399999999999995e-05, 'epoch': 0.04}
+{'loss': 18.4586, 'grad_norm': 19.571237564086914, 'learning_rate': 3.36e-05, 'epoch': 0.04}
+{'loss': 15.8893, 'grad_norm': 16.844707489013672, 'learning_rate': 3.48e-05, 'epoch': 0.05}
+{'loss': 15.1497, 'grad_norm': 18.0694637298584, 'learning_rate': 3.5999999999999994e-05, 'epoch': 0.05}
+{'loss': 16.198, 'grad_norm': 18.38799476623535, 'learning_rate': 3.7199999999999996e-05, 'epoch': 0.05}
+{'loss': 15.5918, 'grad_norm': 18.61817741394043, 'learning_rate': 3.84e-05, 'epoch': 0.05}
+{'loss': 16.1928, 'grad_norm': 20.656465530395508, 'learning_rate': 3.96e-05, 'epoch': 0.05}
+{'loss': 13.5195, 'grad_norm': 16.263877868652344, 'learning_rate': 4.08e-05, 'epoch': 0.05}
+{'loss': 14.3946, 'grad_norm': 18.767169952392578, 'learning_rate': 4.2e-05, 'epoch': 0.06}
+{'loss': 14.2461, 'grad_norm': 19.480947494506836, 'learning_rate': 4.319999999999999e-05, 'epoch': 0.06}
+{'loss': 14.2695, 'grad_norm': 20.49869155883789, 'learning_rate': 4.4399999999999995e-05, 'epoch': 0.06}
+{'loss': 13.8486, 'grad_norm': 20.939620971679688, 'learning_rate': 4.56e-05, 'epoch': 0.06}
+{'loss': 13.7119, 'grad_norm': 22.123334884643555, 'learning_rate': 4.68e-05, 'epoch': 0.06}
+{'loss': 14.1091, 'grad_norm': 29.032527923583984, 'learning_rate': 4.7999999999999994e-05, 'epoch': 0.06}
+{'loss': 14.999, 'grad_norm': 28.069717407226562, 'learning_rate': 4.9199999999999997e-05, 'epoch': 0.07}
+{'loss': 14.6043, 'grad_norm': 30.723072052001953, 'learning_rate': 5.04e-05, 'epoch': 0.07}
+{'loss': 14.0164, 'grad_norm': 30.142724990844727, 'learning_rate': 5.1599999999999994e-05, 'epoch': 0.07}
+{'loss': 12.8172, 'grad_norm': 28.958240509033203, 'learning_rate': 5.279999999999999e-05, 'epoch': 0.07}
+{'loss': 12.7462, 'grad_norm': 31.854141235351562, 'learning_rate': 5.399999999999999e-05, 'epoch': 0.07}
+{'loss': 11.4412, 'grad_norm': 28.455211639404297, 'learning_rate': 5.519999999999999e-05, 'epoch': 0.07}
+{'loss': 10.4074, 'grad_norm': 27.766897201538086, 'learning_rate': 5.6399999999999995e-05, 'epoch': 0.08}
+{'loss': 11.4181, 'grad_norm': 35.45139694213867, 'learning_rate': 5.76e-05, 'epoch': 0.08}
+{'loss': 10.5777, 'grad_norm': 35.00629806518555, 'learning_rate': 5.88e-05, 'epoch': 0.08}
+{'loss': 9.2136, 'grad_norm': 30.027040481567383, 'learning_rate': 5.9999999999999995e-05, 'epoch': 0.08}
+{'loss': 18.2865, 'grad_norm': 103.56065368652344, 'learning_rate': 6.12e-05, 'epoch': 0.08}
+{'loss': 15.0562, 'grad_norm': 86.56218719482422, 'learning_rate': 6.239999999999999e-05, 'epoch': 0.08}
+{'loss': 14.4796, 'grad_norm': 82.1945571899414, 'learning_rate': 6.359999999999999e-05, 'epoch': 0.08}
+{'loss': 10.162, 'grad_norm': 52.5987434387207, 'learning_rate': 6.479999999999999e-05, 'epoch': 0.09}
+{'loss': 12.2572, 'grad_norm': 263.50726318359375, 'learning_rate': 6.599999999999999e-05, 'epoch': 0.09}
+{'loss': 8.1613, 'grad_norm': 40.53132247924805, 'learning_rate': 6.72e-05, 'epoch': 0.09}
+{'loss': 10.1649, 'grad_norm': 64.0225601196289, 'learning_rate': 6.84e-05, 'epoch': 0.09}
+{'loss': 7.0805, 'grad_norm': 35.1747932434082, 'learning_rate': 6.96e-05, 'epoch': 0.09}
+{'loss': 6.6396, 'grad_norm': 32.24826431274414, 'learning_rate': 7.079999999999999e-05, 'epoch': 0.09}
+{'loss': 6.4643, 'grad_norm': 31.730484008789062, 'learning_rate': 7.199999999999999e-05, 'epoch': 0.1}
+{'loss': 6.4411, 'grad_norm': 32.03666687011719, 'learning_rate': 7.319999999999999e-05, 'epoch': 0.1}
+{'loss': 5.66, 'grad_norm': 23.286136627197266, 'learning_rate': 7.439999999999999e-05, 'epoch': 0.1}
+{'loss': 5.3729, 'grad_norm': 20.670251846313477, 'learning_rate': 7.56e-05, 'epoch': 0.1}
+{'loss': 5.1286, 'grad_norm': 15.871679306030273, 'learning_rate': 7.68e-05, 'epoch': 0.1}
+{'loss': 4.8803, 'grad_norm': 11.15343189239502, 'learning_rate': 7.8e-05, 'epoch': 0.1}
+{'loss': 4.9008, 'grad_norm': 12.387083053588867, 'learning_rate': 7.92e-05, 'epoch': 0.11}
+{'loss': 4.705, 'grad_norm': 8.835503578186035, 'learning_rate': 8.04e-05, 'epoch': 0.11}
+{'loss': 4.6347, 'grad_norm': 5.96044397354126, 'learning_rate': 8.16e-05, 'epoch': 0.11}
+{'loss': 4.55, 'grad_norm': 4.373923301696777, 'learning_rate': 8.28e-05, 'epoch': 0.11}
+{'loss': 4.5437, 'grad_norm': 3.950120449066162, 'learning_rate': 8.4e-05, 'epoch': 0.11}
+{'loss': 4.475, 'grad_norm': 4.327428817749023, 'learning_rate': 8.519999999999998e-05, 'epoch': 0.11}
+{'loss': 4.4206, 'grad_norm': 5.038540840148926, 'learning_rate': 8.639999999999999e-05, 'epoch': 0.12}
+{'loss': 4.3619, 'grad_norm': 5.283208847045898, 'learning_rate': 8.759999999999999e-05, 'epoch': 0.12}
+{'loss': 4.3522, 'grad_norm': 5.429969787597656, 'learning_rate': 8.879999999999999e-05, 'epoch': 0.12}
+{'loss': 4.2836, 'grad_norm': 4.981645107269287, 'learning_rate': 8.999999999999999e-05, 'epoch': 0.12}
+{'loss': 4.2366, 'grad_norm': 4.838561058044434, 'learning_rate': 9.12e-05, 'epoch': 0.12}
+{'loss': 4.1618, 'grad_norm': 4.037646293640137, 'learning_rate': 9.24e-05, 'epoch': 0.12}
+{'loss': 4.1763, 'grad_norm': 2.755617380142212, 'learning_rate': 9.36e-05, 'epoch': 0.12}
+{'loss': 4.0608, 'grad_norm': 2.9847090244293213, 'learning_rate': 9.479999999999999e-05, 'epoch': 0.13}
+{'loss': 4.1162, 'grad_norm': 3.5956788063049316, 'learning_rate': 9.599999999999999e-05, 'epoch': 0.13}
+{'loss': 3.9706, 'grad_norm': 3.1633763313293457, 'learning_rate': 9.719999999999999e-05, 'epoch': 0.13}
+{'loss': 4.0539, 'grad_norm': 6.8584303855896, 'learning_rate': 9.839999999999999e-05, 'epoch': 0.13}
+{'loss': 3.9233, 'grad_norm': 2.2297003269195557, 'learning_rate': 9.96e-05, 'epoch': 0.13}
+{'loss': 4.0172, 'grad_norm': 6.489461898803711, 'learning_rate': 0.0001008, 'epoch': 0.13}
+{'loss': 3.9076, 'grad_norm': 2.9540462493896484, 'learning_rate': 0.000102, 'epoch': 0.14}
+{'loss': 3.9456, 'grad_norm': 1.7731634378433228, 'learning_rate': 0.00010319999999999999, 'epoch': 0.14}
+{'loss': 3.9093, 'grad_norm': 1.2879796028137207, 'learning_rate': 0.00010439999999999999, 'epoch': 0.14}
+{'loss': 3.7957, 'grad_norm': 1.4996570348739624, 'learning_rate': 0.00010559999999999998, 'epoch': 0.14}
+{'loss': 3.7925, 'grad_norm': 3.2898361682891846, 'learning_rate': 0.00010679999999999998, 'epoch': 0.14}
+{'loss': 3.8016, 'grad_norm': 2.096083641052246, 'learning_rate': 0.00010799999999999998, 'epoch': 0.14}
+{'loss': 3.8623, 'grad_norm': 5.319262504577637, 'learning_rate': 0.00010919999999999998, 'epoch': 0.15}
+{'loss': 3.8429, 'grad_norm': 1.6835908889770508, 'learning_rate': 0.00011039999999999999, 'epoch': 0.15}
+{'loss': 3.7729, 'grad_norm': 1.5660072565078735, 'learning_rate': 0.00011159999999999999, 'epoch': 0.15}
+{'loss': 3.8433, 'grad_norm': 0.8665121793746948, 'learning_rate': 0.00011279999999999999, 'epoch': 0.15}
+{'loss': 3.8249, 'grad_norm': 5.862734317779541, 'learning_rate': 0.00011399999999999999, 'epoch': 0.15}
+{'loss': 3.8095, 'grad_norm': 2.4911062717437744, 'learning_rate': 0.0001152, 'epoch': 0.15}
+{'loss': 3.9602, 'grad_norm': 7.126469135284424, 'learning_rate': 0.0001164, 'epoch': 0.16}
+{'loss': 3.8379, 'grad_norm': 0.8465694189071655, 'learning_rate': 0.0001176, 'epoch': 0.16}
+{'loss': 3.8803, 'grad_norm': 1.3771048784255981, 'learning_rate': 0.0001188, 'epoch': 0.16}
+{'loss': 3.8788, 'grad_norm': 1.4679234027862549, 'learning_rate': 0.00011999999999999999, 'epoch': 0.16}
+
+
  0%|          | 0/196 [00:00<?, ?it/s]
+
  1%|          | 2/196 [00:00<01:35,  2.03it/s]
+
  2%|▏         | 3/196 [00:02<02:33,  1.26it/s]
+
  2%|▏         | 4/196 [00:03<03:12,  1.00s/it]
+
  3%|▎         | 5/196 [00:04<03:31,  1.11s/it]
+
  3%|▎         | 6/196 [00:06<04:02,  1.28s/it]
+
  4%|▎         | 7/196 [00:08<04:19,  1.37s/it]
+
  4%|▍         | 8/196 [00:09<04:18,  1.37s/it]
+
  5%|▍         | 9/196 [00:12<05:38,  1.81s/it]
+
  5%|▌         | 10/196 [00:15<06:51,  2.21s/it]
+
  6%|▌         | 11/196 [00:18<07:59,  2.59s/it]
+
  6%|▌         | 12/196 [00:22<08:35,  2.80s/it]
+
  7%|▋         | 13/196 [00:23<07:27,  2.44s/it]
+
  7%|▋         | 14/196 [00:24<06:11,  2.04s/it]
+
  8%|▊         | 15/196 [00:25<05:08,  1.70s/it]
+
  8%|▊         | 16/196 [00:27<04:46,  1.59s/it]
+
  9%|▊         | 17/196 [00:28<04:32,  1.52s/it]
+
  9%|▉         | 18/196 [00:30<04:55,  1.66s/it]
+
 10%|▉         | 19/196 [00:33<06:19,  2.15s/it]
+
 10%|█         | 20/196 [00:36<06:54,  2.35s/it]
+
 11%|█         | 21/196 [00:39<07:06,  2.44s/it]
+
 11%|█         | 22/196 [00:41<06:52,  2.37s/it]
+
 12%|█▏        | 23/196 [00:43<06:21,  2.21s/it]
+
 12%|█▏        | 24/196 [00:43<05:00,  1.75s/it]
+
 13%|█▎        | 25/196 [00:44<04:12,  1.48s/it]
+
 13%|█▎        | 26/196 [00:45<03:39,  1.29s/it]
+
 14%|█▍        | 27/196 [00:46<03:21,  1.19s/it]
+
 14%|█▍        | 28/196 [00:47<03:10,  1.14s/it]
+
 15%|█▍        | 29/196 [00:48<03:10,  1.14s/it]
+
 15%|█▌        | 30/196 [00:49<03:09,  1.14s/it]
+
 16%|█▌        | 31/196 [00:50<02:53,  1.05s/it]
+
 16%|█▋        | 32/196 [00:51<02:42,  1.01it/s]
+
 17%|█▋        | 33/196 [00:53<03:10,  1.17s/it]
+
 17%|█▋        | 34/196 [00:55<04:14,  1.57s/it]
+
 18%|█▊        | 35/196 [00:57<04:21,  1.62s/it]
+
 18%|█▊        | 36/196 [00:59<05:04,  1.90s/it]
+
 19%|█▉        | 37/196 [01:01<05:02,  1.90s/it]
+
 19%|█▉        | 38/196 [01:03<04:32,  1.72s/it]
+
 20%|█▉        | 39/196 [01:04<04:11,  1.60s/it]
+
 20%|██        | 40/196 [01:05<03:49,  1.47s/it]
+
 21%|██        | 41/196 [01:06<03:29,  1.35s/it]
+
 21%|██▏       | 42/196 [01:07<03:13,  1.26s/it]
+
 22%|██▏       | 43/196 [01:08<03:09,  1.24s/it]
+
 22%|██▏       | 44/196 [01:10<03:04,  1.21s/it]
+
 23%|██▎       | 45/196 [01:11<02:52,  1.14s/it]
+
 23%|██▎       | 46/196 [01:11<02:38,  1.06s/it]
+
 24%|██▍       | 47/196 [01:12<02:39,  1.07s/it]
+
 24%|██▍       | 48/196 [01:13<02:30,  1.02s/it]
+
 25%|██▌       | 49/196 [01:14<02:26,  1.00it/s]
+
 26%|██▌       | 50/196 [01:15<02:24,  1.01it/s]
+
 26%|██▌       | 51/196 [01:16<02:20,  1.03it/s]
+
 27%|██▋       | 52/196 [01:17<02:19,  1.04it/s]
+
 27%|██▋       | 53/196 [01:18<02:29,  1.05s/it]
+
 28%|██▊       | 54/196 [01:19<02:25,  1.02s/it]
+
 28%|██▊       | 55/196 [01:21<02:40,  1.14s/it]
+
 29%|██▊       | 56/196 [01:22<02:51,  1.22s/it]
+
 29%|██▉       | 57/196 [01:24<03:04,  1.33s/it]
+
 30%|██▉       | 58/196 [01:25<03:11,  1.39s/it]
+
 30%|███       | 59/196 [01:27<03:09,  1.38s/it]
+
 31%|███       | 60/196 [01:28<02:53,  1.27s/it]
+
 31%|███       | 61/196 [01:29<02:35,  1.15s/it]
+
 32%|███▏      | 62/196 [01:30<02:30,  1.12s/it]
+
 32%|███▏      | 63/196 [01:31<02:30,  1.13s/it]
+
 33%|███▎      | 64/196 [01:32<02:30,  1.14s/it]
+
 33%|███▎      | 65/196 [01:33<02:25,  1.11s/it]
+
 34%|███▎      | 66/196 [01:34<02:30,  1.16s/it]
+
 34%|███▍      | 67/196 [01:36<02:35,  1.20s/it]
+
 35%|███▍      | 68/196 [01:37<02:59,  1.40s/it]
+
 35%|███▌      | 69/196 [01:39<03:06,  1.47s/it]
+
 36%|███▌      | 70/196 [01:40<02:51,  1.36s/it]
+
 36%|███▌      | 71/196 [01:41<02:39,  1.27s/it]
+
 37%|███▋      | 72/196 [01:42<02:25,  1.17s/it]
+
 37%|███▋      | 73/196 [01:43<02:11,  1.07s/it]
+
 38%|███▊      | 74/196 [01:44<02:00,  1.01it/s]
+
 38%|███▊      | 75/196 [01:45<01:57,  1.03it/s]
+
 39%|███▉      | 76/196 [01:46<01:53,  1.05it/s]
+
 39%|███▉      | 77/196 [01:47<01:58,  1.00it/s]
+
 40%|███▉      | 78/196 [01:48<02:08,  1.09s/it]
+
 40%|████      | 79/196 [01:49<02:02,  1.05s/it]
+
 41%|████      | 80/196 [01:50<02:09,  1.12s/it]
+
 41%|████▏     | 81/196 [01:52<02:13,  1.16s/it]
+
 42%|████▏     | 82/196 [01:53<02:08,  1.13s/it]
+
 42%|████▏     | 83/196 [01:54<02:10,  1.15s/it]
+
 43%|████▎     | 84/196 [01:55<02:13,  1.19s/it]
+
 43%|████▎     | 85/196 [01:56<02:11,  1.18s/it]
+
 44%|████▍     | 86/196 [01:58<02:15,  1.23s/it]
+
 44%|████▍     | 87/196 [01:59<02:11,  1.20s/it]
+
 45%|████▍     | 88/196 [02:00<02:15,  1.25s/it]
+
 45%|████▌     | 89/196 [02:01<02:19,  1.30s/it]
+
 46%|████▌     | 90/196 [02:03<02:13,  1.26s/it]
+
 46%|████▋     | 91/196 [02:04<02:08,  1.22s/it]
+
 47%|████▋     | 92/196 [02:05<02:03,  1.18s/it]
+
 47%|████▋     | 93/196 [02:06<02:08,  1.25s/it]
+
 48%|████▊     | 94/196 [02:08<02:11,  1.29s/it]
+
 48%|████▊     | 95/196 [02:09<02:04,  1.23s/it]
+
 49%|████▉     | 96/196 [02:10<02:10,  1.30s/it]
+
 49%|████▉     | 97/196 [02:11<02:06,  1.28s/it]
+
 50%|█████     | 98/196 [02:13<02:10,  1.33s/it]
+
 51%|█████     | 99/196 [02:14<01:57,  1.21s/it]
+
 51%|█████     | 100/196 [02:15<01:43,  1.08s/it]
+
 52%|█████▏    | 101/196 [02:15<01:35,  1.00s/it]
+
 52%|█████▏    | 102/196 [02:17<01:40,  1.07s/it]
+
 53%|█████▎    | 103/196 [02:18<01:46,  1.15s/it]
+
 53%|█████▎    | 104/196 [02:20<02:03,  1.34s/it]
+
 54%|█████▎    | 105/196 [02:21<02:06,  1.39s/it]
+
 54%|█████▍    | 106/196 [02:23<02:05,  1.40s/it]
+
 55%|█████▍    | 107/196 [02:24<01:57,  1.32s/it]
+
 55%|█████▌    | 108/196 [02:25<01:42,  1.17s/it]
+
 56%|█████▌    | 109/196 [02:26<01:34,  1.09s/it]
+
 56%|█████▌    | 110/196 [02:26<01:29,  1.04s/it]
+
 57%|█████▋    | 111/196 [02:28<01:29,  1.06s/it]
+
 57%|█████▋    | 112/196 [02:29<01:31,  1.09s/it]
+
 58%|█████▊    | 113/196 [02:30<01:33,  1.13s/it]
+
 58%|█████▊    | 114/196 [02:31<01:25,  1.04s/it]
+
 59%|█████▊    | 115/196 [02:32<01:21,  1.00s/it]
+
 59%|█████▉    | 116/196 [02:33<01:18,  1.02it/s]
+
 60%|█████▉    | 117/196 [02:34<01:14,  1.06it/s]
+
 60%|██████    | 118/196 [02:34<01:06,  1.17it/s]
+
 61%|██████    | 119/196 [02:35<01:08,  1.13it/s]
+
 61%|██████    | 120/196 [02:36<01:11,  1.06it/s]
+
 62%|██████▏   | 121/196 [02:37<01:13,  1.02it/s]
+
 62%|██████▏   | 122/196 [02:38<01:14,  1.01s/it]
+
 63%|██████▎   | 123/196 [02:39<01:13,  1.00s/it]
+
 63%|██████▎   | 124/196 [02:40<01:10,  1.02it/s]
+
 64%|██████▍   | 125/196 [02:41<01:10,  1.01it/s]
+
 64%|██████▍   | 126/196 [02:43<01:18,  1.12s/it]
+
 65%|██████▍   | 127/196 [02:44<01:17,  1.12s/it]
+
 65%|██████▌   | 128/196 [02:45<01:12,  1.06s/it]
+
 66%|██████▌   | 129/196 [02:46<01:11,  1.06s/it]
+
 66%|██████▋   | 130/196 [02:47<01:09,  1.05s/it]
+
 67%|██████▋   | 131/196 [02:48<01:08,  1.06s/it]
+
 67%|██████▋   | 132/196 [02:49<01:03,  1.01it/s]
+
 68%|██████▊   | 133/196 [02:50<01:01,  1.02it/s]
+
 68%|██████▊   | 134/196 [02:51<01:06,  1.07s/it]
+
 69%|██████▉   | 135/196 [02:52<01:03,  1.04s/it]
+
 69%|██████▉   | 136/196 [02:53<00:59,  1.00it/s]
+
 70%|██████▉   | 137/196 [02:54<00:58,  1.00it/s]
+
 70%|███████   | 138/196 [02:55<00:58,  1.01s/it]
+
 71%|███████   | 139/196 [02:56<00:57,  1.01s/it]
+
 71%|███████▏  | 140/196 [02:57<00:56,  1.00s/it]
+
 72%|███████▏  | 141/196 [02:58<00:55,  1.01s/it]
+
 72%|███████▏  | 142/196 [02:59<00:56,  1.04s/it]
+
 73%|███████▎  | 143/196 [03:00<00:59,  1.13s/it]
+
 73%|███████▎  | 144/196 [03:01<00:54,  1.05s/it]
+
 74%|███████▍  | 145/196 [03:02<00:49,  1.04it/s]
+
 74%|███████▍  | 146/196 [03:03<00:44,  1.11it/s]
+
 75%|███████▌  | 147/196 [03:04<00:44,  1.10it/s]
+
 76%|███████▌  | 148/196 [03:05<00:43,  1.10it/s]
+
 76%|███████▌  | 149/196 [03:05<00:41,  1.14it/s]
+
 77%|███████▋  | 150/196 [03:06<00:42,  1.09it/s]
+
 77%|███████▋  | 151/196 [03:07<00:43,  1.02it/s]
+
 78%|███████▊  | 152/196 [03:08<00:42,  1.04it/s]
+
 78%|███████▊  | 153/196 [03:09<00:41,  1.05it/s]
+
 79%|███████▊  | 154/196 [03:10<00:41,  1.02it/s]
+
 79%|███████▉  | 155/196 [03:12<00:43,  1.05s/it]
+
 80%|███████▉  | 156/196 [03:13<00:49,  1.25s/it]
+
 80%|████████  | 157/196 [03:15<00:53,  1.37s/it]
+
 81%|████████  | 158/196 [03:16<00:46,  1.22s/it]
+
 81%|████████  | 159/196 [03:17<00:41,  1.11s/it]
+
 82%|████████▏ | 160/196 [03:18<00:37,  1.04s/it]
+
 82%|████████▏ | 161/196 [03:19<00:36,  1.04s/it]
+
 83%|████████▎ | 162/196 [03:20<00:35,  1.04s/it]
+
 83%|████████▎ | 163/196 [03:21<00:33,  1.01s/it]
+
 84%|████████▎ | 164/196 [03:22<00:31,  1.01it/s]
+
 84%|████████▍ | 165/196 [03:23<00:32,  1.04s/it]
+
 85%|████████▍ | 166/196 [03:24<00:30,  1.01s/it]
+
 85%|████████▌ | 167/196 [03:25<00:28,  1.02it/s]
+
 86%|████████▌ | 168/196 [03:25<00:26,  1.07it/s]
+
 86%|████████▌ | 169/196 [03:26<00:25,  1.05it/s]
+
 87%|████████▋ | 170/196 [03:28<00:27,  1.06s/it]
+
 87%|████████▋ | 171/196 [03:29<00:25,  1.02s/it]
+
 88%|████████▊ | 172/196 [03:30<00:25,  1.05s/it]
+
 88%|████████▊ | 173/196 [03:31<00:23,  1.04s/it]
+
 89%|████████▉ | 174/196 [03:32<00:24,  1.09s/it]
+
 89%|████████▉ | 175/196 [03:34<00:27,  1.32s/it]
+
 90%|████████▉ | 176/196 [03:38<00:41,  2.08s/it]
+
 90%|█████████ | 177/196 [03:41<00:46,  2.43s/it]
+
 91%|█████████ | 178/196 [03:44<00:47,  2.64s/it]
+
 91%|█████████▏| 179/196 [03:48<00:50,  2.96s/it]
+
 92%|█████████▏| 180/196 [03:49<00:37,  2.36s/it]
+
 92%|█████████▏| 181/196 [03:50<00:29,  2.00s/it]
+
 93%|█████████▎| 182/196 [03:51<00:23,  1.69s/it]
+
 93%|█████████▎| 183/196 [03:53<00:22,  1.75s/it]
+
 94%|█████████▍| 184/196 [03:54<00:18,  1.50s/it]
+
 94%|█████████▍| 185/196 [03:55<00:15,  1.43s/it]
+
 95%|█████████▍| 186/196 [03:57<00:15,  1.50s/it]
+
 95%|█████████▌| 187/196 [03:58<00:12,  1.38s/it]
+
 96%|█████████▌| 188/196 [03:59<00:09,  1.24s/it]
+
 96%|█████████▋| 189/196 [04:00<00:08,  1.19s/it]
+
 97%|█████████▋| 190/196 [04:01<00:06,  1.12s/it]
+
 97%|█████████▋| 191/196 [04:01<00:05,  1.03s/it]
+
 98%|█████████▊| 192/196 [04:03<00:04,  1.03s/it]
+
 98%|█████████▊| 193/196 [04:04<00:03,  1.04s/it]
+
 99%|█████████▉| 194/196 [04:05<00:02,  1.04s/it]
+
 99%|█████████▉| 195/196 [04:06<00:01,  1.01s/it]
+
                                                    
+
                                                 
  2%|▏         | 100/5000 [10:40<2:44:15,  2.01s/it]
+
+
                                                 
  2%|▏         | 101/5000 [10:56<112:44:57, 82.85s/it]
                                                      
  2%|▏         | 101/5000 [10:56<112:44:57, 82.85s/it]
  2%|▏         | 102/5000 [11:05<82:27:49, 60.61s/it] 
                                                     
  2%|▏         | 102/5000 [11:05<82:27:49, 60.61s/it]
  2%|▏         | 103/5000 [11:13<60:46:59, 44.68s/it]
                                                     
  2%|▏         | 103/5000 [11:13<60:46:59, 44.68s/it]
  2%|▏         | 104/5000 [11:19<45:14:51, 33.27s/it]
                                                     
  2%|▏         | 104/5000 [11:19<45:14:51, 33.27s/it]
  2%|▏         | 105/5000 [11:26<34:13:05, 25.17s/it]
                                                     
  2%|▏         | 105/5000 [11:26<34:13:05, 25.17s/it]
  2%|▏         | 106/5000 [11:32<26:22:42, 19.40s/it]
                                                     
  2%|▏         | 106/5000 [11:32<26:22:42, 19.40s/it]
  2%|▏         | 107/5000 [11:37<20:40:35, 15.21s/it]
                                                     
  2%|▏         | 107/5000 [11:37<20:40:35, 15.21s/it]
  2%|▏         | 108/5000 [11:42<16:39:34, 12.26s/it]
                                                     
  2%|▏         | 108/5000 [11:42<16:39:34, 12.26s/it]
  2%|▏         | 109/5000 [11:47<13:41:45, 10.08s/it]
                                                     
  2%|▏         | 109/5000 [11:47<13:41:45, 10.08s/it]
  2%|▏         | 110/5000 [11:52<11:31:20,  8.48s/it]
                                                     
  2%|▏         | 110/5000 [11:52<11:31:20,  8.48s/it]
  2%|▏         | 111/5000 [11:57<10:00:45,  7.37s/it]
                                                     
  2%|▏         | 111/5000 [11:57<10:00:45,  7.37s/it]
  2%|▏         | 112/5000 [12:02<8:54:57,  6.57s/it] 
                                                    
  2%|▏         | 112/5000 [12:02<8:54:57,  6.57s/it]
  2%|▏         | 113/5000 [12:06<8:00:26,  5.90s/it]
                                                    
  2%|▏         | 113/5000 [12:06<8:00:26,  5.90s/it]
  2%|▏         | 114/5000 [12:10<7:16:59,  5.37s/it]
                                                    
  2%|▏         | 114/5000 [12:10<7:16:59,  5.37s/it]
  2%|▏         | 115/5000 [12:14<6:46:31,  4.99s/it]
                                                    
  2%|▏         | 115/5000 [12:14<6:46:31,  4.99s/it]
  2%|▏         | 116/5000 [12:18<6:25:16,  4.73s/it]
                                                    
  2%|▏         | 116/5000 [12:18<6:25:16,  4.73s/it]
  2%|▏         | 117/5000 [12:22<6:07:22,  4.51s/it]
                                                    
  2%|▏         | 117/5000 [12:22<6:07:22,  4.51s/it]
  2%|▏         | 118/5000 [12:26<5:43:11,  4.22s/it]
                                                    
  2%|▏         | 118/5000 [12:26<5:43:11,  4.22s/it]
  2%|▏         | 119/5000 [12:29<5:25:03,  4.00s/it]
                                                    
  2%|▏         | 119/5000 [12:29<5:25:03,  4.00s/it]
  2%|▏         | 120/5000 [12:33<5:12:22,  3.84s/it]
                                                    
  2%|▏         | 120/5000 [12:33<5:12:22,  3.84s/it]
  2%|▏         | 121/5000 [12:36<5:03:16,  3.73s/it]
                                                    
  2%|▏         | 121/5000 [12:36<5:03:16,  3.73s/it]
  2%|▏         | 122/5000 [12:40<4:56:44,  3.65s/it]
                                                    
  2%|▏         | 122/5000 [12:40<4:56:44,  3.65s/it]
  2%|▏         | 123/5000 [12:43<4:52:45,  3.60s/it]
                                                    
  2%|▏         | 123/5000 [12:43<4:52:45,  3.60s/it]
  2%|▏         | 124/5000 [12:47<4:47:27,  3.54s/it]
                                                    
  2%|▏         | 124/5000 [12:47<4:47:27,  3.54s/it]
  2%|▎         | 125/5000 [12:49<4:31:41,  3.34s/it]
                                                    
  2%|▎         | 125/5000 [12:49<4:31:41,  3.34s/it]
  3%|▎         | 126/5000 [12:52<4:20:32,  3.21s/it]
                                                    
  3%|▎         | 126/5000 [12:52<4:20:32,  3.21s/it]
  3%|▎         | 127/5000 [12:55<4:12:56,  3.11s/it]
                                                    
  3%|▎         | 127/5000 [12:55<4:12:56,  3.11s/it]
  3%|▎         | 128/5000 [12:58<4:07:34,  3.05s/it]
                                                    
  3%|▎         | 128/5000 [12:58<4:07:34,  3.05s/it]
  3%|▎         | 129/5000 [13:01<4:03:57,  3.01s/it]
                                                    
  3%|▎         | 129/5000 [13:01<4:03:57,  3.01s/it]
  3%|▎         | 130/5000 [13:04<4:01:39,  2.98s/it]
                                                    
  3%|▎         | 130/5000 [13:04<4:01:39,  2.98s/it]
  3%|▎         | 131/5000 [13:07<3:59:31,  2.95s/it]
                                                    
  3%|▎         | 131/5000 [13:07<3:59:31,  2.95s/it]
  3%|▎         | 132/5000 [13:10<3:54:56,  2.90s/it]
                                                    
  3%|▎         | 132/5000 [13:10<3:54:56,  2.90s/it]
  3%|▎         | 133/5000 [13:12<3:41:04,  2.73s/it]
                                                    
  3%|▎         | 133/5000 [13:12<3:41:04,  2.73s/it]
  3%|▎         | 134/5000 [13:14<3:31:40,  2.61s/it]
                                                    
  3%|▎         | 134/5000 [13:14<3:31:40,  2.61s/it]
  3%|▎         | 135/5000 [13:17<3:25:01,  2.53s/it]
                                                    
  3%|▎         | 135/5000 [13:17<3:25:01,  2.53s/it]
  3%|▎         | 136/5000 [13:19<3:20:37,  2.47s/it]
                                                    
  3%|▎         | 136/5000 [13:19<3:20:37,  2.47s/it]
  3%|▎         | 137/5000 [13:21<3:17:14,  2.43s/it]
                                                    
  3%|▎         | 137/5000 [13:21<3:17:14,  2.43s/it]
  3%|▎         | 138/5000 [13:24<3:15:02,  2.41s/it]
                                                    
  3%|▎         | 138/5000 [13:24<3:15:02,  2.41s/it]
  3%|▎         | 139/5000 [13:26<3:13:07,  2.38s/it]
                                                    
  3%|▎         | 139/5000 [13:26<3:13:07,  2.38s/it]
  3%|▎         | 140/5000 [13:28<3:08:53,  2.33s/it]
                                                    
  3%|▎         | 140/5000 [13:28<3:08:53,  2.33s/it]
  3%|▎         | 141/5000 [13:30<2:54:40,  2.16s/it]
                                                    
  3%|▎         | 141/5000 [13:30<2:54:40,  2.16s/it]
  3%|▎         | 142/5000 [13:32<2:44:45,  2.03s/it]
                                                    
  3%|▎         | 142/5000 [13:32<2:44:45,  2.03s/it]
  3%|▎         | 143/5000 [13:33<2:37:59,  1.95s/it]
                                                    
  3%|▎         | 143/5000 [13:33<2:37:59,  1.95s/it]
  3%|▎         | 144/5000 [13:35<2:33:23,  1.90s/it]
                                                    
  3%|▎         | 144/5000 [13:35<2:33:23,  1.90s/it]
  3%|▎         | 145/5000 [13:37<2:29:54,  1.85s/it]
                                                    
  3%|▎         | 145/5000 [13:37<2:29:54,  1.85s/it]
  3%|▎         | 146/5000 [13:39<2:26:05,  1.81s/it]
                                                    
  3%|▎         | 146/5000 [13:39<2:26:05,  1.81s/it]
  3%|▎         | 147/5000 [13:40<2:16:10,  1.68s/it]
                                                    
  3%|▎         | 147/5000 [13:40<2:16:10,  1.68s/it]
  3%|▎         | 148/5000 [13:41<2:04:16,  1.54s/it]
                                                    
  3%|▎         | 148/5000 [13:41<2:04:16,  1.54s/it]
  3%|▎         | 149/5000 [13:42<1:55:55,  1.43s/it]
                                                    
  3%|▎         | 149/5000 [13:42<1:55:55,  1.43s/it]
  3%|▎         | 150/5000 [13:46<2:35:29,  1.92s/it]
                                                    
  3%|▎         | 150/5000 [13:46<2:35:29,  1.92s/it]
  3%|▎         | 151/5000 [14:03<8:56:47,  6.64s/it]
                                                    
  3%|▎         | 151/5000 [14:03<8:56:47,  6.64s/it]
  3%|▎         | 152/5000 [14:13<10:06:23,  7.50s/it]
                                                     
  3%|▎         | 152/5000 [14:13<10:06:23,  7.50s/it]
  3%|▎         | 153/5000 [14:21<10:23:38,  7.72s/it]
                                                     
  3%|▎         | 153/5000 [14:21<10:23:38,  7.72s/it]
  3%|▎         | 154/5000 [14:28<10:11:29,  7.57s/it]
                                                     
  3%|▎         | 154/5000 [14:28<10:11:29,  7.57s/it]
  3%|▎         | 155/5000 [14:35<9:52:15,  7.33s/it] 
                                                    
  3%|▎         | 155/5000 [14:35<9:52:15,  7.33s/it]
  3%|▎         | 156/5000 [14:41<9:25:01,  7.00s/it]
                                                    
  3%|▎         | 156/5000 [14:41<9:25:01,  7.00s/it]
  3%|▎         | 157/5000 [14:47<8:57:19,  6.66s/it]
                                                    
  3%|▎         | 157/5000 [14:47<8:57:19,  6.66s/it]
  3%|▎         | 158/5000 [14:52<8:26:30,  6.28s/it]
                                                    
  3%|▎         | 158/5000 [14:52<8:26:30,  6.28s/it]
  3%|▎         | 159/5000 [14:58<8:04:16,  6.00s/it]
                                                    
  3%|▎         | 159/5000 [14:58<8:04:16,  6.00s/it]
  3%|▎         | 160/5000 [15:03<7:39:05,  5.69s/it]
                                                    
  3%|▎         | 160/5000 [15:03<7:39:05,  5.69s/it]
  3%|▎         | 161/5000 [15:07<7:15:00,  5.39s/it]
                                                    
  3%|▎         | 161/5000 [15:07<7:15:00,  5.39s/it]
  3%|▎         | 162/5000 [15:12<6:58:22,  5.19s/it]
                                                    
  3%|▎         | 162/5000 [15:12<6:58:22,  5.19s/it]
  3%|▎         | 163/5000 [15:16<6:36:59,  4.92s/it]
                                                    
  3%|▎         | 163/5000 [15:16<6:36:59,  4.92s/it]
  3%|▎         | 164/5000 [15:20<6:16:31,  4.67s/it]
                                                    
  3%|▎         | 164/5000 [15:21<6:16:31,  4.67s/it]
  3%|▎         | 165/5000 [15:25<6:02:06,  4.49s/it]
                                                    
  3%|▎         | 165/5000 [15:25<6:02:06,  4.49s/it]
  3%|▎         | 166/5000 [15:29<5:51:45,  4.37s/it]
                                                    
  3%|▎         | 166/5000 [15:29<5:51:45,  4.37s/it]
  3%|▎         | 167/5000 [15:33<5:44:41,  4.28s/it]
                                                    
  3%|▎         | 167/5000 [15:33<5:44:41,  4.28s/it]
  3%|▎         | 168/5000 [15:37<5:37:26,  4.19s/it]
                                                    
  3%|▎         | 168/5000 [15:37<5:37:26,  4.19s/it]
  3%|▎         | 169/5000 [15:40<5:19:41,  3.97s/it]
                                                    
  3%|▎         | 169/5000 [15:40<5:19:41,  3.97s/it]
  3%|▎         | 170/5000 [15:44<5:07:48,  3.82s/it]
                                                    
  3%|▎         | 170/5000 [15:44<5:07:48,  3.82s/it]
  3%|▎         | 171/5000 [15:47<4:58:58,  3.71s/it]
                                                    
  3%|▎         | 171/5000 [15:47<4:58:58,  3.71s/it]
  3%|▎         | 172/5000 [15:51<4:52:54,  3.64s/it]
                                                    
  3%|▎         | 172/5000 [15:51<4:52:54,  3.64s/it]
  3%|▎         | 173/5000 [15:54<4:48:25,  3.59s/it]
                                                    
  3%|▎         | 173/5000 [15:54<4:48:25,  3.59s/it]
  3%|▎         | 174/5000 [15:57<4:44:43,  3.54s/it]
                                                    
  3%|▎         | 174/5000 [15:57<4:44:43,  3.54s/it]
  4%|▎         | 175/5000 [16:01<4:33:54,  3.41s/it]
                                                    
  4%|▎         | 175/5000 [16:01<4:33:54,  3.41s/it]
  4%|▎         | 176/5000 [16:03<4:21:31,  3.25s/it]
                                                    
  4%|▎         | 176/5000 [16:03<4:21:31,  3.25s/it]
  4%|▎         | 177/5000 [16:06<4:12:46,  3.14s/it]
                                                    
  4%|▎         | 177/5000 [16:06<4:12:46,  3.14s/it]
  4%|▎         | 178/5000 [16:09<4:06:53,  3.07s/it]
                                                    
  4%|▎         | 178/5000 [16:09<4:06:53,  3.07s/it]
  4%|▎         | 179/5000 [16:12<4:02:20,  3.02s/it]
                                                    
  4%|▎         | 179/5000 [16:12<4:02:20,  3.02s/it]
  4%|▎         | 180/5000 [16:15<3:59:14,  2.98s/it]
                                                    
  4%|▎         | 180/5000 [16:15<3:59:14,  2.98s/it]
  4%|▎         | 181/5000 [16:18<3:57:04,  2.95s/it]
                                                    
  4%|▎         | 181/5000 [16:18<3:57:04,  2.95s/it]
  4%|▎         | 182/5000 [16:21<3:52:28,  2.90s/it]
                                                    
  4%|▎         | 182/5000 [16:21<3:52:28,  2.90s/it]
  4%|▎         | 183/5000 [16:23<3:39:25,  2.73s/it]
                                                    
  4%|▎         | 183/5000 [16:23<3:39:25,  2.73s/it]
  4%|▎         | 184/5000 [16:25<3:29:44,  2.61s/it]
                                                    
  4%|▎         | 184/5000 [16:25<3:29:44,  2.61s/it]
  4%|▎         | 185/5000 [16:28<3:23:06,  2.53s/it]
                                                    
  4%|▎         | 185/5000 [16:28<3:23:06,  2.53s/it]
  4%|▎         | 186/5000 [16:30<3:18:13,  2.47s/it]
                                                    
  4%|▎         | 186/5000 [16:30<3:18:13,  2.47s/it]
  4%|▎         | 187/5000 [16:32<3:14:56,  2.43s/it]
                                                    
  4%|▎         | 187/5000 [16:32<3:14:56,  2.43s/it]
  4%|▍         | 188/5000 [16:35<3:12:59,  2.41s/it]
                                                    
  4%|▍         | 188/5000 [16:35<3:12:59,  2.41s/it]
  4%|▍         | 189/5000 [16:37<3:11:18,  2.39s/it]
                                                    
  4%|▍         | 189/5000 [16:37<3:11:18,  2.39s/it]
  4%|▍         | 190/5000 [16:39<3:01:04,  2.26s/it]
                                                    
  4%|▍         | 190/5000 [16:39<3:01:04,  2.26s/it]
  4%|▍         | 191/5000 [16:41<2:48:45,  2.11s/it]
                                                    
  4%|▍         | 191/5000 [16:41<2:48:45,  2.11s/it]
  4%|▍         | 192/5000 [16:43<2:40:21,  2.00s/it]
                                                    
  4%|▍         | 192/5000 [16:43<2:40:21,  2.00s/it]
  4%|▍         | 193/5000 [16:44<2:34:24,  1.93s/it]
                                                    
  4%|▍         | 193/5000 [16:44<2:34:24,  1.93s/it]
  4%|▍         | 194/5000 [16:46<2:30:21,  1.88s/it]
                                                    
  4%|▍         | 194/5000 [16:46<2:30:21,  1.88s/it]
  4%|▍         | 195/5000 [16:48<2:27:19,  1.84s/it]
                                                    
  4%|▍         | 195/5000 [16:48<2:27:19,  1.84s/it]
  4%|▍         | 196/5000 [16:50<2:24:45,  1.81s/it]
                                                    
  4%|▍         | 196/5000 [16:50<2:24:45,  1.81s/it]
  4%|▍         | 197/5000 [16:51<2:14:45,  1.68s/it]
                                                    
  4%|▍         | 197/5000 [16:51<2:14:45,  1.68s/it]
  4%|▍         | 198/5000 [16:52<2:03:05,  1.54s/it]
                                                    
  4%|▍         | 198/5000 [16:52<2:03:05,  1.54s/it]
  4%|▍         | 199/5000 [16:53<1:54:58,  1.44s/it]
                                                    
  4%|▍         | 199/5000 [16:53<1:54:58,  1.44s/it]
  4%|▍         | 200/5000 [16:56<2:35:34,  1.94s/it]
                                                    
  4%|▍         | 200/5000 [16:56<2:35:34,  1.94s/it]predictions output file at: /scratch/elec/puhe/p/palp3/MUCS/mucs_language_segregated_data/trainwithtagsv2_warmup500_s300_shuff100/predictionswtagsv2_indicw2v_ad0_3_hd_02_featd_0_2_lr6e-4_warmup500_s300_shuff100.txt
+Printing predictions for a few samples:
+Sample 1:
+  Reference: लिबर ऑफिस ∅ impress ∇ में एक प्रस्तुति ∅ document ∇ बनाना और बुनियादी ∅ formatting ∇ के इस ∅ spoken  tutorial ∇ में आपका स्वागत है
+######
+
+
+  Prediction: 
+
+
+
+Sample 2:
+  Reference: इस ∅ tutorial ∇ में हम ∅ impress  window ∇ के भागों के बारे में सीखेंगे और कैसे स्लाइड इन्सर्ट करें और कॉपी करें फॉन्ट तथा फॉन्ट को फॉर्मेट करना सीखेंगे
+######
+
+
+  Prediction: ee
+
+
+
+Sample 3:
+  Reference: यहाँ हम अपने ऑपरेटिंग सिस्टम के रूप में gnu/linux और लिबरऑफिस वर्जन ∅ 334 ∇ का उपयोग कर रहे हैं
+######
+
+
+  Prediction: 
+
+
+
+Sample 4:
+  Reference: चलिए अपनी प्रस्तुति प्रेजैटेशन ∅ sample  impress  open ∇ करते हैं जिसे पिछले ∅ tutorial ∇ में बनाया था
+######
+
+
+  Prediction: 
+
+
+
+Sample 5:
+  Reference: चलिए देखते हैं कि ∅ screen ∇ पर क्या क्या है
+######
+
+
+  Prediction: 
+
+
+
+last Reference string यह स्क्रिप्ट लता द्वारा अनुवादित है आईआईटी मुंबई की ओर से मैं रवि कुमार अब आपसे विदा ���ेता हूँहमसे जुड़ने के लिए धन्यवाद
+
+
+last prediction string 
+cleaned cs transcription pred and ref 
+
+
+लिबर ऑफिस impress में एक प्रस्तुति document बनाना और बुनियादी formatting के इस spoken  tutorial में आपका स्वागत है
+{'eval_loss': 3.756589651107788, 'eval_cer': 0.9993136082367011, 'eval_wer': 1.0, 'eval_runtime': 255.4395, 'eval_samples_per_second': 12.277, 'eval_steps_per_second': 0.767, 'epoch': 0.16}
+{'loss': 4.8265, 'grad_norm': 38.48965835571289, 'learning_rate': 0.00012119999999999999, 'epoch': 0.16}
+{'loss': 3.995, 'grad_norm': 14.283730506896973, 'learning_rate': 0.0001224, 'epoch': 0.16}
+{'loss': 3.7879, 'grad_norm': 8.576812744140625, 'learning_rate': 0.0001236, 'epoch': 0.16}
+{'loss': 3.9799, 'grad_norm': 21.387664794921875, 'learning_rate': 0.00012479999999999997, 'epoch': 0.17}
+{'loss': 3.7848, 'grad_norm': 2.427260398864746, 'learning_rate': 0.00012599999999999997, 'epoch': 0.17}
+{'loss': 3.7703, 'grad_norm': 1.3663990497589111, 'learning_rate': 0.00012719999999999997, 'epoch': 0.17}
+{'loss': 3.8065, 'grad_norm': 1.7364495992660522, 'learning_rate': 0.00012839999999999998, 'epoch': 0.17}
+{'loss': 3.6977, 'grad_norm': 3.71764874458313, 'learning_rate': 0.00012959999999999998, 'epoch': 0.17}
+{'loss': 3.705, 'grad_norm': 2.993403434753418, 'learning_rate': 0.00013079999999999998, 'epoch': 0.17}
+{'loss': 3.695, 'grad_norm': 3.1739470958709717, 'learning_rate': 0.00013199999999999998, 'epoch': 0.18}
+{'loss': 3.6989, 'grad_norm': 2.5547573566436768, 'learning_rate': 0.00013319999999999999, 'epoch': 0.18}
+{'loss': 3.6776, 'grad_norm': 1.4511839151382446, 'learning_rate': 0.0001344, 'epoch': 0.18}
+{'loss': 3.7139, 'grad_norm': 1.6091411113739014, 'learning_rate': 0.0001356, 'epoch': 0.18}
+{'loss': 3.6809, 'grad_norm': 1.7235424518585205, 'learning_rate': 0.0001368, 'epoch': 0.18}
+{'loss': 3.6593, 'grad_norm': 1.596807837486267, 'learning_rate': 0.000138, 'epoch': 0.18}
+{'loss': 3.625, 'grad_norm': 1.3405994176864624, 'learning_rate': 0.0001392, 'epoch': 0.19}
+{'loss': 3.7073, 'grad_norm': 1.2730778455734253, 'learning_rate': 0.0001404, 'epoch': 0.19}
+{'loss': 3.6353, 'grad_norm': 5.288895130157471, 'learning_rate': 0.00014159999999999997, 'epoch': 0.19}
+{'loss': 3.7244, 'grad_norm': 1.5006777048110962, 'learning_rate': 0.00014279999999999997, 'epoch': 0.19}
+{'loss': 3.6375, 'grad_norm': 2.001701831817627, 'learning_rate': 0.00014399999999999998, 'epoch': 0.19}
+{'loss': 3.7359, 'grad_norm': 1.6458996534347534, 'learning_rate': 0.00014519999999999998, 'epoch': 0.19}
+{'loss': 3.6629, 'grad_norm': 3.332979917526245, 'learning_rate': 0.00014639999999999998, 'epoch': 0.2}
+{'loss': 3.6118, 'grad_norm': 1.4556349515914917, 'learning_rate': 0.00014759999999999998, 'epoch': 0.2}
+{'loss': 3.6565, 'grad_norm': 1.3131866455078125, 'learning_rate': 0.00014879999999999998, 'epoch': 0.2}
+{'loss': 3.6411, 'grad_norm': 3.0149691104888916, 'learning_rate': 0.00015, 'epoch': 0.2}
+{'loss': 3.7214, 'grad_norm': 7.048384189605713, 'learning_rate': 0.0001512, 'epoch': 0.2}
+{'loss': 3.6838, 'grad_norm': 4.727232456207275, 'learning_rate': 0.0001524, 'epoch': 0.2}
+{'loss': 3.6321, 'grad_norm': 4.120789051055908, 'learning_rate': 0.0001536, 'epoch': 0.2}
+{'loss': 3.6596, 'grad_norm': 2.701378345489502, 'learning_rate': 0.0001548, 'epoch': 0.21}
+{'loss': 3.6455, 'grad_norm': 1.1040818691253662, 'learning_rate': 0.000156, 'epoch': 0.21}
+{'loss': 3.6392, 'grad_norm': 2.2652924060821533, 'learning_rate': 0.0001572, 'epoch': 0.21}
+{'loss': 3.6564, 'grad_norm': 1.944316029548645, 'learning_rate': 0.0001584, 'epoch': 0.21}
+{'loss': 3.6666, 'grad_norm': 2.841169834136963, 'learning_rate': 0.0001596, 'epoch': 0.21}
+{'loss': 3.6769, 'grad_norm': 1.1487207412719727, 'learning_rate': 0.0001608, 'epoch': 0.21}
+{'loss': 3.6356, 'grad_norm': 2.734001636505127, 'learning_rate': 0.000162, 'epoch': 0.22}
+{'loss': 3.7166, 'grad_norm': 7.825503349304199, 'learning_rate': 0.0001632, 'epoch': 0.22}
+{'loss': 3.6611, 'grad_norm': 2.640146493911743, 'learning_rate': 0.0001644, 'epoch': 0.22}
+{'loss': 3.787, 'grad_norm': 6.790426254272461, 'learning_rate': 0.0001656, 'epoch': 0.22}
+{'loss': 3.7059, 'grad_norm': 5.147435665130615, 'learning_rate': 0.0001668, 'epoch': 0.22}
+{'loss': 3.6741, 'grad_norm': 1.0099550485610962, 'learning_rate': 0.000168, 'epoch': 0.22}
+{'loss': 3.5931, 'grad_norm': 0.6957960724830627, 'learning_rate': 0.00016919999999999997, 'epoch': 0.23}
+{'loss': 3.6941, 'grad_norm': 0.8608220219612122, 'learning_rate': 0.00017039999999999997, 'epoch': 0.23}
+{'loss': 3.6514, 'grad_norm': 1.106878399848938, 'learning_rate': 0.00017159999999999997, 'epoch': 0.23}
+{'loss': 3.6309, 'grad_norm': 1.4964262247085571, 'learning_rate': 0.00017279999999999997, 'epoch': 0.23}
+{'loss': 3.5667, 'grad_norm': 1.8776533603668213, 'learning_rate': 0.00017399999999999997, 'epoch': 0.23}
+{'loss': 3.6641, 'grad_norm': 1.1998003721237183, 'learning_rate': 0.00017519999999999998, 'epoch': 0.23}
+{'loss': 3.6057, 'grad_norm': 0.7275452017784119, 'learning_rate': 0.00017639999999999998, 'epoch': 0.24}
+{'loss': 3.6273, 'grad_norm': 1.6733245849609375, 'learning_rate': 0.00017759999999999998, 'epoch': 0.24}
+{'loss': 3.6672, 'grad_norm': 1.0381203889846802, 'learning_rate': 0.00017879999999999998, 'epoch': 0.24}
+{'loss': 3.7225, 'grad_norm': 2.804208993911743, 'learning_rate': 0.00017999999999999998, 'epoch': 0.24}
+{'loss': 4.8053, 'grad_norm': 37.25443649291992, 'learning_rate': 0.00018119999999999999, 'epoch': 0.24}
+{'loss': 3.8555, 'grad_norm': 12.150286674499512, 'learning_rate': 0.0001824, 'epoch': 0.24}
+{'loss': 3.8873, 'grad_norm': 9.963776588439941, 'learning_rate': 0.0001836, 'epoch': 0.24}
+{'loss': 3.715, 'grad_norm': 4.422680854797363, 'learning_rate': 0.0001848, 'epoch': 0.25}
+{'loss': 3.9109, 'grad_norm': 7.834131717681885, 'learning_rate': 0.000186, 'epoch': 0.25}
+{'loss': 3.7019, 'grad_norm': 6.25940465927124, 'learning_rate': 0.0001872, 'epoch': 0.25}
+{'loss': 3.7603, 'grad_norm': 8.240117073059082, 'learning_rate': 0.00018839999999999997, 'epoch': 0.25}
+{'loss': 3.8329, 'grad_norm': 8.491787910461426, 'learning_rate': 0.00018959999999999997, 'epoch': 0.25}
+{'loss': 3.833, 'grad_norm': 8.898347854614258, 'learning_rate': 0.00019079999999999998, 'epoch': 0.25}
+{'loss': 3.7302, 'grad_norm': 8.100727081298828, 'learning_rate': 0.00019199999999999998, 'epoch': 0.26}
+{'loss': 3.6727, 'grad_norm': 6.175380229949951, 'learning_rate': 0.00019319999999999998, 'epoch': 0.26}
+{'loss': 3.6329, 'grad_norm': 3.0743486881256104, 'learning_rate': 0.00019439999999999998, 'epoch': 0.26}
+{'loss': 3.6433, 'grad_norm': 0.708350658416748, 'learning_rate': 0.00019559999999999998, 'epoch': 0.26}
+{'loss': 3.6271, 'grad_norm': 5.063936233520508, 'learning_rate': 0.00019679999999999999, 'epoch': 0.26}
+{'loss': 3.7516, 'grad_norm': 9.512127876281738, 'learning_rate': 0.000198, 'epoch': 0.26}
+{'loss': 3.73, 'grad_norm': 9.915925979614258, 'learning_rate': 0.0001992, 'epoch': 0.27}
+{'loss': 3.7317, 'grad_norm': 10.222678184509277, 'learning_rate': 0.0002004, 'epoch': 0.27}
+{'loss': 3.6102, 'grad_norm': 3.9347116947174072, 'learning_rate': 0.0002016, 'epoch': 0.27}
+{'loss': 3.762, 'grad_norm': 7.799042701721191, 'learning_rate': 0.0002028, 'epoch': 0.27}
+{'loss': 3.5983, 'grad_norm': 1.9994298219680786, 'learning_rate': 0.000204, 'epoch': 0.27}
+{'loss': 3.5832, 'grad_norm': 1.4586771726608276, 'learning_rate': 0.0002052, 'epoch': 0.27}
+{'loss': 3.5878, 'grad_norm': 2.8306543827056885, 'learning_rate': 0.00020639999999999998, 'epoch': 0.28}
+{'loss': 3.5579, 'grad_norm': 1.621443510055542, 'learning_rate': 0.00020759999999999998, 'epoch': 0.28}
+{'loss': 3.6199, 'grad_norm': 1.133254885673523, 'learning_rate': 0.00020879999999999998, 'epoch': 0.28}
+{'loss': 3.6086, 'grad_norm': 1.8510676622390747, 'learning_rate': 0.00020999999999999998, 'epoch': 0.28}
+{'loss': 3.5462, 'grad_norm': 1.194270133972168, 'learning_rate': 0.00021119999999999996, 'epoch': 0.28}
+{'loss': 3.4962, 'grad_norm': 1.256672739982605, 'learning_rate': 0.00021239999999999996, 'epoch': 0.28}
+{'loss': 3.5698, 'grad_norm': 1.386613368988037, 'learning_rate': 0.00021359999999999996, 'epoch': 0.28}
+{'loss': 3.5602, 'grad_norm': 3.1640172004699707, 'learning_rate': 0.00021479999999999996, 'epoch': 0.29}
+{'loss': 3.539, 'grad_norm': 1.1303514242172241, 'learning_rate': 0.00021599999999999996, 'epoch': 0.29}
+{'loss': 3.4954, 'grad_norm': 0.9495574831962585, 'learning_rate': 0.00021719999999999997, 'epoch': 0.29}
+{'loss': 3.5047, 'grad_norm': 1.191848635673523, 'learning_rate': 0.00021839999999999997, 'epoch': 0.29}
+{'loss': 3.584, 'grad_norm': 3.533217191696167, 'learning_rate': 0.00021959999999999997, 'epoch': 0.29}
+{'loss': 3.5125, 'grad_norm': 1.7034047842025757, 'learning_rate': 0.00022079999999999997, 'epoch': 0.29}
+{'loss': 3.5211, 'grad_norm': 2.700714111328125, 'learning_rate': 0.00022199999999999998, 'epoch': 0.3}
+{'loss': 3.5052, 'grad_norm': 1.1122382879257202, 'learning_rate': 0.00022319999999999998, 'epoch': 0.3}
+{'loss': 3.5532, 'grad_norm': 1.1783989667892456, 'learning_rate': 0.00022439999999999998, 'epoch': 0.3}
+{'loss': 3.475, 'grad_norm': 1.685303807258606, 'learning_rate': 0.00022559999999999998, 'epoch': 0.3}
+{'loss': 3.4674, 'grad_norm': 3.506218671798706, 'learning_rate': 0.00022679999999999998, 'epoch': 0.3}
+{'loss': 3.4742, 'grad_norm': 1.5587297677993774, 'learning_rate': 0.00022799999999999999, 'epoch': 0.3}
+{'loss': 3.4753, 'grad_norm': 1.766122817993164, 'learning_rate': 0.0002292, 'epoch': 0.31}
+{'loss': 3.5442, 'grad_norm': 2.4157192707061768, 'learning_rate': 0.0002304, 'epoch': 0.31}
+{'loss': 3.5577, 'grad_norm': 1.7758774757385254, 'learning_rate': 0.0002316, 'epoch': 0.31}
+{'loss': 3.4964, 'grad_norm': 1.9026403427124023, 'learning_rate': 0.0002328, 'epoch': 0.31}
+{'loss': 3.4947, 'grad_norm': 1.9833109378814697, 'learning_rate': 0.000234, 'epoch': 0.31}
+{'loss': 3.4913, 'grad_norm': 1.6161296367645264, 'learning_rate': 0.0002352, 'epoch': 0.31}
+{'loss': 3.3045, 'grad_norm': 1.121405839920044, 'learning_rate': 0.0002364, 'epoch': 0.32}
+{'loss': 3.4437, 'grad_norm': 1.822557806968689, 'learning_rate': 0.0002376, 'epoch': 0.32}
+{'loss': 3.5102, 'grad_norm': 1.3127074241638184, 'learning_rate': 0.0002388, 'epoch': 0.32}
+{'loss': 3.7032, 'grad_norm': nan, 'learning_rate': 0.00023999999999999998, 'epoch': 0.32}
+
+
  0%|          | 0/196 [00:00<?, ?it/s]
+
  1%|          | 2/196 [00:00<01:31,  2.11it/s]
+
  2%|▏         | 3/196 [00:02<02:30,  1.28it/s]
+
  2%|▏         | 4/196 [00:03<03:07,  1.02it/s]
+
  3%|▎         | 5/196 [00:04<03:25,  1.07s/it]
+
  3%|▎         | 6/196 [00:06<03:55,  1.24s/it]
+
  4%|▎         | 7/196 [00:07<04:13,  1.34s/it]
+
  4%|▍         | 8/196 [00:09<04:12,  1.34s/it]
+
  5%|▍         | 9/196 [00:11<05:32,  1.78s/it]
+
  5%|▌         | 10/196 [00:14<06:43,  2.17s/it]
+
  6%|▌         | 11/196 [00:18<07:48,  2.53s/it]
+
  6%|▌         | 12/196 [00:21<08:27,  2.76s/it]
+
  7%|▋         | 13/196 [00:23<07:20,  2.41s/it]
+
  7%|▋         | 14/196 [00:24<06:05,  2.01s/it]
+
  8%|▊         | 15/196 [00:25<05:03,  1.68s/it]
+
  8%|▊         | 16/196 [00:26<04:41,  1.57s/it]
+
  9%|▊         | 17/196 [00:27<04:27,  1.49s/it]
+
  9%|▉         | 18/196 [00:29<04:53,  1.65s/it]
+
 10%|▉         | 19/196 [00:33<06:17,  2.13s/it]
+
 10%|█         | 20/196 [00:35<06:49,  2.33s/it]
+
 11%|█         | 21/196 [00:38<06:58,  2.39s/it]
+
 11%|█         | 22/196 [00:40<06:43,  2.32s/it]
+
 12%|█▏        | 23/196 [00:42<06:15,  2.17s/it]
+
 12%|█▏        | 24/196 [00:43<04:57,  1.73s/it]
+
 13%|█▎        | 25/196 [00:43<04:09,  1.46s/it]
+
 13%|█▎        | 26/196 [00:44<03:36,  1.28s/it]
+
 14%|█▍        | 27/196 [00:45<03:18,  1.17s/it]
+
 14%|█▍        | 28/196 [00:46<03:08,  1.12s/it]
+
 15%|█▍        | 29/196 [00:47<03:07,  1.12s/it]
+
 15%|█▌        | 30/196 [00:48<03:07,  1.13s/it]
+
 16%|█▌        | 31/196 [00:49<02:51,  1.04s/it]
+
 16%|█▋        | 32/196 [00:50<02:42,  1.01it/s]
+
 17%|█▋        | 33/196 [00:52<03:09,  1.16s/it]
+
 17%|█▋        | 34/196 [00:54<04:13,  1.56s/it]
+
 18%|█▊        | 35/196 [00:56<04:16,  1.59s/it]
+
 18%|█▊        | 36/196 [00:58<04:59,  1.87s/it]
+
 19%|█▉        | 37/196 [01:00<04:59,  1.88s/it]
+
 19%|█▉        | 38/196 [01:02<04:30,  1.71s/it]
+
 20%|█▉        | 39/196 [01:03<04:10,  1.59s/it]
+
 20%|██        | 40/196 [01:04<03:48,  1.46s/it]
+
 21%|██        | 41/196 [01:05<03:27,  1.34s/it]
+
 21%|██▏       | 42/196 [01:06<03:10,  1.24s/it]
+
 22%|██▏       | 43/196 [01:07<03:06,  1.22s/it]
+
 22%|██▏       | 44/196 [01:09<03:01,  1.20s/it]
+
 23%|██▎       | 45/196 [01:09<02:49,  1.12s/it]
+
 23%|██▎       | 46/196 [01:10<02:36,  1.05s/it]
+
 24%|██▍       | 47/196 [01:11<02:36,  1.05s/it]
+
 24%|██▍       | 48/196 [01:12<02:27,  1.00it/s]
+
 25%|██▌       | 49/196 [01:13<02:23,  1.02it/s]
+
 26%|██▌       | 50/196 [01:14<02:21,  1.03it/s]
+
 26%|██▌       | 51/196 [01:15<02:16,  1.06it/s]
+
 27%|██▋       | 52/196 [01:16<02:14,  1.07it/s]
+
 27%|██▋       | 53/196 [01:17<02:26,  1.02s/it]
+
 28%|██▊       | 54/196 [01:18<02:22,  1.00s/it]
+
 28%|██▊       | 55/196 [01:20<02:37,  1.12s/it]
+
 29%|██▊       | 56/196 [01:21<02:47,  1.20s/it]
+
 29%|██▉       | 57/196 [01:22<03:00,  1.30s/it]
+
 30%|██▉       | 58/196 [01:24<03:07,  1.36s/it]
+
 30%|███       | 59/196 [01:25<03:06,  1.36s/it]
+
 31%|███       | 60/196 [01:26<02:50,  1.25s/it]
+
 31%|███       | 61/196 [01:27<02:33,  1.13s/it]
+
 32%|███▏      | 62/196 [01:28<02:29,  1.11s/it]
+
 32%|███▏      | 63/196 [01:29<02:30,  1.13s/it]
+
 33%|███▎      | 64/196 [01:31<02:29,  1.14s/it]
+
 33%|███▎      | 65/196 [01:32<02:25,  1.11s/it]
+
 34%|███▎      | 66/196 [01:33<02:30,  1.16s/it]
+
 34%|███▍      | 67/196 [01:34<02:34,  1.20s/it]
+
 35%|███▍      | 68/196 [01:36<02:59,  1.40s/it]
+
 35%|███▌      | 69/196 [01:38<03:06,  1.47s/it]
+
 36%|███▌      | 70/196 [01:39<02:51,  1.36s/it]
+
 36%|███▌      | 71/196 [01:40<02:39,  1.27s/it]
+
 37%|███▋      | 72/196 [01:41<02:24,  1.17s/it]
+
 37%|███▋      | 73/196 [01:42<02:11,  1.07s/it]
+
 38%|███▊      | 74/196 [01:42<02:00,  1.01it/s]
+
 38%|███▊      | 75/196 [01:43<01:56,  1.04it/s]
+
 39%|███▉      | 76/196 [01:44<01:52,  1.06it/s]
+
 39%|███▉      | 77/196 [01:45<01:57,  1.01it/s]
+
 40%|███▉      | 78/196 [01:47<02:08,  1.09s/it]
+
 40%|████      | 79/196 [01:48<02:02,  1.04s/it]
+
 41%|████      | 80/196 [01:49<02:09,  1.11s/it]
+
 41%|████▏     | 81/196 [01:50<02:13,  1.16s/it]
+
 42%|████▏     | 82/196 [01:51<02:08,  1.12s/it]
+
 42%|████▏     | 83/196 [01:52<02:10,  1.15s/it]
+
 43%|████▎     | 84/196 [01:54<02:12,  1.19s/it]
+
 43%|████▎     | 85/196 [01:55<02:11,  1.18s/it]
+
 44%|████▍     | 86/196 [01:56<02:13,  1.21s/it]
+
 44%|████▍     | 87/196 [01:57<02:09,  1.19s/it]
+
 45%|████▍     | 88/196 [01:59<02:13,  1.24s/it]
+
 45%|████▌     | 89/196 [02:00<02:17,  1.29s/it]
+
 46%|████▌     | 90/196 [02:01<02:12,  1.25s/it]
+
 46%|████▋     | 91/196 [02:02<02:07,  1.22s/it]
+
 47%|████▋     | 92/196 [02:03<02:02,  1.18s/it]
+
 47%|████▋     | 93/196 [02:05<02:08,  1.25s/it]
+
 48%|████▊     | 94/196 [02:06<02:10,  1.28s/it]
+
 48%|████▊     | 95/196 [02:07<02:03,  1.22s/it]
+
 49%|████▉     | 96/196 [02:09<02:09,  1.29s/it]
+
 49%|████▉     | 97/196 [02:10<02:05,  1.27s/it]
+
 50%|█████     | 98/196 [02:11<02:09,  1.32s/it]
+
 51%|█████     | 99/196 [02:12<01:57,  1.21s/it]
+
 51%|█████     | 100/196 [02:13<01:43,  1.07s/it]
+
 52%|█████▏    | 101/196 [02:14<01:34,  1.00it/s]
+
 52%|█████▏    | 102/196 [02:15<01:39,  1.06s/it]
+
 53%|█████▎    | 103/196 [02:16<01:45,  1.14s/it]
+
 53%|█████▎    | 104/196 [02:18<02:02,  1.34s/it]
+
 54%|█████▎    | 105/196 [02:20<02:05,  1.38s/it]
+
 54%|█████▍    | 106/196 [02:21<02:05,  1.40s/it]
+
 55%|█████▍    | 107/196 [02:22<01:56,  1.31s/it]
+
 55%|█████▌    | 108/196 [02:23<01:42,  1.16s/it]
+
 56%|█████▌    | 109/196 [02:24<01:33,  1.08s/it]
+
 56%|█████▌    | 110/196 [02:25<01:28,  1.03s/it]
+
 57%|█████▋    | 111/196 [02:26<01:27,  1.03s/it]
+
 57%|█████▋    | 112/196 [02:27<01:30,  1.07s/it]
+
 58%|█████▊    | 113/196 [02:28<01:32,  1.11s/it]
+
 58%|█████▊    | 114/196 [02:29<01:25,  1.04s/it]
+
 59%|█████▊    | 115/196 [02:30<01:21,  1.01s/it]
+
 59%|█████▉    | 116/196 [02:31<01:18,  1.02it/s]
+
 60%|█████▉    | 117/196 [02:32<01:14,  1.06it/s]
+
 60%|██████    | 118/196 [02:32<01:06,  1.17it/s]
+
 61%|██████    | 119/196 [02:33<01:08,  1.13it/s]
+
 61%|██████    | 120/196 [02:34<01:11,  1.06it/s]
+
 62%|██████▏   | 121/196 [02:36<01:13,  1.02it/s]
+
 62%|██████▏   | 122/196 [02:37<01:14,  1.01s/it]
+
 63%|██████▎   | 123/196 [02:38<01:13,  1.00s/it]
+
 63%|██████▎   | 124/196 [02:39<01:10,  1.02it/s]
+
 64%|██████▍   | 125/196 [02:40<01:10,  1.01it/s]
+
 64%|██████▍   | 126/196 [02:41<01:18,  1.12s/it]
+
 65%|██████▍   | 127/196 [02:42<01:17,  1.12s/it]
+
 65%|██████▌   | 128/196 [02:43<01:12,  1.06s/it]
+
 66%|██████▌   | 129/196 [02:44<01:10,  1.06s/it]
+
 66%|██████▋   | 130/196 [02:45<01:08,  1.04s/it]
+
 67%|██████▋   | 131/196 [02:46<01:08,  1.05s/it]
+
 67%|██████▋   | 132/196 [02:47<01:03,  1.02it/s]
+
 68%|██████▊   | 133/196 [02:48<01:00,  1.03it/s]
+
 68%|██████▊   | 134/196 [02:49<01:05,  1.06s/it]
+
 69%|██████▉   | 135/196 [02:50<01:03,  1.03s/it]
+
 69%|██████▉   | 136/196 [02:51<00:59,  1.00it/s]
+
 70%|██████▉   | 137/196 [02:52<00:58,  1.01it/s]
+
 70%|███████   | 138/196 [02:53<00:58,  1.00s/it]
+
 71%|███████   | 139/196 [02:54<00:57,  1.00s/it]
+
 71%|███████▏  | 140/196 [02:55<00:55,  1.00it/s]
+
 72%|███████▏  | 141/196 [02:56<00:55,  1.00s/it]
+
 72%|███████▏  | 142/196 [02:57<00:55,  1.03s/it]
+
 73%|███████▎  | 143/196 [02:59<00:59,  1.13s/it]
+
 73%|███████▎  | 144/196 [02:59<00:55,  1.07s/it]
+
 74%|███████▍  | 145/196 [03:00<00:49,  1.03it/s]
+
 74%|███████▍  | 146/196 [03:01<00:45,  1.10it/s]
+
 75%|███████▌  | 147/196 [03:02<00:44,  1.10it/s]
+
 76%|███████▌  | 148/196 [03:03<00:43,  1.10it/s]
+
 76%|███████▌  | 149/196 [03:04<00:40,  1.15it/s]
+
 77%|███████▋  | 150/196 [03:05<00:42,  1.10it/s]
+
 77%|███████▋  | 151/196 [03:06<00:43,  1.03it/s]
+
 78%|███████▊  | 152/196 [03:07<00:42,  1.04it/s]
+
 78%|███████▊  | 153/196 [03:08<00:41,  1.05it/s]
+
 79%|███████▊  | 154/196 [03:09<00:41,  1.02it/s]
+
 79%|███████▉  | 155/196 [03:10<00:42,  1.05s/it]
+
 80%|███████▉  | 156/196 [03:12<00:49,  1.25s/it]
+
 80%|████████  | 157/196 [03:13<00:53,  1.36s/it]
+
 81%|████████  | 158/196 [03:14<00:46,  1.22s/it]
+
 81%|████████  | 159/196 [03:15<00:40,  1.10s/it]
+
 82%|████████▏ | 160/196 [03:16<00:37,  1.04s/it]
+
 82%|████████▏ | 161/196 [03:17<00:36,  1.04s/it]
+
 83%|████████▎ | 162/196 [03:18<00:35,  1.03s/it]
+
 83%|████████▎ | 163/196 [03:19<00:33,  1.01s/it]
+
 84%|████████▎ | 164/196 [03:20<00:31,  1.01it/s]
+
 84%|████████▍ | 165/196 [03:21<00:31,  1.03s/it]
+
 85%|████████▍ | 166/196 [03:22<00:30,  1.01s/it]
+
 85%|████████▌ | 167/196 [03:23<00:28,  1.03it/s]
+
 86%|████████▌ | 168/196 [03:23<00:25,  1.08it/s]
+
 86%|████████▌ | 169/196 [03:24<00:25,  1.06it/s]
+
 87%|████████▋ | 170/196 [03:26<00:27,  1.05s/it]
+
 87%|████████▋ | 171/196 [03:27<00:25,  1.01s/it]
+
 88%|████████▊ | 172/196 [03:28<00:24,  1.04s/it]
+
 88%|████████▊ | 173/196 [03:29<00:23,  1.03s/it]
+
 89%|████████▉ | 174/196 [03:30<00:24,  1.09s/it]
+
 89%|████████▉ | 175/196 [03:32<00:27,  1.31s/it]
+
 90%|████████▉ | 176/196 [03:36<00:41,  2.07s/it]
+
 90%|█████████ | 177/196 [03:39<00:46,  2.42s/it]
+
 91%|█████████ | 178/196 [03:42<00:47,  2.63s/it]
+
 91%|█████████▏| 179/196 [03:46<00:49,  2.89s/it]
+
 92%|█████████▏| 180/196 [03:47<00:37,  2.32s/it]
+
 92%|█████████▏| 181/196 [03:48<00:29,  1.96s/it]
+
 93%|█████████▎| 182/196 [03:49<00:23,  1.66s/it]
+
 93%|█████████▎| 183/196 [03:51<00:22,  1.73s/it]
+
 94%|█████████▍| 184/196 [03:51<00:17,  1.48s/it]
+
 94%|█████████▍| 185/196 [03:53<00:15,  1.42s/it]
+
 95%|█████████▍| 186/196 [03:54<00:14,  1.49s/it]
+
 95%|█████████▌| 187/196 [03:55<00:12,  1.36s/it]
+
 96%|█████████▌| 188/196 [03:56<00:09,  1.22s/it]
+
 96%|█████████▋| 189/196 [03:57<00:08,  1.18s/it]
+
 97%|█████████▋| 190/196 [03:58<00:06,  1.11s/it]
+
 97%|█████████▋| 191/196 [03:59<00:05,  1.03s/it]
+
 98%|█████████▊| 192/196 [04:00<00:04,  1.03s/it]
+
 98%|█████████▊| 193/196 [04:01<00:03,  1.03s/it]
+
 99%|█████████▉| 194/196 [04:02<00:02,  1.04s/it]
+
 99%|█████████▉| 195/196 [04:03<00:01,  1.01s/it]
+
                                                    
+
                                                 
  4%|▍         | 200/5000 [21:10<2:35:34,  1.94s/it]
+
+
                                                 
  4%|▍         | 201/5000 [21:26<109:42:43, 82.30s/it]
                                                      
  4%|▍         | 201/5000 [21:26<109:42:43, 82.30s/it]
  4%|▍         | 202/5000 [21:35<80:16:32, 60.23s/it] 
                                                     
  4%|▍         | 202/5000 [21:35<80:16:32, 60.23s/it]
  4%|▍         | 203/5000 [21:43<59:13:26, 44.45s/it]
                                                     
  4%|▍         | 203/5000 [21:43<59:13:26, 44.45s/it]
  4%|▍         | 204/5000 [21:50<44:17:23, 33.25s/it]
                                                     
  4%|▍         | 204/5000 [21:50<44:17:23, 33.25s/it]
  4%|▍         | 205/5000 [21:56<33:35:12, 25.22s/it]
                                                     
  4%|▍         | 205/5000 [21:56<33:35:12, 25.22s/it]
  4%|▍         | 206/5000 [22:02<25:54:24, 19.45s/it]
                                                     
  4%|▍         | 206/5000 [22:02<25:54:24, 19.45s/it]
  4%|▍         | 207/5000 [22:08<20:29:24, 15.39s/it]
                                                     
  4%|▍         | 207/5000 [22:08<20:29:24, 15.39s/it]
  4%|▍         | 208/5000 [22:13<16:29:27, 12.39s/it]
                                                     
  4%|▍         | 208/5000 [22:14<16:29:27, 12.39s/it]
  4%|▍         | 209/5000 [22:19<13:41:28, 10.29s/it]
                                                     
  4%|▍         | 209/5000 [22:19<13:41:28, 10.29s/it]
  4%|▍         | 210/5000 [22:24<11:33:46,  8.69s/it]
                                                     
  4%|▍         | 210/5000 [22:24<11:33:46,  8.69s/it]
  4%|▍         | 211/5000 [22:29<9:58:05,  7.49s/it] 
                                                    
  4%|▍         | 211/5000 [22:29<9:58:05,  7.49s/it]
  4%|▍         | 212/5000 [22:33<8:50:15,  6.64s/it]
                                                    
  4%|▍         | 212/5000 [22:33<8:50:15,  6.64s/it]
  4%|▍         | 213/5000 [22:38<7:59:27,  6.01s/it]
                                                    
  4%|▍         | 213/5000 [22:38<7:59:27,  6.01s/it]
  4%|▍         | 214/5000 [22:42<7:14:17,  5.44s/it]
                                                    
  4%|▍         | 214/5000 [22:42<7:14:17,  5.44s/it]
  4%|▍         | 215/5000 [22:46<6:42:02,  5.04s/it]
                                                    
  4%|▍         | 215/5000 [22:46<6:42:02,  5.04s/it]
  4%|▍         | 216/5000 [22:50<6:19:32,  4.76s/it]
                                                    
  4%|▍         | 216/5000 [22:50<6:19:32,  4.76s/it]
  4%|▍         | 217/5000 [22:54<6:03:14,  4.56s/it]
                                                    
  4%|▍         | 217/5000 [22:54<6:03:14,  4.56s/it]
  4%|▍         | 218/5000 [22:58<5:43:18,  4.31s/it]
                                                    
  4%|▍         | 218/5000 [22:58<5:43:18,  4.31s/it]
  4%|▍         | 219/5000 [23:01<5:24:54,  4.08s/it]
                                                    
  4%|▍         | 219/5000 [23:01<5:24:54,  4.08s/it]
  4%|▍         | 220/5000 [23:05<5:10:19,  3.90s/it]
                                                    
  4%|▍         | 220/5000 [23:05<5:10:19,  3.90s/it]
  4%|▍         | 221/5000 [23:08<5:00:17,  3.77s/it]
                                                    
  4%|▍         | 221/5000 [23:08<5:00:17,  3.77s/it]
  4%|▍         | 222/5000 [23:12<4:53:21,  3.68s/it]
                                                    
  4%|▍         | 222/5000 [23:12<4:53:21,  3.68s/it]
  4%|▍         | 223/5000 [23:15<4:48:44,  3.63s/it]
                                                    
  4%|▍         | 223/5000 [23:15<4:48:44,  3.63s/it]
  4%|▍         | 224/5000 [23:19<4:45:03,  3.58s/it]
                                                    
  4%|▍         | 224/5000 [23:19<4:45:03,  3.58s/it]
  4%|▍         | 225/5000 [23:22<4:38:56,  3.50s/it]
                                                    
  4%|▍         | 225/5000 [23:22<4:38:56,  3.50s/it]
  5%|▍         | 226/5000 [23:25<4:24:21,  3.32s/it]
                                                    
  5%|▍         | 226/5000 [23:25<4:24:21,  3.32s/it]
  5%|▍         | 227/5000 [23:28<4:14:14,  3.20s/it]
                                                    
  5%|▍         | 227/5000 [23:28<4:14:14,  3.20s/it]
  5%|▍         | 228/5000 [23:31<4:06:55,  3.10s/it]
                                                    
  5%|▍         | 228/5000 [23:31<4:06:55,  3.10s/it]
  5%|▍         | 229/5000 [23:34<4:01:25,  3.04s/it]
                                                    
  5%|▍         | 229/5000 [23:34<4:01:25,  3.04s/it]
  5%|▍         | 230/5000 [23:37<3:57:38,  2.99s/it]
                                                    
  5%|▍         | 230/5000 [23:37<3:57:38,  2.99s/it]
  5%|▍         | 231/5000 [23:39<3:54:46,  2.95s/it]
                                                    
  5%|▍         | 231/5000 [23:39<3:54:46,  2.95s/it]
  5%|▍         | 232/5000 [23:42<3:52:48,  2.93s/it]
                                                    
  5%|▍         | 232/5000 [23:42<3:52:48,  2.93s/it]
  5%|▍         | 233/5000 [23:45<3:50:13,  2.90s/it]
                                                    
  5%|▍         | 233/5000 [23:45<3:50:13,  2.90s/it]
  5%|▍         | 234/5000 [23:48<3:41:16,  2.79s/it]
                                                    
  5%|▍         | 234/5000 [23:48<3:41:16,  2.79s/it]
  5%|▍         | 235/5000 [23:50<3:30:34,  2.65s/it]
                                                    
  5%|▍         | 235/5000 [23:50<3:30:34,  2.65s/it]
  5%|▍         | 236/5000 [23:52<3:22:52,  2.56s/it]
                                                    
  5%|▍         | 236/5000 [23:52<3:22:52,  2.56s/it]
  5%|▍         | 237/5000 [23:55<3:17:33,  2.49s/it]
                                                    
  5%|▍         | 237/5000 [23:55<3:17:33,  2.49s/it]
  5%|▍         | 238/5000 [23:57<3:13:44,  2.44s/it]
                                                    
  5%|▍         | 238/5000 [23:57<3:13:44,  2.44s/it]
  5%|▍         | 239/5000 [23:59<3:11:03,  2.41s/it]
                                                    
  5%|▍         | 239/5000 [23:59<3:11:03,  2.41s/it]
  5%|▍         | 240/5000 [24:02<3:09:01,  2.38s/it]
                                                    
  5%|▍         | 240/5000 [24:02<3:09:01,  2.38s/it]
  5%|▍         | 241/5000 [24:04<2:58:50,  2.25s/it]
                                                    
  5%|▍         | 241/5000 [24:04<2:58:50,  2.25s/it]
  5%|▍         | 242/5000 [24:05<2:46:53,  2.10s/it]
                                                    
  5%|▍         | 242/5000 [24:05<2:46:53,  2.10s/it]
  5%|▍         | 243/5000 [24:07<2:38:29,  2.00s/it]
                                                    
  5%|▍         | 243/5000 [24:07<2:38:29,  2.00s/it]
  5%|▍         | 244/5000 [24:09<2:32:26,  1.92s/it]
                                                    
  5%|▍         | 244/5000 [24:09<2:32:26,  1.92s/it]
  5%|▍         | 245/5000 [24:11<2:28:22,  1.87s/it]
                                                    
  5%|▍         | 245/5000 [24:11<2:28:22,  1.87s/it]
  5%|▍         | 246/5000 [24:12<2:25:36,  1.84s/it]
                                                    
  5%|▍         | 246/5000 [24:12<2:25:36,  1.84s/it]
  5%|▍         | 247/5000 [24:14<2:20:40,  1.78s/it]
                                                    
  5%|▍         | 247/5000 [24:14<2:20:40,  1.78s/it]
  5%|▍         | 248/5000 [24:15<2:06:52,  1.60s/it]
                                                    
  5%|▍         | 248/5000 [24:15<2:06:52,  1.60s/it]
  5%|▍         | 249/5000 [24:16<1:57:05,  1.48s/it]
                                                    
  5%|▍         | 249/5000 [24:16<1:57:05,  1.48s/it]
  5%|▌         | 250/5000 [24:19<2:31:59,  1.92s/it]
                                                    
  5%|▌         | 250/5000 [24:19<2:31:59,  1.92s/it]
  5%|▌         | 251/5000 [24:36<8:30:18,  6.45s/it]
                                                    
  5%|▌         | 251/5000 [24:36<8:30:18,  6.45s/it]
  5%|▌         | 252/5000 [24:45<9:22:20,  7.11s/it]
                                                    
  5%|▌         | 252/5000 [24:45<9:22:20,  7.11s/it]
  5%|▌         | 253/5000 [24:53<9:32:15,  7.23s/it]
                                                    
  5%|▌         | 253/5000 [24:53<9:32:15,  7.23s/it]
  5%|▌         | 254/5000 [24:59<9:22:48,  7.12s/it]
                                                    
  5%|▌         | 254/5000 [24:59<9:22:48,  7.12s/it]
  5%|▌         | 255/5000 [25:06<9:06:29,  6.91s/it]
                                                    
  5%|▌         | 255/5000 [25:06<9:06:29,  6.91s/it]slurmstepd: error: *** JOB 2604812 ON gpu37 CANCELLED AT 2024-09-15T20:24:08 ***

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d6e542b15e77cd1bb8a7693945d939d7b6324a0178a2a54a151c7870a9a3a70
-size 1262426580
+oid sha256:7c8413b0a8098781dd4041c03523bde4a6a9d1f89399e1e1205151e76c329614
+size 1262434780

tokenizer_config.json

@@ -1,36 +1,36 @@
 {
   "added_tokens_decoder": {
-    "147": {
-      "content": "<s>",
+    "149": {
+      "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
       "rstrip": true,
       "single_word": false,
       "special": false
     },
-    "148": {
-      "content": "</s>",
+    "150": {
+      "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
       "rstrip": true,
       "single_word": false,
       "special": false
     },
-    "149": {
-      "content": "[UNK]",
-      "lstrip": true,
+    "151": {
+      "content": "<s>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "150": {
-      "content": "[PAD]",
-      "lstrip": true,
+    "152": {
+      "content": "</s>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     }
   },
   "bos_token": "<s>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:673e3429059d894b526752b0cd1eeaf19c902ddeb9ee9960f32941ecb04f2125
+oid sha256:d94d7876ff002d45f2ef145dcdddba9849824007cb4b40b05b98fdbdff808728
 size 5496

vocab.json

@@ -20,8 +20,6 @@
   ":": 19,
   ";": 20,
   "<": 21,
-  "</s>": 148,
-  "<s>": 147,
   "=": 22,
   ">": 23,
   "@": 24,
@@ -149,5 +147,7 @@
   "›": 143,
   "⅓": 144,
   "→": 145,
+  "∅": 147,
+  "∇": 148,
   "−": 146
 }